A data-driven product collaborative design management method and system
By constructing a dual-stream heterogeneous quantitative acquisition network and a recursive deep belief network, combined with a swarm intelligence optimization algorithm and marginal probability estimation, the data collection and optimization problems in existing product collaborative design management methods are solved, and efficient multi-objective collaborative optimization and adaptive design management are achieved.
Patent Information
- Application Number
- CN202510083371.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-20
- Publication Date
- 2025-09-12
- Estimated Expiration
- 2045-01-20
AI Technical Summary
Existing product collaborative design management methods have problems such as low efficiency, poor reuse rate, and local optimality of optimization results in data collection, knowledge expression and decision optimization. They lack in-depth analysis of the dynamic characteristics and coupling relationships in the design process, resulting in limited system practicality and scalability.
A dual-stream heterogeneous quantitative acquisition network is constructed, data collection and feature extraction are performed through multi-layer convolutional neural networks and long short-term memory networks, association matrices and dynamic coupling strengths are established, and collaborative decision-making units are generated using recursive deep belief networks and swarm intelligence optimization algorithms. Multi-objective optimization solutions are generated by combining marginal probability estimation and Pareto front screening, and convergence verification and online learning adjustments are performed through quantum annealing algorithms.
It has achieved all-round collection of product structure parameters and design process data, improved data integrity and adaptive learning capabilities, and significantly enhanced the quality of design solutions and the robustness and adaptability of the system.