Recently, due to the expansion of the logistics industry, demand for logistics automation equipment is increasing. The modern logistics industry is a high-tech industry that combines various technologies. In general, as various technologies are grafted, the complexity of the system increases, and the occurrence rate of defects and failures also increases. As such, it is time for a predictive maintenance model specialized for logistics automation equipment. In this paper, in order to secure the operational safety and reliability of the parcel loading system, a predictive maintenance platform was implemented based on the Naive Bayes-LSTM(Long Short Term Memory) model. The predictive maintenance platform presented in this paper works by collecting data and receiving data based on a RabbitMQ, loading data in an InMemory method using a Redis, and managing snapshot DB in real time. Also, in this paper, as a verification of the Naive Bayes-LSTM predictive maintenance platform, the function of measuring the time for data collection/storage/processing and determining outliers/normal values was confirmed. The predictive maintenance platform can contribute to securing reliability and safety by identifying potential failures and defects that may occur in the operation of the parcel loading system in the future.

In modern society, the delivery service market has grown explosively due to rapid changes in social structure and the recent COVID-19 pandemic. Therefore, various problems such as injury to workers and an increase in human accidents are occurring due to the loading and unloading of parcels. In order to solve this problem, domestic company n is developing a “robot-based cargo loading and unloading system”. In developing a new technology system, quantitative reliability targets should be set for efficient operation and development. In this paper, reliability analysis was conducted through field data for the pneumatic gripper of the “robot-based cargo loading system”. The reliability of the failure data was analyzed to estimate the distribution parameters and MTTF. Random data was derived for the probability of occurrence of a failure with the estimated value. By repeating the simulation to predict the number and year of failures according to the estimated parameters of the probability distribution, it was proposed as a method that reflects realistic probabilities rather than calculating with simple arithmetic using the average MTTF previously used in the field.