Search

Physics-informed machine learning (PIML) has proven to be a valuable approach for overcoming data scarcity challenges by incorporating physical models into machine learning methods. However, PIML faces limitations in handling complex spatial relationships, as its process information is obtained from disordered collocation points. Fuzzy systems, based on expert knowledge, can provide an interpretable way for tackling strong process nonlinearities. This article proposes a brand-new physics-informed spatial fuzzy system framework (PiFuz) to capture the essential system information of complex distributed parameter systems. PiFuz utilizes spatial membership functions to transform collocation points into a 3-D fuzzy input. This input is processed by the inference mechanism, leveraging its 3-D nature to produce fuzzy outputs with distinctive spatial characteristics. A feature fusion module is utilized to integrate these characteristics and generate the distributed system state. Utilizing the known physical knowledge base, the proposed framework undergoes automatic tuning while preserving process interpretability, resulting in an optimal model that aligns with the actual physical process. A reliable prediction of strong spatial nonlinear behaviors is achieved without the dependency of process data. For modeling higher dimensional spatiotemporal problems, the extension, a multikernel PiFuz framework (MKPiFuz), is further developed to improve the representation of heterogeneous time-varying nonlinear behaviors. By incorporating spatial and wavelet kernels, MKPiFuz extracts underlying features from spatial and temporal dimensions, respectively. Experimental investigations on thermal process of the battery module demonstrate the good accuracy in modeling complex spatiotemporal systems.

Fault detection for distributed parameter systems (DPSs) generally requires the complete model information to be known so far. However, for numerous industrial applications, it is common that accurate first-principles physical models are extremely difficult to obtain. Hence, the applicability of traditional model-based methods is being restricted. To pave the way, an adaptive neural network (AdNN) is constructed to simultaneously estimate the state variable and the unknown nonlinearity for a class of partially known nonlinear DPSs. Moreover, considering that full-state measurement is unrealistic in applications, the proposed adaptive neural observer is based on a reduced-order model, which also increases the computation efficiency. Then, the residual generation and evaluation are conducted using the output estimation error of the proposed adaptive neural observer. Bearing the effects of the neglected fast dynamics in mind, a data-driven threshold generation scheme is proposed. Extensive experimental results are presented and analyzed to validate the effectiveness of the proposed method.

The charging process design is crucial for optimizing the performance of lithium-ion batteries by identifying protocols that meet diverse demands. The main challenges include: 1) the high costs of battery experiments; 2) the multiple user preferences associated with the demands; and 3) the intricate high-dimensional search space of charging protocols. In light of this, this article presents a Gaussian process-accelerated multiobjective evolutionary design method for effective charging process design. To resolve the first concern, an electrochemical-thermal-aging model is constructed to evaluate charging protocols precisely, substituting the need for expensive battery experiments. Besides, the Gaussian process is applied to accelerate the evaluation process further. Regarding the second issue, a Gaussian process-accelerated two-archive evolutionary algorithm (GPA-TAEA) is developed to efficiently search for a set of optimal charging protocols that satisfy multiple user preferences. To address the third challenge, differential evaluation—an evolutionary algorithm proven effective for large-scale optimization—is employed to enhance the search process. The simulation results demonstrate that: 1) the proposed method effectively reduces the time required for charging process design, yielding a collection of optimal charging protocols that includes 530 solutions within 1000 simulations; 2) compared with five other multiobjective optimization algorithms, GPA-TAEA exhibits superior convergence and diversity; and 3) compared with fixed preference-based methods, GPA-TAEA demonstrates greater efficiency, saving 54% in simulation evaluations and 70% in time when considering seven user preferences.

Distributed parameter systems (DPSs) are commonly used to characterize various industrial processes, but the coupling of spatiotemporal data and time-delay effects poses challenges for their fault detection. This article proposes a fault detection method for a class of nonlinear parabolic DPSs with limited sensors. A time/space separation method is first applied to decouple the spatiotemporal data to obtain time coefficients that are available for data-driven modeling. Then, the obtained dominant time coefficients are modeled by a dynamic partial least-squares (D-PLSs) method. Finally, the residual space is utilized to establish two monitoring statistics and a reference boundary is established with the aid of the mirrored data kernel density estimation (KDE). This method exploits the separable characteristics of parabolic DPSs and is a data-driven method that is independent of an explicit mathematical model of the system processes. The proposed method is validated on a curing oven experimental platform, and comparative results with other methods show that it achieves satisfactory performance in fault detection accuracy and first-time detection timeliness.

Surface defect detection is very important for the printed circuit board (PCB) to ensure their quality requirements. This article proposes a reliable and lightweight adaptive convolution (LAC) network for PCB surface defect detection. First, an automated optical inspection (AOI) for collecting PCB defects is introduced, and the formation mechanism of PCB defects is systematically analyzed. After that, LAC strategically aggregates multiple convolution kernels and simplifies model complexity through tensor decomposition. Furthermore, the confidence gate learning (CGL) strategy aims to cope with dataset noise by combining collaborative learning (CL) and confidence evaluation. Complexity and convergence analyses support the theoretical basis of the method. Finally, three industrial defect datasets are used to evaluate the effectiveness. The results show that the methodology has powerful feature representation, visual interpretability, and detection robustness.

Modeling the temperature distribution of a battery is critical to its safe operation. Data-based modeling methods are computationally efficient, but require a large number of sensors, whereas physics-based modeling methods have better generalization, but the unknown dynamics of the actual scene are ignored. A physics-dominated neural network is presented to integrate electric–thermal mechanism of the battery and data information through a weight adaptive function. The electric–thermal coupling equation of the battery under complex conditions is taken as the prior knowledge to update parameters of the network, whereas the characteristic data obtained by the unique sensor are used to compensate the unknown disturbance in the actual scene. A well-trained model can predict the temperature distribution of the battery over entire space with a single sensor, and can also provide reasonable predictions for longer periods of time under extreme conditions. Experiments show that the proposed method outperforms traditional methods that rely only on pure data or pure physics.

In industrial applications, the modeling of distributed parameter systems (DPSs) is of significance for process control and monitoring. Due to infinite dimension, spatiotemporal coupled dynamics, nonlinearity, and model uncertainties, however, modeling and online applications of DPSs are very difficult. To address these issues, an online spatiotemporal modeling method is proposed based on confidence-aware multiscale learning. From the spacial-scale perspective, an evolutionary learning-based spatial basis function is designed by learning from two dimensionality reduction methods, including Karhunen–Lo$\grave{e}$ ve and diffusion maps. From the temporal-scale perspective, an efficient broad learning system is developed as reduced-order model to online address temporal dynamics of DPSs. As for the spatiotemporal-scale learning, Gaussian process regression is proposed as confidence-aware estimator to compensate for model generalization errors caused by spatiotemporal coupled dynamics. Through integration with the three-scale learning, the proposed method enables online confidence-aware prediction for DPSs. Experiments based on the curing process in snap curing oven demonstrate the effectiveness of proposed method.