State prediction method for stacker, electronic device and storage medium

An electronic device, comprising:

• at least one processor;
• and
• a memory connected in communication with the at least one processor;
• wherein the memory stores an instruction executable by the at least one processor, and the instruction, when executed by the at least one processor, enables the at least one processor to execute following operations:
• obtaining historical work data and historical maintenance data of the stacker, wherein the historical work data comprises a number of historical work tasks, content of the historical work tasks, and time of the historical work tasks, and the historical maintenance data comprises maintenance records and component life of a first type of components comprised in the stacker;
• obtaining a work task of the stacker within a preset time period, wherein the work task is a task pre-assigned by a warehouse management system to the stacker;
• predicting a state of the stacker during execution of the work task based on the historical work data and the historical maintenance data, by:
• inputting the historical work data and the historical maintenance data into a state prediction model, wherein the state prediction model is trained by:
• obtaining historical work sample data and historical maintenance sample data of the stacker;
• inputting the historical work sample data and the historical maintenance sample data into a preset model;
• obtaining a predicted value of the state of the stacker output by the preset model;
• constructing a loss function based on a true value of the state of the stacker and the predicted value of the state of the stacker;
• and
• training the preset model based on the loss function, to obtain the state prediction model;
• and
• obtaining the state of the stacker output by the state prediction model;
• wherein the state at least comprises time when the stacker fails and a stop position of the stacker when failing;
• simulating the execution of the work task by the stacker within the preset time period based on the historical work data, to obtain a simulation execution result of the stacker;
• generating a state prediction result of the stacker based on the time when the stacker fails and the stop position of the stacker when failing in combination with the simulation execution result, wherein the state prediction result comprises:
• a probability that the stacker is able to complete the work task normally within the preset time period, a probability that the stacker fails within the preset time period, the time when the stacker fails, and the stop position of the stacker when failing;
• predicting a first duration for which the stacker is in a fault state when failing and a second duration required to maintain the stacker based on the historical work data and the historical maintenance data, comprising:
• determining a first faulty component when the stacker fails based on the maintenance records and the component life of the first type of components;
• and
• determining the first duration and the second duration based on the first faulty component when the stacker fails;
• and
• adjusting the work task of the stacker within the preset time period based on the first duration and the second duration.

A non-transitory computer-readable storage medium storing a computer instruction thereon, wherein the computer instruction is used to cause a computer to execute following operations:

• obtaining historical work data and historical maintenance data of the stacker, wherein the historical work data comprises a number of historical work tasks, content of the historical work tasks, and time of the historical work tasks, and the historical maintenance data comprises maintenance records and component life of a first type of components comprised in the stacker;
• obtaining a work task of the stacker within a preset time period, wherein the work task is a task pre-assigned by a warehouse management system to the stacker;
• predicting a state of the stacker during execution of the work task based on the historical work data and the historical maintenance data, by:
• inputting the historical work data and the historical maintenance data into a state prediction model, wherein the state prediction model is trained by:
• obtaining historical work sample data and historical maintenance sample data of the stacker;
• inputting the historical work sample data and the historical maintenance sample data into a preset model;
• obtaining a predicted value of the state of the stacker output by the preset model;
• inputting the historical work sample data and the historical maintenance sample data into a preset model;
• obtaining a predicted value of the state of the stacker output by the preset model;
• constructing a loss function based on a true value of the state of the stacker and the predicted value of the state of the stacker;
• and
• training the preset model based on the loss function, to obtain the state prediction model;
• and
• obtaining the state of the stacker output by the state prediction model;
• wherein the state at least comprises time when the stacker fails and a stop position of the stacker when failing;
• simulating the execution of the work task by the stacker within the preset time period based on the historical work data, to obtain a simulation execution result of the stacker;
• generating a state prediction result of the stacker based on the time when the stacker fails and the stop position of the stacker when failing in combination with the simulation execution result, wherein the state prediction result comprises:
• a probability that the stacker is able to complete the work task normally within the preset time period, a probability that the stacker fails within the preset time period, the time when the stacker fails, and the stop position of the stacker when failing;
• predicting a first duration for which the stacker is in a fault state when failing and a second duration required to maintain the stacker based on the historical work data and the historical maintenance data, comprising:
• determining a first faulty component when the stacker fails based on the maintenance records and the component life of the first type of components;
• and
• determining the first duration and the second duration based on the first faulty component when the stacker fails;
• and
• adjusting the work task of the stacker within the preset time period based on the first duration and the second duration.