The current popular machine learning-based fault diagnosis methods make it difficult to explain the diagnostic results, leading to low user trust in such diagnostic techniques. In this regard, this paper explores the study of the interpretability of intelligent fault diagnosis algorithms using the elevator of a fixed-wing unmanned aerial vehicle (UAV) as a diagnostic object. The Transformer model combines excellent modeling capability and efficient sequence data processing, is chosen to mine fault signal features to guarantee accurate diagnosis. Among the proposed interpretable fault diagnosis models, the local interpretable model-agnostic explanations (LIME) model is used to provide explicit interpretability for the decision-making process of the diagnosis model. In addition, a loss function called RDCE (reinforced diagnostic cross-entropy) Loss is designed to minimize the negative impact of different sample sizes for different fault types on the diagnostic performance. This loss function is designed to weigh the various types of faults to speed up the convergence of the model and improve the diagnostic accuracy. By comparing the proposed diagnostic strategy with other commonly used machine learning models, including long short term memory and recurrent neural network (RNN), the average diagnostic accuracy of the proposed diagnostic strategy is 99.97%, significantly better than that of the comparison algorithms. At the same time, this paper provides an in-depth interpretable analysis of the diagnostic process of the Transformer. The diagnostic process of the Transformer model gives the reasons for the diagnostic results from the point of view of the kind of features processed by the model. Based on this, the diagnostic model is simplified. After streamlining the number of features from 40 to 24 according to their importance, the diagnostic accuracy of the model is improved by 0.26%, and the diagnostic efficiency is improved. In addition, the proposed diagnostic strategy also shows significant advantages in terms of noise robustness.

The effectiveness and safety of an aircraft’s flight depend heavily on the flight control system. Since the attitude sensor is the weakest link, identifying its failure modes is crucial. To overcome the shortcomings of a single diagnosis model and a single input signal, this paper proposes a hybrid deep fault diagnosis model based on multi-data fusion. First, the normal and fault models of the sensor are established, and the residual timing signals of the sensor in different fault states are obtained. The frequency domain and timefrequency domain representations of the original timing signals are collected by means of fast Fourier transform and S-transform, and they are used as the input of the hybrid deep diagnosis model. The deep model is designed for the three inputs to mine the characteristics of the input data. These three deep features are concatenated and dimensionally reduced to obtain more comprehensive and representative features. Finally, the classifier is used to classify and obtain the diagnosis results. Through experiments, the advantages of the proposed method are verified by comparing it with several other methods.

Research on the explanation of the reasons for the output classification results of intelligent diagnostic algorithms is still in its infancy, and interpreting the operation process of intelligent algorithms can help users trust and accept such methods. In this paper, we take the intelligent algorithm-based fault diagnosis of the rudder control circuit of an airplane flight control system as an example and carry out research on the interpretability of the diagnostic algorithm based on SHapley Additive exPlanation (SHAP). The Transformer feature capture module is designed in the diagnostic model, which establishes the dependency of the fault timing signals in the time perspective by embedding the attention mechanism and guarantees the ability to classify the dataset with less differentiation. In addition, given the characteristics of circuit data with multiple classes and similar features, this paper optimizes the model by designing a new loss function called Anomaly Data Feature Enhancement (ADFE) Loss in a targeted manner. The loss function can amplify the fault data so that the model can converge faster, thus improving the accuracy and efficiency of fault diagnosis. Based on SHAP, the diagnostic process of the Transformer model was analyzed in terms of local and global interpretability, which led to the streamlining of some features and optimization of the model. The results show that the optimized model can maintain a smoother and more accurate diagnostic process in a shorter number of iterations while reducing the consumption of computational resources. Meanwhile, the proposed diagnostic strategy also exhibits better noise robustness.

The attitude sensor of the aircraft can give feedback on the perceived flight attitude information to the input of the flight controller to realize the closed-loop control of the flight attitude. Therefore, the fault diagnosis of attitude sensors is crucial for the flight safety of aircraft, in view of the situation that the existing diagnosis methods fail to give consideration to both the diagnosis rate and the diagnosis accuracy. In this paper, a fast and high-precision fault diagnosis strategy for aircraft sensor is proposed. Specifically, the aircraft’s dynamics model and the attitude sensor’s fault model are built. The SENet attention mechanism is used to allocate weights for the collected time-domain fault signals and transformed time-frequency signals, and then inject the fused feature signals with weights into the RepVGG based on the convolutional neural network structure for deep feature mining and classification. Experimental results show that the proposed method can achieve good precision speed tradeoff.

As a pivotal integral component within electronic systems, analog circuits are of paramount importance for the timely detection and precise diagnosis of their faults. However, the objective reality of limited fault samples in operational devices with analog circuitry poses challenges to the direct applicability of existing diagnostic methods. This study proposes an innovative approach for fault diagnosis in analog circuits by integrating deep convolutional generative adversarial networks (DCGANs) with the Transformer architecture, addressing the problem of insufficient fault samples affecting diagnostic performance. Firstly, the employment of the continuous wavelet transform in combination with Morlet wavelet basis functions serves as a means to derive time–frequency images, enhancing fault feature recognition while converting time-domain signals into time–frequency representations. Furthermore, the augmentation of datasets utilizing deep convolutional GANs is employed to generate synthetic time–frequency signals from existing fault data. The Transformer-based fault diagnosis model was trained using a mixture of original signals and generated signals, and the model was subsequently tested. Through experiments involving single and multiple fault scenarios in three simulated circuits, a comparative analysis of the proposed approach was conducted with a number of established benchmark methods, and its effectiveness in various scenarios was evaluated. In addition, the ability of the proposed fault diagnosis technique was investigated in the presence of limited fault data samples. The outcome reveals that the proposed diagnostic method exhibits a consistently high overall accuracy of over 96% in diverse test scenarios. Moreover, it delivers satisfactory performance even when real sample sizes are as small as 150 instances in various fault categories.

As a core component of photovoltaic power generation systems, the three-phase rectifier device plays a crucial role, and its failure can potentially reduce energy conversion efficiency and output quality. Presently, the performance of fault time-domain signal diagnosis methods based on three-phase rectifier circuits is challenging to enhance. This paper proposes a novel fault detection method for three-phase rectifier devices based on Vision Transformer, referred to as CWT-ViT, to address this issue. This method transforms time-domain fault signals into images through Continuous Wavelet Transform (CWT), subsequently inputting these images into a Vision Transformer model. Relying on its powerful self-attention mechanism and fully connected layers, it realizes the extraction and learning of rectifier device image features. A Simulink simulation model of a three-phase bridge controllable rectifier circuit is established for fault injection to collect fault signals. Fault diagnosis experiments demonstrate that the proposed diagnostic method achieves a prediction accuracy of 98.6%, maintaining a relatively high precision level. In comparison to four excellent classification models currently available: AlexNet, RepVGG, ResNet, and GoogLeNet, the proposed method demonstrates superior diagnostic performance. Additionally, this paper conducts ablation experiments to meticulously analyze the impact of each module in the fault diagnosis process. This research achieves more precise and efficient fault diagnosis in photovoltaic power generation systems, thereby reducing downtime and maintenance costs for actual equipment and enhancing the stability of photovoltaic power generation systems. This research provides an innovative, intelligent solution for the intelligent operations and maintenance of photovoltaic power generation.