Research On The Wire Harness Insertion Guidance And Defect Detection Technology Based On Machine Vision

With the accelerated development of modern science and technology,industrial automation and intelligence are necessary processes to promote the development of enterprises and accelerate the transformation.Although many existing industrial products can be fully automated production,considering the high cost of introduction of automation and the complexity of the product’s own manufacturing process,there are still some assembly and quality inspection tasks that require manual participation,and manual operations can easily cause instability in product assembly quality.Therefore,in the manual assembly process of the product,online guidance and real-time detection of each assembly process will bring a great improvement to the stability of product quality.In view of this,this article uses machine vision technology to develop a set of wire harness insertion guidance and defect detection system based on machine vision,taking the wiring harness insertion of a pre-installed module in a certain type of electrical control cabinet as the research object.The main contents are as follows:(1)First,the inspection content and requirements of this system are clarified according to the industry inspection standards for the internal wiring harness plug-in of the control cabinet and the actual production requirements of the enterprise;then the system framework is modularized,and its workflow is introduced in detail;finally,based on the actual production situation,a visual imaging scheme is constructed,including the selection of hardware such as cameras,lenses and light sources,as well as the design of the lighting schemes.(2)The positioning algorithm of the terminal block plug-in guide reference point is designed.For specific simple application scenarios,a标记auxiliary positioning algorithm for insertion port positioning is proposed;for applications scenarios with higher degrees of freedom,an automatic positioning algorithm for insertion point based on无标记is proposed;The accuracy and timeliness of the two algorithms are verified through experiments.The experimental results show that the positioning accuracy of the two algorithms can reach more than 98%,and a single picture takes about 60ms.Finally,according to the actual application requirements,the appropriate algorithm is selected as the system positioning scheme.(3)The defect detection algorithm after instrumentation is designed.First of all,based on the inspection requirements,the inspection area is extracted as the ROI for the subsequent quality inspection of the insertion.Then,the coarse and fine two-level positioning algorithm are designed to locate the characters on the harness number tube and use it as the benchmark to further design various defect detection algorithms,including: SVM-based number tube content detection algorithm;wire harness color recognition algorithm based on improved color difference method,wire harness missing insertion detection algorithm based on area judgment,wire harness insertion depth detection algorithm based on length characteristics;Finally,the offline test shows that the accuracy of each algorithm can reach more than 98%,which verifies the effectiveness and accuracy of the proposed algorithm,and can meet the actual production needs of the enterprise.(4)The wiring harness insertion guide and defect detection software system is developed.On the basis of the built framework,the software system is developed on the.Net platform through the joint programming of C++ and C#;through online application testing,it is verified that the system has the characteristics of simple operation,stability and reliability,and can meet the design requirements of the system.