Conveyor belt fault prediction method, system and device based on HTM

Abstract

The present invention discloses a conveyor belt fault prediction method, system and device based on the HTM (Hierarchical Temporal Memory). The method comprises the steps of: collecting state data ofa conveyor belt device; and inputting the state data of the conveyor belt device into an HTM algorithm model for processing so as to output abnormal scores. The system comprises a collection unit anda processing unit. The device comprises at least one storage and at least one processor configured to load a program in the storage to execute the conveyor belt fault prediction method based on the HTM. The conveyor belt fault prediction scheme does not need manual operation to define a rule in advance, does not need manual operation to perform rule association mining between states of a lot of states and does not need manual operation of updating the rule to greatly reduce the workload and work burden of operators, improve the working efficiency and operation usage convenience and greatly improve the fault prediction accuracy and real-time effectiveness. The conveyor belt fault prediction method, system and device based on the HTM can be widely applied in the airport transmission facilities.

Description

technical field [0001] The invention relates to fault prediction technology, in particular to a method, system and device for fault prediction of a conveyor belt (airport luggage conveyor belt) based on HTM algorithm. Background technique [0002] Explanation of technical terms: [0003] HTM: Hierarchical Temporal Memory, hierarchical temporal memory algorithm. [0004] Maintenance procedures for airport baggage conveyor belts, a production facility with old and even obsolete equipment, often lead to unnecessary costs, such as losses due to operational downtime, wasted energy and labor costs. Usually, according to the traditional maintenance procedures, it needs to be regularly maintained, which means that the operator is likely to maintain some equipment that does not need to be maintained, which means that time and resources are wasted; or , Replace the equipment that still has use value. In addition, using traditional maintenance procedures, if a piece of equipment doe...

AI Technical Summary

Problems solved by technology

However, using the method of "condition monitoring + rule matching" to realize fault prediction has many disadvantages, for example: 1. It is necessary to define a number of rules in advance based on the experience of operators, which involves too many human operations, resulting in the staff's work 2. If a new fault type appears and the original rules cannot be matched correctly, it is necessary to manually update the rules, and the timeliness of updating iterations is low; 3. When the status is relatively low For many times, it is difficult for humans to discover the rule associations between states. Therefore, it is difficult for manually defined rules to accurately match the corresponding states, resulting in low accuracy of fault prediction.

Images