Bioinspired membrane learnable spiking neural network for autonomous vehicle sensors fault diagnosis under open environments. (May 2023)

• Record Type: Journal Article
• Authors: Wang, Huan; Li, Yan-Fu
• Is Part Of: Reliability engineering & system safety. Volume 233(2023)
• Publication Date: 2023-05
• Subjects: Fault diagnosis -- Health status prediction -- Spiking neural network -- Autonomous vehicle sensors; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2023.109102
• Languages: English
• ISSNs: 0951-8320

Abstract

Highlights: A brain-inspired SNN framework for autonomous vehicle sensors' health monitoring is studied for the first time. A membrane learnable residual SNN framework for fault diagnosis and health index prediction of autonomous vehicle sensors is proposed. The spiking residual block can eliminate the gradient vanishing and exploding problems to build deep biomimetic architectures. The introduced membrane learnable mechanism simulates the diversity of brain neuron membrane parameters, giving the model a strong learning ability. Abstract: Autonomous vehicles have successfully driven autonomously on urban roads, relying on numerous sensors for environmental perception and vehicle control. However, the abnormality and degradation of sensors will make vehicles face serious safety risks. Therefore, autonomous vehicles must have complete sensor fault diagnosis systems to detect anomalies and avoid accidents. Therefore, this paper explores brain-inspired spiking neural networks (SNN) for sensor fault diagnosis. Specifically, this paper proposes a brain-inspired membrane learnable residual spiking neural network (MLR-SNN) for sensor fault and health index prediction. SNN accurately simulates the dynamic mechanism of biological neurons and exhibits excellent spatiotemporal information processing potential and low power consumption while being highly biologically credible. Based on the convolution topology, this study designs a spike-residual-based SNN framework that optimizes the gradient transfer efficiency to enable deep-level spiking information encoding. In addition, membrane-learnable mechanisms are introduced to simulate the differences of neuronal membrane-related parameters in brains, which can better characterize the dynamics of neurons. The proposed MLR-SNN is validated on actual autonomous vehicle sensor datasets. Experimental results show that MLR-SNN with neural dynamics mechanism has excellent performance, and it can accurately predict fault mode and health index from multivariate sensor data under open environments.