Research

Intelligent systems are widely used in our industrial and economic world, such as intelligent transportation systems and smart factories, which have brought a lot of convenience to our lives, but the design and application of cyber-physical systems are still very difficult tasks and require more researchers' efforts. The problems to be solved urgently in cyber-physical system design mainly include lack of trustable monitoring tools, lack of safe guarantees and lack of interpretable algorithms.

1. Lack of trustable monitoring tools:

2. Lack of safe guarantees:

3. Lack of interpretable algorithms:

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. Formal languages can be used to describe the behavious of CPSs in an interpretable way. However, traditional formal languages cannot deal with noisy environments. Additionally, finding the optimal formal language for CPS is still a challenge due to the sparse reward issue. This research direction tries to find formal languages to describe the behaviours of CPS. The formal language defined is robust to noise, acts as the classifier or prognoiser, and provides interpretabilities for human operators. Moreover, the learned formal lanugae can be applied to other applicaiton, such as CPS design, guiding learning direction in neural networks.

Technologies: Formal language generation, machine learning, fault diagnosis.

Formal Language Generation for Fault Diagnosis with Spectral Logic via Adversarial Training

Gang Chen, Peng Wei, Huiming Jiang, and Mei Liu

IEEE Transactions on Industrial Informatics, 2020

PDF, CODE

Frequency-temporal-logic-based Bearing Fault Diagnosis and Fault Interpretation using Bayesian Optimization with Bayesian Neural Networks

Gang Chen, Mei Liu, and Jin Chen

Mechanical Systems and Signal Processing, 2020

PDF, CODE

Temporal-logic-based Semantic Fault Diagnosis with Time-series Data from Industrial Internet of Things

Gang Chen, Mei Liu, and Zhaodan Kong

IEEE Transactions on Industrial Electronics, 2020

PDF , CODE