基于自诊模型的直角机器人闭环检测系统研发

Research and development of a closed-loop inspection system for cartesian robots based on a self-diagnosis model

为满足市场对直角机器人相关检测需求,该文研发了基于自诊模型的直角机器人闭环检测系统。首先调研已有检测标准和新需求,确定闭环检测系统的关键技术和目标,搭建基于知识库的自诊模型架构。然后在自诊模型中,分别引入故障树、功能列表和数学模型构建知识库管理系统;引入规则推理、功能验证和实时计算实现检测系统关键技术。最后通过搭建实验平台验证检测系统符合设计目标,能满足直角坐标类智能装备分析与检测的需求。

[Objective]With the steady advancement of industrial automation,Cartesian robots have become increasingly prevalent in intelligent manufacturing.However,traditional inspection systems for these robots struggle with issues such as incomplete detection parameters and a lack of self-diagnosis capabilities,which are insufficient to meet emerging market demands.This study aims to address these challenges by developing a closed-loop inspection system that incorporates a self-diagnosis model for Cartesian robots.The proposed system seeks to enhance the inspection efficiency and accuracy of Cartesian robots,ensuring their performance and safety and promoting the healthy development of the intelligent manufacturing industry.[Methods]This paper first identifies the core technologies and inspection objectives necessary for a Cartesian robot inspection system,comparing existing inspection standards with new market demands.Next,a knowledge-based self-diagnosis model is proposed and established,integrating fault tree analysis,function lists,and mathematical models to form the foundation of the knowledge base management system.The system employs rule-based reasoning,functional verification,and real-time calculation techniques within the inference engine to facilitate decision-making regarding detection results.To implement the system,a modular programming approach is adopted,segmenting it into application and interface layers for design simplicity and flexibility.The application layer revolves around the four primary modules of the Cartesian robot system,while the interface layer encapsulates interface classes for the control card,enabling cross-platform migration through a link library,thereby enhancing system scalability.In building the knowledge base,the objectives and scope are first outlined,followed by the collection and organization of relevant knowledge.Appropriate methods are then utilized to represent and shape the initial knowledge base.For constructing the fault detection knowledge base,this paper employs fault tree modeling and analysis techniques.This includes conducting quantitative assessments of the probability importance and critical importance of key events and representing knowledge through production rules.[Results]The implementation of this system reveals several key outcomes:①The closed-loop inspection system for Cartesian robots,rooted in the self-diagnosis model,can encompass vital modules such as the control system and execution mechanism,ensuring comprehensive detection of performance,functions,and faults.②By incorporating a knowledge-based management system and an intelligent reasoning mechanism,the inspection system possesses self-learning and self-iteration capabilities,thus continuously enhancing inspection efficiency and accuracy.③The system demonstrates scalability and compatibility,adapting seamlessly to the inspection requirements of diverse types and specifications of Cartesian robots.[Conclusions]The intelligent inspection system devised for Cartesian robots in this paper addresses prevalent issues in traditional industrial robot inspection systems and aligns with the emerging market demands for Cartesian robot inspection.This system employs a self-diagnosis model anchored in a knowledge base,combining fault tree analysis,rule-based reasoning,and other techniques for comprehensive detection.Experimental validation has shown that the system performs exceptionally well in fault detection,functional verification,and performance evaluation.Future efforts will focus on refining and enhancing this system to better cater to the application needs of Cartesian robots in intelligent manufacturing and industrial automation.