Research And System Development For Impurity Detection In Pickled And Dried Mustard Based On Multispectral Image Technology

Pickled and dried mustard(PDM)is a traditional fermented vegetable product,it is made from common mustard greens by drying and piling up the leaves,then salting and drying them.It is not only rich in nutritional elements such as vitamins,amino acids and dietary fiber,but also exists as a food auxiliary material for a long time due to its unique flavor.Pickled and dried mustard is a dry form of pickled vegetables,the manufacturing process is complex and requires long periods of outdoor exposure and yellowing,and various foreign matter(FM)will be mixed in the later process of transportation,storage,processing and packaging,which seriously affects the food quality of the pickled and dried mustard.Therefore,it is necessary to adopt a detection technology with rapid detection characteristics to detect impurities in the pickled and dried mustard.Synthetically analyzing the characteristics and applications of traditional detection techniques and advanced spectral detection techniques in the field of food inspection,the multispectral imaging technology can meet the needs of online detection,making the multispectral imaging technology a promising option.The purpose of this paper is to research and develop a set of equipment and system which can detect impurities in the pickled and dried mustard online and perform impurities separation,and the system can be used stably in the food production sites.The research contents and development work of this article are as follows:1.The detection method of impurities in the pickled and dried mustard on the moving conveyor belt based on multispectral image technology was studied.Multispectral images of PDM and FM in a quiescent state and the PDM mixed with FM in a moving state were respectively obtained by using the multispectral camera with a spectral range from 676 to952nm?Pure pixel data of PDM and FM were extracted from multispectral images of the PDM and the FM in a quiescent state,and then the support vector machine(SVM)and the back propagation neural network(BPNN)were applied to develop models to classify FM and PDM on the full bands,respectively.The classification accuracy and the mean prediction time of SVM model were 98.23% and 6.8s;the classification accuracy and the mean prediction time of BPNN model were 98.07% and 0.04 s.The BPNN model was selected as the optimal model considering the classification accuracy and prediction time synthetically.Using the optimal model to detect FM in the PDM during the moving process,the identification accuracy of FM was 97.9%.The results demonstrated that multispectral imaging technology could be used for the online detection of foreign matter in the pickled and dried mustard.2.The hardware design of the impurity detection and sorting system for the pickled and dried mustard was completed.Based on the hardware structure diagram of the system,the selection of multispectral equipment,transmission equipment,sorting equipment and industrial computer was completed.According to the control requirements of programmable logic controller(PLC),the selection of related equipment was completed,and the PLC control system was built.The electrical test and functional test of the hardware system were carried out,which can realize the control of conveyor belt,integrated solenoid valve and other devices.3.The software design of impurity detection and sorting system for the pickled and dried mustard was completed,which can realize the real-time detection and impurity removal functions of impurities in the pickled and dried mustard.The design of the software system is based on the functional requirements and the impurity detection algorithm of the pickled and dried mustard.The function modules and visual operation interface are completed by graphical programming through LabVIEW development software,and the functions of motion platform control,multispectral image acquisition,display and processing,and impurity removal by controlling color selection equipment are realized together with the communication with the lower computer PLC.The whole system is easy to operate and stable to meet the actual needs of industrial production.