To enhance the quality and mechanical performance of a carbon fiber–reinforced polymer (CFRP) workpiece, this paper prepares a polyacrylonitrile (PAN)-based carbon fiber–reinforced thermosetting polymer (CFRTP) laminated board through compression molding, and carries out orthogonal tests and single-factor tests to disclose the effects of different process parameters (i.e., compression temperature, compression pressure, pressure-holding time, and cooling rate) on the mechanical performance of the CFRTP workpieces. Moreover, the process parameters of compression molding were optimized based on the test results. The research results show that: The process parameters of compression molding can be ranked as compression temperature, pressure-holding time, compression pressure, cooling rate, and mold-opening temperature, in descending order of the impact on the mechanical property of the CFRTP; the optimal process parameters for compression molding include a compression temperature of 150 °C, a pressure-holding time of 20 min, a compression pressure of 50 T, a cooling rate of 3.5 °C/min, and a mold-opening temperature of 80 °C. Under this parameter combination, the tensile strength, bending strength, and the interlaminar shear strength (ILSS) of the samples were, respectively, 785.28, 680.36, and 66.15 MPa.

Human action recognition algorithms have garnered significant research interest due to their vast potential for applications. Existing human behavior recognition algorithms primarily focus on recognizing general behaviors using a large number of datasets. However, in industrial applications, there are typically constraints such as limited sample sizes and high accuracy requirements, necessitating algorithmic improvements. This article proposes a graph convolution neural network model that combines prior knowledge supervision and attention mechanisms, designed to fulfill the specific action recognition requirements for workers installing solar panels. The model extracts prior knowledge from training data, improving the training effectiveness of action recognition models and enhancing the recognition reliability of special actions. The experimental results demonstrate that the method proposed in this paper surpasses traditional models in terms of recognizing solar panel installation actions accurately. The proposed method satisfies the need for highly accurate recognition of designated person behavior in industrial applications, showing promising application prospects.

The carbon-fiber-reinforced polymer (CFRP) is a mainstream material for lightweight products from the end of the 20th century to the present day. Its compression molding process has obvious advantages in mass production. This paper attempts to establish the constitutive models of compression molding of the CFRP materials and study their mechanism. Based on anisotropic linear elastic mechanics, viscoelastic mechanics, and thermodynamics, as well as the Maxwell viscoelastic constitutive model, we first establish the constitutive model of thermorheologically simple CFRP materials (TSMs). Then, considering the influence of temperature on the initial stiffness and equilibrium stiffness, the concept of temperature stiffness coefficient is introduced, and the Cartier coordinate system is converted into a cylindrical coordinate system, thereby establishing the constitutive model of thermorheologically complex materials (TCMs) using the tensor form. Finally, by comparing to the structure of the Zocher model, the two constitutive models established in this study are verified. The research findings have important theoretical research significance for studying the compression molding mechanism of carbon fiber and further improving the quality of product molding.