Energy-saving strategy recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an energy-saving strategy recommendation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining production work order information, generating a production energy consumption sample, and carrying out the judgment of the comprehensive energy consumption level, sensitive process steps and process route steps according to the production energy consumption sample, meanwhile, high-energy-consumption equipment and high-energy-consumption processes are judged, and effect prediction and evaluation are performed according to the obtained energy-saving strategy and improvement strategy to obtain an evaluation result, so that on the premise that a large number of measurement instruments are newly added and low-cost construction is not needed, the energy-saving effect of the high-energy-consumption equipment is evaluated through an artificial intelligence data analysis method; the method can help enterprises to complete energy consumption fine analysis based on production lines, procedures, processes and equipment, specifically give energy-saving and carbon-reducing strategies which can be adopted by sensitive links, processes and energy-consuming equipment for energy conservation and consumption reduction in enterprise production, and give expected energy-saving and carbon-reducing effect evaluation after the strategies are imported.

Description

Technical Field

[0001] The present application relates to the field of energy management technology, and in particular to a method, device, electronic device and storage medium for recommending an energy-saving strategy. Background Art

[0002] As a major energy consumer and carbon emitter, the manufacturing industry faces tremendous environmental pressure. At the same time, for the enterprise itself, energy consumption cost is an important part of product production cost. By counting production energy consumption, accurately finding the links and problems of energy waste, and realizing energy saving through technological transformation, and reducing production costs, it can bring significant economic benefits to the enterprise. Therefore, for the manufacturing industry, the importance of production energy consumption statistics and energy-saving optimization technology is self-evident. It is not only a need to cope with environmental pressure, but also a driving force for pursuing economic benefits, and also an opportunity to promote technological progress and enjoy policy support.

[0003] At present, energy management systems for production enterprises are already widely used, and Internet of Things technology is also widely used in the monitoring and collection of energy consumption such as electricity, steam, and natural gas. Although energy management systems can meet the basic needs of enterprises for energy consumption measurement, meter reading, monitoring, and statistics, in the technical field of refined management of production energy consumption, if you want to obtain energy consumption data with smaller granularity on the basis of existing energy management, the only way to achieve this is to install additional metering instruments for IoT monitoring of production lines, production lines, processes, energy-consuming equipment, etc. that need to be monitored, and then combine the company's production work order information to conduct production-related statistical analysis on the monitored data. By installing metering instruments on the energy paths that need to be monitored, and obtaining monitoring and metering data through IoT communication between the energy management system and the metering instruments, real-time monitoring and data analysis of the company's energy consumption can be achieved.

[0004] In the adoption of energy-saving and carbon-reduction strategies, current technologies mostly use horizontal and vertical comparisons of energy consumption data, daily / monthly / annual trend comparisons, and statistical charts (line charts, bar charts, energy flow charts) to form more intuitive data comparison results, and then rely on the subjective experience of supervisors to determine the general direction of energy saving and carbon reduction. Using existing technologies, if an enterprise wants to conduct refined energy consumption management, it needs to install a large number of monitoring instruments, which has high construction costs and high project risks, reducing the willingness of enterprises to implement refined energy management. At the same time, based on the obtained statistical charts, manual subjective judgments on the direction of energy saving and carbon reduction are low in accuracy and efficiency. How to improve the accuracy and efficiency of energy saving and carbon reduction is an urgent problem to be solved. Summary of the invention

[0005] Some embodiments of the present application aim to provide a method, device, electronic device and storage medium for recommending an energy-saving strategy. Through the technical solution of the embodiments of the present application, by obtaining production work order information and determining the production energy consumption sample corresponding to the production work order information based on the production work order information; judging the comprehensive energy consumption level of the production energy consumption sample to determine the first improvement strategy; judging the sensitive process steps of the production energy consumption sample to determine the second improvement strategy; judging the process route steps of the production energy consumption sample to determine the third improvement strategy; judging the high-energy-consuming equipment in the production energy consumption sample to determine the first energy-saving strategy; judging the high-energy-consuming process in the production energy consumption sample to determine the second energy-saving strategy; according to the first improvement strategy, the second improvement strategy, the third improvement strategy and the first energy-saving strategy and the second energy-saving strategy, perform effect prediction and evaluation, and obtain an evaluation result corresponding to the production work order information. In the embodiment of the present application, the production work order information is obtained to generate a production energy consumption sample, and the comprehensive energy consumption level, sensitive process steps and process route steps are judged according to the production energy consumption sample. At the same time, high-energy-consuming equipment and high-energy-consuming processes are judged, and the effect prediction and evaluation are performed according to the obtained energy-saving strategy and improvement strategy to obtain the evaluation result. In this way, without the need for a large number of new measuring instruments to be constructed at a low cost, the data analysis method of artificial intelligence can help enterprises complete the refined analysis of energy consumption based on production lines, processes, technologies, and equipment, and provide targeted energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in the production of enterprises, and provide an expected energy-saving and carbon-reduction effect evaluation after the introduction of the strategy.

[0006] In a first aspect, some embodiments of the present application provide a method for recommending an energy-saving strategy, including:

[0007] Acquire production work order information, and determine, based on the production work order information, a production energy consumption sample corresponding to the production work order information;

[0008] Determine the comprehensive energy consumption level of the production energy consumption sample and determine the first improvement strategy;

[0009] Determine the sensitive process steps of the production energy consumption sample and determine the second improvement strategy;

[0010] Determine the process route steps of the production energy consumption sample and determine the third improvement strategy;

[0011] Judging the high energy-consuming equipment in the production energy consumption sample and determining a first energy-saving strategy;

[0012] Judging the high energy-consuming processes in the production energy consumption sample and determining a second energy-saving strategy;

[0013] According to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy and the second energy-saving strategy, effect prediction and evaluation are performed to obtain an evaluation result corresponding to the production work order information.

[0014] Some embodiments of the present application obtain production work order information and then generate production energy consumption samples, and judge the comprehensive energy consumption level, sensitive process steps and process route steps according to the production energy consumption samples, and judge high-energy-consuming equipment and high-energy-consuming processes at the same time, and predict and evaluate the effects based on the obtained energy-saving strategies and improvement strategies to obtain evaluation results. In this way, without the need for a large number of new measuring instruments to be constructed at low cost, artificial intelligence data analysis methods can be used to help enterprises complete refined energy consumption analysis based on production lines, processes, technologies, and equipment, and provide targeted energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in the enterprise's production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0015] Optionally, judging the comprehensive energy consumption level of the production energy consumption sample and determining the first improvement strategy includes:

[0016] According to the production energy consumption samples, the product historical energy consumption ratio parameters, product single product energy consumption parameters and product improvement space parameters are calculated respectively to obtain the first improvement strategy; wherein:

[0017] The product historical energy consumption ratio parameter is obtained by calculating the ratio of each product's energy consumption to the total production energy consumption based on historical production energy consumption samples in a preset time period, and sorting the ratios in descending order;

[0018] The energy consumption parameters of each product are obtained by calculating the total energy consumption of each product and the production quantity of the product;

[0019] The product improvement space parameter is classified and counted according to the energy consumption of each product and the type of work order product to obtain the maximum and minimum unit consumption of each product. Based on the maximum and minimum values, the unit consumption improvement space is determined, and the unit consumption improvement space is sorted in descending order.

[0020] In some embodiments of the present application, the strategy content for evaluating the comprehensive energy consumption level of a product includes three parts: the proportion of historical energy consumption of the product, the energy consumption of a single product, and the room for product improvement. The target products are divided into two types of analysis: system default recommendation and user-selected target product analysis, thereby improving the accuracy of energy consumption improvement.

[0021] Optionally, judging the sensitive process steps of the production energy consumption sample and determining the second improvement strategy includes:

[0022] Determine the process route corresponding to the target product based on the target product and related products;

[0023] Determine, according to the target product and the process route, a multivariate linear regression equation of energy consumption of the target product with respect to the process route;

[0024] Inputting the work order energy consumption data of the product to be screened into the energy consumption multivariate linear regression equation to determine the undetermined coefficient group of the linear regression equation, wherein the undetermined coefficient value at least includes the energy consumption coefficient required for each process step;

[0025] According to the undetermined coefficient groups of different linear regression equations, the sensitive step with the most sensitive product unit consumption of the product to be screened is determined;

[0026] According to the sensitive steps, a linear regression equation for energy consumption of the process route of the product to be screened in different production lines is determined;

[0027] Calculate the process steps in the process route of the product to be screened that are most sensitive to environmental impacts based on a linear regression equation for energy consumption of the process route of the screened product in different production lines;

[0028] The second improvement strategy is determined based on the process step in the process route of the product to be screened that is most sensitive to environmental influences.

[0029] Some embodiments of the present application determine the sensitive process steps of production energy consumption samples, the sensitive processes in the process, and improve the sensitive processes in different production lines.

[0030] Optionally, judging the process route steps of the production energy consumption sample to determine the third improvement strategy includes:

[0031] Determine the process route corresponding to the target product according to the target product and related products;

[0032] The third improvement strategy is determined according to the unit consumption ranking of the preset process route corresponding to the target product.

[0033] In some embodiments of the present application, the accuracy of energy-saving improvement is improved by performing process route analysis on production energy consumption samples and determining improvement strategies according to the ranking of unit consumption.

[0034] Optionally, judging the high energy-consuming equipment in the production energy consumption sample and determining the first energy-saving strategy includes:

[0035] Acquire a first target production line and a preset production tree structure, and determine a first associated production line process corresponding to the first target production line;

[0036] Determine, according to the first target production line and the first associated production line process, a first energy consumption multivariate linear regression equation of the first target production line based on the first associated production line process;

[0037] Determine the energy consumption coefficient of the first process of the first energy consumption multivariate linear regression equation according to the production work order information and the first energy consumption multivariate linear regression equation;

[0038] Calculating a first high-energy-consuming process step of the first target production line, and determining a first energy consumption improvement space parameter corresponding to the first high-energy-consuming process step according to the first high-energy-consuming process step;

[0039] According to the first high-energy-consuming process step, determining the high-energy-consuming equipment associated with the process;

[0040] Determine the process associated with the high energy consumption process, and judge whether the associated process is a production environment sensitive process;

[0041] According to the associated process, determining equipment corresponding to the associated process;

[0042] The first energy-saving strategy is determined according to the energy consumption coefficient of the first process, the first production environment sensitive process, the first energy consumption improvement space parameter and the energy consumption of the equipment corresponding to the associated process.

[0043] Some embodiments of the present application determine the high-energy-consuming equipment in the production energy consumption samples and improve the high-energy-consuming equipment, and thus can improve the energy-consuming equipment as required.

[0044] Optionally, judging the high energy-consuming process in the production energy consumption sample and determining the second energy-saving strategy includes:

[0045] Acquire a second target production line and a preset production tree structure, and determine a second associated production line process corresponding to the second target production line;

[0046] Determine, according to the second target production line and the associated production line process, a second energy consumption multivariate linear regression equation of the second target production line based on the second associated production line process;

[0047] Determine a second process energy consumption coefficient of the second energy consumption multiple linear regression equation according to the production work order information and a second energy consumption multiple linear regression equation of the second target production line based on the second associated production line process;

[0048] Calculating a second high energy consumption process step of the second target production line, and determining a second energy consumption improvement space parameter corresponding to the second high energy consumption process step according to the second high energy consumption process step;

[0049] Determine a second high energy consumption process in the second associated production line process, and determine whether the second high energy consumption process is a production environment sensitive process;

[0050] The second energy-saving strategy is determined based on the second target production line, the production environment sensitive process and the energy consumption improvement space parameters.

[0051] Some embodiments of the present application determine high energy-consuming processes in production energy consumption samples and improve the high energy-consuming processes.

[0052] Optionally, performing effect prediction and evaluation according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy, and the second energy-saving strategy to obtain an evaluation result corresponding to the production work order information includes:

[0053] Obtaining the name of the product whose process is to be improved, and determining the process route corresponding to the product name according to the product name;

[0054] According to the product name and the process route, determine a multiple linear regression equation for energy consumption of the product name based on the process route;

[0055] Obtain target process improvement steps;

[0056] According to the parameters in the target process improvement step, the energy consumption multivariate linear regression equation is corrected to obtain a corrected energy consumption multivariate linear regression equation, and the energy saving effect of the unit consumption of the production line is calculated;

[0057] According to the energy-saving effect of the unit consumption of the production line, the energy-saving effect of the production work order within a preset time period is estimated, and the evaluation result corresponding to the production work order information is determined.

[0058] Some embodiments of the present application specifically provide energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in enterprise production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0059] Optionally, performing effect prediction and evaluation according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy, and the second energy-saving strategy to obtain an evaluation result corresponding to the production work order information includes:

[0060] Acquire a production line of the process to be improved, and determine a process corresponding to the production line according to the production line of the process to be improved;

[0061] Obtain target improvement process or target improvement equipment;

[0062] According to the production line, determining a multivariate linear regression equation of energy consumption of the production line based on the process;

[0063] Correct the coefficients of the energy consumption multivariate linear regression equation according to the target improvement process to obtain a corrected energy consumption multivariate linear regression equation, and calculate the energy saving effect of the production line unit consumption;

[0064] According to the energy-saving effect of the unit consumption of the production line, the production energy-saving effect of the production work order within a preset time period is estimated to obtain an evaluation result corresponding to the production work order information.

[0065] Some embodiments of the present application specifically provide energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in enterprise production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0066] In a second aspect, some embodiments of the present application provide a device for recommending an energy-saving strategy, including:

[0067] An acquisition module, used to acquire production work order information, and determine a production energy consumption sample corresponding to the production work order information according to the production work order information;

[0068] A first determination module is used to determine the comprehensive energy consumption level of the production energy consumption sample and determine a first improvement strategy;

[0069] A second determination module is used to determine the sensitive process steps of the production energy consumption sample and determine a second improvement strategy;

[0070] A third determination module is used to determine the process route steps of the production energy consumption sample and determine a third improvement strategy;

[0071] A fourth determination module, used to judge the high energy-consuming equipment in the production energy consumption sample and determine a first energy-saving strategy;

[0072] A fifth determination module, used to determine the high energy consumption process in the production energy consumption sample and determine the second energy saving strategy;

[0073] A recommendation module is used to predict and evaluate the effects according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy and the second energy-saving strategy, and obtain an evaluation result corresponding to the production work order information.

[0074] Some embodiments of the present application obtain production work order information and then generate production energy consumption samples, and judge the comprehensive energy consumption level, sensitive process steps and process route steps according to the production energy consumption samples, and judge high-energy-consuming equipment and high-energy-consuming processes at the same time, and predict and evaluate the effects based on the obtained energy-saving strategies and improvement strategies to obtain evaluation results. In this way, without the need for a large number of new measuring instruments to be constructed at low cost, artificial intelligence data analysis methods can be used to help enterprises complete refined energy consumption analysis based on production lines, processes, technologies, and equipment, and provide targeted energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in the enterprise's production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0075] In a third aspect, some embodiments of the present application provide an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the method for recommending an energy-saving strategy as described in any embodiment of the first aspect can be implemented.

[0076] In a fourth aspect, some embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the method for recommending an energy-saving strategy as described in any embodiment of the first aspect.

[0077] In a fifth aspect, some embodiments of the present application provide a computer program product, comprising a computer program, wherein the computer program, when executed by a processor, can implement the method for recommending energy-saving strategies as described in any embodiment of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0079] Figure 1 A flowchart of a method for recommending an energy-saving strategy provided in an embodiment of the present application;

[0080] Figure 2 A schematic diagram of the structure of the energy-saving strategy diagnosis and evaluation system provided in an embodiment of the present application;

[0081] Figure 3 A schematic diagram of the process flow of IoT instrument management provided in the embodiment of the present application;

[0082] Figure 4 A schematic diagram of the production model management process provided in the embodiment of the present application;

[0083] Figure 5 A schematic diagram of the process flow of product process management provided in the embodiment of the present application;

[0084] Figure 6 A schematic diagram of the process of calculating production energy consumption information provided in the embodiment of the present application;

[0085] Figure 7 A schematic diagram of a process flow diagram of a method for recommending a strategy for sensitive steps in a product process provided in an embodiment of the present application;

[0086] Figure 8 A schematic diagram of a process flow of a device energy saving recommendation strategy method provided in an embodiment of the present application;

[0087] Fig. 9 A schematic diagram of a process improvement evaluation strategy method provided in an embodiment of the present application;

[0088] Fig.10 A schematic diagram of the process improvement effect provided in the embodiment of the present application;

[0089] Fig.11 A schematic diagram of a process flow of a production equipment improvement evaluation strategy method provided in an embodiment of the present application;

[0090] Fig.12 A schematic diagram of the process improvement effect provided in the embodiment of the present application;

[0091] Fig.13 A schematic diagram of a structure of a recommended device for an energy-saving strategy provided in an embodiment of the present application;

[0092] Fig.14 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0093] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.

[0094] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0095] As a major energy consumer and carbon emitter, the manufacturing industry faces tremendous environmental pressure. At the same time, for the enterprise itself, energy consumption cost is an important part of product production cost. By counting production energy consumption, accurately finding the links and problems of energy waste, and realizing energy saving through technological transformation, and reducing production costs, it can bring significant economic benefits to the enterprise. Therefore, for the manufacturing industry, the importance of production energy consumption statistics and energy-saving optimization technology is self-evident. It is not only a need to cope with environmental pressure, but also a driving force for pursuing economic benefits, and also an opportunity to promote technological progress and enjoy policy support.

[0096] At present, energy management systems for production enterprises are already widely used, and Internet of Things technology is also widely used in the monitoring and collection of energy consumption such as electricity, steam, and natural gas. Although energy management systems can meet the basic needs of enterprises for energy consumption measurement, meter reading, monitoring, and statistics, in the technical field of refined management of production energy consumption, if you want to obtain energy consumption data with smaller granularity on the basis of existing energy management, the only way to achieve this is to install additional metering instruments for IoT monitoring of production lines, production lines, processes, energy-consuming equipment, etc. that need to be monitored, and then combine the company's production work order information to conduct production-related statistical analysis on the monitored data. By installing metering instruments on the energy paths that need to be monitored, and obtaining monitoring and metering data through IoT communication between the energy management system and the metering instruments, real-time monitoring and data analysis of the company's energy consumption can be achieved.

[0097] In the adoption of energy-saving and carbon-reduction strategies, current technologies mostly use horizontal and vertical comparisons of energy consumption data, daily / monthly / annual trend comparisons, and statistical charts (line charts, bar charts, energy flow charts) to form more intuitive data comparison results, and then rely on the subjective experience and judgment of supervisors to determine the general direction of energy saving and carbon reduction. If an enterprise wants to carry out refined energy consumption management by adopting the existing technology, it needs to install a large number of monitoring instruments, which has high construction costs and high project risks, and reduces the willingness of enterprises to implement refined energy management. At the same time, according to the obtained statistical charts, manual subjective judgments are made on the direction of energy conservation and carbon reduction, and the judgment accuracy and efficiency are low. How to improve the accuracy and efficiency of energy conservation and carbon reduction is a problem that urgently needs to be solved. In view of this, some embodiments of the present application provide a method for recommending energy-saving strategies, which includes obtaining production work order information, and determining a production energy consumption sample corresponding to the production work order information based on the production work order information; judging the comprehensive energy consumption level of the production energy consumption sample to determine a first improvement strategy; judging the sensitive process steps of the production energy consumption sample to determine a second improvement strategy; judging the process route steps of the production energy consumption sample to determine a third improvement strategy; judging the high-energy-consuming equipment in the production energy consumption sample to determine a first energy-saving strategy; and The process is judged to determine the second energy-saving strategy; according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy and the second energy-saving strategy, the effect is predicted and evaluated to obtain an evaluation result corresponding to the production work order information. In the embodiment of the present application, the production work order information is obtained to generate a production energy consumption sample, and the comprehensive energy consumption level, sensitive process steps and process route steps are judged according to the production energy consumption sample. At the same time, high-energy-consuming equipment and high-energy-consuming processes are judged, and the effect prediction and evaluation are performed according to the obtained energy-saving strategy and improvement strategy to obtain the evaluation result. In this way, there is no need for a large number of new measuring instruments to be constructed at a low cost as a prerequisite. Through the data analysis method of artificial intelligence, it can help enterprises complete the refined analysis of energy consumption based on production lines, processes, technologies and equipment, and provide targeted energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes and energy-consuming equipment in the production of enterprises, and provide the expected energy-saving and carbon-reduction effect evaluation after the introduction of the strategy.

[0098] like Figure 1 As shown, an embodiment of the present application provides a method for recommending an energy-saving strategy, the method comprising:

[0099] S101, obtaining production work order information, and determining a production energy consumption sample corresponding to the production work order information according to the production work order information;

[0100] S102, judging the comprehensive energy consumption level of the production energy consumption samples and determining the first improvement strategy;

[0101] S103, judging the sensitive process steps of the production energy consumption samples and determining the second improvement strategy;

[0102] S104, judging the process route steps of the production energy consumption sample and determining the third improvement strategy;

[0103] S105, judging high energy-consuming equipment in the production energy consumption sample and determining a first energy-saving strategy;

[0104] S106, judging the high energy-consuming processes in the production energy consumption sample and determining the second energy-saving strategy;

[0105] S107. According to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy and the second energy-saving strategy, effect prediction and evaluation are performed to obtain evaluation results corresponding to the production work order information.

[0106] Some embodiments of the present application obtain production work order information and then generate production energy consumption samples, and judge the comprehensive energy consumption level, sensitive process steps and process route steps according to the production energy consumption samples, and judge high-energy-consuming equipment and high-energy-consuming processes at the same time, and predict and evaluate the effects based on the obtained energy-saving strategies and improvement strategies to obtain evaluation results. In this way, without the need for a large number of new measuring instruments to be constructed at low cost, artificial intelligence data analysis methods can be used to help enterprises complete refined energy consumption analysis based on production lines, processes, technologies, and equipment, and provide targeted energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in the enterprise's production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0107] Another embodiment of the present application further supplements the method for recommending energy-saving strategies provided in the above embodiments.

[0108] Figure 2 A schematic diagram of the structure of the energy-saving strategy diagnosis and evaluation system provided in the embodiment of the present application, such as Figure 2 As shown, an embodiment of the present application discloses an energy-saving strategy diagnosis and evaluation system, which includes an Internet of Things instrument management module 11, a production model management module 12, a product process management module 13, a production work order information management module 14, an energy-saving strategy diagnosis module 15, and an energy-saving effect evaluation module 16.

[0109] The IoT instrument management module 11 includes an instrument registration management submodule 111 and an instrument attribute marking submodule 112. The instrument registration management submodule 111 is used to implement the IoT identity registration and authorization platform for energy consumption instruments. After registration, each collection instrument obtains a unique identity code (instrument code), and communicates data through the physical model and the platform to complete the collection and reporting of energy consumption data; the instrument attribute marking submodule 112 marks the energy consumption type and production line ID of each instrument's collected data. The data collected by the marked instrument can be identified by the platform as the energy consumption type, energy consumption amount, production line, and occurrence time represented by the data. For details, please refer to Figure 3 .

[0110] A production line can be associated with multiple energy consumption meters of different types to collect different types of energy consumption, such as common electricity, water, heat, etc. When a production line is associated with multiple meters of the same energy consumption type, the energy consumption data will be accumulated and calculated.

[0111] The production model management module 12 includes a production tree structure management submodule 121 and a process attribute marking submodule 122. The production tree structure management module manages the production and manufacturing structure of the enterprise according to the tree structure of plant area-factory-workshop-production line-process; the granularity of the production line level is used to associate energy consumption collection instruments, and the structure of the lower level of the production line is process / station. The process is the minimum granularity of the production tree structure, and the levels of the remaining tree structures can be increased or decreased. The process attribute marking submodule 122 is used to mark the process steps associated with the process and the production equipment used by the process.

[0112] After marking the process attributes, the processes included in a single production line, the processes that need to be enabled when a single production line produces a certain product, and the corresponding processes executed by the enabled processes complete the overall logical mapping. Figure 4 As shown, there is not a one-to-one correspondence between the process steps in the process route and the processes of the production line. The process range that can be executed by the production line process is greater than or equal to the process range included in the process route, that is, the production line can produce products by enabling some processes.

[0113] The product process management module 13 includes a product information management submodule 131, a process information management submodule 132, and a process route management submodule 133. The product information management submodule 131 is used to manage the products (finished products) produced by the enterprise. The products have unique numbers and are associated with process routes; the process information management submodule 132 is used to manage a single process (not in production) for producing products. Each process has a unique number, and the process is associated with the production process that can implement this process; the process route management submodule 133 is used to manage the process route for producing products. The process route is a combination of a group of single processes. More than one single process is combined in a sequential form. Each process in the process route is called a process step; the process route is associated with the product. Generally speaking, there is only one process route for a product, but the same process route can produce several products.

[0114] like Figure 5 After product process information management, the mapping relationship between the process steps required to produce a single product, the enabled production lines and the corresponding processes of the production lines can all be clarified.

[0115] The production work order information module 14 is mainly used to manage the result information of the production work orders of the enterprise. The work order information mainly includes: production products, production lines, production quantities, and production start and end times. The work order information can be manually entered by the user or directly connected to the MES system, etc. The production work order can be divided into completed work orders and planned work orders (forecast work orders) according to its completion status. Among them, the completed work orders are used as objective data to perform model statistics and training for the system, and the planned work orders can be used by the system to predict future energy consumption trends.

[0116] After introducing the production work order information, the energy type and quantity consumed by each production work order can be calculated based on the production line information and start and end time of the work order and the above energy consumption data information. When multiple different types of energy consumption are required, they are uniformly converted into standard coal for cumulative calculation.

[0117] By adding the product number and production quantity of the production work order, the energy consumption required to produce different quantities of different products can be calculated, which serves as basic data for subsequent analysis.

[0118] After being processed by the production work order information module, the system cleans the basic information of the work order, eliminates the time loss caused by material shortage, equipment failure and other reasons (there is energy consumption error in waiting time), and only takes the work orders completed in normal and continuous state as the production energy consumption sample;

[0119] The energy-saving strategy diagnosis module 15 includes a product process improvement strategy submodule 151 , an equipment energy-saving strategy submodule 152 , and a production energy-saving strategy submodule 153 .

[0120] The product process improvement strategy submodule 151 is used to evaluate the comprehensive energy consumption level of the company's existing products, calculate sensitive process step strategies, and calculate process route improvement strategies.

[0121] Optionally, a comprehensive energy consumption level is determined for the production energy consumption sample to determine a first improvement strategy, including:

[0122] According to the production energy consumption samples, the product historical energy consumption ratio parameters, product single product energy consumption parameters and product improvement space parameters are calculated respectively to obtain the first improvement strategy; among which:

[0123] The product historical energy consumption ratio parameter is obtained by calculating the ratio of each product's energy consumption to the total production energy consumption based on the historical production energy consumption samples in the preset time period, and sorting the ratios in descending order;

[0124] The energy consumption parameters of individual products are obtained by calculating the total energy consumption of each product and the quantity of product produced;

[0125] The product improvement space parameters are classified and counted according to the energy consumption of each product and the type of work order product to obtain the maximum and minimum unit consumption of each product. Based on the maximum and minimum values, the unit consumption improvement space is determined and the products are sorted in descending order according to the unit consumption improvement space.

[0126] Specifically, the strategy for evaluating the comprehensive energy consumption level of products includes three parts: the proportion of historical energy consumption of products, the energy consumption of individual products, and the room for product improvement. The target products are divided into two types: system default recommendation and user-selected target product analysis, but the calculation logic is basically the same.

[0127] The calculation steps for the product's historical energy consumption percentage are as follows: filter the production energy consumption samples for a fixed historical period (the default is the past year), count the energy consumption by product number, calculate the percentage of each product's energy consumption in the overall production energy consumption, and rank the percentages in descending order.

[0128]

[0129] Terminal equipment recommends improving the products with the highest historical energy consumption. The recommended format is: The product with the highest production energy consumption in the past year is: XXX; Energy consumption percentage: XX%; Other products exceeding XX%.

[0130] The user may also manually select a target product for evaluation. The evaluation format is: the current product's production energy consumption in the past year accounted for: XX%; exceeding XX% of other products.

[0131] The calculation steps for product energy consumption are as follows: based on the cumulative energy consumption of each product mentioned above, divide it by the production quantity of the corresponding product to obtain the unit production energy consumption of each product, that is, the product energy consumption. The system ranks the product energy consumption in descending order.

[0132] The system recommends improving the product with the highest energy consumption. The recommendation format is: The product with the highest energy consumption in the past year is: XXX; it exceeds XX% of other products.

[0133] The user may also manually select a target product for evaluation, and the evaluation format is: the current product's single product energy consumption ranking is X, exceeding XX% of other products.

[0134] The method for calculating the product improvement space is as follows: the above-mentioned production energy consumption samples after cleaning are used to calculate the unit consumption of the work order products; then, the products produced by the work order are classified and counted, and the maximum and minimum unit consumption of each product in the historical work order production are obtained, and the unit consumption improvement space is calculated, and the energy consumption improvement space of the products is ranked in descending order;

[0135] Unit consumption of work order product = total energy consumption of work order / number of work order production

[0136] Unit consumption improvement space = (Maximum unit consumption of product - minimum unit consumption of product) / Maximum unit consumption of product * 100%

[0137] The system recommends improving the product with the highest potential for improvement. The recommended format is: The product with the highest potential for improvement in energy consumption is: XXX; the potential for improvement is XX%, which exceeds the other XX% of products.

[0138] The user can also manually select a target product for evaluation. The evaluation format is: the current product has room for improvement of XX%, which exceeds XX% of other products.

[0139] In some embodiments of the present application, the strategy content for evaluating the comprehensive energy consumption level of a product includes three parts: the proportion of historical energy consumption of the product, the energy consumption of a single product, and the room for product improvement. The target products are divided into two types of analysis: system default recommendation and user-selected target product analysis, thereby improving the accuracy of energy consumption improvement.

[0140] Optionally, a sensitive process step is determined for the production energy consumption sample to determine a second improvement strategy, including:

[0141] Determine the process route corresponding to the target product based on the target product and related products;

[0142] According to the target product and the process route, determine the multivariate linear regression equation of the energy consumption of the target product with respect to the process route;

[0143] Inputting the work order energy consumption data of the product to be screened into the energy consumption multivariate linear regression equation to determine the undetermined coefficient group of the linear regression equation, wherein the undetermined coefficient value at least includes the energy consumption coefficient required for each process step;

[0144] According to the undetermined coefficient groups of different linear regression equations, the sensitive step with the most sensitive product unit consumption of the product to be screened is determined;

[0145] According to the sensitive steps, determine the linear regression equation of energy consumption of the process route of the product to be screened in different production lines;

[0146] According to the linear regression equation of energy consumption of the process routes of the screened products in different production lines, calculate the process steps in the process routes of the screened products that are most sensitive to environmental impacts;

[0147] Determine the second improvement strategy based on the process step in the process route of the product to be screened that is most sensitive to environmental impacts.

[0148] Specifically, the basis for the recommendation of sensitive process step strategy is to calculate the linear regression equation of the process route for each product. The calculation process is as follows: Figure 7 As shown:

[0149] 61. The user selects the target product A, and the system associates the process route that product A needs to go through and marks it as a1→a2→a3…→an;

[0150] 62. The energy consumption required to produce product A is defined as the dependent variable EA. Given that there is a linear relationship between the production quantity i and the energy consumption E, a multivariate linear regression equation for the energy consumption of a single product A based on its process route a can be established:

[0151] EA(i)=e0+e1 a1i+e2a2i+e3 a3i+…+en ani,

[0152] Where a is a constant representing the process step, i is the independent variable = production quantity,

[0153] e is the undetermined energy consumption coefficient of the process step, (regression coefficient) series {e0, e1, e2, e3, …en}, where en is the energy consumption coefficient required for process step an, and e0 is the intercept term, that is, the correction term and the energy consumption of the production line idling.

[0154] 63. After cleaning, filter only the work order data with product A, substitute the work order energy consumption data (independent variable = production quantity, dependent variable = work order energy consumption) into the linear regression model, set the confidence interval to 95%, and then solve the value of the unknown coefficients {e0, e1, e2, e3, ...en}.

[0155] 64. At this time, except for e0, the maximum value in {e1, e2, e3, ... en} is the coefficient with the highest influence in the equation, and the process step an corresponding to the coefficient en is the process step that is most sensitive to the unit consumption of the product;

[0156] 65. Although the process route of the product is the same, due to the production environment and the different equipment used in the process, there will be different energy consumption performance;

[0157] The work order data in step 3 is further divided into different groups according to different production lines. The production line name is marked as X, and multiple production lines are marked as XI, XII, XIII, etc.

[0158] By superimposing the energy consumption data of EA in different production lines XI, XII, XIII…, the energy consumption coefficient e of EAX will eventually be expressed as a matrix;

[0159]

[0160] 66. Use the standard deviation formula to evaluate the stability of the energy consumption coefficient group en of a single process step an:

[0161]

[0162] Where σ is the standard deviation, N is the number of Xn (the number of production lines X producing product A), ei is the energy efficiency coefficient of each process step, and μ is the mean value of the data.

[0163] The larger the standard deviation, the more unstable the energy consumption of the process is when it is produced on different production lines. Considering that the coefficient ratios between various process steps may affect each other, the system recommends the three steps with the largest standard deviation as production environment sensitive process steps to users;

[0164] At the same time, record the energy consumption improvement space of the corresponding process:

[0165] Process energy consumption improvement space = (Maximum process energy consumption coefficient - min process energy consumption coefficient) / Maximum process energy consumption coefficient 100%;

[0166] If the corresponding process is bound to only one production equipment, the process improvement space is equal to the equipment energy saving improvement space;

[0167] Similarly, because the coefficient ratios between process steps may affect each other, this improvement space coefficient should be marked as a reference value when recommended to users to reflect the rigor of the system.

[0168] 67. The system gives the sensitive process step strategy of target product A. The evaluation format is: the unit consumption process sensitive step of product A is an. Improving this step can have the greatest impact on the unit consumption of the product. Production environment sensitive Production environment sensitive The production environment sensitive processes of product A are a1, a2, and a3. The above steps are greatly affected by the production environment. It is recommended to evaluate the differences in the corresponding processes of the production line.

[0169] Some embodiments of the present application determine the sensitive process steps of production energy consumption samples, the sensitive processes in the process, and improve the sensitive processes in different production lines.

[0170] Optionally, the process route steps of the production energy consumption sample are judged to determine the third improvement strategy, including:

[0171] Determine the process route corresponding to the target product based on the target product and related products;

[0172] Determine the third improvement strategy based on the unit consumption ranking of the preset process routes corresponding to the target product.

[0173] Specifically, the algorithm for recommending process route improvement strategies is based on the product unit consumption ranking and product process route calculated in the previous step, and searches for highly similar process routes with lower unit product consumption as a reference for improving product process routes. The implementation logic is as follows:

[0174] The user selects the target product A, and the system associates the process route that product A needs to go through and marks it as a1→a2→a3…→an;

[0175] The system queries the ranking of product A in the product unit energy consumption ranking (in descending order), and includes the products ranked after it (whose unit energy consumption is lower than that of product A) in the calculation scope;

[0176] Only products with a process route number ≥ A and that completely include all steps in process route A (a1, a2, a3…an) are selected. The order of the steps is not considered here.

[0177] The screened products are divided into four categories, and the system provides different process route improvement strategies:

[0178] The first type: The process steps and sequence of the process route of product An are exactly the same as those of product A, and the unit consumption of the product is lower than that of product A. It is recommended that users conduct a comparative analysis of the specific parameters of the process steps of the two (such as equipment processing parameters, auxiliary materials used, etc.); it is recommended to merge the process routes for management;

[0179] The second type: The process steps of product An are the same as those of product A, but the process sequence is different. The unit consumption of the product is lower than that of product A. It is recommended that users adjust the sequence of the process route of product A.

[0180] The third type: The process route steps of product An include A and are more than A, and the unit consumption of the product is lower than that of A. It is recommended that users conduct a comparative analysis of the specific parameters of the process steps of the two.

[0181] The fourth type: The system has not discovered effective process route improvement strategies.

[0182] In some embodiments of the present application, the accuracy of energy-saving improvement is improved by performing process route analysis on production energy consumption samples and determining improvement strategies according to the ranking of unit consumption.

[0183] Optionally, judging high energy-consuming equipment in the production energy consumption sample and determining a first energy-saving strategy includes:

[0184] Acquire a first target production line and a preset production tree structure, and determine a first associated production line process corresponding to the first target production line;

[0185] According to the first target production line and the first associated production line process, determining a first energy consumption multivariate linear regression equation of the first target production line based on the first associated production line process;

[0186] Determine the energy consumption coefficient of the first process of the first energy consumption multiple linear regression equation according to the production work order information and the first energy consumption multiple linear regression equation;

[0187] Calculating a first high energy consumption process step of a first target production line, and determining a first energy consumption improvement space parameter corresponding to the first high energy consumption process step according to the first high energy consumption process step;

[0188] According to the first high-energy-consuming process step, determining the high-energy-consuming equipment associated with the process;

[0189] Identify the processes associated with high energy-consuming processes and determine whether the associated processes are sensitive to the production environment;

[0190] According to the associated process, determine the equipment corresponding to the associated process;

[0191] A first energy-saving strategy is determined according to the energy consumption coefficient of the first process, the first production environment sensitive process, the first energy consumption improvement space parameter and the energy consumption of equipment corresponding to the associated process.

[0192] Specifically, the equipment energy-saving strategy submodule 152 is mainly used to evaluate the high-energy-consuming equipment in each production line, whether the energy consumption performance fluctuates greatly with the change of the production environment, the room for improvement and the equipment reference group that can be used for comparison; the equipment list in this module comes from the production equipment associated with the production process in the process attribute marking submodule 122, and the specific implementation steps refer to Figure 8 :

[0193] 71. Specify a target production line X as the start, and the process steps in the production line are marked as x1, x2, x3...xn;

[0194] 72. Define the energy consumption required for production line production as the dependent variable EX; given the linear relationship between production quantity i and energy consumption E, a multivariate linear regression equation for energy consumption of a single production line X based on its process can be established:

[0195] EX(i)=e0+e1 x1i+e2x2i+e3 x3i+…+enxni,

[0196] Where x is a constant representing the process step, i is the independent variable = production quantity,

[0197] e is the undetermined energy consumption coefficient of the process step, (regression coefficient) series {e0, e1, e2, e3, …en}, where en is the energy consumption coefficient required for process step xn, and e0 is the intercept term, that is, the correction term and the energy consumption of the production line idling.

[0198] 73. Classify the cleaned work order data according to the production line, substitute the work order energy consumption data (independent variable = production quantity, dependent variable = work order energy consumption) into the linear regression model, set the confidence interval to 95%, and then solve the value of the unknown coefficients {e0, e1, e2, e3, ... en}.

[0199] 74. At this time, except for e0, the maximum value in {e1, e2, e3, ... en} is the coefficient with the highest influence in the equation. The process step xn corresponding to the coefficient en is the process step with high energy consumption on the production line; the process energy consumption improvement space parameters of the associated process steps are queried;

[0200] 75. The production equipment associated with the current process step is marked as high-energy-consuming equipment of the corresponding production line;

[0201] 76. Query the processes associated with high energy consumption steps, and check whether the corresponding processes are marked as [production environment sensitive processes] in the process routes to which they belong;

[0202] 77. If yes, query the process group associated with the corresponding process step → query the production equipment group, record the equipment group name list, and recommend it to the user for comparative analysis; if no, go to 78;

[0203] 78: Execute steps 71 to 77 repeatedly to analyze all production lines. You can find the high-energy-consuming equipment links of all production lines and the reference groups of equipment with obvious energy consumption differences. There may be duplications between the reference groups. After removing the duplications, you can make recommendations.

[0204] 79. The system gives an energy-saving strategy for equipment. The format is as follows: The high-energy-consuming equipment on production line X is X X. The reference value of energy consumption improvement space is XX%. Because the energy consumption performance of different production lines fluctuates greatly (the production environment is sensitive), it is recommended to analyze and compare the reference group equipment {XX1, XX2, XX3...} and improve the equipment.

[0205] Some embodiments of the present application determine the high-energy-consuming equipment in the production energy consumption samples and improve the high-energy-consuming equipment, and thus can improve the energy-consuming equipment as required.

[0206] Optionally, judging the high energy-consuming process in the production energy consumption sample and determining the second energy-saving strategy includes:

[0207] Acquire a second target production line and a preset production tree structure, and determine a second associated production line process corresponding to the second target production line;

[0208] Determine, according to the second target production line and the associated production line processes, a second energy consumption multivariate linear regression equation of the second target production line based on the second associated production line processes;

[0209] Determine the second process energy consumption coefficient of the second energy consumption multivariate linear regression equation according to the production work order information and the second target production line based on the second energy consumption multivariate linear regression equation of the second associated production line process;

[0210] Calculating a second high energy consumption process step of a second target production line, and determining a second energy consumption improvement space parameter corresponding to the second high energy consumption process step according to the second high energy consumption process step;

[0211] Determine the second high energy consumption process in the second associated production line process, and determine whether the second high energy consumption process is a production environment sensitive process;

[0212] Determine the second energy-saving strategy based on the second target production line, production environment sensitive processes and energy consumption improvement space parameters.

[0213] Specifically, the production energy-saving strategy submodule 153 is used to evaluate the high-energy-consuming processes in each production line, whether the energy consumption performance fluctuates greatly with changes in the production environment, and the room for improvement of the high-energy-consuming processes.

[0214] The calculation process of the production energy-saving strategy is similar to that of the equipment energy-saving strategy submodule 152; just repeat 71, 72, 73, 74, 76, and 78.

[0215] The system provides a production energy-saving strategy, with the format as follows: The high-energy-consuming process of production line X is XX. The reference value of energy consumption improvement space is XX%, and the energy consumption performance fluctuates greatly due to different production lines (production environment is sensitive);

[0216] Some embodiments of the present application determine high energy-consuming processes in production energy consumption samples and improve the high energy-consuming processes.

[0217] The energy-saving effect evaluation module 16 is used to enable the user to predict and evaluate the energy-saving effect of the energy-saving strategy to be introduced, and specifically includes a process improvement evaluation submodule 161 and a production equipment improvement evaluation submodule 162 .

[0218] The process improvement evaluation submodule 161 is used to predict and evaluate the effect of the process improvement to be performed by the user. The specific implementation steps are as follows: Fig. 9 :

[0219] Optionally, according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy, and the second energy-saving strategy, effect prediction and evaluation are performed to obtain an evaluation result corresponding to the production work order information, including:

[0220] Obtain the name of the product whose process is to be improved, and determine the process route corresponding to the product name according to the product name;

[0221] According to the product name and process route, determine the multivariate linear regression equation of energy consumption of the product name based on the process route;

[0222] Obtain target process improvement steps;

[0223] According to the parameters in the target process improvement step, the energy consumption multivariate linear regression equation is corrected to obtain the corrected energy consumption multivariate linear regression equation, and the energy saving effect of the production line unit consumption is calculated;

[0224] According to the energy-saving effect of production line unit consumption, the energy-saving effect of production orders within the preset time period is estimated, and the evaluation results corresponding to the production order information are determined.

[0225] Specifically, 81. The user selects product A for process improvement, and the system returns the existing process route of product A. The main purpose of this step is to help users clarify the process route and facilitate the next step of locating the process step. It does not mean that only product A will be improved. If the user clearly knows the process route ID to be improved, it can be directly entered;

[0226] 82. The user fills in the process steps and improvement effects for improvement based on the returned process route;

[0227] Fill out the effect as Fig.10 As shown, users only need to tick the process step to be improved and fill in the expected energy saving effect; if the order is adjusted, fill in the improvement effect in a single process step;

[0228] 83. The system queries the energy consumption multivariate linear regression equation EA of product A based on its process route a; and modifies the corresponding coefficient according to the improvement effect input by the user; the specific calculation method is to convert the energy consumption coefficient of the corresponding step into a new ratio according to the energy saving ratio;

[0229] For example, the multivariate linear regression equation of energy consumption of product A based on process route a is: EA(i)=e0+e1a1i+e2a2i+e3a3i+…+en ani,

[0230] The user improves step a1 and is expected to save 10% of energy. At the same time, the user improves step a4 and is expected to save 20% of energy. The equation is adjusted to:

[0231] EA(i)=e0+e1(1-10%)a1i+e2a2i+e3 a3i+e4(1-20%)a4i+…+en ani,

[0232] Substituting i=1 (producing 1 product) into the two equations before and after the improvement, the energy saving effect of the unit consumption of the product can be obtained;

[0233] Energy saving effect per unit consumption = (unit consumption before improvement - unit consumption after improvement) / unit consumption before improvement X 100%;

[0234] 84. The system queries the planned work orders (unproduced work orders) in the production work order information, and counts the planned production of product A in the future. Substituting the total planned production into the above equation, the total production energy saving of this improvement in the future can be calculated:

[0235] Total energy saving in production = improvement effect of unit consumption * total planned production;

[0236] 85. The system queries the product range of the same process route; repeat steps 83 and 84 to obtain the improvement effect of other products with the same process route;

[0237] 86. The system gives a comprehensive prediction and evaluation of the effect of the process improvement strategy. The format is as follows:

[0238] The product types, energy-saving effects and total planned energy-saving evaluation results of this process improvement are as follows:

[0239]

[0240] Some embodiments of the present application specifically provide energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in enterprise production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0241] The production equipment improvement evaluation submodule 162 is used to predict and evaluate the effects of the process improvement or production equipment to be performed by the user. The specific implementation steps are as follows: Fig.11 :

[0242] Optionally, according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy, and the second energy-saving strategy, effect prediction and evaluation are performed to obtain an evaluation result corresponding to the production work order information, including:

[0243] Obtain the production line of the process to be improved, and determine the process corresponding to the production line based on the production line of the process to be improved;

[0244] Obtain target improvement process or target improvement equipment;

[0245] According to the production line, determine the multivariate linear regression equation of energy consumption based on the production process;

[0246] According to the target improvement process, the coefficient of the multivariate linear regression equation of energy consumption is corrected to obtain the corrected multivariate linear regression equation of energy consumption, and the energy saving effect of the unit consumption of the production line is calculated;

[0247] According to the energy-saving effect of production line unit consumption, the production energy-saving effect of the production work order within the preset time period is estimated to obtain the evaluation result corresponding to the production work order information.

[0248] Specifically, 91. The user selects the production line X for process improvement, and the system returns to the existing process of production line X. The main function of this step is to help the user locate the process. If the user is improving equipment, just fill in the process where the corresponding equipment is located.

[0249] 92. The user fills in the process steps and improvement results for improvement based on the returned process;

[0250] Fill out the effect as Fig.12 As shown, users only need to tick the process to be improved and fill in the expected energy saving effect;

[0251] 93. The system queries the multivariate linear regression equation EX of energy consumption of production line X based on its process x; and modifies the corresponding coefficient according to the improvement effect input by the user; the specific calculation method is to convert the energy consumption coefficient of the corresponding step into a new ratio according to the energy saving ratio;

[0252] For example, the multivariate linear regression equation of energy consumption of production line X based on its process x is: EX(i)=e0+e1x1i+e2x2i+e3x3i+…+enxni,

[0253] The user improves step x1 and estimates energy saving of 10%, and improves step x4 and estimates energy saving of 20%. The equation is adjusted to:

[0254] EX(i)=e0+e1(1-10%)x1i+e2x2i+e3 x3i+e4(1-20%)x4i+…+en xni,

[0255] Substituting i=1 (producing 1 product) into the two equations before and after the improvement, the energy saving effect of the production line can be obtained;

[0256] Energy saving effect per unit consumption = (unit consumption before improvement - unit consumption after improvement) / unit consumption before improvement X 100%;

[0257] 94. The system queries the planned work orders (unproduced work orders) in the production work order information, counts the planned output of production line X in the future, substitutes the total planned output into the above equation, and calculates the total energy saving of production in the future:

[0258] Total energy saving in production = improvement effect of unit consumption * total planned production;

[0259] 95. The system gives a comprehensive prediction and evaluation of the effect of the production equipment improvement strategy. The format is as follows: This production equipment energy-saving evaluation involves production line X, processes x1, x4, the energy-saving effect of unit consumption is X%, the planned output is XXpcs, and the total production energy saving is expected to be XXtce.

[0260] Some embodiments of the present application specifically provide energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in enterprise production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0261] The embodiment of the present application conducts artificial intelligence analysis on the company's current product process, production structure, and production plan data. It only needs to install energy consumption monitoring instruments based on the production line to construct energy consumption prediction equations for products and production lines, and conduct lean energy consumption management on product process steps and process links. It points out high-energy-consuming links and links that are sensitive to environmental factors and gives corresponding energy-saving improvement strategy recommendations. At the same time, it can also conduct a quantitative evaluation of the effects of energy-saving measures that the company plans to introduce.

[0262] The embodiment of the present application does not require users to install a large number of monitoring instruments to perform fine-grained management of energy consumption. The same energy consumption management effect can be achieved only through artificial intelligence algorithms. The hardware cost is low, the implementation cost is low, and the entry threshold for fine-grained energy consumption management is greatly reduced.

[0263] While reducing construction costs, the present invention provides products, processes, process links, equipment, energy-saving space, energy-saving and carbon-reduction improvement strategies, improvement directions, and even reference comparison groups that can be improved through data analysis without the need for human experience intervention;

[0264] Before an enterprise constructs an energy-saving project, it can predict the energy-saving effect of the project and evaluate the objective and quantitative energy-saving effect based on production plan data; this enables the enterprise to have a digital assessment of the project's expected benefits and reduce risks.

[0265] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0266] Another embodiment of the present application provides an energy-saving strategy recommendation device, which is used to execute the energy-saving strategy recommendation method provided in the above embodiment.

[0267] like Fig.13 , which is a schematic diagram of the structure of the energy-saving strategy recommendation device provided in an embodiment of the present application. The energy-saving strategy recommendation device includes an acquisition module 1301, a first determination module 1302, a second determination module 1303, a third determination module 1304, a fourth determination module 1305, a fifth determination module 1306 and a recommendation module 1307, wherein:

[0268] The acquisition module 1301 is used to acquire production work order information, and determine the production energy consumption sample corresponding to the production work order information according to the production work order information;

[0269] The first determination module 1302 is used to determine the comprehensive energy consumption level of the production energy consumption sample and determine the first improvement strategy;

[0270] The second determination module 1303 is used to determine the sensitive process steps of the production energy consumption sample and determine the second improvement strategy;

[0271] The third determination module 1304 is used to determine the process route steps of the production energy consumption sample and determine the third improvement strategy;

[0272] The fourth determination module 1305 is used to judge the high energy consumption equipment in the production energy consumption sample and determine the first energy saving strategy;

[0273] The fifth determination module 1306 is used to determine the high energy consumption process in the production energy consumption sample and determine the second energy saving strategy;

[0274] The recommendation module 1307 is used to predict and evaluate the effects according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy and the second energy-saving strategy, and obtain an evaluation result corresponding to the production work order information.

[0275] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0276] Some embodiments of the present application obtain production work order information and then generate production energy consumption samples, and judge the comprehensive energy consumption level, sensitive process steps and process route steps according to the production energy consumption samples, and judge high-energy-consuming equipment and high-energy-consuming processes at the same time, and predict and evaluate the effects based on the obtained energy-saving strategies and improvement strategies to obtain evaluation results. In this way, without the need for a large number of new measuring instruments to be constructed at low cost, artificial intelligence data analysis methods can be used to help enterprises complete refined energy consumption analysis based on production lines, processes, technologies, and equipment, and provide targeted energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in the enterprise's production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0277] Another embodiment of the present application further supplements the energy-saving strategy recommendation device provided in the above embodiment.

[0278] Optionally, the first determining module is used to:

[0279] According to the production energy consumption samples, the product historical energy consumption ratio parameters, product single product energy consumption parameters and product improvement space parameters are calculated respectively to obtain the first improvement strategy; among which:

[0280] The product historical energy consumption ratio parameter is obtained by calculating the ratio of each product's energy consumption to the total production energy consumption based on the historical production energy consumption samples in the preset time period, and sorting the ratios in descending order;

[0281] The energy consumption parameters of individual products are obtained by calculating the total energy consumption of each product and the quantity of product produced;

[0282] The product improvement space parameters are classified and counted according to the energy consumption of each product and the type of work order product to obtain the maximum and minimum unit consumption of each product. Based on the maximum and minimum values, the unit consumption improvement space is determined and the products are sorted in descending order according to the unit consumption improvement space.

[0283] In some embodiments of the present application, the strategy content for evaluating the comprehensive energy consumption level of a product includes three parts: the proportion of historical energy consumption of the product, the energy consumption of a single product, and the room for product improvement. The target products are divided into two types of analysis: system default recommendation and user-selected target product analysis, thereby improving the accuracy of energy consumption improvement.

[0284] Optionally, the second determining module is used to:

[0285] Determine the process route corresponding to the target product based on the target product and related products;

[0286] According to the target product and the process route, determine the multivariate linear regression equation of the energy consumption of the target product with respect to the process route;

[0287] Inputting the work order energy consumption data of the product to be screened into the energy consumption multivariate linear regression equation to determine the undetermined coefficient group of the linear regression equation, wherein the undetermined coefficient value at least includes the energy consumption coefficient required for each process step;

[0288] According to the undetermined coefficient groups of different linear regression equations, the sensitive step with the most sensitive product unit consumption of the product to be screened is determined;

[0289] According to the sensitive steps, determine the linear regression equation of energy consumption of the process route of the product to be screened in different production lines;

[0290] According to the linear regression equation of energy consumption of the process routes of the screened products in different production lines, calculate the process steps in the process routes of the screened products that are most sensitive to environmental impacts;

[0291] Determine the second improvement strategy based on the process step in the process route of the product to be screened that is most sensitive to environmental impacts.

[0292] Some embodiments of the present application determine the sensitive process steps of production energy consumption samples, the sensitive processes in the process, and improve the sensitive processes in different production lines.

[0293] Optionally, the third determining module is used to:

[0294] Determine the process route corresponding to the target product based on the target product and related products;

[0295] Determine the third improvement strategy based on the unit consumption ranking of the preset process routes corresponding to the target product.

[0296] In some embodiments of the present application, the accuracy of energy-saving improvement is improved by performing process route analysis on production energy consumption samples and determining improvement strategies according to the ranking of unit consumption.

[0297] Optionally, the fourth determining module is used to:

[0298] Acquire a first target production line and a preset production tree structure, and determine a first associated production line process corresponding to the first target production line;

[0299] According to the first target production line and the first associated production line process, determining a first energy consumption multivariate linear regression equation of the first target production line based on the first associated production line process;

[0300] Determine the energy consumption coefficient of the first process of the first energy consumption multiple linear regression equation according to the production work order information and the first energy consumption multiple linear regression equation;

[0301] Calculating a first high energy consumption process step of a first target production line, and determining a first energy consumption improvement space parameter corresponding to the first high energy consumption process step according to the first high energy consumption process step;

[0302] According to the first high-energy-consuming process step, determining the high-energy-consuming equipment associated with the process;

[0303] Identify the processes associated with high energy-consuming processes and determine whether the associated processes are sensitive to the production environment;

[0304] According to the associated process, determine the equipment corresponding to the associated process;

[0305] A first energy-saving strategy is determined according to the energy consumption coefficient of the first process, the first production environment sensitive process, the first energy consumption improvement space parameter and the energy consumption of equipment corresponding to the associated process.

[0306] Some embodiments of the present application determine the high-energy-consuming equipment in the production energy consumption samples and improve the high-energy-consuming equipment, and thus can improve the energy-consuming equipment as required.

[0307] Optionally, the fifth determining module is used to:

[0308] Acquire a second target production line and a preset production tree structure, and determine a second associated production line process corresponding to the second target production line;

[0309] Determine, according to the second target production line and the associated production line processes, a second energy consumption multivariate linear regression equation of the second target production line based on the second associated production line processes;

[0310] Determine the second process energy consumption coefficient of the second energy consumption multivariate linear regression equation according to the production work order information and the second target production line based on the second energy consumption multivariate linear regression equation of the second associated production line process;

[0311] Calculating a second high energy consumption process step of a second target production line, and determining a second energy consumption improvement space parameter corresponding to the second high energy consumption process step according to the second high energy consumption process step;

[0312] Determine the second high energy consumption process in the second associated production line process, and determine whether the second high energy consumption process is a production environment sensitive process;

[0313] Determine the second energy-saving strategy based on the second target production line, production environment sensitive processes and energy consumption improvement space parameters.

[0314] Some embodiments of the present application determine high energy-consuming processes in production energy consumption samples and improve the high energy-consuming processes.

[0315] Optionally, recommended modules for:

[0316] Obtain the name of the product whose process is to be improved, and determine the process route corresponding to the product name according to the product name;

[0317] According to the product name and process route, determine the multivariate linear regression equation of energy consumption of the product name based on the process route;

[0318] Obtain target process improvement steps;

[0319] According to the parameters in the target process improvement step, the energy consumption multivariate linear regression equation is corrected to obtain the corrected energy consumption multivariate linear regression equation, and the energy saving effect of the production line unit consumption is calculated;

[0320] According to the energy-saving effect of production line unit consumption, the energy-saving effect of production orders within the preset time period is estimated, and the evaluation results corresponding to the production order information are determined.

[0321] Some embodiments of the present application specifically provide energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in enterprise production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0322] Optionally, recommended modules for:

[0323] Obtain the production line of the process to be improved, and determine the process corresponding to the production line based on the production line of the process to be improved;

[0324] Obtain target improvement process or target improvement equipment;

[0325] According to the production line, determine the multivariate linear regression equation of energy consumption based on the production process;

[0326] According to the target improvement process, the coefficient of the multivariate linear regression equation of energy consumption is corrected to obtain the corrected multivariate linear regression equation of energy consumption, and the energy saving effect of the unit consumption of the production line is calculated;

[0327] According to the energy-saving effect of production line unit consumption, the production energy-saving effect of the production work order within the preset time period is estimated to obtain the evaluation result corresponding to the production work order information.

[0328] Some embodiments of the present application specifically provide energy-saving and carbon-reduction strategies that can be adopted for sensitive links, processes, and energy-consuming equipment in enterprise production, and provide an evaluation of the expected energy-saving and carbon-reduction effects after the introduction of the strategies.

[0329] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0330] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0331] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the operation of the method corresponding to any embodiment of the recommended method for energy-saving strategies provided in the above embodiments can be implemented.

[0332] An embodiment of the present application further provides a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the operations corresponding to the method of any embodiment of the recommended method for energy-saving strategies provided in the above embodiments.

[0333] like Fig.14 As shown, some embodiments of the present application provide an electronic device 1400, which includes: a memory 1410, a processor 1420, and a computer program stored in the memory 1410 and executable on the processor 1420, wherein the processor 1420 can implement any embodiment of the method included in the recommended method of the above-mentioned energy-saving strategy when reading the program from the memory 1410 through a bus 1430 and executing the program.

[0334] Processor 1420 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 1420 can be a microprocessor.

[0335] The memory 1410 may be used to store instructions executed by the processor 1420 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some or all functions of one or more modules described in the embodiments of the present application. The processor 1420 of the disclosed embodiment may be used to execute instructions in the memory 1410 to implement the method shown above. The memory 1410 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memory known to those skilled in the art.

[0336] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0337] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0338] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for recommending an energy-saving strategy, characterized in that: The method comprises: Acquire production work order information, and determine, based on the production work order information, a production energy consumption sample corresponding to the production work order information; Determine the comprehensive energy consumption level of the production energy consumption sample and determine the first improvement strategy; Determine the sensitive process steps of the production energy consumption sample and determine the second improvement strategy; Determine the process route steps of the production energy consumption sample and determine the third improvement strategy; Judging the high energy-consuming equipment in the production energy consumption sample and determining a first energy-saving strategy; Judging the high energy-consuming processes in the production energy consumption sample and determining a second energy-saving strategy; According to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy and the second energy-saving strategy, effect prediction and evaluation are performed to obtain an evaluation result corresponding to the production work order information.

2. The energy saving strategy recommendation method according to claim 1, characterized in that: The step of judging the comprehensive energy consumption level of the production energy consumption sample and determining the first improvement strategy includes: According to the production energy consumption samples, the product historical energy consumption ratio parameters, product single product energy consumption parameters and product improvement space parameters are calculated respectively to obtain the first improvement strategy; wherein: The product historical energy consumption ratio parameter is obtained by calculating the ratio of each product's energy consumption to the total production energy consumption based on historical production energy consumption samples in a preset time period, and sorting the ratios in descending order; The energy consumption parameters of each product are obtained by calculating the total energy consumption of each product and the production quantity of the product; The product improvement space parameter is classified and counted according to the energy consumption of each product and the type of work order product to obtain the maximum and minimum unit consumption of each product. Based on the maximum and minimum values, the unit consumption improvement space is determined, and the unit consumption improvement space is sorted in descending order.

3. The energy saving strategy recommendation method according to claim 1, characterized in that: The step of judging the sensitive process steps of the production energy consumption sample and determining the second improvement strategy includes: Determine the process route corresponding to the target product based on the target product and related products; Determine, according to the target product and the process route, a multivariate linear regression equation of energy consumption of the target product with respect to the process route; Inputting the work order energy consumption data of the product to be screened into the energy consumption multivariate linear regression equation to determine the undetermined coefficient group of the linear regression equation, wherein the undetermined coefficient value at least includes the energy consumption coefficient required for each process step; According to the undetermined coefficient groups of different linear regression equations, the sensitive step with the most sensitive product unit consumption of the product to be screened is determined; According to the sensitive steps, a linear regression equation for energy consumption of the process route of the product to be screened in different production lines is determined; Calculate the process steps in the process route of the product to be screened that are most sensitive to environmental impacts based on a linear regression equation for energy consumption of the process route of the screened product in different production lines; The second improvement strategy is determined based on the process step in the process route of the product to be screened that is most sensitive to environmental influences.

4. The energy saving strategy recommendation method according to claim 1, characterized in that: The step of judging the process route of the production energy consumption sample and determining the third improvement strategy includes: Determine the process route corresponding to the target product according to the target product and related products; The third improvement strategy is determined according to the unit consumption ranking of the preset process route corresponding to the target product.

5. The energy saving strategy recommendation method according to claim 1, characterized in that: The step of judging the high energy-consuming equipment in the production energy consumption sample and determining the first energy-saving strategy includes: Acquire a first target production line and a preset production tree structure, and determine a first associated production line process corresponding to the first target production line; Determine, according to the first target production line and the first associated production line process, a first energy consumption multivariate linear regression equation of the first target production line based on the first associated production line process; Determine the energy consumption coefficient of the first process of the first energy consumption multivariate linear regression equation according to the production work order information and the first energy consumption multivariate linear regression equation; Calculating a first high-energy-consuming process step of the first target production line, and determining a first energy consumption improvement space parameter corresponding to the first high-energy-consuming process step according to the first high-energy-consuming process step; According to the first high-energy-consuming process step, determining the high-energy-consuming equipment associated with the process; Determine the process associated with the high energy consumption process, and judge whether the associated process is a production environment sensitive process; According to the associated process, determining equipment corresponding to the associated process; The first energy-saving strategy is determined according to the energy consumption coefficient of the first process, the first production environment sensitive process, the first energy consumption improvement space parameter and the energy consumption of the equipment corresponding to the associated process.

6. The energy saving strategy recommendation method according to claim 1, characterized in that: The step of judging the high energy-consuming process in the production energy consumption sample and determining the second energy-saving strategy includes: Acquire a second target production line and a preset production tree structure, and determine a second associated production line process corresponding to the second target production line; Determine, according to the second target production line and the associated production line process, a second energy consumption multivariate linear regression equation of the second target production line based on the second associated production line process; Determine a second process energy consumption coefficient of the second energy consumption multiple linear regression equation according to the production work order information and a second energy consumption multiple linear regression equation of the second target production line based on the second associated production line process; Calculating a second high energy consumption process step of the second target production line, and determining a second energy consumption improvement space parameter corresponding to the second high energy consumption process step according to the second high energy consumption process step; Determine a second high energy consumption process in the second associated production line process, and determine whether the second high energy consumption process is a production environment sensitive process; The second energy-saving strategy is determined based on the second target production line, the production environment sensitive process and the energy consumption improvement space parameters.

7. The energy saving strategy recommendation method according to claim 1, characterized in that: The effect prediction and evaluation are performed according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy and the second energy-saving strategy to obtain an evaluation result corresponding to the production work order information, including: Obtaining the name of the product whose process is to be improved, and determining the process route corresponding to the product name according to the product name; According to the product name and the process route, determine a multiple linear regression equation for energy consumption of the product name based on the process route; Obtain target process improvement steps; According to the parameters in the target process improvement step, the energy consumption multivariate linear regression equation is corrected to obtain a corrected energy consumption multivariate linear regression equation, and the energy saving effect of the unit consumption of the production line is calculated; According to the energy-saving effect of the unit consumption of the production line, the energy-saving effect of the production work order within a preset time period is estimated, and the evaluation result corresponding to the production work order information is determined.

8. The energy saving strategy recommendation method according to claim 1, characterized in that: The effect prediction and evaluation are performed according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy and the second energy-saving strategy to obtain an evaluation result corresponding to the production work order information, including: Acquire a production line of the process to be improved, and determine a process corresponding to the production line according to the production line of the process to be improved; Obtain target improvement process or target improvement equipment; According to the production line, determining a multivariate linear regression equation of energy consumption of the production line based on the process; Correct the coefficients of the energy consumption multivariate linear regression equation according to the target improvement process to obtain a corrected energy consumption multivariate linear regression equation, and calculate the energy saving effect of the production line unit consumption; According to the energy-saving effect of the unit consumption of the production line, the production energy-saving effect of the production work order within a preset time period is estimated to obtain an evaluation result corresponding to the production work order information.

9. A device for recommending energy-saving strategies, characterized in that: The device comprises: An acquisition module, used to acquire production work order information, and determine a production energy consumption sample corresponding to the production work order information according to the production work order information; A first determination module is used to determine the comprehensive energy consumption level of the production energy consumption sample and determine a first improvement strategy; A second determination module is used to determine the sensitive process steps of the production energy consumption sample and determine a second improvement strategy; A third determination module is used to determine the process route steps of the production energy consumption sample and determine a third improvement strategy; A fourth determination module, used to judge the high energy-consuming equipment in the production energy consumption sample and determine a first energy-saving strategy; A fifth determination module, used to determine the high energy consumption process in the production energy consumption sample and determine the second energy saving strategy; A recommendation module is used to predict and evaluate the effects according to the first improvement strategy, the second improvement strategy, the third improvement strategy, the first energy-saving strategy and the second energy-saving strategy, and obtain an evaluation result corresponding to the production work order information.

10. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor can implement the energy-saving strategy recommendation method described in any one of claims 1 to 8 when executing the program.

Images