Because of its simple structure, high efficiency, low noise, and high reliability, the brushless direct current motor (BLDCM) has an irreplaceable role compared with other types of motors in many aspects. The traditional proportional integral derivative (PID) control algorithm has been widely used in practical engineering because of its simple structure and convenient adjustment, but it has many shortcomings in control accuracy and other aspects. Therefore, in this paper, a fuzzy single neuron neural network (FSNNN) PID algorithm based on an automatic speed regulator (ASR) is designed and applied to a BLDCM control system. This paper introduces a BLDCM mathematical model and its control system and designs an FSNNN PID algorithm that takes speed deviation e at different sampling times as inputs of a neural network to adjust the PID parameters, and then it uses a fuzzy system to adjust gain K of the neural network. In addition, the frequency domain stability of a double closed loop PID control system is analyzed, and the control effect of traditional PID, fuzzy PID, and FSNNN PID algorithms are compared by setting different reference speeds, as well as the change rules of three-phase current, back electromotive force (EMF), electromagnetic torque, and rotor angle position. Finally, results show that a motor controlled by the FSNNN PID algorithm has certain superiority compared with traditional PID and fuzzy PID algorithms and also has better control effects.

In modern warfare, the accurate prediction of the intercept time and intercept point of the interceptor is the key to achieving penetration. Aiming at this problem, firstly, a convolutional neural network (CNN) is used to automatically extract high-level features from the data, and then these features are used as the input of support vector regression (SVR) for regression prediction. The Harris Hawk optimization (HHO) is used to optimize the hyperparameters of SVR, and the HHO-CNN-SVR algorithm is proposed. In order to verify the effectiveness of the algorithm for the prediction of the interception point and interception time, this paper constructs a dataset to test the method of simulating the missile interception maneuvering target. Compared with BP, ELM, SVR, HHO-SVR, and CNN-SVR models, the HHO-CNN-SVR model has outstanding performance in prediction accuracy and stability, especially for the interception time. The error is the smallest, and the error fluctuation is small. The MAE of the prediction result is only 0.0139 s; in the interception point prediction, the error of the range and elevation direction is significantly lower than that of the models used for comparison. The MAE in the range direction is 2.3 m, and the MAE in the elevation direction is 2.01 m, which meet the engineering requirements. The HHO-CNN-SVR model has strong prediction accuracy and stability in interception time and interception point prediction. In addition, different control strategies are used to construct a new prediction set, and noise is added to the prediction set. The HHO-CNN-SVR algorithm can maintain good prediction results. The results show that the HHO-CNN-SVR model proposed in this paper has strong generalization ability and high robustness, which can provide reliable support for penetration decision making and defense system optimization.

Most existing fault diagnosis methods, although capable of extracting interpretable features such as attention-weighted fault-related frequencies, remain essentially black-box models that provide only classification results without transparent reasoning or diagnostic justification, limiting users’ ability to understand and trust diagnostic outcomes. In this work, we present a novel, interpretable fault diagnosis framework that integrates spectral feature extraction with large language models (LLMs). Vibration signals are first transformed into spectral representations using Hilbert- and Fourier-based encoders to highlight key frequencies and amplitudes. A channel attention-augmented convolutional neural network provides an initial fault type prediction. Subsequently, structured information—including operating conditions, spectral features, and CNN outputs—is fed into a fine-tuned enhanced LLM, which delivers both an accurate diagnosis and a transparent reasoning process. Experiments demonstrate that our framework achieves high diagnostic performance while substantially improving interpretability, making advanced fault diagnosis accessible to non-expert users in industrial settings.