Optimization of manufacturing innovation and entrepreneurship efficiency based on the integration of multimodal large models and PLC systems

The manufacturing industry is currently facing an urgent need for intelligent transformation, but problems such as long innovation cycles and insufficient decision-making data support constrain entrepreneurial efficiency. To address this, this study proposes an optimization model integrating a multimodal large-scale model and a programmable logic controller (PLC) system. By constructing a dedicated data interface, it achieves cross-modal alignment of text commands, equipment images, and real-time control signals. The innovations of this study include: first, establishing a bidirectional information flow architecture between the multimodal large-scale model and the industrial control system; second, developing a dynamic analysis method for control logic based on natural language; and third, constructing a multi-dimensional evaluation system for quantifying innovation and entrepreneurship efficiency. Experiments conducted on an automotive parts production line show that after deployment, the overall equipment efficiency increased by 7.2%, the average fault diagnosis time was reduced by 43%, and the iteration cycle for new process parameters was reduced from 14 to 5 days. This model can effectively improve the agility and scientific decision-making of manufacturing systems, providing a new path for the digital transformation of the manufacturing industry.