An industrial big data driven energy consumption intelligent optimization method and device, electronic equipment and storage medium

Abstract

This invention discloses an intelligent optimization method, device, electronic equipment, and storage medium for energy consumption driven by industrial big data. The method includes: acquiring basic data and information of each piece of equipment in the same production line to form a matrix data structure; retrieving energy consumption analysis models of different production line equipment groups under production capacity conditions; retrieving basic data and model analysis results from different production lines to generate energy efficiency benchmark labels, wherein the energy efficiency benchmark labels are used for energy efficiency comparison of different production line equipment groups and for locating energy waste points; comparing the energy consumption of different production line equipment groups using the energy efficiency benchmark labels, determining whether the energy consumption deviates from the benchmark, and issuing instructions to adjust the basic data of the equipment groups; updating the energy consumption analysis model based on the basic data of the equipment groups. This invention, by judging deviations based on energy consumption benchmarks and issuing adjustment instructions, can achieve real-time energy consumption monitoring and automatic optimization adjustments, effectively avoiding energy waste caused by abnormal energy consumption and improving energy utilization efficiency.

Description

Technical Field

[0001] This invention relates to the field of energy optimization technology, and in particular to an intelligent optimization method, device, electronic device, and storage medium for energy consumption driven by industrial big data. Background Technology

[0002] In modern industrial production, energy consumption is an important factor affecting production costs and environmental sustainability. Sufficient energy is a prerequisite for human sustainable development. One of the hallmarks of human social progress and development is the emergence and transformation of metallurgical materials. However, the irreconcilable conflict between excessive energy consumption and material production is becoming increasingly apparent. Summary of the Invention

[0003] This invention overcomes the shortcomings of the prior art and provides an intelligent optimization method, device, electronic device, and storage medium for energy consumption driven by industrial big data.

[0004] To achieve the above objectives, the technical solution adopted by this invention is: an intelligent energy consumption optimization method driven by industrial big data, comprising the following steps:

[0005] Step S1: Obtain the basic data and information of each piece of equipment in the same production line to form a matrix data structure;

[0006] Step S2: Retrieve basic data of equipment in the same production line and generate energy efficiency benchmark labels, which are used for energy efficiency comparison of equipment in the same production line and location of energy waste points;

[0007] Step S3: Retrieve the energy consumption analysis model and energy efficiency analysis model of the equipment under production capacity, compare the equipment energy efficiency with the energy efficiency benchmark label, determine whether the energy efficiency deviates from the benchmark and issue an instruction to adjust the feeding amount of the equipment.

[0008] Step S4: Introduce the time dimension and combine it with the energy consumption analysis model and energy efficiency analysis model to calculate the optimal feeding amount for different time intervals;

[0009] Step S5: Update and optimize the energy consumption analysis model based on the basic data of the equipment group.

[0010] In a preferred embodiment of the present invention, in step S1, the basic data of the equipment group includes: material data, process parameters, energy consumption data, and pollution emissions;

[0011] The material data includes: main materials and auxiliary materials;

[0012] Process parameters include: standby load rate, operating rate, and input material quantity;

[0013] Energy consumption data includes: input energy, output energy, consumed energy, recovered energy, and lost energy;

[0014] Pollution emissions include: emitted materials and emitted energy;

[0015] The equipment group information includes: production demand, concentrate particle size, and non-ferrous metal content in the same production line.

[0016] In a preferred embodiment of the present invention, the main materials include: input materials, output materials, output products, and output waste; the auxiliary materials include: input auxiliary materials, recycled auxiliary materials, and auxiliary waste.

[0017] In a preferred embodiment of the present invention, step S2, generating an energy efficiency benchmark label, includes the following steps:

[0018] Step S31: Obtain historical basic data of each piece of equipment in the same production line;

[0019] Step S32: Identify the historical energy efficiency data and calculate the historical average energy efficiency of different production lines;

[0020] Step S33: Take the average energy efficiency as the benchmark energy efficiency, and use the benchmark energy efficiency combined with the standard deviation to set warning values ​​and critical values ​​as energy efficiency benchmark labels. ,in, This is a coefficient used to determine the range, with a value of 1.5. The standard deviation is denoted as .

[0021] In a preferred embodiment of the present invention, in step S3, the energy consumption analysis model is constructed by using a neural network algorithm to generate a neural network algorithm for the relationship between equipment energy consumption and input material quantity, concentrate quality, equipment load rate, and operating rate. This algorithm is used to analyze the influence of factors on energy consumption and to analyze the product energy consumption, material and energy utilization efficiency of the production line equipment group, thereby obtaining equipment energy consumption.

[0022] Specifically: ,in Indicates the energy consumption of the equipment. This indicates a specific input factor among material quantity, concentrate quality, equipment load rate, and operating rate. This represents the weight of a particular input factor. Indicates basic energy consumption;

[0023] The energy efficiency analysis model is built on the energy consumption analysis model to analyze the efficiency of material use and energy use.

[0024] In a preferred embodiment of the present invention, step S3, determining whether the energy efficiency deviates from the benchmark and issuing a command, includes the following steps:

[0025] Step S31: Based on the energy efficiency analysis model, the energy efficiency of each piece of equipment on the same production line is analyzed and compared with the benchmark energy efficiency to calculate the deviation value. ,in, Indicates the deviation value. This represents the energy efficiency calculated by the energy efficiency analysis model. This refers to a piece of equipment in the production line;

[0026] Step S32: Determine whether the deviation value deviates from the benchmark energy efficiency. If... This indicates that the energy efficiency is higher than the benchmark energy efficiency. This indicates that the energy efficiency is lower than the energy efficiency rating, and all of these are abnormal.

[0027] Step S33: Based on abnormal results and deviation values The generated instructions, using the energy consumption analysis model to output the reverse, adjust the basic data of the equipment group, so that... .

[0028] In a preferred embodiment of the present invention, step S4 includes the following sub-steps:

[0029] Step S41: Divide the smelting working time into several time intervals T1, T2, ..., Tn, where n represents the number of time intervals;

[0030] Step S42: Calculate the device degradation coefficient based on the time interval. ,in The range [0,1] represents the rate of decay of combustion efficiency per unit time. The heat exchange efficiency of the equipment is obtained based on the decay coefficient within the time interval during which the equipment operates. ,in It is the initial thermal efficiency of the equipment;

[0031] Step S43: Incorporate the time dimension into the energy consumption analysis model to obtain the dynamic energy consumption analysis model. ,in, This indicates a specific input factor among material quantity, concentrate quality, equipment load rate, and operating rate. This represents the weight of a particular input factor. Indicates basic energy consumption;

[0032] Step S44: Calculate the unit product energy consumption under different feeding amounts within the time interval, record the data, and fit the relationship curve between unit product energy consumption and feeding amount based on the data within the interval. Where a, b, and c are fitting coefficients, and a, b, and c are solved using the least squares method to calculate the feed amount corresponding to the minimum energy consumption. Then calculate the optimal feeding amount within the time interval. .

[0033] An intelligent energy consumption optimization device driven by industrial big data includes: a data acquisition module, an energy consumption analysis module, an energy efficiency analysis module, an energy efficiency benchmark generation module, a deviation judgment and instruction generation module, and a model update module;

[0034] The data acquisition module is used to collect basic data and information from each device in the same production line and form structured matrix data.

[0035] The energy consumption analysis module uses a neural network algorithm to analyze the impact of factors such as the amount of input material, concentrate quality, equipment load rate, and operating rate on energy consumption.

[0036] The energy efficiency analysis module is built on the energy consumption analysis module to analyze the material utilization efficiency and energy utilization efficiency of the production line equipment group.

[0037] The energy efficiency benchmark generation module is used to calculate the historical average energy efficiency of different production lines and generate energy efficiency benchmark labels to facilitate energy efficiency comparison of equipment in the same production line and to locate energy waste points.

[0038] The deviation judgment and instruction generation module is used to compare the actual energy efficiency of different production line equipment groups with the energy efficiency benchmark label, determine whether the energy efficiency of the equipment group deviates from the benchmark energy efficiency, and generate corresponding adjustment instructions to adjust the basic data using the energy consumption analysis module.

[0039] The model update module is used to receive basic data of the device group in real time and analyze its impact on energy consumption.

[0040] An electronic device for intelligent optimization of energy consumption driven by industrial big data includes: a memory for storing processor-executable instructions;

[0041] The processor is configured to execute executable instructions in the memory to implement the steps of the industrial big data-driven intelligent energy consumption optimization method.

[0042] A storage medium for intelligent optimization of energy consumption driven by industrial big data stores a computer program, which, when executed by a processor, implements the steps of the aforementioned intelligent optimization method for energy consumption driven by industrial big data.

[0043] This invention addresses the shortcomings of the prior art and has the following beneficial effects:

[0044] This invention provides an intelligent optimization method for energy consumption driven by industrial big data. By analyzing the energy efficiency of different production line equipment groups under production capacity, and comparing it with energy efficiency benchmark labels, it determines whether the energy efficiency of different production line equipment is within the normal range, thereby determining whether its energy consumption is within the normal range. Based on the judgment results, combined with an energy consumption analysis model that incorporates a time dimension, the feeding amount of equipment in the production line is dynamically adjusted so that the feeding amount of the equipment is at the optimal feeding amount in different time intervals. This adjusts the material utilization efficiency and energy utilization efficiency in the production line, maximizing energy efficiency and achieving refined energy management and optimization.

[0045] This invention introduces a time dimension and a thermal efficiency degradation coefficient into the energy consumption analysis model, mapping changes in equipment status within different time intervals to the energy consumption model. This allows for real-time correction of equipment thermal efficiency, ensuring that energy consumption calculations always reflect the true operating state of the equipment, thereby improving the accuracy of energy efficiency calculations. Simultaneously, it automatically identifies energy consumption inflection points within different time intervals and dynamically adjusts the feeding amount, ensuring that the feeding amount is at the optimal level in different time intervals. This, in turn, enables the equipment to always operate within the lowest energy consumption range, achieving energy saving and consumption reduction.

[0046] This invention sets up an energy consumption analysis model to deeply analyze the energy input and output during the production process, accurately calculates the energy consumption of each equipment group, and sets up an energy efficiency analysis model to calculate the energy and material usage required per unit of product. The combination of these two methods identifies high-energy-consuming equipment, enabling comprehensive management of energy and resources, reducing energy consumption and improving resource utilization efficiency, thereby enhancing overall economic benefits.

[0047] This invention provides a unified and quantifiable energy efficiency benchmark for different production line equipment groups by setting energy efficiency benchmark labels. It compares the actual energy efficiency of the equipment group with the benchmark energy efficiency in real time, identifies energy efficiency deviations in a timely manner, locates equipment groups with abnormal energy efficiency, and ensures that the system can continuously maintain optimal energy efficiency during operation by adjusting the basic data of the equipment group in reverse, avoiding energy waste and significantly improving the economy and sustainability of production.

[0048] This invention enables real-time energy consumption monitoring and automatic optimization by identifying deviations based on energy efficiency benchmark labels and issuing adjustment instructions. This effectively avoids energy waste caused by abnormal energy consumption, improves energy utilization efficiency, reduces human intervention and misoperation, ensures a more refined and intelligent production process, thereby reducing production costs and promoting sustainable development. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart of a preferred embodiment of the present invention, which describes an intelligent energy consumption optimization method driven by industrial big data. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein. Therefore, the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0053] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the scope of protection of this application. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0054] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this application based on the specific circumstances.

[0055] Application Overview

[0056] The metallurgical industry is one of my country's important pillar industries, playing a positive role in promoting the social economy. However, the production cost of domestic metal products is currently high, energy consumption is high, and the production process is long. There is an urgent need to achieve energy conservation and emission reduction through technological innovation, reduce enterprise costs, improve the competitiveness of enterprise products, and accelerate the achievement of national energy conservation and emission reduction targets.

[0057] Therefore, in response to the above problems, this invention proposes an intelligent optimization method for energy consumption driven by industrial big data. It aims to help enterprises achieve efficient energy utilization, reduce energy loss in the production process, and realize real-time monitoring and dynamic optimization of energy efficiency for different production lines and equipment groups through big data analysis and intelligent model optimization.

[0058] like Figure 1 As shown, an intelligent energy consumption optimization method driven by industrial big data includes the following steps:

[0059] Step S1: Obtain the basic data and information of each piece of equipment in the same production line to form a matrix data structure;

[0060] Step S2: Retrieve basic data of equipment in the same production line and generate energy efficiency benchmark labels, which are used for energy efficiency comparison of equipment in the same production line and location of energy waste points;

[0061] Step S3: Retrieve the energy consumption analysis model and energy efficiency analysis model of the equipment under production capacity, compare the equipment energy efficiency with the energy efficiency benchmark label, determine whether the energy efficiency deviates from the benchmark and issue an instruction to adjust the feeding amount of the equipment.

[0062] Step S4: Introduce the time dimension and combine it with the energy consumption analysis model and energy efficiency analysis model to calculate the optimal feeding amount for different time intervals;

[0063] Step S5: Update and optimize the energy consumption analysis model based on the basic data of the equipment group.

[0064] In step S1, the equipment group information includes: production demand, concentrate particle size in the same production line, and non-ferrous metal content;

[0065] The basic data for the equipment group includes: material data, process parameters, energy consumption data, and pollution emissions;

[0066] The material data includes: main materials and auxiliary materials;

[0067] Process parameters include: standby load rate, operating rate, and input material quantity;

[0068] Energy consumption data includes: input energy, output energy, consumed energy, recovered energy, and lost energy;

[0069] Pollution emissions include: emitted materials and emitted energy.

[0070] Main materials include: input materials, output materials, output products, and output waste; auxiliary materials include: input auxiliary materials, recycled auxiliary materials, and auxiliary waste.

[0071] In step S1, it is necessary to specify the type of data to be collected. The data should come from equipment on different production lines under the same production process. Process uniformity ensures the comparability of data, while the differences in data from different production lines can reveal the differences in energy consumption between each production line.

[0072] The collected data needs to be cleaned to remove outliers, null values, and noisy data. At the same time, the data needs to be normalized according to its dimensions so that different data types can be comprehensively calculated under the same analytical framework.

[0073] The collected data is summarized by device to construct a multidimensional data matrix. The matrix structure provides the input data basis for subsequent analysis models, which facilitates the calculation of device energy efficiency and energy consumption, and comparative analysis with benchmark energy efficiency.

[0074] Specifically, a multidimensional data matrix is ​​constructed by determining the dimensions of the matrix, including row dimensions and column dimensions. Each row in the row dimension represents a piece of equipment, and each piece of equipment corresponds to a set of equipment on a different production line. Different production lines will have different equipment, so the number of rows depends on the number of production lines and equipment. Each column in the column dimension represents a data variable, including key elements such as material data, process parameters, energy consumption data, and pollution emissions. These variables will cover all the important operating information of the equipment.

[0075] Collect equipment data from different production lines and summarize the data for each piece of equipment separately; ensure that the collected data covers the entire production cycle and includes all parameters of all equipment to guarantee the comprehensiveness and consistency of the data;

[0076] Fill the data according to row and column dimensions, as shown in Table 1.

[0077] Table 1:

[0078] In step S2, by retrieving the basic data of the equipment in the same production line to generate an energy efficiency benchmark label, and comparing it with the energy efficiency of equipment in different production lines, it is possible to directly identify which production lines have higher energy efficiency and which production lines have energy waste problems. Using the energy efficiency benchmark label as a reference point, when the actual energy efficiency deviates from the energy efficiency benchmark label, the potential energy waste links can be quickly located, and instructions are issued based on the value of the actual energy efficiency deviating from the energy efficiency benchmark label, and the basic data of the equipment is adjusted according to the energy consumption analysis model.

[0079] By comparing the generated energy efficiency benchmark label with the energy consumption of different production line equipment, the energy consumption data of the equipment can be monitored in real time to detect abnormal energy consumption in a timely manner. Dynamic monitoring can react quickly when energy consumption deviates from the benchmark, thereby avoiding potential resource waste. At the same time, if the energy consumption is identified as too high or too low, the system can quickly generate adjustment instructions to ensure that the energy efficiency of the equipment is always kept at the best state. The feedback mechanism can effectively prevent further increase in energy consumption.

[0080] Furthermore, by comparing actual energy consumption with benchmark energy efficiency, potential energy waste can be quickly identified, allowing for targeted optimization measures to be implemented. This not only helps reduce energy consumption but also lowers production costs.

[0081] In step S3, since the energy consumption of equipment in the production environment is affected by various nonlinear factors, a neural network algorithm is used to learn the complex nonlinear relationship between the input material quantity, concentrate quality, equipment load rate, and operating rate and energy consumption, and to construct an energy consumption analysis model. The input material quantity, concentrate quality, equipment load rate, and operating rate are used as input variables of the energy consumption analysis model to predict the energy consumption of the production line equipment, thereby making energy budgets and plans. Since they are in the same process, the concentrate quality, equipment load rate, and operating rate of different production line equipment are basically the same. Therefore, it is necessary to adjust the input material quantity to achieve the expected energy consumption.

[0082] The energy consumption analysis model can not only predict energy consumption, but also analyze the impact of factors such as input material quantity, concentrate quality, equipment load rate, and operating rate on energy consumption, thereby providing a basis for subsequent adjustments based on energy consumption.

[0083] The energy efficiency analysis model is built on the energy consumption analysis model to analyze the efficiency of material use and energy use.

[0084] Among them, there are many factors that should be considered in the metallurgical industry. Taking copper smelting as an example, we can analyze the sources of energy consumption in the smelter.

[0085] The input material quantity in copper smelting needs to be reasonably matched with the equipment load to ensure that the smelting furnace operates under optimal conditions. The "Energy Consumption Optimization Research of Copper Smelting Process in High Energy-Consuming Industries" points out that as the material quantity increases, energy consumption gradually increases, but output can be increased within a certain range. When the material quantity exceeds the rated load of the furnace body, the unit energy consumption increases dramatically. Studies have shown that for every 10% increase in the input material quantity of a copper smelting furnace, the unit energy consumption increases by 5%-10% when operating under overload.

[0086] In a smelting furnace with a load of 200 tons, if the amount of copper ore input increases to 220 tons, the unit energy consumption due to overload will increase by about 8%. If the basic energy consumption of the unit copper smelting process is 300 kWh / ton, under the condition of 220 tons of input material, the energy consumption per ton of copper will increase by 24 kWh, and the total energy consumption will increase by 5280 kWh. Conversely, if the input material is reduced to 180 tons, the unit energy consumption will increase by 10% because the heat utilization rate in the furnace body will decrease, resulting in heat energy waste. Therefore, reasonably controlling the amount of input material within the design load range can significantly reduce unnecessary energy loss. The amount of input material is one of the main factors affecting energy consumption.

[0087] The quality of concentrate, especially the copper grade, is crucial to smelting energy consumption. The higher the grade, the less smelting energy is required, and the more efficient the removal of impurities. The "Analysis of the Relationship between Energy Consumption and Quality in Copper Ore Refining" points out that for every 5 percentage point increase in copper content, the unit energy consumption can be reduced by 15%-20%. High-grade concentrate can shorten smelting time and reduce the energy consumption for impurity separation, thereby optimizing the overall balance between energy consumption and output.

[0088] When smelting copper using low-grade ore with a copper content of 25%, the energy consumption is 330 kWh per ton of ore. If high-grade ore with a copper content of 30% is used instead, the energy consumption can be reduced to 270 kWh per ton of ore, a reduction of about 18%. In a production line that processes 1,000 tons of ore per day, this is equivalent to saving 60,000 kWh per day, which translates to tens of thousands of yuan in production costs. Therefore, improving the grade of concentrate not only helps to reduce direct energy consumption but also increases output and improves the energy efficiency ratio of equipment.

[0089] The study "Systematic Analysis of the Relationship between Load Rate and Energy Efficiency in Copper Smelting" points out that the energy efficiency is best when the equipment load rate is between 85% and 95%. Higher or lower than this range will increase the unit energy consumption. When the load rate is below 75%, the no-load time and heat loss increase significantly, and the energy efficiency decreases by more than 20%.

[0090] If the design load rate of a copper smelting furnace is 90%, the unit energy consumption is 320 kWh / ton when operating at the optimal load rate. When the load rate drops to 70%, the energy consumption per ton of copper smelting increases to 384 kWh, an increase of 20%. Based on smelting 1,000 tons of copper ore per day, the additional energy consumption caused by the low load rate is 64,000 kWh, which significantly increases production costs. In addition, the overload rate will also cause additional energy waste and equipment wear and tear, and prolong maintenance time. Therefore, maintaining operation within an appropriate load rate range can effectively reduce the redundant energy consumption of the smelting furnace.

[0091] The operating rate, which is the ratio of the actual start-up time to the planned running time of the equipment, directly affects the overall energy efficiency of the equipment. The study "The Impact of Operating Rate Optimization on Energy Efficiency in Copper Smelting Process" points out that the energy waste caused by frequent start-ups and shutdowns is about 10%-15%, especially in high-temperature smelting equipment, where the energy loss from frequent cooling and reheating is particularly significant.

[0092] If a copper smelting furnace experiences one hour of non-productive downtime daily due to equipment maintenance, waiting for material supply, etc., and the additional energy consumption for the reheating process is 4,000 kWh per cycle, then by optimizing the operating rate and reducing non-productive downtime by 30 minutes, 2,000 kWh of redundant energy consumption can be saved. Over the entire annual production cycle, energy-saving improvements can save the company more than 700,000 kWh of electricity consumption, bringing significant economic benefits. Therefore, optimizing the operating rate helps to avoid unnecessary equipment idling and heat loss, enabling the equipment to operate stably and efficiently.

[0093] Therefore, the energy consumption of copper smelting is mainly related to the amount of input materials, the quality of concentrate, the equipment load rate, and the operating rate.

[0094] In step S3, basic data from different production lines is first acquired. Based on this data, energy consumption analysis and energy efficiency analysis models are used to analyze the results. Specifically, the basic data is organized into a format that meets the input requirements of the models to ensure the accuracy and consistency of the data. By inputting the acquired basic data, neural network analysis tools are used to calculate and generate an energy consumption prediction for the production line under the current state. Based on the prediction results, the energy usage efficiency is calculated to provide a basis for the subsequent generation of benchmark energy efficiency.

[0095] In step S4, considering that the combustion efficiency of the combustion system in the smelting process often decreases after a long period of operation, due to reasons such as ash accumulation in the burner, incomplete combustion process, and failure of the air supply system, incomplete combustion leads to more energy waste, which in turn leads to a gradual decrease in heat exchange efficiency and a poorer heat transfer effect, resulting in more energy waste. This means that the same metal smelting process requires more energy to compensate for heat loss.

[0096] Therefore, it is necessary to add different weights of materials at different time intervals so that the equipment can still maintain high energy efficiency when the equipment status changes.

[0097] In step S5, real-time basic data of the equipment is collected, including energy consumption, production load, and process parameter information, to ensure the accuracy and timeliness of the data. The data is also organized to conform to the input format of the energy consumption analysis model, ensuring that the model can correctly parse and apply the data.

[0098] In summary, by analyzing the energy consumption of different production line equipment under production capacity, we can determine whether the equipment's energy efficiency is within the normal range, and thus determine whether its energy consumption is within the normal range. By combining this with the time dimension and adjusting the material feeding amount of the equipment in the production line based on the calculation results of the time dimension, we can ensure that the equipment is always at its optimal energy efficiency, i.e., the energy efficiency benchmark label. This optimizes the material utilization efficiency and energy utilization efficiency in the production line, maximizes energy efficiency, and achieves refined energy management and optimization.

[0099] In step S2, generating an energy efficiency benchmark label includes the following steps:

[0100] Step S21: Obtain historical basic data of each piece of equipment in the same production line;

[0101] Step S22: Identify the historical energy efficiency data and calculate the historical average energy efficiency of different production lines;

[0102] Step S23: Take the average energy efficiency as the benchmark energy efficiency, and use the benchmark energy efficiency combined with the standard deviation to set warning values ​​and critical values ​​as energy efficiency benchmark labels. ,in, This is a coefficient used to determine the range, with a value of 1.5. The standard deviation is denoted as .

[0103] By setting energy efficiency benchmark labels, a unified and quantifiable energy consumption benchmark can be provided for equipment on different production lines. The actual energy consumption of the equipment can be compared with the benchmark energy efficiency in real time, and deviations in energy consumption can be identified in a timely manner. Equipment with abnormal energy consumption can be located, and the basic data of the equipment can be adjusted in reverse. The dynamic and adaptive optimization method ensures that the system can continuously maintain optimal energy efficiency during operation, avoid energy waste, realize real-time intelligent optimization of the production process, and greatly improve the economy and sustainability of production.

[0104] In this invention, in step S3, the energy consumption analysis model is constructed by using a neural network algorithm to generate a neural network algorithm that generates equipment energy consumption and input material quantity, concentrate quality, equipment load rate, and operating rate. This algorithm is used to analyze the influence of factors on energy consumption, as well as to analyze the product energy consumption, material and energy utilization efficiency of production line equipment, and predict energy consumption.

[0105] Specifically: ,in Indicates the energy consumption of the equipment. This indicates a specific input factor among material quantity, concentrate quality, equipment load rate, and operating rate. This represents the weight of a particular input factor. This represents the basic energy consumption; the weight of the factors is determined by comparing them in pairs based on expert experience to determine which factor is more important and to what extent.

[0106] The energy efficiency analysis model is constructed based on the energy consumption analysis model to analyze the efficiency of material use and energy use. Specifically, an energy balance equation is established: Input energy + Material input energy = Recoverable energy + Consumed energy + Material output energy + Output energy + Emission energy. Based on the energy balance equation, the flow of energy factors such as material input energy, material output energy, input energy, output energy, recoverable energy, and consumed energy is analyzed.

[0107] In step S3, it is determined whether the energy efficiency deviates from the benchmark and an instruction is issued, including the following steps:

[0108] Step S31: Based on the energy efficiency analysis model, the energy efficiency of each piece of equipment on the same production line is analyzed and compared with the benchmark energy efficiency to calculate the deviation value. ,in, Indicates the deviation value. This represents the energy efficiency calculated by the energy efficiency analysis model. This refers to a piece of equipment in the production line;

[0109] Step S32: Determine whether the deviation value deviates from the benchmark energy efficiency. If... This indicates that the energy efficiency is higher than the benchmark energy efficiency. This indicates that the energy efficiency is lower than the energy efficiency rating, and all of these are abnormal.

[0110] Step S33: Based on abnormal results and deviation values The generated instructions, using the energy consumption analysis model to output the reverse, adjust the basic data of the equipment group, so that... .

[0111] When determining whether actual energy consumption deviates from the benchmark, current energy consumption data is extracted from equipment on different production lines. The extracted energy consumption data is compared with the previously generated energy efficiency benchmark label, and a deviation threshold is set to determine the degree of energy consumption abnormality. For abnormality judgment, it is necessary to determine whether there is an energy consumption abnormality by judging the relationship between the deviation value and the set threshold. The specific judgment logic is as follows:

[0112] like This indicates that the energy consumption is higher than the benchmark. This indicates that energy consumption is lower than the benchmark, and all of these are abnormal.

[0113] like If so, the surface energy consumption is normal;

[0114] Furthermore, based on the deviation judgment results, the system generates corresponding adjustment instructions. For example, if the energy consumption is normal, no adjustment instruction will be generated; if the energy consumption is abnormal, an adjustment instruction will be generated. The specific value of the deviation of the adjustment instruction will be determined, and the basic data of the equipment will be adjusted according to the energy consumption analysis model.

[0115] By judging deviations based on energy consumption benchmarks and issuing adjustment instructions, real-time energy consumption monitoring and automatic optimization can be achieved, effectively avoiding energy waste caused by abnormal energy consumption, improving energy utilization efficiency, reducing human intervention and misoperation, ensuring a more refined and intelligent production process, thereby reducing production costs and promoting sustainable development.

[0116] Step S4 includes the following sub-steps:

[0117] Step S41: Divide the smelting working time into several time intervals T1, T2, ..., Tn, where n represents the number of time intervals;

[0118] Step S42: Calculate the device degradation coefficient based on the time interval. ,in The range [0,1] represents the rate of decay of combustion efficiency per unit time. The heat exchange efficiency of the equipment is obtained based on the decay coefficient within the time interval during which the equipment operates. ,in It is the initial thermal efficiency of the equipment;

[0119] Step S43: Incorporate the time dimension into the energy consumption analysis model to obtain the dynamic energy consumption analysis model. ,in, This indicates a specific input factor among material quantity, concentrate quality, equipment load rate, and operating rate. This represents the weight of a particular input factor. Indicates basic energy consumption;

[0120] Step S44: Calculate the unit product energy consumption under different feeding amounts within the time interval, record the data, and fit the relationship curve between unit product energy consumption and feeding amount based on the data within the interval. Where a, b, and c are fitting coefficients, and a, b, and c are solved using the least squares method to calculate the feed amount corresponding to the minimum energy consumption. Then calculate the optimal feeding amount within the time interval. .

[0121] By introducing a time dimension and thermal efficiency degradation coefficient into the energy consumption analysis model, the changes in equipment status within different time intervals are mapped to the energy consumption model, and the thermal efficiency of the equipment is corrected in real time. This ensures that the energy consumption calculation always reflects the true working state of the equipment, thereby improving the accuracy of energy efficiency calculation. At the same time, the energy consumption inflection point is automatically identified according to different time intervals, and the feeding amount is dynamically adjusted so that the feeding amount of the equipment is at the optimal feeding amount in different time intervals. This ensures that the equipment always operates in the lowest energy consumption range, achieving energy saving and consumption reduction.

[0122] An intelligent energy consumption optimization device driven by industrial big data includes: a data acquisition module, an energy consumption analysis module, an energy efficiency benchmark generation module, a deviation judgment and instruction generation module, and a model update module;

[0123] The data acquisition module is used to collect basic data and information from each device in the same production line and form structured matrix data.

[0124] The energy consumption analysis module uses a neural network algorithm to analyze the impact of factors such as equipment energy consumption, input material quantity, concentrate quality, equipment load rate, and operating rate on energy consumption, as well as analyze the product energy consumption, material and energy utilization efficiency of the production line equipment group.

[0125] The energy efficiency benchmark generation module is used to generate energy efficiency benchmark labels to facilitate energy efficiency comparison of various equipment in the same production line and to locate energy waste points.

[0126] The deviation judgment and instruction generation module is used to compare the actual energy consumption of different production line equipment groups with the energy efficiency benchmark label, determine whether the energy consumption deviates from the benchmark, and generate corresponding adjustment instructions to adjust the basic data.

[0127] The model update module is used to receive basic data of the device group in real time and analyze its impact on energy consumption.

[0128] An electronic device for intelligent optimization of energy consumption driven by industrial big data includes: a memory for storing processor-executable instructions;

[0129] The processor is configured to execute executable instructions in the memory to implement a method for intelligent optimization of energy consumption driven by industrial big data.

[0130] A storage medium for intelligent optimization of energy consumption driven by industrial big data, wherein a computer program is stored thereon, and when the program is executed by a processor, the steps of an intelligent optimization method for energy consumption driven by industrial big data are implemented.

[0131] Based on the preferred embodiments of the present invention described above, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A smart energy consumption optimization method driven by industrial big data, characterized in that, Includes the following steps: Step S1: Obtain the basic data and information of each piece of equipment in the same production line to form a matrix data structure; Step S2: Retrieve basic data of equipment in the same production line and generate energy efficiency benchmark labels, which are used for energy efficiency comparison of equipment in the same production line and location of energy waste points; Step S3: Retrieve the energy consumption analysis model and energy efficiency analysis model of the equipment under production capacity, compare the equipment energy efficiency with the energy efficiency benchmark label, determine whether the energy efficiency deviates from the benchmark and issue an instruction to adjust the feeding amount of the equipment. Step S4: Introduce the time dimension and combine it with the energy consumption analysis model and energy efficiency analysis model to calculate the optimal feeding amount for different time intervals; Step S5: Update and optimize the energy consumption analysis model based on the basic data of the equipment group; In step S4, introducing the time dimension includes the following sub-steps: Step S41: Divide the smelting working time into several time intervals T1, T2, ..., Tn, where n represents the number of time intervals; Step S42: Calculate the device degradation coefficient based on the time interval. ,in The range [0,1] represents the rate of decay of combustion efficiency per unit time. The heat exchange efficiency of the equipment is obtained based on the decay coefficient within the time interval during which the equipment operates. ,in It is the initial thermal efficiency of the equipment; Step S43: Incorporate the time dimension into the energy consumption analysis model to obtain the dynamic energy consumption analysis model. ,in, This indicates a specific input factor among material quantity, concentrate quality, equipment load rate, and operating rate. This represents the weight of a particular input factor. Indicates basic energy consumption; Step S44: Calculate the unit product energy consumption under different feeding amounts within the time interval, record the data, and fit the relationship curve between unit product energy consumption and feeding amount based on the data within the interval. Where a, b, and c are fitting coefficients, and a, b, and c are solved using the least squares method to calculate the feed amount corresponding to the minimum energy consumption. Then calculate the optimal feeding amount within the time interval. .

2. The intelligent energy consumption optimization method driven by industrial big data according to claim 1, characterized in that: In step S1, the basic data of the equipment group includes: material data, process parameters, energy consumption data, and pollution emissions; The material data includes: main materials and auxiliary materials; Process parameters include: standby load rate, operating rate, and input material quantity; Energy consumption data includes: input energy, output energy, consumed energy, recovered energy, and lost energy; Pollution emissions include: emitted materials and emitted energy; The equipment group information includes: production demand, concentrate particle size, and non-ferrous metal content in the same production line.

3. The intelligent energy consumption optimization method driven by industrial big data according to claim 2, characterized in that: The main materials include: input materials, output materials, output products, and output waste; the auxiliary materials include: input auxiliary materials, recycled auxiliary materials, and auxiliary waste.

4. The intelligent energy consumption optimization method driven by industrial big data according to claim 1, characterized in that: In step S2, generating an energy efficiency benchmark label includes the following steps: Step S21: Obtain historical basic data of each piece of equipment in the same production line; Step S22: Identify the historical energy efficiency data and calculate the historical average energy efficiency of different production lines; Step S23: Take the average energy efficiency as the benchmark energy efficiency, and use the benchmark energy efficiency combined with the standard deviation to set warning values ​​and critical values ​​as energy efficiency benchmark labels. ,in, This is a coefficient used to determine the range, with a value of 1.

5. The standard deviation is denoted as .

5. The intelligent energy consumption optimization method driven by industrial big data according to claim 1, characterized in that: In step S3, the energy consumption analysis model is constructed by using a neural network algorithm to generate a neural network algorithm that generates equipment energy consumption and input material quantity, concentrate quality, equipment load rate, and operating rate. This algorithm is used to analyze the influence of factors on energy consumption, as well as to analyze the product energy consumption, material and energy utilization efficiency of the production line equipment group, and obtain equipment energy consumption. Specifically: ,in Indicates the energy consumption of the equipment. This indicates a specific input factor among material quantity, concentrate quality, equipment load rate, and operating rate. This represents the weight of a particular input factor. Indicates basic energy consumption; The energy efficiency analysis model is built on the energy consumption analysis model to analyze the efficiency of material use and energy use.

6. The intelligent energy consumption optimization method driven by industrial big data according to claim 1, characterized in that: In step S3, it is determined whether the energy efficiency deviates from the benchmark and an instruction is issued, including the following steps: Step S31: Based on the energy efficiency analysis model, the energy efficiency of each piece of equipment on the same production line is analyzed and compared with the benchmark energy efficiency to calculate the deviation value. ,in, Indicates the deviation value. This represents the energy efficiency calculated by the energy efficiency analysis model. This refers to a piece of equipment in the production line; Step S32: Determine whether the deviation value deviates from the benchmark energy efficiency. If... This indicates that the energy efficiency is higher than the benchmark energy efficiency. This indicates that the energy efficiency is lower than the benchmark energy efficiency, and all of these are abnormal. Step S33: Based on abnormal results and deviation values The generated instructions, using the energy consumption analysis model to output the reverse, adjust the basic data of the equipment group, so that... .

7. An electronic device for intelligent optimization of energy consumption driven by industrial big data, characterized in that, include: Memory is used to store processor-executable instructions; A processor is configured to execute executable instructions in the memory to implement the steps of the method according to any one of claims 1-6.

8. A storage medium for intelligent optimization of energy consumption driven by industrial big data, wherein a computer program is stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method described in any one of claims 1-6.

Images