Research On Energy Consumption Optimization Method Of Printing And Dyeing Process Based On Machine Learning

In recent years,people's pursuit of quality of life is getting higher and higher,especially in terms of ecological environment.Coupled with the country's efforts to strengthen the construction of ecological civilization,General Secretary Xi Jinping put forward the idea that green mountains and green mountains are the golden mountains and the silver mountains during the inspection in Anji,Zhejiang,accelerating the progress of energy saving and emission reduction.As a printing and dyeing textile industry with high energy consumption and high pollution,energy saving and emission reduction have become an urgent problem to be solved in this industry.Initially,the optimization of the process flow and the optimization of the scheduling of the workshop achieved a certain effect.However,with the rise and maturity of the Internet of Things and big data technologies,it has become possible to explore the energy saving and emission reduction methods of printing and dyeing companies from a data perspective.Each process of printing and dyeing contains a large amount of production data,including process parameters and energy consumption data,and these large amounts of data also contain some unknown laws.This paper starts from the data of the printing and dyeing process finalization process,combines order-related information,process parameter-related information,energy-related information,etc.,to construct energy consumption categories and energy consumption per unit output as predicted values,and conducts model training after certain data preprocessing.Through the application of the improved differential evolution algorithm based on the gradient lifting tree model,the energy consumption in the subsequent production process is optimized,and the recommended process parameters are used to guide the subsequent production and processing process,thereby achieving the effect of energy saving and emission reduction.The main work and results of this article are as follows:1.Research on Energy Consumption Classification and Regression in Printing and Dyeing Process.Starting from the order,combining the related process parameters and energy consumption data of the setting machine to classify and optimize the data,an gradient boosting tree model is used for the classification and regression prediction of the setting machine data,and its comparison with the comparison is carried out through comparative experiments.The effectiveness of other methods proves the effectiveness of this method.2.Research on energy consumption optimization and recommendation algorithm in the process of dyeing and dyeing.Using historical data for model training,an improved differential evolution algorithm(GBDT-IDE)based on the gradient boosting tree model is proposed to optimize the energy consumption of the processing machine.According to the different input of each raw material,the process parameters of the setting machine are recommended to a certain extent to guide the subsequent setting process,so as to achieve the purpose of energy consumption optimization.Using subsequent production data and combining historical data,continue to optimize the energy consumption during the sizing process,and continue to optimize to achieve better results.3.Development of a web-based printing and dyeing data platform system.This system analyzes and optimizes the energy consumption data of the printing and dyeing process during the use of the setting machine,visualizes the data analysis results,and can perform a certain degree of energy input during the later use according to the actual situation of different orders in the later period recommend.The system also provides query,analysis and mining functions for various historical data,as well as detailed statistical reports and logs.This article mainly analyzes and optimizes the energy consumption of the setting machine,and uses the printing and dyeing data center to visually analyze and optimize the energy consumption data in the printing and dyeing process to guide subsequent production.