Bearing Fault Diagnosis via Robust PCA with Nonconvex Rank Approximation
Cai Li; Penghong Lu; Guangming Dong, and Gang Chen*
IEEE Sensors Journal,2024
PDF   Abstract   BibTeX  

Feature extraction is an essential part of bearing fault diagnosis. Robust principal component analysis (RPCA) provides a general technique for extracting fault features. However, Although the convex relaxed RPCA is convex and easy to optimize, the global optimal solution obtained may deviate significantly from reality. To address this issue, we propose a nonconvex RPCA method for bearing fault diagnosis, utilizing the γ norm penalty. Leveraging the unitary invariance property of the γ norm and the Moreau-Yosida operator, we transform the original equation into a singular value optimization problem using a difference of convex programming to obtain a feasible solution. The most important advantage of Nonconvex RPCA over conventional filtering methods is that it can improve fault feature extraction while decreasing noise interference, which results in substantially enhanced estimation accuracy of the bearing fault signal. Simulation analysis and experimental results confirm the effectiveness of the developed approach. Comparison experiments demonstrate that nonconvex RPCA provides more accurate extraction results compared to L1-norm regularization, Variational Mode Decomposition, and Feature Mode Decomposition.

                @article{li2024bearing,
                  title={Bearing Fault Diagnosis via Robust PCA with Nonconvex Rank Approximation},
                  author={Li, Cai and Lu, Penghong and Dong, Guangming and Chen, Gang},
                  journal={IEEE Sensors Journal},
                  year={2024},
                  publisher={IEEE}
                }
              

Knowledge-based Clustering Federated Learning for fault diagnosis in robotic assembly
Peng Xiao, Chuang Wang, Ze Lin, Ying Hao, Gang Chen* and Longhan Xie*
Knowledge-Based Systems,2024
PDF   Abstract   BibTeX  

Fault diagnosis in industrial robots is a critical aspect of intelligent manufacturing. However, the accuracy of fault diagnosis models can be significantly affected by the few-shot problem, which refers to the limited availability of labeled data for training. Traditional methods often rely on combining data from different sources, which can raise privacy concerns due to the sensitive nature of the data involved. Federated Learning has emerged as a privacy-preserving approach, but it faces challenges in dealing with the Non-IID (Non-Independent and Identically Distributed) data distribution across different robot systems. In this study, we propose a novel approach called Knowledge-Based Clustering Federated Learning (KCFed) to address both the few-shot problem in robot fault diagnosis and the Non-IID problem in Federated Learning. KCFed incorporates Federated Learning principles to ensure privacy protection during the model training process. Additionally, by leveraging the Knowledge-based Clustering Mechanism (KCM) and Knowledge Accumulation Mechanism (KAM), KCFed aims to improve the performance of fault diagnosis models by clustering similar tasks and accumulating useful prior information. To evaluate the effectiveness of KCFed, we conducted experiments using data collected from industrial robots performing 12 different tasks, resulting in a diverse set of 48 states. The experimental results demonstrate the promising performance of KCFed in improving fault diagnosis accuracy while preserving privacy in a federated learning setting.

                @article{xiao2024knowledge,
                  title={Knowledge-based Clustering Federated Learning for fault diagnosis in robotic assembly},
                  author={Xiao, Peng and Wang, Chuang and Lin, Ze and Hao, Ying and Chen, Gang and Xie, Longhan},
                  journal={Knowledge-Based Systems},
                  volume={294},
                  pages={111792},
                  year={2024},
                  publisher={Elsevier}
                }
              

Extended Residual Learning with One-shot Imitation Learning for Robotic Assembly in Semi-structured Environment
Chuang Wang , Chupeng Su , Bozheng Sun , Gang Chen* and Longhan Xie*
Frontiers in Neurorobotics,2024
PDF   Abstract   BibTeX  

Robotic assembly tasks require precise manipulation and coordination, often necessitating advanced learning techniques to achieve efficient and effective performance. While residual reinforcement learning with a base policy has shown promise in this domain, existing base policy approaches often rely on hand-designed full-state features and policies or extensive demonstrations, limiting their applicability in semi-structured environments. In this study, we propose an innovative Object-Embodiment-Centric Imitation and Residual Reinforcement Learning (OEC-IRRL) approach that leverages an object-embodiment-centric (OEC) task representation to integrate vision models with imitation and residual learning. By utilizing a single demonstration and minimizing interactions with the environment, our method aims to enhance learning efficiency and effectiveness. The proposed method involves three key steps: creating an object-embodiment-centric task representation, employing imitation learning for a base policy using via-point movement primitives for generalization to different settings, and utilizing residual RL for uncertainty-aware policy refinement during the assembly phase. Through a series of comprehensive experiments, we investigate the impact of the OEC task representation on base and residual policy learning and demonstrate the effectiveness of the method in semi-structured environments. Our results indicate that the approach, requiring only a single demonstration and less than 1.2 hours of interaction, improves success rates by 46% and reduces assembly time by 25%. This research presents a promising avenue for robotic assembly tasks, providing a viable solution without the need for specialized expertise or custom fixtures.

                @article{wang2024task,
                  title={Task attention-based multimodal fusion and curriculum residual learning for context generalization in robotic assembly},
                  author={Wang, Chuang and Lin, Ze and Liu, Biao and Su, Chupeng and Chen, Gang and Xie, Longhan},
                  journal={Applied Intelligence},
                  pages={1--23},
                  year={2024},
                  publisher={Springer}
                }
              

Task attention-based multimodal fusion and curriculum residual learning for context generalization in robotic assembly
Chuang Wang, Ze Lin, Biao Liu, Chupeng Su, Gang Chen*, Longhan Xie*
Applied Intelligence,2024
PDF   Abstract   BibTeX  

In the domain of flexible manufacturing, Deep Reinforcement Learning (DRL) has emerged as a pivotal technology for robotic assembly tasks. Despite advancements in sample efficiency and interaction safety through residual reinforcement learning with initial policies, challenges persist in achieving context generalization amidst stochastic systems characterized by large random errors and variable backgrounds. Addressing these challenges, this study introduces a novel framework that integrates task attention-based multimodal fusion with an adaptive error curriculum within a residual reinforcement learning paradigm. Our approach commences with the formulation of a task attention-based multimodal policy that synergizes task-centric visual, relative pose, and tactile data into a compact, end-to-end model. This model is explicitly designed to enhance context generalization by improving observability, thereby ensuring robustness against stochastic errors and variable backgrounds. The second facet of our framework, curriculum residual learning, introduces an adaptive error curriculum that intelligently modulates the guidance and constraints of a model-based feedback controller. This progression from perfect to significantly imperfect initial policies incrementally enhances policy robustness and learning process stability. Empirical validation demonstrates the capability of our method to efficiently acquire a high-precision policy for assembly tasks with clearances as tight as 0.1 mm and error margins up to 20 mm within a 3.5-hour training window-a feat challenging for existing RL-based methods. The results indicate a substantial reduction in average completion time by 75 and a 34 increase in success rate over the classical two-step approach. An ablation study was conducted to assess the contribution of each component within our framework. Real-world task experiments further corroborate the robustness and generalization of our method, achieving over a 90 success rate in variable contexts..

                @article{wang2024task,
                  title={Task attention-based multimodal fusion and curriculum residual learning for context generalization in robotic assembly},
                  author={Wang, Chuang and Lin, Ze and Liu, Biao and Su, Chupeng and Chen, Gang and Xie, Longhan},
                  journal={Applied Intelligence},
                  pages={1--23},
                  year={2024},
                  publisher={Springer}
                }
              

A Neural-symbolic Network for Interpretable Fault Diagnosis of Rolling Element Bearings Based on Temporal Logic
Ruoyao Tian, Mengqian Cui, Gang Chen*
IEEE Transactions on Instrumentation and Measurement,2024
PDF   Abstract   BibTeX  

This study examines the issue of interpretability in fault diagnosis for rolling bearings using a symbolic learning technique. We propose the adoption of weighted signal temporal logic (wSTL) as a formal language and introduce the temporal logic network (TLN) as a neural-symbolic learning architecture capable of encoding symbolic wSTL representations for input signals. TLN comprises three subnetworks: a basic predicate network for abstracting features and generating predicates from vibration signals, an autoencoder for identifying significant signal components, and a logic network for constructing a formal language that aids in fault classification and model interpretation. To improve comprehensibility, timed failure propagation graphs (TFPGs) are used to visually represent the logical relationships and propagation of fault events. Experimental results demonstrate TLN’s ability to extract impulse fault patterns from signals, accurately describe fault events through learned wSTL formulas, and enhance understanding of fault events for nonexpert individuals through TFPGs. These findings contribute to the field of fault diagnosis in rolling bearings by incorporating symbolic learning techniques, using formal language representation and TFPG for improved interpretability.

                @article{tian2024neural,
                  title={A Neural-symbolic Network for Interpretable Fault Diagnosis of Rolling Element Bearings Based on Temporal Logic},
                  author={Tian, Ruoyao and Cui, Mengqian and Chen, Gang},
                  journal={IEEE Transactions on Instrumentation and Measurement},
                  year={2024},
                  publisher={IEEE}
                }
              

Control/physical systems co-design with spectral temporal logic specifications and its applications to MEMS
Gang Chen, Zhaodan Kong, Longhan Xie
International Journal of Control,2024
PDF   Abstract   BibTeX  

‘Co-design’ problems try to simultaneously design the physical and control components to improve the overall system performance. However, existing co-design paradigms cannot deal with complex frequency temporal domain specifications. In this paper, we investigate the co-design problem for a class of linear parameter-varying (LPV) systems with frequency temporal domain specifications. Firstly, the frequency temporal domain specifications are written in a formal language called spectral temporal logic (STL). Secondly, the satisfaction conditions of the spectral temporal logic specifications have been transformed into non-linear matrices inequality forms with necessary and sufficient conditions. Thirdly, the co-design problem is transformed into a non-convex optimisation problem with mixed-integer linear matrix inequalities (MILMIs) constraints, and then an iterative algorithm is proposed to solve the co-design problem with semidefinite programming (SDP). Finally, the performance of the algorithm and the expressiveness of spectral temporal logic are illustrated with the applications to micro-electromechanical systems (MEMS).

              @article{chen2024control,
                title={Control/physical systems co-design with spectral temporal logic specifications and its applications to MEMS},
                author={Chen, Gang and Kong, Zhaodan and Xie, Longhan},
                journal={International Journal of Control},
                pages={1--16},
                year={2024},
                publisher={Taylor \& Francis}
              }
            

Evolution strategies-based optimized graph reinforcement learning for solving dynamic job shop scheduling problem
Chupeng Su, Cong Zhang, Dan Xia, Baoan Han, Chuang Wang, Gang Chen*, Longhan Xie*
Applied Soft Computing, 2023
PDF   Abstract   BibTeX  

The job shop scheduling problem (JSSP) with dynamic events and uncertainty is a strongly NP-hard combinatorial optimization problem (COP) with extensive applications in the manufacturing system. Recently, growing interest has been aroused in utilizing machine learning techniques to solve the JSSP. However, most prior arts cannot handle dynamic events and barely consider uncertainties. To close this gap, this paper proposes a framework to solve a dynamic JSSP (DJSP) with machine breakdown and stochastic processing time based on Graph Neural Network (GNN) and deep reinforcement learning (DRL). To this end, we first formulate the DJSP as a Markov Decision Process (MDP), where disjunctive graph represent the states. Secondly, we propose a GNN-based model to effectively extract the embeddings of the state by considering the features of the dynamic events and the stochasticity of the problem, e.g., the machine breakdown and stochastic processing time. Then, the model constructs solutions by dispatching optimal operations to machines based on the learned embeddings. Notably, we propose to use the evolution strategies (ES) to find optimal policies that are more stable and robust than conventional DRL algorithms. The extensive experiments show that our method substantially outperforms existing reinforcement learning-based and traditional methods on multiple classic benchmarks.

              @article{su2023evolution,
                title={Evolution strategies-based optimized graph reinforcement learning for solving dynamic job shop scheduling problem},
                author={Su, Chupeng and Zhang, Cong and Xia, Dan and Han, Baoan and Wang, Chuang and Chen, Gang and Xie, Longhan},
                journal={Applied Soft Computing},
                volume={145},
                pages={110596},
                year={2023},
                publisher={Elsevier}
              }
            

Interpretable fault diagnosis with shapelet temporal logic: Theory and application
Gang Chen*, Yu Lu, Rong Su
Automatica, 2022
PDF   Abstract   BibTeX  

Shapelets are discriminative subsequences of sequential data that best predict the target variable and are directly interpretable, which have attracted considerable interest within the interpretable fault diagnosis community. Despite their immense potential as a data mining primitive, currently, shapelet-based methods ignore the temporal properties of shapelets. This paper presents a shapelet temporal logic, which is an expressive formal language to describe the temporal properties of shapelets. Moreover, an incremental algorithm is proposed to find the optimal logic expression with formal and theoretical guarantees, and the obtained logic expression can be used for fault diagnosis. Additionally, a case study on rolling element bearing fault diagnosis shows the proposed method can diagnose and interpret faults with high accuracy. Comparison experiments with other logic-based and shapelet-based methods illustrate the proposed method has better interpretability at the cost of computation efficiency.

              @article{chen2022interpretable,
                title={Interpretable fault diagnosis with shapelet temporal logic: Theory and application},
                author={Chen, Gang and Lu, Yu and Su, Rong},
                journal={Automatica},
                volume={142},
                pages={110350},
                year={2022},
                publisher={Elsevier}
              }
            

Timed failure propagation graph construction with supremal language guided Tree-LSTM and its application to interpretable fault diagnosis
Gang Chen*
Applied Intelligence, 2022
PDF   Abstract   BibTeX  

Timed failure propagation graphs (TFPGs) perform fault diagnosis in a transparent way. However, accurate TFPGs depend on experts’ knowledge or accurate model of the system, which is hard to obtain for complex systems. This paper presents a data-driven TFPG construction approach for fault diagnosis, which finds spectral-timed failure propagation graphs (sTFPG) directly from data. The sTFPG construction problem is transformed into a spectral-temporal logic inference problem and solved with a tree-structured long short-term memory (LSTM) network. Therefore, no expert or accurate model is needed to construct the TFPG. Moreover, the training process is guided and sped up by the supremacy property of the spectral-temporal logic, which focuses on the structure information of the signals and incorporates the physical meanings in the learning process. Experimental results on real rolling element bearing data sets illustrate that the performance of the proposed fault diagnosis method is comparable with state-of-the-art machine learning methods in fault diagnosis accuracy, and outperforms the logic-based method in computational efficiency. Additionally, fault diagnosis with TFPG can be understood by humans and reveal the fault mechanism.

            @article{chen2022timed,
              title={Timed failure propagation graph construction with supremal language guided Tree-LSTM and its application to interpretable fault diagnosis},
              author={Chen, Gang},
              journal={Applied Intelligence},
              pages={1--16},
              year={2022},
              publisher={Springer}
            }
          

Temporal Logic Inference for Fault Detection of Switched Systems With Gaussian Process Dynamics
Gang Chen* et al.
IEEE Transactions on Automation Science and Engineering, 2021
PDF   Abstract   BibTeX  

In this article, we present a method for constructing the fault detector in the form of signal temporal logic (STL) formulas, which can be understood by human users and formally proven to detect faults with probabilistic satisfaction guarantees, for a class of switched nonlinear systems with partially unknown dynamics. First, the partially unknown internal dynamics are approximated by the Gaussian process with stability guarantees. Second, a novel temporal logic inference algorithm is proposed to find the fault detector, which takes advantage of the internal properties of temporal logic and searches for the optimal formula along a partially ordered direction. Moreover, the algorithm is not allowed for missing faults but allowed for false alarms during the temporal logic inference process. In addition, we simulate finitely many trajectories with Chua’s circuit and infer the temporal logic formulas with the Gaussian optimization. The results show that the proposed method can find a temporal logic formula to detect the faulty trajectory with a probability guarantee. Note to Practitioners—The method proposed in this article can be used to detect faults for switched systems with partially unknown dynamics. STL is used to describe the behaviors of the system, which acts as a classifier and detector, such that all normal behaviors of the system will satisfy the description, while the faulty behaviors will violate the description. Moreover, STL formulas can be understood by human operators, which is important for the timely response to faulty events. For example, the normal behavior of a smart grid can be described as follows: “if the smart grid is safe, it should reach 9 kV within 15 min when the voltage to region A is above 12 kV,” which can be expressed with STL. Due to the unknown dynamics, the Gaussian process regression is applied to estimate the model and the region that is robust to noises.

                    @article{chen2021temporal,
                      title={Temporal Logic Inference for Fault Detection of Switched Systems With Gaussian Process Dynamics},
                      author={Chen, Gang, et al.},
                      journal={IEEE Transactions on Automation Science and Engineering},
                      year={2021},
                      publisher={IEEE}
                    }

              

Formal language generation for fault diagnosis with spectral logic via adversarial training
Gang Chen et al.
IEEE Transactions on Industrial Informatics, 2020
PDF   Abstract   BibTeX  

Fault diagnosis with formal languages can be performed in an interpretable way. However, the traditional formal languages cannot deal with noisy environments. Additionally, finding the optimal formal language for fault diagnosis is still a challenge due to the sparse reward issue. This article presents a novel method to find formal languages, written with signal spectral logic (SSL), to describe the fault behaviors among frequency domain for fault diagnosis. The formal language defined by SSL is robust to noise, acts as the fault diagnoser, and provides interpretabilities for human operators. Moreover, the fault diagnoser construction procedure has been formulated as a language generation process and an adversarial training technique is used to find the optimal formal language and avoid sparse reward issue existing in language generation problems. Some experiments with real rolling element bearing data and simulated signals demonstrate that our method is able to find formal languages to diagnose faults efficiently and accurately under noisy environments.

       
            
                  @article{chen2020formal,
                    title={Formal language generation for fault diagnosis with spectral logic via adversarial training},
                    author={Chen, Gang  et al.},
                    journal={IEEE Transactions on Industrial Informatics},
                    volume={18},
                    number={1},
                    pages={119--129},
                    year={2020},
                    publisher={IEEE}
                  }
                  

Frequency-temporal-logic-based bearing fault diagnosis and fault interpretation using Bayesian optimization with Bayesian neural networks
Gang Chen et al.
Mechanical Systems and Signal Processing, 2020
PDF   Abstract   BibTeX  

Rolling element bearings are widely used components in modern rotary machines, and accurate diagnosis and interpretation for faults of bearings are significant for equipment maintenance. This paper introduces a fault diagnosis method with a formal specification language, which overcomes the difficulty of understanding the decision process of fault diagnosis. The formal specification is written with a novel formal language, called frequency-temporal-logic, defining the time-frequency properties of time series signals, which not only is a classifier to diagnose the faults but also gives interpretations for the fault signals with its semantics. To find an optimal description for the fault signals, the Bayesian optimization with Bayesian neural networks has been utilized to infer the structure and parameters of the formal specification. The semantics of frequency-temporal-logic then gives the fault interpretation. Moreover, the quantitative semantics for the formal language is defined based on a novel satisfaction metric, which has a noise resistance property. Analysis of the proposed method shows that the formal description can deal with noisy signals and variable speed operations of the bearings. Finally, comparison experimental results indicate the proposed method can obtain high fault diagnosis accuracy.

       
          
                @article{chen2020frequency,
                  title={Frequency-temporal-logic-based bearing fault diagnosis and fault interpretation using Bayesian optimization with Bayesian neural networks},
                  author={Chen, Gang et al.},
                  journal={Mechanical Systems and Signal Processing},
                  volume={145},
                  pages={106951},
                  year={2020},
                  publisher={Elsevier}
                }
                

Data-driven real-valued timed-failure-propagation-graph refinement for complex system fault diagnosis
Gang Chen, Xinfan Lin, Zhaodan Kong*
IEEE Control Systems Letters, 2020
PDF   Abstract   BibTeX  

Timed Failure Propagation Graphs (TFPGs) have been widely used for the failure modeling and diagnosis of safety-critical systems. Currently most TFPGs are manually constructed by system experts, a process that can be time-consuming, error-prone, and even impossible for systems with highly nonlinear and machine-learning-based components. This letter proposes a new type of TFPGs, called Real-Valued Timed Failure Propagation Graphs (rTFPGs), designed for continuous-state systems. More importantly, it presents a systematic way of constructing rTFPGs by combining the powers of human experts and data-driven methods: first, an expert constructs a partial rTFPG based on his/her expertise; then a data-driven algorithm refines the rTFPG by adding nodes and edges based on a given set of labeled signals. The proposed approach has been successfully implemented and evaluated on three case studies.

       
            
                  @article{chen2020data,
                    title={Data-driven real-valued timed-failure-propagation-graph refinement for complex system fault diagnosis},
                    author={Chen, Gang and Lin, Xinfan and Kong, Zhaodan},
                    journal={IEEE Control Systems Letters},
                    volume={5},
                    number={3},
                    pages={1049--1054},
                    year={2020},
                    publisher={IEEE}
                  }  
  
                  

Temporal-logic-based semantic fault diagnosis with time-series data from industrial internet of things
Gang Chen, et al.
IEEE Transactions on Industrial Electronics, 2020
PDF   Abstract   BibTeX  

The maturity of sensor network technologies has facilitated the emergence of an industrial Internet of Things (IIoT), which has collected an increasing volume of data. Converting these data into actionable intelligence for fault diagnosis is key to reducing unscheduled downtime and performance degradation, among other examples. This article formalizes a problem called semantic fault diagnosis- to construct the formal specifications of faults directly from data collected from IIoT-enabled systems. The specifications are written as signal temporal logic formulas, which can be easily interpreted by humans. To tackle the issue of the combinatorial explosion that arises, we propose an algorithm that combines ideas from agenda-based searching and imitation learning to train a policy that searches formulas in a strategic order. Specifically, we formulate the problem as a Markov decision process, which is further solved with a reinforcement learning algorithm. Our algorithm is applied to time-series data collected from an IIoT-enabled iron-making factory. The results show empirically that our proposed algorithm is both scalable to the size of the data set and interpretable, therefore allowing human users to take actions, for example, predictive maintenance.

       
          
                @article{chen2020temporal,
                  title={Temporal-logic-based semantic fault diagnosis with time-series data from industrial internet of things},
                  author={Chen, Gang  et al.},
                  journal={IEEE Transactions on Industrial Electronics},
                  volume={68},
                  number={5},
                  pages={4393--4403},
                  year={2020},
                  publisher={IEEE}
                }
                

Semantic Inference for Cyber-Physical Systems with Signal Temporal Logic
Gang Chen et al.
IEEE 58th Conference on Decision and Control (CDC), 2019
PDF   Abstract   BibTeX  

Formal specification plays crucial roles in the rigorous verification and design of cyber-physical systems (CPS). The challenge of getting high-quality formal specifications is well documented. This challenge is further exacerbated in CPS with artificial-intelligence- or machine-learning-based components. This paper presents a problem called `semantic inference', the goal of which is to automatically translate the behavior of a CPS to a formal specification written in signal temporal logic (STL). To reduce the potential combinatorial explosion inherent to the problem, this paper adopts a search strategy called agenda-based computation, which is inspired by natural language processing. Based on such a strategy, the semantic inference problem can be formulated as a Markov decision process (MDP) and then solved using reinforcement learning (RL). The obtained formal specification can be viewed as an interpretable classifier, which, on the one hand, can classify desirable and undesirable behaviors, and, on the other hand, is expressed in a human-understandable form. The performance of the proposed method is demonstrated with a case study.

                    @inproceedings{chen2019semantic,
                      title={Semantic Inference for Cyber-Physical Systems with Signal Temporal Logic},
                      author={Chen, Gang et al},
                      booktitle={2019 IEEE 58th Conference on Decision and Control (CDC)},
                      pages={6269--6274},
                      year={2019},
                      organization={IEEE}
                    }          
                

Optimised dispensing of predatory mites by multirotor UAVs in wind: A distribution pattern modelling approach for precision pest management
April L Teske, Gang Chen, Christian Nansen, Zhaodan Kong*
Biosystems Engineering
PDF   Abstract   BibTeX  

Multirotor unmanned aerial vehicles (UAVs), or drones, are increasingly being used to spray liquid pesticides to control emerging pest infestations in field crops. In recent years, UAVs have been used to release predatory mites and other natural enemies to optimise and promote sustainable pest management practices by relying less on conventional insecticides. Drone dispensed samples of predatory mites are typically mixed with a granular material, vermiculite, which serves as a filler. The low density of the vermiculite and weather conditions (mainly wind), influences the distribution pattern of predatory mites when delivered by a UAV-based system. The purpose of this paper is to present a data-driven methodology to develop a mathematical model that can be used to optimise UAV-based autonomous dispensing of predatory mites. The model characterises the distribution of vermiculite as a function of wind speed and direction, and the UAVs altitude and forward speed. The model is constructed by first conducting outdoor experiments and then using machine-learning techniques on the collected data. The constructed model produced an average generalisation error of 12.8%, RMSE. Due to its parametric and predictive nature, the model is amenable for the future design of UAV flight controllers that can compensate for the targeting error caused by wind. The proposed modelling methodology could be useful not only for the dispensing of predatory mites, but also for other UAV dispensing applications, such as liquid or granular pesticide deliveries.

                  @article{teske2019optimised,
                    title={Optimised dispensing of predatory mites by multirotor UAVs in wind: A distribution pattern modelling approach for precision pest management},
                    author={Teske, April L and Chen, Gang and Nansen, Christian and Kong, Zhaodan},
                    journal={Biosystems Engineering},
                    volume={187},
                    pages={226--238},
                    year={2019},
                    publisher={Elsevier}
                  }
              

Semantic parsing of automobile steering systems
Gang Chen, Zachary Sabato, Zhaodan Kong
Proceedings of the 8th International Conference on the Internet of Things, 2018
PDF   Abstract   BibTeX    

Formal specification plays crucial roles in the rigorous verification and design of automobile steering systems. The challenge of getting high-quality formal specifications is well documented. This paper presents a problem called'semantic parsing', the goal of which is to automatically translate the behavior of an automobile steering system to a formal specification written in signal temporal logic (STL) with human-in-the loop manner. To tackle the combinatorial explosion inherent to the problem, this paper adopts a search strategy called agenda-based parsing, which is inspired by natural language processing. Based on such a strategy, the semantic parsing problem can be formulated as a Markov decision process (MDP) and then solved using reinforcement learning. The obtained formal specification can be viewed as an interpretable classifier, which, on the one hand, can classify desirable and undesirable behaviors …

                @inproceedings{chen2018semantic,
                  title={Semantic parsing of automobile steering systems},
                  author={Chen, Gang and Sabato, Zachary and Kong, Zhaodan},
                  booktitle={Proceedings of the 8th International Conference on the Internet of Things},
                  pages={1--3},
                  year={2018}
                }
              

Formal interpretation of cyber-physical system performance with temporal logic
Gang Chen, Zachary Sabato, Zhaodan Kong
Cyber-Physical Systems, 2018
PDF   Abstract   BibTeX    

The inherent and increasing complexity of many cyber-physical systems (CPSs) makes it challenging for human users or designers to comprehend and interpret their performance. This issue, without proper attention paid, may lead to unwanted and even catastrophic consequences, particularly with safety-critical CPSs. This paper presents a new methodology of enabling (i) a human to interrogate a CPS by inquiring with questions written in formal logic and (ii) the CPS to interpret its performance precisely in the context of the inquiry. This formal interpretation problem is first formulated as temporal logic inference problem, which, aided by the concept of robustness degree, can be converted into an optimisation problem with probably approximately correct solutions. A new Gaussian-process-based active learning algorithm is then proposed to address the potential computational budget issue arising from solving the…

                @article{chen2018formal,
                  title={Formal interpretation of cyber-physical system performance with temporal logic},
                  author={Chen, Gang and Sabato, Zachary and Kong, Zhaodan},
                  journal={Cyber-Physical Systems},
                  volume={4},
                  number={3},
                  pages={175--203},
                  year={2018},
                  publisher={Taylor \& Francis}
                }
              

Data-driven approximate abstraction for black-box piecewise affine systems
Gang Chen, Zhaodan Kong
CAnnual American Control Conference (ACC), 2018
PDF   Abstract   BibTeX    

How to effectively and reliably guarantee the correct functioning of safety-critical cyber-physical systems in uncertain conditions is a challenging problem. This paper presents a data-driven algorithm to derive approximate abstractions for piecewise affine systems with unknown dynamics. It advocates a significant shift from the current paradigm of abstraction, which starts from a model with known dynamics. Given a black-box system with unknown dynamics and a linear temporal logic specification, the proposed algorithm is able to obtain an abstraction of the system with an arbitrarily small error and a bounded probability. The algorithm consists of three components, system identification, system abstraction, and active sampling. The effectiveness of the algorithm is demonstrated by a case study with a soft robot.

                @inproceedings{chen2018data,
                  title={Data-driven approximate abstraction for black-box piecewise affine systems},
                  author={Chen, Gang and Kong, Zhaodan},
                  booktitle={2018 Annual American Control Conference (ACC)},
                  pages={786--791},
                  year={2018},
                  organization={IEEE}
                }
              

Correct-by-Construction Approach for Self-Evolvable Robots
Gang Chen, Zhaodan Kong
International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, 2017
PDF   Abstract   BibTeX    

The paper presents a new formal way of modeling and designing reconfigurable robots, in which case the robots are allowed to reconfigure not only structurally but also functionally. We call such kind of robots “self-evolvable”, which have the potential to be more flexible to be used in a wider range of tasks, in a wider range of environments, and with a wider range of users. To accommodate such a concept, i.e., allowing a self-evovable robot to be configured and reconfigured, we present a series of formal constructs, e.g., structural reconfigurable grammar and functional reconfigurable grammar. Furthermore, we present a correct-by-construction strategy, which, given the description of a workspace, the formula specifying a task, and a set of available modules, is capable of constructing during the design phase a robot that is guaranteed to perform the task satisfactorily. We use a planar multi-link manipulator as an …

                @inproceedings{chen2017correct,
                  title={Correct-by-Construction Approach for Self-Evolvable Robots},
                  author={Chen, Gang and Kong, Zhaodan},
                  booktitle={International Design Engineering Technical Conferences and Computers and Information in Engineering Conference},
                  volume={58233},
                  pages={V009T07A051},
                  year={2017},
                  organization={American Society of Mechanical Engineers}
                }
              

Active learning based requirement mining for cyber-physical systems
Gang Chen, Zhaodan Kong
IEEE 55th Conference on Decision and Control (CDC),2016
PDF   Abstract   BibTeX    

This paper uses active learning to solve the problem of mining signal temporal requirements of cyber-physical systems or simply the requirement mining problem. By utilizing robustness degree, we formulate the requirement mining problem as an optimization problem. We then propose a new active learning algorithm called Gaussian Process Adaptive Confidence Bound (GP-ACB) to help in solving the optimization problem. We show theoretically that the GP-ACB algorithm has a lower regret bound-thus a larger convergence rate-than some existing active learning algorithms, such as GP-UCB. We finally illustrate and apply our requirement mining algorithm with two case studies: the Ackley's function and a real world automotive power steering model. Our results demonstrate that there is a principled and efficient way of extracting requirements for complex cyber-physical systems.

                @inproceedings{chen2016active,
                  title={Active learning based requirement mining for cyber-physical systems},
                  author={Chen, Gang and Sabato, Zachary and Kong, Zhaodan},
                  booktitle={2016 IEEE 55th Conference on Decision and Control (CDC)},
                  pages={4586--4593},
                  year={2016},
                  organization={IEEE}
                }
              

A novel wrapper method for feature selection and its applications
Gang Chen, Jin Chen
Neurocomputing,2015
PDF   Abstract   BibTeX    

This paper introduces a wrapper method, namely cosine similarity measure support vector machines (CSMSVM), to eliminate irrelevant or redundant features during classifier construction by introducing the cosine distance into support vector machines (SVM). Traditionally, feature selection approaches typically extract features and learn SVM parameters independently or in the attribute space, which might result in a loss of information related to classification process or lead to the increase of classification error when introduce the kernel SVM. The proposed CSMSVM framework, however, jointly performs feature selection, SVM parameter learning and remove low relevance features by optimizing the shape of an anisotropic RBF kernel in feature space. Moreover, the Bayesian interpretation of the novel methodology reveals its Bayesian character, which builds the proposed method on solid theory foundation, and the …

                @article{chen2015novel,
                  title={A novel wrapper method for feature selection and its applications},
                  author={Chen, Gang and Chen, Jin},
                  journal={Neurocomputing},
                  volume={159},
                  pages={219--226},
                  year={2015},
                  publisher={Elsevier}
                }
              

Study on Hankel matrix-based SVD and its application in rolling element bearing fault diagnosis
Huiming Jiang, Jin Chen, Guangming Dong, Tao Liu, Gang Chen
Mechanical systems and signal processing,2015
PDF   Abstract   BibTeX    

Based on the traditional theory of singular value decomposition (SVD), singular values (SVs) and ratios of neighboring singular values (NSVRs) are introduced to the feature extraction of vibration signals. The proposed feature extraction method is called SV–NSVR. Combined with selected SV–NSVR features, continuous hidden Markov model (CHMM) is used to realize the automatic classification. Then the SV–NSVR and CHMM based method is applied in fault diagnosis and performance assessment of rolling element bearings. The simulation and experimental results show that this method has a higher accuracy for the bearing fault diagnosis compared with those using other SVD features, and it is effective for the performance assessment of rolling element bearings.

                @article{jiang2015study,
                  title={Study on Hankel matrix-based SVD and its application in rolling element bearing fault diagnosis},
                  author={Jiang, Huiming and Chen, Jin and Dong, Guangming and Liu, Tao and Chen, Gang},
                  journal={Mechanical systems and signal processing},
                  volume={52},
                  pages={338--359},
                  year={2015},
                  publisher={Elsevier}
                }
              

An adaptive non-parametric short-time Fourier transform: application to echolocation
Gang Chen, Jin Chen, Guangming Dong, Huiming Jiang
Applied Acoustics,2015
PDF   Abstract   BibTeX    

This paper studies a novel time–frequency representation method—adaptive non-parametric short-time Fourier transform (ANSTFT), together with its application to the echolocation signal analysis. By rotating the signal in the analysis window, the local instantaneous frequency has been reset to parallel to the time axis. Then the high frequency and time resolution have been achieved with the mono-frequency signal simultaneously. To find the optimal rotating angle of the local signal, an iterative approximation algorithm has been utilized, which makes the ANSTFT a non-parametric data driving method and have the better generalization ability than the conventional adaptive STFT. Moreover, several numerical examples are presented to illustrate the aforementioned characteristics and the application of ANSTFT to echolocation signal analysis demonstrates its validity.

                @article{chen2015adaptive,
                  title={An adaptive non-parametric short-time Fourier transform: application to echolocation},
                  author={Chen, Gang and Chen, Jin and Dong, Guangming and Jiang, Huiming},
                  journal={Applied Acoustics},
                  volume={87},
                  pages={131--141},
                  year={2015},
                  publisher={Elsevier}
                }
              

An adaptive analog circuit for LVDT’s nanometer measurement without losing sensitivity and range
Gang Chen, Bo Zhang, Pinkuan Liu, Han Ding
IEEE Sensors Journal,2015
PDF   Abstract   BibTeX    

A self-adaptive circuit for the linear variable differential transformer (LVDT) has been developed to enhance its nanometer measurement range without loss resolution. By applying a fuzzy-proportional-integral-derivative controlled programmable gain amplifier array to produce a reference signal, which can adjust itself according to LVDT's core position, the conditioning circuit has ensured the signal to analog-to-digital converter varying in a very small interval over full-scale operating range. Thus, the sensitivity of the measurement system can be improved without losing measurement range. The simulation result demonstrated that the proposed circuit has solved the contradiction between resolution and range, which usually occurs in weak signal detection. Moreover, the signal-to-noise ratio has been ameliorated greatly. Additionally, the DSP-based signal conditioner, which utilizes the self-adaptive circuit …

                @article{chen2014adaptive,
                  title={An adaptive analog circuit for LVDT’s nanometer measurement without losing sensitivity and range},
                  author={Chen, Gang and Zhang, Bo and Liu, Pinkuan and Ding, Han},
                  journal={IEEE Sensors Journal},
                  volume={15},
                  number={4},
                  pages={2248--2254},
                  year={2014},
                  publisher={IEEE}
                }
              

Chirplet Wigner–Ville distribution for time–frequency representation and its application
Gang Chen, Jin Chen, Guangming Dong
Mechanical Systems and Signal Processing,2013
PDF   Abstract   BibTeX    

This paper presents a Chirplet Wigner–Ville Distribution (CWVD) that is free for cross-term that usually occurs in Wigner–Ville distribution (WVD). By transforming the signal with frequency rotating operators, several mono-frequency signals without intermittent are obtained, WVD is applied to the rotated signals that is cross-term free, then some frequency shift operators corresponding to the rotating operator are utilized to relocate the signal′s instantaneous frequencies (IFs). The operators′ parameters come from the estimation of the IFs which are approached with a polynomial functions or spline functions. What is more, by analysis of error, the main factors for the performance of the novel method have been discovered and an effective signal extending method based on the IFs estimation has been developed to improve the energy concentration of WVD. The excellent performance of the novel method was …

                @article{chen2013chirplet,
                  title={Chirplet Wigner--Ville distribution for time--frequency representation and its application},
                  author={Chen, G and Chen, J and Dong, GM},
                  journal={Mechanical Systems and Signal Processing},
                  volume={41},
                  number={1-2},
                  pages={1--13},
                  year={2013},
                  publisher={Elsevier}
                }