Active Scheduling Model Based On Uncertain Order Deep Prediction And Its Application Research

With the rapid development of smart manufacturing,the traditional manufacturing industry is facing the necessary transformation.Enterprises need to adapt to new production methods.Informatization,automation and intelligence have become the trend of advanced manufacturing technology development.Intelligent manufacturing will become an important direction for the development of manufacturing.The competitive field of manufacturing companies has also expanded into a global market.To compensate for the lack of competitiveness,companies have to look to the refined product market and focus on the diversification of customer orders in order to gain a foothold in the fierce market competition.In this context,the model of production according to customer orders is rapidly popularized in the manufacturing industry because it can effectively improve the production flexibility of production enterprises and reduce the impact of uncertain factors on the production and operation of enterprises.At the enterprise level,it is difficult to achieve enterprise agility simply by order production.How to deal with uncertain orders is an important issue for enterprises.At the production level,shop scheduling is an important part of manufacturing companies to improve response speed,reduce costs and improve service.It is especially important to predict the occurrence of abnormal events in advance based on the real-time data and historical data of the production site,and then redistribute the resources of the manufacturing system and actively realize the scheduling and control of the plant equipment.In summary,the prediction of uncertain orders and active scheduling of production workshops are key issues for urgent research.In the past few decades,the traditional manufacturing model has made more mature research results on enterprise order forecasting and production scheduling.However,there are few research results on uncertain order prediction and active scheduling based on deep learning.Therefore,this paper has important theoretical and practical significance for the study of active scheduling based on uncertain order Deep prediction.The main work of this paper is as follows:(1)Explain the impact of uncertain orders,uncertain orders on the production of manufacturing companies,and how companies should respond to uncertain orders;(2)Using the deep learning method,applying the LSTM method to the order forecasting,establishing the uncertain order Deep prediction model,determining the model input and model output,and proposing an adaptive training method,which is compared with the traditional training method to determine The results of the adaptation training method are more accurate;(3)Construct an active scheduling model,use the order forecasting result as the basis of enterprise active scheduling,determine the framework and strategy of active scheduling,and establish an active scheduling robustness model.Improve the agility of the enterprise through active scheduling;(4)Applying the active scheduling method based on uncertain order Deep prediction proposed in this paper to display manufacturing enterprises,through the use of historical data and programming software,it is proved that the uncertain order prediction and active mobility method proposed in this paper is applicable to reality.Manufacturing company,and can help companies complete forecasting and scheduling tasks more efficiently and reasonably.The research indicates that the active scheduling method based on uncertain order Deep prediction proposed in this paper can provide reference and reference for solving the uncertain order forecasting and active scheduling of real manufacturing enterprises.