Energy-Based Prognostics for Gradual Loss of Conveyor Belt Tension in Discrete Manufacturing Systems

Abstract

This paper presents a data-driven approach for the prognosis of the gradual behavioural deterioration of conveyor belts used for the transportation of pallets between processing workstations of discrete manufacturing systems. The approach relies on the knowledge of the power consumption of a conveyor belt motor driver. Data are collected for two separate cases: the static case and dynamic case. In the static case, power consumption data are collected under different loads and belt tension. These data are used by a prognostic model (artificial neural network (ANN)) to learn the conveyor belt motor driver’s power consumption pattern under different belt tensions and load conditions. The data collected during the dynamic case are used to investigate how the belt tension affects the movement of pallets between conveyor zones. During the run time, the trained prognostic model takes real-time power consumption measurements and load information from a testbench (a discrete multirobot mobile assembling line) and predicts a belt tension class. A consecutive mismatch between the predicted belt tension class and optimal belt tension class is an indication of failure, i.e., a gradual loss of belt tension. Hence, maintenance steps must be taken to avoid further catastrophic situations such as belt slippages on head pulleys, material slippages and belt wear and tear.

Artificial Intelligence for Predictive Maintenance Applications: Key Components, Trustworthiness, and Future Trends

“…It may be indicative of problems if unusual energy consumption is observed. In [122][123][124][125], PdM has been provided by analyzing their energy consumption patterns to gain information on the health of such devices.…”

FASTory assembly line power consumption data

“…In the static case, the data gathered was used to build a data-driven model capable of learning the power consumption pattern of the conveyor belt motor driver under varying belt tensions and load conditions, while in the dynamic case, the relationship between the belt tension and the pallet transportation was examined. This data article adds value to the original research article [6] by making data available for studying, understanding, and establishing the relationship between the health of a conveyor belt and its remaining useful life, which is particularly important for the predictive maintenance of the conveyor belt. Specifically, the data may be utilized for the development of data-driven models for predicting the remaining useful life of conveyor belts.…”

“… Load Combination Active Zones Description 0 0000 No load 1 1000 1 pallet at Z1 2 0100 1 pallet at Z2 3 1100 2 pallets; 1 pallet at each zone (Z1, Z2) 4 0010 1 pallet at Z3 5 1010 2 pallets; 1 pallet at each zone (Z1, Z3) 6 0110 2 pallets; 1 pallet at each zone (Z1, Z3) 7 1110 3 pallets; 1 pallet at each zone (Z1, Z2, Z3) 8 0001 1 pallet at Z5 9 1001 2 pallets; 1 pallet at each zone (Z1, Z5) 10 0101 2 pallets; 1 pallet at each zone (Z1, Z5) 11 1101 3 pallets; 1 pallet at each zone (Z1, Z2, Z5) 12 0011 2 pallets; 1 pallet at each zone (Z3, Z5) 13 1011 3 pallets; 1 pallet at each zone (Z1, Z3, Z5) 14 0111 3 pallets; 1 pallet at each zone (Z2, Z3, Z5) 15 1111 4 pallets; 1 pallet at each zone (Z1, Z2, Z3, Z5)

Fig. 6 Motor driver with head pulley at main conveyor [6] .

…”

Novel Fault Diagnosis of a Conveyor Belt Mis-Tracking via Motor Current Signature Analysis

“…Ref. [ 12 ] proposed energy-based prognostics for the gradual loss of conveyor belt tension in discrete manufacturing systems. Ref.…”