Data-driven Energy Analysis And Energy-saving Optimization Of Manufacturing Workshops

The manufacturing industry,which is an important pillar industry of our national economy has the problems of high energy consumption,low energy efficiency,and large carbon emissions and become the key areas of focus for the country to implement major strategies such as energy conservation,emission reduction,and climate change."Made in China 2025" is the first ten-year action plan for our country to implement the strategy of making a strong country.The plan clarifies the strategic policy of "innovation-driven,quality-first,green development,structure optimization,and talent-oriented"."Green manufacturing engineering" is listed as one of the five major projects to be implemented,emphasizing sustainable development as an important focus of the manufacturing power,and taking the path of ecological civilization and environment-friendly development.Green manufacturing and an efficient,clean and low-carbon green manufacturing system should be promoted and constructed in the manufacturing industry.The manufacturing shop is a typical manufacturing system composed of machine tools and auxiliary facilities,which energy consumption has the characteristics of the large total amount,complex structure and characteristics,and many influencing factors.So there exists a large space for energy saving in the manufacturing shop.How to achieve energy saving in the production process of the manufacturing shop is one of the problems that our country's manufacturing industry needs to solve urgently under the global low-carbon development situation,and it is also a problem worthy of in-depth study.Therefore,this paper relies on the Ministry of Industry and Information Technology's comprehensive standardization of intelligent manufacturing and new model application project “New Model Application of Intelligent Manufacturing of Precision Electronic Components”(Ministry of Industry and Information Technology [2016]No.213),taking the energy consumption analysis and energy-saving optimization problems of three typical manufacturing shop as the research objects,and using the energy-saving strategies,intelligent optimization algorithms and scheduling methods as the technical methods to conduct research on energy analysis modelling and energy-saving optimization of flow shop,job shop and flexible flow shop.The research content is as follows:(1)HGSA-based energy-saving optimization method for flow shop.In the production process of the flow shop,a large number of energy consumption problems are generated during the time when the machine waits for the arrival of the workpiece,and an improved Hybrid Genetic Simulated Annealing Algorithm(HGSA)is proposed.First,a heuristic algorithm MME is used for the initial population generation.In the crossover and mutation stage,the operation of randomly selecting crossover and mutation operators is designed.The simulated annealing operation based on the hormone modulation mechanism is performed to avoid the algorithm falling into a local optimum after the crossover and mutation operations are completed.Finally,the proposed algorithm is compared with five algorithms of MA,G-RIS,HGA,DSOMA,IIGA,and it is proved that the proposed algorithm can be close the theoretical optimal makespan of the benchmarks.In the benchmark of 500x20,compared with the five algorithms of MA,G-RIS,HGA,DSOMA and IIGA,the makespan of HGSA is reduced by 31.7%,30.5%,80.6%,36.1% and 71.9% respectively.Finally,the energy-saving effect analysis shows that reducing the idle waiting time of the machine can reduce the energy consumption of the workshop.(2)U-NSGA-III based multi-objective energy saving optimization method for job shop.Aiming at the problem of energy consumption wasting due to underutilization of machine tools in job shop production,a machine state switching energy-saving framework is proposed.And based on this framework,there job shop scheduling optimization models of minimizing makespan,non-processing energy consumption and total weighted tardiness and earliness are analyzed.The unified non-dominated sorting genetic algorithm(U-NSGA-III)combined with MME is used to solve this problem.Three sets of numerical experiments are carried out in the extended Taillard benchmarks to verify the effectiveness of the three-objective model(makespan,non-processing energy consumption and total weighted tardiness and earliness)and the multi-objective optimization algorithm(U-NSGA-III).The results show that,compared with NSGA-II and NSGA-III,U-NSGA-III obtains a better Pareto solution in most test problem instances.The energy efficiency-oriented multi-objective job scheduling algorithm proposed in this paper can achieve significant energy-saving effects,among which non-processing energy consumption can save up to69%.(3)IMVO based energy-saving optimization method for flexible flow shop.Aiming at the energy-saving problem of flexible flow shop,a multi-objective optimization model based on mixed integer nonlinear programming is established to minimize the maximum makespan and energy consumption.In order to solve the problem,an improved multi-universe optimization algorithm(IMVO)is proposed.Firstly the randomly generating method is used to generate the initial population for ensuring the diversity of the individuals in the initial population;the matrix coding is used to indicate the machine allocation of each process of the job(workpiece),and an adaptive factor is introduced to improve the cosmic individual movement formula and the WEP parameter update method;Improved the adaptive formula of WEP can accelerate the algorithm optimization speed in the early stage and improve the accuracy of the local search in the later stage of the optimization.Finally,the IMVO proposed in this paper is compared with MBO algorithm in the literature.The experimental results show that the IMVO algorithm in this paper can better solve the multi-objective energy-saving problem of flexible flow shop.(4)Data-driven energy consumption analysis and energy-saving optimization prototype system.We develop a data-driven manufacturing shop energy consumption analysis and energy saving prototype system.The system mainly includes six modules: user management,order management,process management,equipment management,scheduling management and project management.The scheduling management module mainly displays production scheduling scheme and energy-saving effect flow shop and operations the production scheduling plan and energy-saving result of flow shop,job shop and flexible flow shop.This paper combines the workshop production energy saving strategy,intelligent optimization algorithm and scheduling method to form the intelligent optimization method of workshop energy-saving scheduling,which alleviates the problems of high energy consumption and low energy efficiency existing in the three typical manufacturing workshops,namely flow shop,job shop and flexible flow shop.The results show that the proposed intelligent optimization method can improve the production efficiency of the workshop,reduce the energy consumption and improve the energy utilization efficiency.