Multi-model small-batch production line resource load prediction method

Abstract

The invention discloses a multi-model small-batch production line resource load prediction method, which comprises three processes of establishing a resource load prediction function model, preparing simulation data, and performing Monte Carlo simulation by using Crystal Ball software, and is characterized in that simulation operation is performed on the proposed resource load prediction function model by using a Monte Carlo simulation method; obtaining a specific load result of the equipment resource, and performing resource load prediction check on the existing production scheme; according to the method, the production resource load is predicted, making of a dynamic scheduling plan can be effectively supported, the robustness of a scheduling scheme can be improved through an accurate load prediction result, and the production cost is reduced.

Description

technical field [0001] The invention belongs to the technical field of production line resource optimization, and in particular relates to a multi-model and small-batch production line resource load prediction method. Background technique [0002] In the multi-type mixed production process of products, there are often conflicts in the demand for production resources in each process link, and the resource load in the production process is mainly affected by the product quality and human factors in each link of the production line, and the relationship between resource load and influencing factors is usually There is a non-linear relationship. The realization of resource load forecasting usually requires the construction of an effective forecasting model based on a large amount of historical data; however, in the production process, there are great randomness and uncertainty in product quality and human factors in each link; at the same time, due to the lack of relatively unif...

AI Technical Summary

Problems solved by technology

The realization of resource load forecasting usually requires the construction of an effective forecasting model based on a large amount of historical data; however, in the production process, there are great randomness and uncertainty in product quality and human factors in each link; at the same time, due to the lack of relatively unified data Management platform, the data about product quality and production resource demand in each link is usually incomplete, which makes it difficult to predict and evaluate the production resource load

Images