The vibration signals of faulty rotating machinery are typically nonstationary, nonlinear, and mixed with abundant compounded background noise. To extract the potential excitations from the observed rotating machinery, signal demodulation and time-frequency analysis are indispensable. This work proposes a novel particle swarm optimization-based variational mode decomposition method, which adopts the minimum mean envelope entropy to optimize the parameters (α and K) in the existing variational mode decomposition. The proposed fault-detection framework separated the observed vibration signals into a series of intrinsic modes. A certain number of the intrinsic modes are then selected by means of the Hilbert transform-based square envelope spectral kurtosis. Subsequently, in this study, the feature representations were reconstructed via the selected intrinsic modes; then, the envelope spectra of the real faulty conditions were generated in the rotating machinery. To verify the performance of the proposed method, a testbed platform of a gearbox with a combination of different faults was implemented. The experimental results demonstrated that the proposed method represented the patterns of the fault frequency more explicitly than the available empirical mode decomposition, the local mean decomposition, and the wavelet package transform method.

Parameter uncertainties and fluctuated disturbances have brought great difficulties to the smooth and precise control of robot manipulators in some industrial environments. To address these challenges, a robust adaptive sliding mode controller is proposed in this work for accurate control of the robot manipulator. In case of the modeling uncertainties caused by parameters variation during the operational process, the adaptive technique integrated with radial basis function neural networks is utilized. Under such scheme the parameters are automatically adjusted during the tracking process to enhance the system robustness. A new sliding mode disturbance observer is adopted in order to give compensation of the interference and a new variable structure scheme is proposed to effectively suppress the chattering phenomenon. Based on robot assembly and other application verification, the robustness and stability of the proposed approach are demonstrated with superior and smooth tracking performance.

Effective fault diagnosis of rotating machinery plays a pretty important role in the enhanced reliability and improved safety of industrial informatics applications. Although traditional intelligent fault diagnosis techniques such as support vector machine, extreme learning machine and convolutional neural network might achieve satisfactory accuracy, a very high price is caused by marking all samples manually. In this paper, a novel fault diagnosis method of the rotating machinery is proposed by integrating semi-supervised generative adversarial nets (SSGANs) with wavelet transform (WT), namely WT-SSGANs. The proposed WT-SSGANs method involves two parts. In the first part, WT is adopted to transform 1-D raw vibration signals into 2-D time-frequency images. In the second part, the 2-D time-frequency images are inputted into the built SSGANs model to realize fault diagnosis with little labeled samples. The advantage of the built model is that the unlabeled samples might be made full use of through an adversarial learning mechanism. Finally, two case studies are implemented to verify the proposed method. The results indicate that it can achieve higher accuracy and use less labeled samples than other existing methods in literatures. In addition, its performance in stability is pretty good as well. Competitive and promising results are still achieved when working conditions are changed.

EMG-based continuous wrist joint motion estimation has been identified as a promising technique with huge potential in assistive robots. Conventional data-driven model-free methods tend to establish the relationship between the EMG signal and wrist motion using machine learning or deep learning techniques, but cannot interpret the functional relationship between neuro-commands and relevant joint motion. In this paper, an EMG-driven musculoskeletal model is proposed to estimate continuous wrist joint motion. This model interprets the muscle activation levels from EMG signals. A muscle-tendon model is developed to compute the muscle force during the voluntary flexion/extension movement, and a joint kinematic model is established to estimate the continuous wrist motion. To optimize the subject-specific physiological parameters, a genetic algorithm is designed to minimize the differences of joint motion prediction from the musculoskeletal model and joint motion measurement using motion data during training. Results show that mean root-mean-square-errors are 10.08°, 10.33°, 13.22° and 17.59° for single flexion/extension, continuous cycle and random motion trials, respectively. The mean coefficient of determination is over 0.9 for all the motion trials. The proposed EMG-driven model provides an accurate tracking performance based on user’s intention.