Fault diagnosis is a challenging topic for complex industrial systems due to the varying environments such systems find themselves in. In order to improve the performance of fault diagnosis, this study designs a novel approach by using particle swarm optimization (PSO) with wavelet mutation and least square support (LSSVM). The implementation entails the following three steps. Firstly, the original signals are decomposed through an orthogonal wavelet packet decomposition algorithm. Secondly, the decomposed signals are reconstructed to obtain the fault features. Finally, the extracted features are used as the inputs of the fault diagnosis model established in this research to improve classification accuracy. This joint optimization method not only solves the problem of PSO falling easily into the local extremum, but also improves the classification performance of fault diagnosis effectively. Through experimental verification, the wavelet mutation particle swarm optimazation and least sqaure support vector machine ( WMPSO-LSSVM) fault diagnosis model has a maximum fault recognition efficiency that is 12% higher than LSSVM and 9% higher than extreme learning machine (ELM). The error of the corresponding regression model under the WMPSO-LSSVM algorithm is 0.365 less than that of the traditional linear regression model. Therefore, the proposed fault scheme can effectively identify faults that occur in complex industrial systems.

In recent years, numerous scholars have studied how to detect weakly maneuvering targets under strong background noise and strong jamming with frequency modulated continuous wave (FMCW) radars. The realization of this technology can produce profound civil value. However, in order to effectively and clearly detect the target, it is necessary to overcome the difficulty of detecting the target energy in a complex environment. To address the difficulties of detecting weak target with strong background noise, this study presents a novel target recognition algorithm based on the coupling relationship among the velocity, range walk, and Doppler frequency of the weak target. The improved Hough Transform method cannot only realizes the transformation of a line from image coordinate system to parametric coordinate system of the weak target with background noise, but also achieve a large degree of accumulation of weak target energy. It is shown that the proposed method is able to achieve better performance compared with the existing schemes in weak target recognition. In addition, the energy of the detected target is more concentrated based on the method proposed in this study.