Aiming at fault visualization and automatic feature extraction, this paper presents a new and intelligent bearing fault diagnostic method by combining Symmetrized Dot Pattern (SDP) representation with Squeeze-and-Excitation enabled Convolutional Neural Network (SE-CNN) model. Graphical representations of bearing states are shown intuitively by using SDP method. Meanwhile, optimal parameters during SDP images generation are selected to enhance the image resolution for distinctly distinguishing different bearing states, and create corresponding bearing fault sample sets. To automatically and effectively extract SDP image features, the channel attention mechanism using squeeze-and-excitation (SE) network is integrated with the CNN network. The proposed SE-CNN based diagnostic framework has ability to assign certain weight to each feature extraction channel, and further enforce the bearing diagnosis model focusing on the major features, meanwhile reduce the redundant information. The final diagnosis task is realized by the Softmax classifier located behind the SE-CNN model. Experimental results prove that the proposed method not only achieves the classification rate over 99%, but also has better generalization ability and stability.

This paper presents a new control method to suppress current harmonics for permanent magnet synchronous linear motor (PMSLM) that is applied in the miniature microsecond laser cutting system. In the control method, the resonant-two-degree-of-freedom (R-2DOF) proportional-integral-derivative (PID) controller is proposed by combining a resonant controller and a two-degree-of-freedom (2DOF) PID controller. The current harmonic components are first analyzed. The resonant controller is subsequently added to the current loop in parallel to the traditional PI controller to suppress the current harmonic components. However, with the current harmonics suppression, the resonant controller can result in the overshoot in the current loop response. The 2DOF PID controller is adopted to reduce the overshoot. Thus, an R-2DOF PID controller is developed by combining the resonant controller and 2DOF PID controller. Meanwhile, the stability of the proposed controller is analyzed. Compared with the traditional PID controller and the Kalman filter, the proposed controller not only can suppress the current harmonics but can reduce the overshoot and thrust ripple as well. Finally, the simulation and experimental comparison results confirm the validity of the proposed control algorithm.

This paper focuses on the multiobjective design optimization of the permanent magnet synchronous linear motors (PMSLMs), which are applied to a high-precision laser engraving machine. A novel efficient multiobjective design optimization method for a PMSLM is proposed to achieve optimal performances as indicated by high average thrust, low thrust ripple, and low total harmonic distortion at different running speeds. First, based on the finite-element analysis (FEA) data, a regression machine learning algorithm, called an extreme learning machine (ELM), is introduced to solve the calculation modeling problem by mapping out the nonlinear and complex relationship between input structural factors and output motor performances. Comparative simulation experiments conducted using the traditional analytical modeling method and another machine learning modeling method, i.e., support vector machine, confirm the superiority of the ELM. Then, a new bionic intelligent optimization algorithm, called the gray wolf optimizer algorithm, is used to search the best optimization performances and structural parameters by performing iteration optimization calculation for multiobjective functions. Finally, FEA and prototype motor experiments prove the effectiveness and validity of the proposed method.

Accurately and intelligently identifying faults of the planetary gearbox is essential in the safe and reliable operation and maintenance of the mechanical drive system. Recently, fault diagnosis of planetary gearbox has acquired tremendous progress, especially with the rising popularity of deep learning (DL). However, most methods are standard supervised learning where the input is directly mapped to a fault type, and with strong feedback. Also, their learning ways are static and unlike human learning that gradually acquires knowledge by interaction with the environment. To a certain extent, these deficiencies reduce the generalization and intelligence level of DL-based fault diagnosis methods. Besides, due to harsh working conditions, signals acquired often have strong noise and nonlinear features, leading to relatively low accuracy if raw signals are used as the input directly. Thus, this article proposes a new fault diagnosis method based on time-frequency representation and deep reinforcement learning (DRL). We first define fault diagnosis as a sequential decision-making problem in the classification Markov decision process. Next, the vibration signals are converted to uniform-sized TF maps by synchro-extracting transform to enhance the robustness of feature representation. Finally, a diagnosis agent is built and trained in the framework of DRL to learn the optimal classification policy automatically. Experimental results show that this method not only achieves better generalization and stability with an overall accuracy of over 99.5% in single-speed load cases but also outperforms others in multiwork conditions.

This paper proposes a multi-objective optimization method for the optimization design of a new dual-stator arc permanent magnet machine (DS-APMM) which can be applied on the direct-drive scanning systems with limited angular movement. The proposed optimization method integrates light gradient boosting machine (LightGBM) with differential evolution algorithm (DEA) to achieve optimal design objectives of high back electromotive force, low total harmonic distortion, high average torque, and low torque ripple at different rotor speeds. The machine topology and analytical model of DS-APMM are firstly presented to determine the structural parameters to be optimized. The sensitivity of each structural parameter to the optimization objectives is analyzed based on the SHAP (SHapley Additive exPlanations) value. Then, a finite-element analysis (FEA)-based DS-APMM model is developed to acquire sample data. Based on the acquired sample data, a machine learning algorithm, LightGBM, is introduced to establish surrogate model that can fit the function relationship between design objectives and structural parameters. Subsequently, an intelligent search algorithm named DEA is adopted to search optimal combination of the structural parameters and hence obtain optimal machine performances of DS-APMM. Finally, both FEA and prototype experiments verify the feasibility and superiority of the proposed multi-objective optimization method.

This paper is dedicated to studying a new position measurement method of a linear motor mover based on machine vision, which provides a novel idea for the detection of mover position. A rapid-precise measurement system based on a fence image and a phase correlation algorithm (PCA) is established. Multiline sampling and parallel computing methods are used to simplify the fence image directly; these methods can convert the 2-D image motion estimation into a simpler, 1-D signal process. To rapidly detect the mover position with high precision, a 1-D extended phase correlation algorithm (EPCA) is proposed. During position measurement, three key steps for the implementation are applied as follows. 1) Capture objective fence stripes using a high-speed camera installed beside the mover; 2) suppress the spectral leakage of discrete Fourier transform by a Hanning window function; and 3) calculate the displacement vector of the linear motor mover using a 1-D PCA and the least square method. Finally, the actual displacement of the mover can be obtained according to the system calibration. Experimental results demonstrate that the proposed 1-D EPCA implemented at measuring mover position is strongly robust and speedy with a detecting accuracy of 0.02 mm.