CN-122022402-A - Intelligent scheduling method and system for multi-station joint regeneration of waste sand

CN122022402ACN 122022402 ACN122022402 ACN 122022402ACN-122022402-A

Abstract

The invention belongs to the technical field of waste sand regeneration treatment and intelligent control, and relates to an intelligent scheduling method and system for waste sand multi-procedure joint regeneration, which are used for generating a real-time working condition data set by acquiring waste sand characteristic parameters and equipment state parameters of a plurality of procedures in the waste sand regeneration process, inputting the real-time working condition data set into a preset virtual mapping model for influence prediction and outputting procedure collaborative prediction data, and combining a scheduling algorithm for balancing the multidimensional production targets to generate an initial scheduling scheme, introducing a dynamic change device constraint condition according to the initial scheduling scheme to generate a dynamic scheduling instruction, controlling waste sand regeneration equipment to execute the dynamic scheduling instruction, collecting feedback data in the execution process, updating the real-time working condition data set according to the feedback data, and realizing dynamic collaborative optimization and self-adaptive control on the regeneration flow, thereby improving the overall production efficiency and system robustness.

Inventors

DING YI
REN QIFANG
JIN ZHEN
MA RUI
ZHANG MIAO

Assignees

安徽建筑大学

Dates

Publication Date: 20260512
Application Date: 20260413

Claims (10)

1. The intelligent scheduling method for the multi-station joint regeneration of the waste sand is characterized by comprising the following steps of: Acquiring waste sand characteristic parameters and equipment state parameters of a plurality of working procedures in the waste sand regeneration process, and performing fusion processing to generate a real-time working condition data set; Inputting the real-time working condition data set into a preset virtual mapping model for influence prediction, and outputting working procedure collaborative prediction data, wherein the virtual mapping model is used for representing dynamic association among working procedures; Based on the procedure collaborative prediction data, generating an initial scheduling scheme by combining a scheduling algorithm for balancing the multidimensional production target; Introducing dynamic equipment constraint conditions according to the initial scheduling scheme to generate a dynamic scheduling instruction; and controlling the waste sand regeneration equipment to execute the dynamic scheduling instruction, collecting feedback data in the execution process, and updating the real-time working condition data set according to the feedback data.
2. The intelligent scheduling method for joint regeneration of multiple sand operations of claim 1, wherein the step of generating the real-time working condition data set comprises: collecting real-time parameters of a plurality of procedures in the regeneration process of the waste sand, and obtaining original state data through pretreatment; the method comprises the steps of calling historical data related to current working conditions from a database pre-stored with historical production information based on multi-dimensional similarity matching of current working condition characteristics and historical working condition records to obtain historical working condition data; and carrying out weighted fusion on the original state data and the historical working condition data to generate the real-time working condition data set, wherein fusion weights are dynamically distributed according to the real-time confidence coefficient and the historical similarity of the data sources.
3. The intelligent scheduling method for the joint regeneration of the waste sand and the multiple processes according to claim 2, wherein the construction and the application of the virtual mapping model comprise the following steps: Training to obtain an initial relation model by a machine learning method based on historical production information; based on correlation analysis among historical process parameters, quantifying the dependency intensity among the processes, and generating a process chain weight factor; and integrating the process chain weight factors into the initial relation model, and forming the virtual mapping model by adjusting the contribution degree of the upstream process output to the downstream process input.
4. The intelligent scheduling method for joint regeneration of multiple sand operations according to claim 1, wherein the step of generating the initial scheduling scheme comprises: analyzing the process collaborative prediction data, and generating a process priority list by quantifying the comprehensive influence degree of each process on a multi-dimensional production target, wherein the multi-dimensional production target comprises the energy consumption, quality and efficiency of a production task; generating an optimized set value of the equipment operation parameters through multi-objective optimization calculation according to the procedure priority list and combining with equipment operation constraint conditions to form the initial scheduling scheme; The multi-objective optimization calculation adopts a particle swarm optimization algorithm, and sequentially carries out parameter optimization on each process according to the sequence of the priority of the process from high to low.
5. The intelligent scheduling method for joint regeneration of multiple sand operations of claim 4, wherein the step of generating the dynamic scheduling command comprises: Calculating the time margin of each process based on the buffer capacity and the historical execution time fluctuation range between the processes, and generating an elasticity parameter; Applying the elastic parameters to the initial scheduling scheme, expanding the fixed time node into a flexible execution time window, and generating an adjusted scheduling instruction; And performing conflict detection on the adjusted scheduling instruction, if the conflict is detected, cooperatively adjusting the elastic parameters and the priorities of related procedures to eliminate the conflict, performing limited iterative verification on the adjusted instruction until the elastic execution windows of all the procedures are consistent and have no conflict, and outputting a final dynamic scheduling instruction.
6. The intelligent scheduling method for joint regeneration of multiple sand waste processes according to claim 5, wherein the generating of the elastic parameters further comprises: Dynamically adjusting the value of the elastic parameter according to the prediction result of future working condition fluctuation in the working procedure collaborative prediction data to generate a self-adaptive elastic parameter; The adjusted scheduling instructions are generated using the adaptive elastic parameters, thereby enabling flexibility of the scheduling instructions to predictively adapt to future production changes.
7. The intelligent scheduling method for joint regeneration of multiple sand waste sites according to claim 1, wherein the application of the feedback data comprises: Comparing the feedback data in the executing process with an expected executing target in the dynamic scheduling instruction, and calculating an executing deviation; feeding back the execution deviation to a virtual mapping model, and triggering on-line parameter correction of the model; and updating the procedure collaborative prediction data by using the corrected virtual mapping model to realize closed-loop optimization of the scheduling instruction.
8. The intelligent scheduling method for the multi-station joint regeneration of the waste sand according to claim 1, further comprising: Performing trend analysis on the execution deviation in the continuous scheduling period, identifying systematic performance drift, and generating a strategy adjustment factor; dynamically adjusting the weight distribution of the multidimensional production targets in the scheduling algorithm based on the strategy adjustment factors; And generating an initial scheduling scheme by adopting a scheduling algorithm for updating the weight, and realizing autonomous evolution and continuous optimization of a scheduling strategy.
9. The intelligent scheduling method for the multi-station joint regeneration of the waste sand according to claim 1, further comprising: According to the statistical characteristics of the execution deviation, the confidence weight of the original state data and the historical working condition data in the fusion process is dynamically adjusted; And carrying out weighted fusion on the original state data and the historical working condition data by adopting the confidence coefficient weight to generate a real-time working condition data set, so that the data fusion process has self-adaption capability on the system reliability.
10. An intelligent scheduling system for joint regeneration of waste sand and multiple processes, which is characterized by comprising: The data fusion module is used for acquiring the characteristic parameters of the waste sand and the state parameters of the equipment, and generating a real-time working condition data set by combining the historical working condition data; the prediction analysis module is used for processing the real-time working condition data set through a virtual mapping model and outputting working procedure collaborative prediction data; The scheme making module is used for generating an initial scheduling scheme according to the procedure collaborative prediction data and combining a scheduling algorithm for balancing the multidimensional production target; The dynamic scheduling module is used for generating a dynamic scheduling instruction by introducing equipment constraint conditions according to the initial scheduling scheme; And the control execution module is used for controlling the waste sand regeneration equipment to execute the dynamic scheduling instruction, collecting feedback data and transmitting the feedback data to the data fusion module so as to update the real-time working condition data set.

Description

Intelligent scheduling method and system for multi-station joint regeneration of waste sand Technical Field The invention belongs to the technical field of waste sand regeneration treatment and intelligent control, and relates to an intelligent scheduling method and system for waste sand multi-station joint regeneration. Background The regeneration of used sand, especially in the field of foundry industry, refers to the process of treating used sand by a series of physical or chemical methods to restore its useful properties for recycling. This process typically involves multiple closely coupled steps of crushing, sieving, magnetic separation, washing, drying, and cooling. The operation efficiency and the coordination degree of the procedures directly determine the quality, the regeneration rate, the energy consumption and the final production cost of the regenerated sand, so that the efficient production scheduling of multiple processes is important. In the existing waste sand regeneration production line, the scheduling mode mainly depends on manual experience or a simple automatic control system based on fixed rules. And an operator decides the start-stop time and the operation parameters of each process equipment according to field observation and past experience. In a production line with higher automation degree, although a programmable logic controller is adopted to control a single device, a control system of each process usually operates independently, and connection and material circulation among the processes mainly depend on preset and static logic rules, for example, a level gauge signal triggers the starting of downstream devices. However, the prior art has obvious technical defects that firstly, the process control systems are mutually independent, and lack of global information sharing and cooperative mechanisms, so that the coordination among the processes is poor, and the phenomenon that materials are jammed in one link and equipment in the other link is idle easily occurs. Secondly, the scheduling strategy based on fixed rules is stiff, and cannot adapt to the characteristics of waste sand raw materials, such as humidity and dynamic change of impurity content, so that the treatment effect is poor or unnecessary energy waste is often caused. In addition, the existing scheduling mode lacks predictability of the production process, can only perform passive response to potential bottlenecks or equipment anomalies, has a response lag, and is difficult to optimize the overall production benefit. Disclosure of Invention In order to overcome the defects of the prior art, the invention provides the technical scheme that the first embodiment of the invention provides an intelligent scheduling method for multi-process combined regeneration of waste sand, which comprises the steps of obtaining waste sand characteristic parameters and equipment state parameters of a plurality of processes in the waste sand regeneration process, and performing fusion processing to generate a real-time working condition data set. And inputting the real-time working condition data set into a preset virtual mapping model for influence prediction, and outputting working procedure collaborative prediction data, wherein the virtual mapping model is used for representing dynamic association among working procedures. And generating an initial scheduling scheme by combining a scheduling algorithm for balancing the multidimensional production target based on the procedure collaborative prediction data. And generating a dynamic scheduling instruction according to the initial scheduling scheme and introducing dynamic changing equipment constraint conditions. And controlling the waste sand regeneration equipment to execute the dynamic scheduling instruction, collecting feedback data in the execution process, and updating the real-time working condition data set according to the feedback data. The second embodiment of the invention provides an intelligent scheduling system for multi-process combined regeneration of waste sand, which comprises a data fusion module, a prediction analysis module, a scheme making module, a dynamic scheduling module and a control execution module. The data fusion module is connected with the prediction analysis module, the prediction analysis module is connected with the scheme making module, the scheme making module is connected with the dynamic scheduling module, the dynamic scheduling module is connected with the control execution module, and the control execution module is connected with the data fusion module. And the data fusion module is used for acquiring the waste sand characteristic parameters and the equipment state parameters and generating a real-time working condition data set by combining the historical working condition data. And the prediction analysis module is used for processing the real-time working condition data set through a preset virtual mapping model and outputting working proc