C: Prediction Module
This module uses records of events from various periods to predict their development in the future. To this end, the results of planned basic research are employed that aim at adapting an evolution genetic algorithm, which treats belt damage analogically to subsequent stages of the development of living organisms populations. Population development rate is identified and adjusted to the recorded change gradient of the state of damage. Calibration process takes place in operating conditions.
Research results confirm that over time the rate of damage density increment increases not only linearly but also according to quadratic function.
This is why it seems justified to do further research into core condition change with the use of other belt durability measures, e.g. the number of complete cycles traveled by the loop of the belt. Analysis of complete cycles traveled by belt loop around the conveyor allows to broaden the comparative group by including belts operating on conveyors of different length and different speed. It also allows to precisely identify the influence of those factors (both “spot” and “linear”) on the belt’s life time.
The research also allowed to identify the influence of conveyor length on the rate of damage increment, which serves as confirmation to earlier research and shows that individual selection of damage trajectory for each of the separate belt sections should lead to the best results. Further investigation into the change characteristics may lead to establishing a methodology for predicting optimal belt replacement time.
The change of belt damage density in relation
to operating time with a selected model of quadratic function
The percentage share of “spot” and “linear” damage factors
at play in the process of belt wear, depending on conveyor length
Response surface for damage density non-linear regression depending
on belt loop length and previous operating time of belt sections, in months
Analysis of research data confirms that over time the rate of damage density increment increases and not only linearly but also according to quadratic function (e.g. a quadratic function model may be applied). What is more, it was also possible to identify the influence of conveyor length on the rate of damage increment, which serves as confirmation to earlier research and shows that individual selection of damage trajectory for each of the separate belt sections should lead to the best results. The models obtained may be used to predict optimal moment for replacement of a belt section in the loop.