Considering the complexity and the criticality of the stacker equipment, in order to solve the problem that the stop accuracy of the stacker reduces or even fails to work due to abrasion of the running rail, this paper proposes a cooperative detection method based on Pulse Coupling Neural Network (PCNN) and wavelet transform theory to detect the abnormal points of the stacker running rail in industrial environment by analyzing the variation signals. First of all, considering the fact that the data is mixed up with noises because of the environment at the site and the possibility of the data acquisition equipment breaking down, a noise reduction method for the vibration signal data of stacker is constructed based on PCNN. Then, the basic theory of wavelet transform is introduced and then the rules of judging anomaly points on stackers’ running tracks are discussed based on wavelet transform. In addition, a cooperative detection method based on PCNN and wavelet transform theory is carried out based on the space-time distribution feature of the vibration of the stacker orbits in the industrial environment. Then the rationality of the proposed algorithm is verified by simulation through data provided by State Grid Measuring Center of China. This paper constructs a model of the abnormal point detection of the stackers in an industrial environment. The experimental simulation and example simulation show that the cooperative detection method based on PCNN and wavelet transform theory can effectively detect and locate the anomaly points of the stacker running tracks. The expansibility in engineering applications is promising. Lastly, some conclusions are discussed.
A New Cooperative Anomaly Detection Method for Stacker Running Track of Automated Storage and Retrieval System in Industrial Environment
