Sometimes the automation equipment cannot solve all the problems for industrial enterprises, and human workers cannot be replaced by machines in production activities. The possibility that the workers develop work-related musculoskeletal disorders, while performing high intensity and repetitive installation and commissioning work over a long period of time, is very high. A mechanical design of a passive upper extremities exoskeleton suit to reduce the muscles effort of upper limbs is proposed in this article. Thereby, a decrease in the work-related musculoskeletal disorders risk is expected. To evaluate the ergonomic contribution of the passive upper extremities exoskeleton suit, both static and dynamic tool lift experiments were designed, in which 10 volunteers were asked to participate in the experiments. The surface electromyography is captured from these volunteers to measure the magnitude of muscle output forces that are applied with and then without passive upper extremities exoskeleton suit assistance during the process of manual handling, and the tests are collected for comparison. Results show that there is a significant decrease in the output force and fatigue in deltoid, biceps brachii, and brachioradiali, especially in biceps brachial which is up to 67.8%. The implementation of passive upper extremities exoskeleton suit is not only a benefit to reduce workers’ upper extremities fatigue but also ultimately increase the work efficiency by minimizing work-related musculoskeletal disorders and safety accidents.

In this study, a knee-assisted exoskeleton that can assist the wearer's knee joints at the appropriate phase of the gait cycle is designed. A convolutional neural network (CNN) model is used in the gait control to identify the locomotion modes of the exoskeleton. In order to verify the CNN-based locomotion mode identification method, an offline CNN model was created in MATLAB. The experiment was conducted and seven healthy subjects’ hip, knee, and ankle joint angles were captured and six common locomotion modes were recognized in the experiments. The recorded data were segmented with overlapping sliding windows of varying sizes and were tested using a stratified 5-fold cross-validation technique. The experimental findings showed that the appropriate window size was 1.25T (T stands for the normal adult gait cycle). The lowest and the highest accuracies of the test sets at the window size of 1.25T were 96.47% ± 0.83% and 99.67% ± 0.49% on different subjects. It also showed that the model has strong generalization. Thus, the algorithm had proved useful to extract the characteristics of lower limb joint angles in various locomotion modes and the approach in this paper can be extended to the recognition of motion patterns in lower limb exoskeletons. GRAPHICAL ABSTRACT