A method for reducing costs and increasing efficiency through intelligent collaborative operation of the entire process of a steel plant

Abstract

A method for cost reduction and efficiency improvement through intelligent collaborative operation throughout the entire steel plant process addresses the problem that traditional energy-saving and consumption-reduction methods in the steel industry cannot meet industry needs and cannot further achieve cost reduction and efficiency improvement based on the existing management level. This method for cost reduction and efficiency improvement through intelligent collaborative operation throughout the entire steel plant process provides calibration data upload through the intelligent metering module and performs calculations based on the thermal system operation principle model; then, it uses the indicator system and diagnostic system in the intelligent analysis and diagnosis module for analysis, and the dynamic feedback module provides online feedback on diagnostic optimization suggestions to guide the operation of various equipment in the enterprise; and the actual operating status of each equipment is analyzed and decided through the intelligent auxiliary decision module; then, the optimization results and decision suggestions are automatically fed back to the intelligent analysis and diagnosis module to guide the iterative upgrade of the indicator system and diagnostic system. This method can achieve real-time and accurate online transmission of steel plant metering data, effectively improving the intelligence level of energy conservation and consumption reduction work.

Description

Technical Field

[0001] The present invention belongs to the field of industrial artificial intelligence technology for metallurgical automation, and specifically relates to a method for realizing real-time, accurate and online transmission of steel plant metering data, and online analysis and diagnosis of high-energy-consuming nodes in the steel production process, thereby avoiding the invalidity of guidance plans due to delayed diagnosis; and realizing the self-learning, iterative improvement process of steel plant operations, thereby effectively improving the intelligence level of energy-saving and consumption-reducing work, and realizing a method for reducing costs and increasing efficiency in the entire process of steel plants through intelligent collaborative operation. Background Art

[0002] Currently, energy conservation efforts for thermal furnaces in the steel industry primarily rely on project-based approaches. Through data collection, aggregation, offline calculations, analysis, and diagnosis, the results are generated into analytical reports and improvement plans to guide steel mills in optimizing energy-consuming equipment. However, because energy-saving projects for energy-consuming equipment require the support of electrical and instrumentation signal processing, thermal analysis, and diagnostic technologies, implementation faces technical limitations. In the era of relatively backward production levels at domestic steel mills, offline diagnostic methods were effective, significantly reducing furnace energy consumption. However, with advances in my country's steel production processes and the widespread use of information technology, these static statistical methods have become less effective. The offline diagnostic results they provide cannot meet the dynamic adjustments required for furnace equipment. Therefore, improvements are necessary to existing energy conservation and consumption reduction methods in steel enterprises. Summary of the Invention

[0003] The present invention is aimed at the above-mentioned problems and provides a method for realizing real-time, accurate and online transmission of steel plant metering data, capable of online analysis and diagnosis of high-energy consumption nodes in the steel production process, avoiding the invalidity of guidance plans due to delayed diagnosis; and realizing the self-learning and iterative improvement process of steel plant operations, effectively improving the intelligence level of energy-saving and consumption-reducing work, and realizing a method for reducing costs and increasing efficiency of the entire process of steel plants through intelligent collaborative operation.

[0004] The technical solution adopted by the present invention is: the method for reducing costs and increasing efficiency through intelligent collaborative operation of the entire steel plant process includes the following steps:

[0005] Step 1: Targeting the main factors that affect the accuracy of energy consumption measurement in steel plants, such as insufficient straight pipe length, low flow rate in the pipeline, siltation in the pipeline, and high moisture content in the gas, an online flow measurement model for the intelligent metering module was established.

[0006] Step 2: Establish a thermal calculation model for the online thermal calculation module based on product production and energy consumption;

[0007] Step 3: Establish an indicator system corresponding to various energy-consuming equipment in the steel plant, and determine the reasonable range of each indicator based on the operating characteristics of the equipment. The two work together to affect the energy-consuming equipment in the steel plant, so that the equipment can operate within a reasonable production range, forming an intelligent analysis and diagnosis module;

[0008] Step 4: The improvement suggestions generated by the intelligent analysis and diagnosis module can be fed back online to the corresponding equipment end through the dynamic feedback module to guide the improvement of equipment operation. This dynamic feedback process requires rationality judgment to analyze whether the equipment's production status suddenly changes due to production needs. If the operating status suddenly changes, it is necessary to start the above modules in sequence and recalculate according to the new equipment status to generate improvement suggestions online. If the equipment status is normal, the improvement suggestions can be directly output to the corresponding material supply system, product output system, and energy supply system of the equipment to guide production.

[0009] Step 5. Establish an intelligent decision-making support module. The decision-making support module consists of two stages: First, when the above-mentioned improvement information is fed back to the corresponding equipment end at time t, a reasonable decision needs to be made to ensure reasonable coordination with the equipment production status; second, after the equipment implements specific operations according to the improvement suggestions, the implementation effect needs to be analyzed. If the actual operation effect of the equipment is qualified, the analysis ends; if the actual operation effect is not ideal, the improvement rules need to be activated.

[0010] In the first step, the energy medium flow model is shown in formula (1):

[0011] V 介质流量 =F(C 直管段不足 , C 小流量 , C 管道淤积 , C 含湿严重 ,……,C 多组分 ) (1)

[0012] Where V 介质流量 —Indicates the accurate flow rate of the energy medium being measured;

[0013] C 直管段不足 —Indicates that the straight pipe section of the on-site pipeline is insufficient;

[0014] C 小流量 —Indicates that the flow medium in the pipeline is at a low flow rate;

[0015] C 管道淤积 —Indicates the situation of siltation in the pipeline;

[0016] C 含湿严重 —Indicates the presence of moisture in the pipe;

[0017] C 多组分 —Indicates the situation where multiple mixed media flow in the pipeline;

[0018] The metering data of the steel plant equipment layer is accurately processed and uploaded to the intelligent metering module.

[0019] In step 2, the generation and consumption models of the nine energy media in the steel plant are shown in formulas (2) and (3):

[0020]

[0021]

[0022] Where V 产生,i — represents the amount of energy generated by Category i, which is generated during the production process of the product;

[0023] P 产品,j — represents the product output of energy generation equipment j;

[0024] D dc,j — represents the amount of energy type i generated per unit product produced by equipment j, which can be referred to as unit output;

[0025] dc—subscript, meaning yield;

[0026] V 消耗,i — represents the consumption of type i energy, which is consumed during the production process of the product;

[0027] D dh,j — represents the energy consumption of type i per unit product produced by equipment j, which can be referred to as unit consumption;

[0028] dh—subscript, meaning unit consumption;

[0029] i—indicates the type of energy;

[0030] j—Indicates the type of device.

[0031] In the second step, the steel plant's product output is calculated as shown in formula (4):

[0032] P h,k =α(β1p 料1 +β2p 料2 +…+β n p 料n ) (4)

[0033] Where, P h,k — represents the quantity of product type k produced by equipment h;

[0034] h—indicates the type of equipment in the steel plant;

[0035] k—indicates the type of product produced;

[0036] p 料1 、p料2 、…p 料n —Indicates the types of materials corresponding to the production equipment;

[0037] β1, β2, …, β n —Indicates the accounting weight coefficient of various material inputs on the final product output;

[0038] α—represents the product output correction coefficient corresponding to different operating states of the equipment. The equipment is generally divided into three states: normal operation, equipment production reduction (non-full load operation), and equipment shutdown. The definition is as follows:

[0039]

[0040] Where ψ can be obtained by fitting historical data.

[0041] In the third step, the plant-wide indicator series consists of a two-dimensional and three-level system; the two-dimensional system refers to the production indicator dimension and the energy consumption indicator dimension, and the three-level system refers to the equipment-level indicator, the process-level indicator and the enterprise-level total indicator; then, based on the production process characteristics of the equipment, the reasonable production green range of each process equipment is determined to ensure efficient operation of the equipment and energy utilization in the economic zone of the process principle; using the synergistic effect of this range and the established monitoring indicator series, automatic analysis and diagnosis are made to generate optimization operation suggestions for each equipment system in the steel plant.

[0042] The third step is to establish a production index system:

[0043] ① Equipment level

[0044]

[0045] Where, i—represents the production process of the steel plant;

[0046] j—indicates the energy-consuming equipment within the process;

[0047] k—indicates the type of production materials used in energy-consuming equipment;

[0048] G ijk —Indicates the amount of type k material consumed by type j energy-consuming equipment in process i to produce a unit of product;

[0049] M j,k —The amount of type K materials consumed by type J energy-consuming equipment;

[0050] M 设备j,产品 —Product generation of type j energy-consuming equipment;

[0051] ②Process level

[0052]

[0053]

[0054] Where G ik —Indicates the amount of type k materials consumed by process i in producing a unit of main product;

[0055] M j,k —The amount of material k consumed by energy-consuming equipment j in process i;

[0056] M 工序i,产品 —The amount of main product produced in process i;

[0057] ③Enterprise level

[0058]

[0059] Where M i,j,k —The amount of type k material consumed by energy-consuming equipment j in process i;

[0060] G 企业,k —During the statistical period, the enterprise consumed a total of k types of materials.

[0061] The third step is to establish an energy consumption index system:

[0062] ① Equipment level

[0063]

[0064] Where, i—represents the production process of the steel plant;

[0065] j—indicates the energy-consuming equipment within the process;

[0066] l—indicates the type of energy used by energy-consuming equipment;

[0067] E ijl — represents the amount of standard coal equivalent of type l energy consumed by type j energy-consuming equipment in process i to produce a unit of main product;

[0068] ζ l —Indicates the standard coal conversion coefficient of Class I energy;

[0069] E j,l —Amount of Class I energy consumed by Class J energy-consuming equipment;

[0070] M 设备j,产品 —The amount of main products produced by type j energy-consuming equipment;

[0071] ②Process level

[0072]

[0073]

[0074]

[0075] Where, E il — represents the amount of type l energy consumed in the production of unit main product of process i in terms of standard coal equivalent;

[0076] E i — represents the total energy consumed in producing a unit of main product in process i in terms of standard coal equivalent;

[0077] ζ l —Indicates the standard coal conversion coefficient of Class I energy;

[0078] E j,l —The amount of Class I energy consumed by Class J energy-consuming equipment converted into standard coal;

[0079] M 工序i,产品 —The amount of main product produced in process i;

[0080] ③Enterprise level

[0081]

[0082]

[0083] Where, E i — represents the total energy consumed in producing a unit of main product in process i in terms of standard coal equivalent;

[0084] p i —Shows the steel ratio coefficient of each process in the steel plant;

[0085] M 工序i,产品 —Indicates the product output of each process in the steel plant;

[0086] M 企业,钢产量 —Indicates the qualified steel output of the steel plant.

[0087] The beneficial effects of the present invention are as follows: the steel plant's full-process intelligent collaborative operation cost reduction and efficiency improvement method provides calibration data upload through the intelligent metering module for use by the online thermal calculation module, performs calculations based on the thermal system operation principle model, and outputs a series of results; then, the indicator system and diagnostic system in the intelligent analysis and diagnosis module are used for analysis, and various indicators are monitored and online over-standard early warning prompts are implemented. The diagnostic optimization suggestions are then fed back online through the dynamic feedback module to guide the operation of various equipment in the enterprise and ensure that the steel plant system operates in a stable and efficient green range; and the actual operating status of each equipment is analyzed and decided through the intelligent auxiliary decision module. Finally, the optimization results and decision suggestions are automatically fed back to the intelligent analysis and diagnosis module to guide the iterative upgrade of the indicator system and diagnostic system.

[0088] Through the implementation of the present invention, the following effects and purposes can be achieved: 1. The intelligent metering module can realize the real-time online, accurate up and down transmission of the metering data of the steel plant to ensure the online timeliness of the calculation process data requirements. 2. Realize the online association of the data system and the energy consumption index system to achieve online analysis and diagnosis of high-energy consumption nodes in the steel production process, which is conducive to the targeted and efficient energy conservation and consumption reduction work of the steel plant. 3. Associate the diagnostic system with the online monitoring of the operating status of the steel plant equipment group, so that the high-energy consumption nodes and high-energy consumption factors of the entire plant are displayed online in this system, thereby generating a guidance plan for the entire plant to avoid invalidity due to delayed diagnosis. 4. Through the various parameter analysis systems and benchmarking functions of the production process, the self-learning iterative improvement process of the steel plant operation is realized. Thereby, the intelligence level of the energy conservation and consumption reduction work of the steel enterprise is greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 It is a simplified diagram of the system structure of the present invention.

[0090] Figure 2 It is a simplified diagram of the implementation limitations of the energy-saving diagnosis project for furnace equipment in the steel industry.

[0091] Figure 3 It is a schematic diagram of the implementation effect of the present invention.

[0092] Figure 4 This is a simplified diagram of the structure and operation of the intelligent metering module of the present invention.

[0093] Figure 5 It is a simplified diagram of the steel mill index system of the present invention.

[0094] Figure 6 It is a relationship diagram of steel plant index monitoring and various materials, products and energy sources according to the present invention.

[0095] Figure 7 It is a simplified diagram of the analysis and diagnosis and healthy green operation of the equipment system of the present invention.

[0096] Figure 8 It is a dynamic feedback flow chart of the present invention.

[0097] Figure 9 This is a flowchart of the auxiliary decision module operation of the present invention (one).

[0098] Figure 10 This is the operation flow chart of the auxiliary decision module of the present invention (part 2).

[0099] Figure 11 Implementation flow chart of the steel plant full-process intelligent collaborative operation cost reduction and efficiency improvement system of the present invention. DETAILED DESCRIPTION

[0100] The present invention consists of five modules. They are intelligent metering module, online thermal calculation module, intelligent analysis and diagnosis module, dynamic feedback module and intelligent auxiliary decision module (such as Figure 1 As shown). Moreover, through the cooperation between modules, the limitations of traditional methods are eliminated (limited links such as Figure 2 As shown in the figure), it has opened up key links such as the steel plant's online data supply system, dynamic thermal analysis system, and energy-saving diagnosis and adjustment system; established a measurement data process accounting model, an energy-consuming equipment thermal analysis model, and an energy-saving diagnosis model; integrated the measurement system, thermal analysis system, and energy consumption index system to form a set of cost-cutting and efficiency-enhancing methods with self-learning and iterative improvement capabilities. It can achieve efficient system operation, save a lot of labor costs, and generate intelligent guidance plans online (achievement effects such as Figure 3 shown).

[0101] The specific steps of the present invention are described in detail. The steel plant full-process intelligent collaborative operation cost reduction and efficiency improvement method includes:

[0102] Step 1: Data accuracy is the foundation of effective big data and, more importantly, of intelligent manufacturing. Factors that most significantly impact the accuracy of energy consumption measurement in steel mills include insufficient straight pipe lengths, low flow rates, siltation within the pipelines, and high moisture content in the gas. This patent addresses these issues by establishing an online flow measurement model.

[0103] The energy medium flow model is shown in formula (1):

[0104] V 介质流量 =F(C 直管段不足 , C 小流量 , C 管道淤积 , C 含湿严重 ,……,C 多组分 ) (1)

[0105] Where V 介质流量 —Indicates the accurate flow rate of the energy medium being measured;

[0106] C 直管段不足 —Indicates that the straight pipe section of the on-site pipeline is insufficient;

[0107] C 小流量 —Indicates that the flow medium in the pipeline is at a low flow rate;

[0108] C 管道淤积 —Indicates the situation of siltation in the pipeline;

[0109] C 含湿严重 —Indicates the presence of moisture in the pipe;

[0110] C 多组分 —Indicates the situation where multiple mixed media flow in the pipeline.

[0111] The measurement data of the steel plant equipment layer is accurately processed and uploaded to the intelligent measurement process calculation system (such as Figure 4 shown).

[0112] Step 2: The thermal calculation model is mainly developed around product production and energy consumption. The generation and consumption models of the nine major energy media in the steel plant are shown in Equations (2) and (3):

[0113]

[0114]

[0115] Where V 产生,i — represents the amount of energy generated by Category i, which is generated during the production process of the product;

[0116] P 产品,j — represents the product output of energy generation equipment j;

[0117] D dc,j — represents the amount of energy type i generated per unit product produced by equipment j, which can be referred to as unit output;

[0118] dc—subscript, meaning yield;

[0119] V 消耗,i — represents the consumption of type i energy, which is consumed during the production process of the product;

[0120] D dh,j — represents the energy consumption of type i per unit product produced by equipment j, which can be referred to as unit consumption;

[0121] dh—subscript, meaning unit consumption;

[0122] i—indicates the type of energy;

[0123] j—Indicates the type of device.

[0124] At the same time, the steel plant's product output is calculated as shown in formula (4):

[0125] P h,k =α(β1p 料1 +β2p 料2 +…+β n p 料n ) (4)

[0126] Where, P h,k — represents the quantity of product type k produced by equipment h;

[0127] h—indicates the type of equipment in the steel plant;

[0128] k—indicates the type of product produced;

[0129] p 料1 、p 料2 、…p 料n —Indicates the types of materials corresponding to the production equipment;

[0130] β1, β2, …, β n —Indicates the accounting weight coefficient of various material inputs on the final product output;

[0131] α—represents the product output correction coefficient corresponding to different operating states of the equipment. The equipment is generally divided into three states: normal operation, equipment production reduction (non-full load operation), and equipment shutdown. The definition is as follows:

[0132]

[0133] Where ψ can be obtained by fitting historical data.

[0134] Step 3: Establish an indicator system corresponding to various energy-consuming equipment in the steel plant, and determine the reasonable range of various indicators based on the operating characteristics of the equipment. The two work together to affect the energy-consuming equipment in the steel plant, so that it can operate within a reasonable green production range and form an intelligent analysis and diagnosis module. The design, optimization ideas and interaction relationships of the specific indicator system are as follows: Figure 5 and Figure 6 shown.

[0135] The plant-wide indicator series consists of a two-dimensional and three-tier system. The two-dimensional system refers to the production indicator dimension and the energy consumption indicator dimension; the three-tier system refers to the equipment-level indicator, the process-level indicator, and the enterprise-level overall indicator. The specific indicator system is established as follows:

[0136] 1. Production indicator system

[0137] ① Equipment level

[0138]

[0139] Where, i—represents the production process of the steel plant;

[0140] j—indicates the energy-consuming equipment within the process;

[0141] k—indicates the type of production materials used in energy-consuming equipment;

[0142] G ijk —Indicates the amount of type k material consumed by type j energy-consuming equipment in process i to produce a unit of product;

[0143] M j,k —The amount of type K materials consumed by type J energy-consuming equipment;

[0144] M 设备j,产品—Product generation of type j energy-consuming equipment.

[0145] ②Process level

[0146]

[0147]

[0148] Where G ik —Indicates the amount of type k materials consumed by process i in producing a unit of main product;

[0149] M j,k —The amount of material k consumed by energy-consuming equipment j in process i;

[0150] M 工序i,产品 —The amount of main product produced in process i.

[0151] ③Enterprise level

[0152]

[0153] Where M i,j,k —The amount of type k material consumed by energy-consuming equipment j in process i;

[0154] G 企业,k —During the statistical period, the enterprise consumed a total of k types of materials.

[0155] 2. Energy consumption indicator system

[0156] ① Equipment level

[0157]

[0158] Where, i—represents the production process of the steel plant;

[0159] j—indicates the energy-consuming equipment within the process;

[0160] l—indicates the type of energy used by energy-consuming equipment;

[0161] E ijl — represents the amount of standard coal equivalent of type l energy consumed by type j energy-consuming equipment in process i to produce a unit of main product;

[0162] ζ l —Indicates the standard coal conversion coefficient of Class I energy;

[0163] E j,l —The amount of Class I energy consumed by Class J energy-consuming equipment;

[0164] M 设备j,产品 —The amount of main products produced by type j energy-consuming equipment.

[0165] ②Process level

[0166]

[0167]

[0168]

[0169] Where, E il — represents the amount of type l energy consumed in the production of unit main product of process i in terms of standard coal equivalent;

[0170] E i — represents the total energy consumed in producing a unit of main product in process i in terms of standard coal equivalent;

[0171] ζ l —Indicates the standard coal conversion coefficient of Class I energy;

[0172] E j,l —The amount of Class I energy consumed by Class J energy-consuming equipment converted into standard coal;

[0173] M 工序i,产品 —The amount of main product produced in process i.

[0174] ③Enterprise level

[0175]

[0176]

[0177] Where, E i — represents the total energy consumed in producing a unit of main product in process i in terms of standard coal equivalent;

[0178] p i —Indicates the steel ratio coefficient of each process in the steel plant;

[0179] M 工序i,产品 —Indicates the product output of each process in the steel plant;

[0180] M 企业,钢产量 —Indicates the qualified steel output of the steel plant.

[0181] 3. Analysis and diagnosis

[0182] According to the production process characteristics of the equipment, the reasonable production green range of each process equipment is determined to ensure the efficient operation of the equipment and the energy utilization is in the economic zone of the process principle. By using the synergy of this range and the established monitoring indicator series, the system automatically makes analysis and diagnosis and generates optimization operation suggestions for each equipment system in the steel plant. For equipment groups that are operating outside the green and reasonable economic zone, the system automatically gives improvement suggestions (such as Figure 7 shown).

[0183] Step 4. The improvement suggestions generated by the intelligent analysis and diagnosis module can be fed back to the corresponding equipment end online through the dynamic feedback module to guide the improvement of equipment operation. The dynamic feedback process requires rationality judgment to analyze whether the equipment suddenly changes its production status due to production needs; if the operating status suddenly changes, it is necessary to start the above modules in sequence according to the new status of the equipment and recalculate to generate improvement suggestions online; if the equipment status is normal, the improvement suggestions can be directly output to the corresponding material supply system, product output system and energy supply system of the equipment to guide production (such as Figure 8 shown).

[0184] Step 5: The intelligent auxiliary decision-making module consists of two stages: First, when the above improvement information is fed back to the corresponding equipment end at time t, a reasonable decision needs to be made to ensure reasonable coordination with the equipment production status (such as Figure 9 Second, when the equipment implements specific operations according to the improvement suggestions, it is necessary to analyze the implementation effect. If the actual operation effect of the equipment is qualified, the analysis ends; if the actual operation effect is not ideal, it is necessary to start the improvement rules (such as Figure 10 The implementation of the improvement rules needs to be determined based on the changes in the equipment energy consumption indicators. The three rules established are as follows:

[0185] Rule 1: If the energy consumption index decreases, it means that the improvement suggestions are reasonable and the improvement effect is satisfactory;

[0186] Rule 2: If the energy consumption index remains unchanged, it means that the improvement suggestions have not achieved better results and the improvement is ineffective;

[0187] Rule 3: If the energy consumption indicator increases, it indicates that the equipment's energy consumption actually increases after the improvement suggestion is implemented. This indicates that the improvement is unreasonable and there are unaccounted factors. If the influencing factor can be found based on the site conditions, a new model is fitted to correct the original model. Otherwise, the improvement suggestion is removed.

[0188] The steel plant's full-process intelligent collaborative operation method for reducing costs and increasing efficiency relies on the joint operation of the five modules that constitute this system. Figure 11 As shown) are as follows:

[0189] 1. Intelligent metering module → ensure data accuracy and online supply;

[0190] 2. Thermal online module → ensure dynamic process calculation of online data;

[0191] 3. Intelligent diagnosis module → ensures that the system operates in the green range;

[0192] 4. Dynamic feedback module → ensure timely response to online feedback of diagnostic results;

[0193] 5. Decision-making support module → Ensure reasonable coordination with the current status of equipment production.

Claims

1. A method for reducing costs and increasing efficiency through intelligent collaborative operation of the entire process of a steel plant, characterized in that: The steps include: Step 1: To address factors that affect the accuracy of energy consumption measurement in steel plants, such as insufficient straight pipe length, low flow rate in the pipeline, siltation in the pipeline, and high moisture content in the gas, an online flow measurement model for the intelligent metering module was established. Step 2: Establish a thermal calculation model for the online thermal calculation module based on product production and energy consumption; Step 3: Establish an indicator system corresponding to various energy-consuming equipment in the steel plant, and determine the reasonable range of each indicator based on the operating characteristics of the equipment. The established indicator system and the determined reasonable range of indicators will work together to apply to the energy-consuming equipment in the steel plant, so that the equipment can operate within a reasonable production range, forming an intelligent analysis and diagnosis module; Step 4: The improvement suggestions generated by the intelligent analysis and diagnosis module can be fed back online to the corresponding equipment end through the dynamic feedback module to guide the improvement of equipment operation. This dynamic feedback process requires rationality judgment to analyze whether the equipment's production status suddenly changes due to production needs. If the operating status suddenly changes, the intelligent metering module, online thermal calculation module, and intelligent analysis and diagnosis module need to be started according to the new equipment status to recalculate in sequence and generate improvement suggestions online. If the equipment is in normal condition, improvement suggestions can be directly output to the corresponding material supply system, product output system, and energy supply system to guide production; Step 5. Establish an intelligent decision-making support module. The decision-making support module consists of two stages: First, when improvement information is fed back to the corresponding equipment end at time t, a reasonable decision needs to be made to ensure reasonable coordination with the equipment production status; second, after the equipment implements specific operations according to the improvement suggestions, the implementation effect needs to be analyzed. If the actual operation effect of the equipment is qualified, the analysis ends; if the actual operation effect is not ideal, the improvement rules need to be activated.

2. The method for reducing costs and increasing efficiency through intelligent collaborative operation of the entire steel plant process according to claim 1 is characterized by: In step 1, the online flow metering model is shown in formula (1): V 介质流量 =F(C 直管段不足 ,C 小流量 ,C 管道淤积 ,C 含湿严重 ,C 多组分 ) (1) Where V 介质流量 —Indicates the accurate flow rate of the energy medium being measured; C 直管段不足 —Indicates that the straight pipe section of the on-site pipeline is insufficient; C 小流量 —Indicates that the flow medium in the pipeline is at a low flow rate; C 管道淤积 —Indicates the situation of siltation in the pipeline; C 含湿严重 —Indicates the presence of moisture in the pipe; C 多组分 —Indicates the situation where multiple mixed media flow in the pipeline; The metering data of the steel plant equipment layer is accurately processed and uploaded to the intelligent metering module.

3. The method for reducing costs and increasing efficiency through intelligent collaborative operation of the entire steel plant process according to claim 1 is characterized by: In step 2, the generation and consumption models of the nine energy media in the steel plant are shown in formulas (2) and (3): Where V 产生,i — represents the amount of energy generated by Category i, which is generated during the production process of the product; P 产品,j — represents the product output of energy generation equipment j; D dc,j — represents the amount of energy type i generated per unit product produced by equipment j, which can be referred to as unit output; dc—subscript, meaning yield; V 消耗,i — represents the consumption of type i energy, which is consumed during the production process of the product; D dh,j — represents the energy consumption of type i per unit product produced by equipment j, which can be referred to as unit consumption; dh—subscript, meaning unit consumption; i—indicates the type of energy; j—Indicates the type of device.

4. The method for reducing costs and increasing efficiency through intelligent collaborative operation of the entire steel plant process according to claim 3 is characterized by: In the second step, the steel plant's product output is calculated as shown in formula (4): P h,k =α(β1p 料1 +β2p 料2 +…+b n p 料n ) (4) Where, P h,k — represents the quantity of product type k produced by equipment h; h—indicates the type of equipment in the steel plant; k—indicates the type of product produced; p 料1 、p 料2 、…p 料n —Indicates the types of materials corresponding to the production equipment; β1, β2, …, β n —Indicates the accounting weight coefficient of various material inputs on the final product output; α—represents the product output correction coefficient corresponding to different operating states of the equipment. The equipment is divided into three states: normal operation, equipment production reduction, and equipment production stoppage. The definition is as follows: Where ψ can be obtained by fitting historical data.

5. The method for reducing costs and increasing efficiency through intelligent collaborative operation of the entire steel plant process according to claim 1 is characterized by: In the third step, the plant-wide indicator series consists of a two-dimensional and three-level system; the two-dimensional system refers to the production indicator dimension and the energy consumption indicator dimension, and the three-level system refers to the equipment-level indicator, the process-level indicator and the enterprise-level total indicator; then, based on the production process characteristics of the equipment, the reasonable production green range of each process equipment is determined to ensure efficient operation of the equipment and energy utilization in the economic zone of the process principle; using the synergistic effect of this range and the established monitoring indicator series, automatic analysis and diagnosis are made to generate optimization operation suggestions for each equipment system in the steel plant.

6. The method for reducing costs and increasing efficiency through intelligent collaborative operation of the entire steel plant process according to claim 5 is characterized by: The third step is to establish a production index system: ① Equipment level Where, i—represents the production process of the steel plant; j—indicates the energy-consuming equipment within the process; k—indicates the type of production materials used in energy-consuming equipment; G ijk —Indicates the amount of type k material consumed by type j energy-consuming equipment in process i to produce a unit of product; M j,k —The amount of type K materials consumed by type J energy-consuming equipment; M 设备j,产品 —Product generation of type j energy-consuming equipment; ②Process level Where G ik —Indicates the amount of type k materials consumed by process i in producing a unit of main product; M j,k —The amount of material k consumed by energy-consuming equipment j in process i; M 工序i,产品 —The amount of main product produced in process i; ③Enterprise level Where M i,j,k —The amount of type k material consumed by energy-consuming equipment j in process i; G 企业,k —During the statistical period, the enterprise consumed a total of k types of materials.

7. The method for reducing costs and increasing efficiency through intelligent collaborative operation of the entire steel plant process according to claim 5 is characterized by: The third step is to establish an energy consumption index system: ① Equipment level Where, i—represents the production process of the steel plant; j—indicates the energy-consuming equipment within the process; l—indicates the type of energy used by energy-consuming equipment; E ijl — represents the amount of standard coal equivalent of type l energy consumed by type j energy-consuming equipment in process i to produce a unit of main product; ζ l —Indicates the standard coal conversion coefficient of Class I energy; E j,l —Amount of Class I energy consumed by Class J energy-consuming equipment; M 设备j,产品 —The amount of main products produced by type j energy-consuming equipment; ②Process level Where, E il — represents the amount of type l energy consumed in the production of unit main product of process i in terms of standard coal equivalent; E i — represents the total energy consumed in producing a unit of main product in process i in terms of standard coal equivalent; ζ l —Indicates the standard coal conversion coefficient of Class I energy; E j,l —The amount of Class I energy consumed by Class J energy-consuming equipment converted into standard coal; M 工序i,产品 —The amount of main product produced in process i; ③Enterprise level Where, E i — represents the total energy consumed in producing a unit of main product in process i in terms of standard coal equivalent; p i —Shows the steel ratio coefficient of each process in the steel plant; M 工序i,产品 —Indicates the product output of each process in the steel plant; M 企业,钢产量 —Indicates the qualified steel output of the steel plant.

Images