A method for energy efficiency evaluation and intelligent diagnosis of process industry production systems

Abstract

The present invention provides an energy efficiency evaluation and intelligent diagnosis method for a process industrial production system, comprising: determining energy efficiency evaluation indicators according to equipment characteristics, process matching and overall production process in industrial production, establishing an energy balance equation, and calculating the thermal efficiency, exergy efficiency and energy consumption of each equipment, production process and system; constructing an industrial production process database and performing data preprocessing; based on the industrial production process database, using a grey correlation analysis method to quantitatively evaluate the influence of each parameter on thermal efficiency, exergy efficiency and energy consumption, and taking the parameters with greater influence as key parameters; analyzing the linear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption by constructing a multivariate regression model; hierarchically dividing the key parameters, screening benchmark operating conditions based on similarity analysis K-Means clustering, determining and comparing the best operating conditions with the actual operating conditions, implementing intelligent diagnosis, taking energy consumption as the core evaluation target, determining the optimal production method, and carrying out auxiliary decision-making.

Description

Technical Field

[0001] The present invention relates to the technical field of energy efficiency management of process industry production systems, and in particular to an energy efficiency evaluation and intelligent diagnosis method for process industry production systems. Background Art

[0002] Process industries (such as steel, petrochemicals, cement, etc.) are typical high-energy-consuming industries with complex production processes and a wide variety of energy media, involving the coordinated operation of multiple processes and equipment. Taking steel production as an example, it involves multiple processes from raw material processing, ironmaking, steelmaking, steel rolling to finished product processing. This process not only has complex production steps, but also involves energy consumption of multiple energy media. The energy efficiency levels of different equipment and processes have a significant impact on the overall production energy efficiency. Steel production companies are facing an urgent need to save energy, reduce carbon emissions, reduce costs and increase efficiency.

[0003] The energy-saving development process of my country's process industry can be divided into several stages, including the primary stage with energy saving of single equipment and process as the core, the intermediate stage with energy saving optimization of the system as the focus, the advanced stage focusing on energy flow behavior and network construction, and the new stage of promoting the green and intelligent development of metallurgical plants with energy flow as the entry point. The optimization research on industrial process energy system mainly focuses on the following three categories: the first category is the optimization of single equipment and process, which is based on the first and second laws of thermodynamics and aims to maximize energy efficiency or minimize energy loss by constructing optimization models. This type of research focuses on the improvement of equipment structure, energy structure and material composition, and explores specific measures for energy saving and consumption reduction. The second category is the optimization of specific energy media, which aims to improve energy utilization efficiency and reduce losses by optimizing the supply and demand balance and energy matching of specific energy media such as coal gas, steam and electricity. The third category is the overall process optimization, which takes the industrial process as the overall optimization object, adjusts the production structure, optimizes the material ratio and improves the energy structure to comprehensively improve the energy utilization efficiency of the production process, reduce the comprehensive energy consumption level, and help achieve the goal of sustainable development.

[0004] However, traditional energy efficiency evaluation methods have exposed significant deficiencies when dealing with the complex hierarchical comprehensive energy efficiency characteristics in process industries. These methods usually lack systematic hierarchical diagnostic analysis, and it is difficult to go deep from the whole process level to the process and equipment level to accurately identify the key driving factors of energy efficiency and their mechanisms of action. Therefore, when evaluating the influencing factors of equipment, process and whole process energy efficiency, traditional methods often find it difficult to take into account the multi-level and multi-dimensional complexity, resulting in the scientificity and pertinence of the optimization strategy being limited.

[0005] When optimizing single equipment and processes, people usually only focus on the energy efficiency optimization of a single equipment or process, but fail to fully consider the energy flow between equipment and equipment, and between processes. Without systematically considering the energy efficiency transfer and feedback in the overall production process, local optimization may not achieve overall energy efficiency improvement, and may even lead to a decrease in overall system efficiency due to uncoordinated optimization measures.

[0006] Optimization of specific energy media usually focuses on the optimization of a certain type of energy, such as electricity, gas or steam, etc. However, process industrial production involves multiple energy media (such as electricity, gas, steam, oxygen, nitrogen, argon, coal powder, etc.), ignoring the coordinated optimization of the entire process. Even if energy saving effects are achieved in the optimization of a certain energy medium, the comprehensive energy efficiency of each process in the entire production process cannot be considered. Different energy media have different demands and usage methods in different processes. Optimizing the supply and demand relationship of a single medium may not effectively coordinate the energy efficiency relationship between the various processes, resulting in the inability of local energy saving effects to be fully reflected in the entire process;

[0007] Optimizing the overall process ignores the energy-saving potential of a single process or equipment. Although the optimization of the main production process can bring about certain energy efficiency improvements, without refined optimization of specific processes or equipment, the overall energy-saving effect may be affected by local inefficiencies.

[0008] Therefore, it is necessary to conduct multi-level and multi-dimensional energy efficiency evaluation of the production process to comprehensively improve the energy utilization efficiency of process industrial production. Summary of the invention

[0009] According to the technical problems raised above, a method for energy efficiency evaluation and intelligent diagnosis of process industrial production systems is provided. The present invention mainly constructs a hierarchical evaluation system covering the entire process, process and equipment level, and forms a comprehensive energy efficiency evaluation framework from multiple dimensions such as equipment operation status, process and energy compatibility, and economic benefits. It also combines intelligent diagnostic analysis methods to accurately identify key driving factors of energy efficiency and their influencing mechanisms, and realize multi-level and multi-dimensional energy efficiency evaluation of production processes, thereby comprehensively improving the energy utilization efficiency of steel production. At the same time, it provides dynamic energy-saving optimization strategies to support enterprises in realizing intelligent management and control of production processes, and help reduce energy consumption comprehensively.

[0010] The technical means adopted by the present invention are as follows:

[0011] A process industry production system energy efficiency evaluation and intelligent diagnosis method, comprising:

[0012] According to the equipment characteristics, process matching and overall production process in industrial production, determine the energy efficiency evaluation index, build the analysis model of material flow, energy flow and exergy flow flowing through each equipment, process and process in the production process, and establish the energy balance equation to calculate the thermal efficiency, exergy efficiency and energy consumption;

[0013] An industrial production process database is constructed through the historical data set of industrial production, and data preprocessing is performed to calculate the thermal efficiency, exergy efficiency and energy consumption of the historical data, and the data are stored in the industrial production process database in correspondence with the historical data;

[0014] Based on the industrial production process database, the grey correlation analysis method is used to quantitatively evaluate the impact of various parameters on thermal efficiency, exergy efficiency and energy consumption, and the parameters are ranked, with the parameters with greater influence as the key parameters.

[0015] The linear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption is analyzed by constructing a multivariate regression model, and a machine learning algorithm is introduced to model the key parameters of nonlinear and multidimensional interactions, and the nonlinear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption is analyzed;

[0016] Key parameters are divided into levels, and benchmark operating conditions are screened based on similarity analysis K-Means clustering. The optimal operating conditions and actual operating conditions are determined and compared, and intelligent diagnosis is implemented. With energy consumption as the core evaluation target, intelligent diagnosis is performed on actual operating conditions, the optimal energy-saving strategy and production method are determined, and auxiliary decision-making is carried out.

[0017] Furthermore, the energy efficiency evaluation index includes thermal efficiency, exergy efficiency and energy consumption;

[0018] The establishment of the energy balance equation and the calculation of thermal efficiency, exergy efficiency and energy consumption specifically include:

[0019]

[0020]

[0021]

[0022]

[0023] In the formula, represents the thermal efficiency of the process, represents the exergy efficiency of the process, Indicates the energy consumption of the process; Indicates the energy brought in from the previous process or raw materials. Indicates exergy brought in from the previous process or raw materials; It means that the energy consumed is brought into the energy. Indicates the exergy brought in by energy consumption, Indicates the energy carried into the next process, Indicates the exergy carried into the next process. Represents the energy of recycling or by-products, Exergy that represents recycling or by-products, represents the energy dissipated in the environment, Indicates the amount of raw materials provided from the previous process or the outside world. Indicates the amount of energy consumed. Indicates the amount of product carried into the next process. Indicates the amount of recovered energy or by-products, Indicates the standard coal coefficient of raw materials, Indicates the standard coal coefficient of energy consumption, Indicates the standard coal coefficient of the product, Indicates the standard coal coefficient for recovered energy or by-products, Indicates the output of qualified products;

[0024] Furthermore, the parameters in the industrial production process database include: raw material composition, fuel physical composition, energy consumption, operation parameters and product parameters; the data in the industrial production process database is stored hierarchically according to the time granularity of hour, shift, day and month;

[0025] The industrial production process database is subjected to data preprocessing, including: using the median filling method to fill in the missing data for the data missing problem; and eliminating the outliers in the data based on the box plot method for the data anomaly problem.

[0026] Furthermore, the grey correlation analysis method is used to quantitatively evaluate the impact of parameters in the industrial production process database on thermal efficiency, exergy efficiency and energy consumption;

[0027] Take thermal efficiency, exergy efficiency and energy consumption as target sequence , and the target sequence As a reference sequence, the parameter sequence is expressed as ,in, , Indicates the time point or sample number, Indicates the number of parameters, and uses the parameter sequence as a comparison sequence to perform association analysis with the target sequence;

[0028] The data is standardized using range standardization, mapped to the [0,1] interval, and the influence of different indicator dimensions is eliminated:

[0029]

[0030]

[0031] in, represents the dimensionless value of the target sequence after normalization, represents the dimensionless value after the comparison sequence is standardized. Represents the minimum value in the target sequence; Indicates the maximum value in the target sequence; Indicates The minimum value of the parameter, Indicates The maximum value of the parameters;

[0032] The correlation coefficient is used to calculate the correlation between the target sequence and the comparison sequence:

[0033]

[0034] in, Indicates that the two sequences are The absolute value of the moment; represents the minimum absolute difference, Indicates the maximum value of the absolute difference; represents the resolution coefficient, ; For the The parameters in The correlation coefficient of the moment;

[0035] Grey correlation calculation formula:

[0036]

[0037] in, Indicates The grey relational degree of the parameters, represents the number of data points for the reference and comparison sequences;

[0038] According to the grey relational The parameters are sorted by their size. The parameters with higher correlation have more significant impact on the target sequence. The parameters with greater impact on thermal efficiency, exergy efficiency and energy consumption are identified as key parameters through the sorting results.

[0039] Furthermore, the maximum and minimum values ​​of the absolute difference in the correlation coefficient are calculated as follows:

[0040]

[0041]

[0042] in, Indicates that the two sequences are The absolute value of the moment; represents the minimum absolute difference, Indicates the maximum absolute difference.

[0043] Furthermore, the construction of a multivariate regression model to analyze the linear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption specifically includes:

[0044] The multivariate regression model is expressed mathematically as:

[0045]

[0046] in, represents the target value, Indicates Influencing factors, represents a constant term, is the regression coefficient, is the random error term; the influence of each parameter is quantified through parameter estimation and significance test.

[0047] Furthermore, the step of dividing the key parameters into different levels specifically includes:

[0048] The key parameters are divided into primary influencing factors and secondary influencing factors. The primary influencing factors are based on global variables. Through statistical analysis, the direct impact of global variables on the thermal efficiency, exergy efficiency and energy consumption of equipment, processes and the entire process is quantified, and the driving factors and their changing trends are identified; the secondary influencing factors are based on the primary influencing factors, and the direction and degree of influence of other parameters on the thermal efficiency, exergy efficiency and energy consumption of equipment, processes and the entire process are analyzed to identify the nonlinear relationship between key parameters and energy efficiency indicators.

[0049] Furthermore, the similarity analysis based K-Means clustering screens the benchmark working conditions, determines the optimal working conditions and the actual working conditions, takes energy consumption as the core evaluation target, and determines the optimal energy-saving strategy and production method, specifically including:

[0050] Based on the benchmark working condition, continuous full-process data under similar production conditions is selected from the industrial production process database, and the full-process data is sorted from high to low, the production record with the lowest energy consumption is selected, and the corresponding production parameters are obtained as the optimal working condition; the full-process energy consumption index and its related production parameters under the current similar working condition are obtained from the real-time production data as the current actual working condition;

[0051] Compare and analyze the thermal efficiency, exergy efficiency and energy consumption of the best working condition and the actual working condition, determine the key parameters that affect energy consumption, and compare the key parameters of the best working condition and the actual working condition with the primary and secondary influencing factors as references, calculate the absolute value and relative change rate of the deviation of the key parameters on the thermal efficiency, exergy efficiency and energy consumption of the equipment, process and different levels of the whole process, and quantify the contribution of the key parameters to the overall energy consumption;

[0052] According to the calculation results of the contribution of the key parameters to the overall energy consumption, the key parameters at all levels are quantitatively ranked, and energy consumption is taken as the core evaluation target. Combined with thermal efficiency and exergy efficiency as goals, a comprehensive optimization plan covering equipment, processes and the entire process is formulated.

[0053] Compared with the prior art, the present invention has the following advantages:

[0054] The energy efficiency evaluation and intelligent diagnosis method for process industrial production system provided by the present invention determines energy efficiency evaluation indicators according to the equipment characteristics, process matching and overall production process in industrial production, constructs analysis models of material flow, energy flow and exergy flow flowing through each equipment, process and process in the production process, and establishes an energy balance equation to calculate the thermal efficiency, exergy efficiency and energy consumption of each process; constructs an industrial production process database through a collection of historical data of industrial production, performs data preprocessing, calculates the thermal efficiency, exergy efficiency and energy consumption of historical data, and stores them in the industrial production process database corresponding to the historical data; based on the industrial production process database, a grey correlation analysis method is used to quantify the thermal efficiency, exergy efficiency and energy consumption of each process. Evaluate the impact of various parameters on thermal efficiency, exergy efficiency and energy consumption, rank the parameters, and take the parameters with greater influence as key parameters; analyze the linear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption by constructing a multivariate regression model, and introduce machine learning algorithms to model key parameters with nonlinear and multidimensional interactions, and analyze the nonlinear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption; divide the key parameters into levels, screen the benchmark operating conditions based on similarity analysis K-Means clustering, determine and compare the best operating conditions with the actual operating conditions, implement intelligent diagnosis, take energy consumption as the core evaluation target, and determine the optimal energy-saving strategy and production method.

[0055] The energy efficiency evaluation and intelligent diagnosis method for process industry production systems provided by the present invention realizes accurate analysis and dynamic optimization of the energy efficiency of the entire process of process industry production by constructing a multi-level and multi-dimensional energy efficiency evaluation and intelligent diagnosis framework. By using indicators such as thermal efficiency, exergy efficiency, and energy consumption, combined with intelligent diagnosis technology, energy efficiency bottlenecks and key driving factors are deeply explored to provide customized energy-saving strategies. This technology can monitor and dynamically manage energy efficiency in real time, improve resource utilization efficiency, reduce energy consumption, and lay a solid foundation for the intelligent and green transformation of process industries.

[0056] Based on the above reasons, the present invention can be widely promoted in the fields of energy efficiency management of process industry production systems, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0058] Figure 1 This is a flow chart of the energy efficiency evaluation and intelligent diagnosis method of the process industry production system in the present invention.

[0059] Figure 2 It is a material flow, energy flow and exergy flow analysis model flowing through each unit process (device) in the steel production process in the embodiment of the present invention.

[0060] Figure 3 Schematic diagram of the steel production process range in an embodiment of the present invention.

[0061] Figure 4 The figure is a flowchart of a method for storing data in a database and processing data in an embodiment of the present invention.

[0062] Figure 5 Schematic diagram of the intelligent diagnosis and analysis process in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0064] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0065] like Figure 1As shown, the present invention provides an energy efficiency evaluation and intelligent diagnosis method for a process industry production system. In a specific embodiment, taking a steel production process as an example, the method includes:

[0066] According to the equipment characteristics, process matching and overall production process in industrial production, determine the energy efficiency evaluation index, build the analysis model of material flow, energy flow and exergy flow flowing through each equipment, process and process in the production process, and establish the energy balance equation to calculate the thermal efficiency, exergy efficiency and energy consumption;

[0067] At present, the energy efficiency evaluation methods of process industries are mainly divided into the following four categories: thermodynamic indicators, physical-caloric indicators, economic-caloric indicators and pure economic methods. According to actual application requirements, the thermal efficiency and exergy efficiency in thermodynamic indicators and the energy consumption in physical-caloric indicators are used to evaluate the energy efficiency of process industries. Among them, thermal efficiency can measure the quantitative performance of energy conversion and reflect the operating status of equipment; exergy efficiency can evaluate energy grade and irreversible loss, revealing the matching of energy structure and production process; energy consumption can quantify energy consumption, intuitively reflect economic and environmental impact, and is a key indicator for macro energy efficiency optimization and policy formulation. This choice can start from the basic laws of energy conversion and consumption, so as to more scientifically identify and optimize the energy efficiency bottlenecks of key links and improve the overall energy utilization efficiency.

[0068] In specific implementation, as a preferred embodiment of the present invention, the energy efficiency evaluation index includes thermal efficiency, exergy efficiency and energy consumption;

[0069] like Figure 2 As shown in the figure, the energy balance equation is established to calculate the thermal efficiency, exergy efficiency and energy consumption, including:

[0070]

[0071]

[0072]

[0073]

[0074] In the formula, Represents the thermal efficiency of the process, %, Represents the exergy efficiency of the process, %, Indicates process energy consumption, kgce / t; Indicates the energy brought in from the previous process or raw materials, kJ, Indicates the exergy brought in from the previous process or raw materials; kJ, Indicates the energy brought in by the consumed energy, kJ, Indicates the exergy brought in by energy consumption, kJ, Indicates the energy carried into the next process, kJ, represents the exergy carried into the next process, kJ, Indicates the energy of recycling or by-product, kJ, Indicates exergy of recycled or by-product, kJ, represents the energy dissipated in the environment, kJ, Indicates the amount of raw materials provided from the previous process or the outside world, kg or , Indicates the amount of energy consumed, kg or , Indicates the amount of product carried into the next process, kg or , Indicates the amount of recovered energy or by-products, kg or , Indicates the standard coal coefficient of raw materials, kgce / kg or , Indicates the standard coal coefficient of energy consumption, kgce / kg or , Indicates the product's standard coal coefficient, kgce / kg or , Indicates the standard coal coefficient for recovered energy or by-products, kgce / kg or , Represents the output of qualified products, in t. Figure 2 middle is the exergy dissipated in the environment, kJ, Indicates the amount of waste such as flue gas generated, kg or .

[0075] When implementing, Figure 3 The steel production process shown in the figure shows that the main process stages include coking, sintering, ironmaking, converter steelmaking and hot rolling processes. The main equipment includes coke oven, dry quenching furnace, sintering machine, ring cooler, hot blast stove, blast furnace, TRT, converter, heating furnace and waste heat boiler.

[0076] From a logistics perspective, the production boundary of the coking process covers the entire process from raw material input to product and by-product output. Its input logistics include coal, gas and energy-consuming working fluids, and the coal enters the coke oven after storage, coal blending and coal loading; the output logistics covers the main products and by-products such as coke, coke oven gas, tar, crude benzene, steam, etc.

[0077] The boundary of the sintering process starts with the input of raw fuel, coal gas, flux and energy-consuming working fluids, and ends with the output of the main product sintered ore, recovered steam, etc. It includes material preparation and mixing, dust removal, sintering, cooling and waste heat recovery systems.

[0078] The boundary of the ironmaking process starts with the input of raw fuel, coal gas and energy-consuming working fluids, and ends with the output of the main product molten iron and by-product blast furnace gas, TRT power generation, etc. It includes charging, blasting, blowing, blast furnace, coal gas purification, TRT power generation and dust removal.

[0079] The boundary of the converter steelmaking process starts with the input of molten iron, flux, coal gas and energy-consuming working fluids, and ends with the output of the main product molten steel and by-products converter coal gas, steel slag, recovered steam, etc. It includes molten iron pretreatment, ladle baking, converter, coal gas purification, waste heat boiler and dust removal.

[0080] The hot rolling process boundary starts with the input of continuous casting billets, natural gas, coal gas and energy-consuming working fluids, and ends with the output of main product steel and by-product recovered steam. It includes the heating of slabs in heating furnaces, waste heat boilers and rolling lines.

[0081] The research boundary of the steel production process includes coking, sintering, ironmaking, converter steelmaking and hot rolling processes. The detailed boundaries of each process are as shown in the above steps. The steel production process starts with the input of raw materials, flux, coal, natural gas and energy-consuming working fluids, and ends with the output of the main product steel, by-products coke oven gas, blast furnace gas, converter gas, recovered steam and recovered electricity.

[0082] An industrial production process database is constructed through the historical data set of industrial production, and data preprocessing is performed to calculate the thermal efficiency, exergy efficiency and energy consumption of the historical data, and the data are stored in the industrial production process database in correspondence with the historical data;

[0083] In specific implementation, as a preferred embodiment of the present invention, the parameters in the industrial production process database include: raw material composition, fuel physical composition, energy consumption, operation parameters and product parameters; the data in the industrial production process database are stored hierarchically according to the time granularity of hours, shifts, days and months;

[0084] Data preprocessing is performed on industrial production process databases, such as Figure 4 As shown in the figure, the data processing process is carried out in the python environment.

[0085] Based on the industrial production process database, the grey correlation analysis method is used to quantitatively evaluate the impact of various parameters on thermal efficiency, exergy efficiency and energy consumption, and the parameters are ranked, with the parameters with greater influence as the key parameters.

[0086] In specific implementation, as a preferred embodiment of the present invention, the grey correlation analysis method is used to quantitatively evaluate the influence of parameters in the industrial production process database on thermal efficiency, exergy efficiency and energy consumption;

[0087] Take thermal efficiency, exergy efficiency and energy consumption as target sequence , and the target sequence As a reference sequence, the parameter sequence is expressed as ,in, , Indicates the time point or sample number, Indicates the number of parameters, and uses the parameter sequence as a comparison sequence to perform association analysis with the target sequence;

[0088] The data is standardized using range standardization, mapped to the [0,1] interval, and the influence of different indicator dimensions is eliminated:

[0089]

[0090]

[0091] in, represents the dimensionless value of the target sequence after normalization, represents the dimensionless value after the comparison sequence is standardized. Represents the minimum value in the target sequence; Indicates the maximum value in the target sequence; Indicates The minimum value of the parameter, Indicates The maximum value of the parameters;

[0092] The maximum and minimum absolute differences in the correlation coefficient are calculated as follows:

[0093]

[0094]

[0095] in, Indicates that the two sequences are The absolute value of the moment; represents the minimum absolute difference, Indicates the maximum absolute difference.

[0096] The correlation coefficient is used to calculate the correlation between the target sequence and the comparison sequence:

[0097]

[0098] in, Indicates that the two sequences are The absolute value of the moment; represents the minimum absolute difference, Indicates the maximum value of the absolute difference; represents the resolution coefficient, ; For the The parameters in The correlation coefficient of the moment;

[0099] Grey correlation calculation formula:

[0100]

[0101] in, Indicates The grey relational degree of the parameters, represents the number of data points for the reference and comparison sequences;

[0102] According to the grey relational The parameters are sorted by their size. The parameters with higher correlation have more significant impact on the target sequence. The parameters with greater impact on thermal efficiency, exergy efficiency and energy consumption are identified as key parameters through the sorting results to provide guidance for production optimization.

[0103] The linear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption is analyzed by constructing a multivariate regression model, and a machine learning algorithm is introduced to model the key parameters of nonlinear and multidimensional interactions, and the nonlinear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption is analyzed;

[0104] In the specific implementation, as a preferred embodiment of the present invention, a multivariate regression model is constructed to analyze the linear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption, specifically including:

[0105] The multivariate regression model is expressed mathematically as:

[0106]

[0107] in, represents the target value, Indicates Influencing factors, represents a constant term, is the regression coefficient, is a random error term; through parameter estimation and significance test, the influence of each parameter is quantified, revealing the specific influence degree and direction of each factor on thermal efficiency, exergy efficiency and energy consumption indicators.

[0108] Key parameters are divided into levels, and benchmark operating conditions are screened based on similarity analysis K-Means clustering. The optimal operating conditions and actual operating conditions are determined and compared, and intelligent diagnosis is implemented. Energy consumption is used as the core evaluation target to determine the optimal energy-saving strategy and production method.

[0109] In specific implementation, as a preferred embodiment of the present invention, the key parameters are divided into levels, which specifically include:

[0110] The key parameters are divided into primary influencing factors and secondary influencing factors. The primary influencing factors are based on global variables such as fuel consumption. Through statistical analysis, the direct impact of global variables on the thermal efficiency, exergy efficiency and energy consumption of equipment, processes and the entire process is quantified, and the driving factors and their changing trends are identified; the secondary influencing factors are based on the primary influencing factors, and other parameters such as ignition temperature, composition, preheated air temperature, etc. are analyzed to determine the direction and degree of influence on the thermal efficiency, exergy efficiency and energy consumption of equipment, processes and the entire process, and the nonlinear relationship between key parameters and energy efficiency indicators is identified.

[0111] In the specific implementation, as a preferred embodiment of the present invention, the benchmark operating conditions are screened based on similarity analysis K-Means clustering, the optimal operating conditions and actual operating conditions are determined and compared, intelligent diagnosis is implemented, energy consumption is taken as the core evaluation target, the optimal energy-saving strategy and production method are determined, and auxiliary decision-making is carried out, which specifically includes:

[0112] Based on the benchmark working condition, the full process data of 30 consecutive days under similar production conditions in the industrial production process database is selected, and the full process data is sorted from high to low, and the production record with the lowest energy consumption is selected to obtain the corresponding production parameters as the optimal working condition; the full process energy consumption index and its related production parameters under the current similar working condition are obtained from the real-time production data as the current actual working condition;

[0113] Compare and analyze the thermal efficiency, exergy efficiency and energy consumption of the best working condition and the actual working condition, determine the key parameters that affect energy consumption, and use the primary and secondary influencing factors as references to compare the key parameters of the best working condition and the actual working condition, such as fuel consumption, ignition temperature, preheating air temperature, etc., calculate the absolute value and relative change rate of the deviation of the key parameters on the thermal efficiency, exergy efficiency and energy consumption of the equipment, process and different levels of the whole process, and quantify the contribution of the key parameters to the overall energy consumption;

[0114] Based on the calculation results of the contribution of key parameters to the overall energy consumption, key parameters at all levels are quantitatively ranked. With energy consumption as the core evaluation target and thermal efficiency and exergy efficiency as the targets, an optimization plan is formulated covering equipment, processes and the entire process, and comprehensively proposed from three dimensions: equipment status, energy structure and process adaptability, and economic benefits.

[0115] When implementing, Figure 5As shown in the figure, based on the strength of the positive effects on the three-level scales of equipment, process and the whole process and the difficulty of implementation, the optimization measures with significant effects on the three-level, partial-level and single-level are prioritized, and optimization suggestions are comprehensively put forward from the three dimensions of equipment status, energy structure and process adaptability, and economic benefits. The energy-saving potential of each optimization measure is quantitatively ranked, and finally a scientific and feasible graded implementation plan is formed.

[0116] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0117] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0120] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0121] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A process industry production system energy efficiency evaluation and intelligent diagnosis method, characterized in that: include: According to the equipment characteristics, process matching and overall production process in industrial production, determine the energy efficiency evaluation index, build the analysis model of material flow, energy flow and exergy flow flowing through each equipment, process and process in the production process, and establish the energy balance equation to calculate the thermal efficiency, exergy efficiency and energy consumption; The energy efficiency evaluation indicators include thermal efficiency, exergy efficiency and energy consumption; The establishment of the energy balance equation and the calculation of thermal efficiency, exergy efficiency and energy consumption specifically include: In the formula, represents the thermal efficiency of the process, represents the exergy efficiency of the process, Indicates the energy consumption of the process; Indicates the energy brought in from the previous process or raw materials. Indicates exergy brought in from the previous process or raw materials; It means that the energy consumed is brought into the energy. Indicates the exergy brought in by energy consumption, Indicates the energy carried into the next process, Indicates the exergy carried into the next process. Represents the energy of recycling or by-products, Exergy that represents recycling or by-products, represents the energy dissipated in the environment, Indicates the amount of raw materials provided from the previous process or the outside world. Indicates the amount of energy consumed. Indicates the amount of product carried into the next process. Indicates the amount of recovered energy or by-products, Indicates the standard coal coefficient of raw materials, Indicates the standard coal coefficient of energy consumption, Indicates the standard coal coefficient of the product, Indicates the standard coal coefficient for recovered energy or by-products, Indicates the output of qualified products; An industrial production process database is constructed through the historical data set of industrial production, and data preprocessing is performed to calculate the thermal efficiency, exergy efficiency and energy consumption of the historical data, and the data are stored in the industrial production process database in correspondence with the historical data; Based on the industrial production process database, the grey correlation analysis method is used to quantitatively evaluate the impact of various parameters on thermal efficiency, exergy efficiency and energy consumption, and the parameters are ranked, with the parameters with greater influence as the key parameters. The linear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption is analyzed by constructing a multivariate regression model, and a machine learning algorithm is introduced to model the key parameters of nonlinear and multidimensional interactions, and the nonlinear relationship between key parameters and thermal efficiency, exergy efficiency and energy consumption is analyzed; The multivariate regression model is expressed mathematically as: in, represents the target value, Indicates Influencing factors, represents a constant term, is the regression coefficient, is the random error term; through parameter estimation and significance test, the influence of each parameter is quantified; Divide key parameters into levels, select benchmark operating conditions based on similarity analysis K-Means clustering, determine and compare optimal operating conditions with actual operating conditions, implement intelligent diagnosis, take energy consumption as the core evaluation target, determine the optimal energy-saving strategy and production method, and carry out auxiliary decision-making; The hierarchical division of key parameters specifically includes: The key parameters are divided into primary influencing factors and secondary influencing factors. The primary influencing factors are based on global variables. Through statistical analysis, the direct impact of global variables on the thermal efficiency, exergy efficiency and energy consumption of equipment, processes and the entire process is quantified, and the driving factors and their changing trends are identified; the secondary influencing factors are based on the primary influencing factors, and the direction and degree of influence of other parameters on the thermal efficiency, exergy efficiency and energy consumption of equipment, processes and the entire process are analyzed to identify the nonlinear relationship between key parameters and energy efficiency indicators.

2. The process industry production system energy efficiency evaluation and intelligent diagnosis method according to claim 1 is characterized in that: The parameters in the industrial production process database include: raw material composition, fuel physical composition, energy consumption, operation parameters and product parameters; the data in the industrial production process database are stored hierarchically according to the time granularity of hours, shifts, days and months; The industrial production process database is subjected to data preprocessing, including: using the median filling method to fill in the missing data for the data missing problem; and eliminating the outliers in the data based on the box plot method for the data anomaly problem.

3. The process industry production system energy efficiency evaluation and intelligent diagnosis method according to claim 1 is characterized in that: The grey relational analysis method is used to quantitatively evaluate the impact of parameters in the industrial production process database on thermal efficiency, exergy efficiency and energy consumption; Take thermal efficiency, exergy efficiency and energy consumption as target sequence , and the target sequence As a reference sequence, the parameter sequence is expressed as ,in, , Indicates the time point or sample number, Indicates the number of parameters, and uses the parameter sequence as a comparison sequence to perform association analysis with the target sequence; The data is standardized using range standardization, mapped to the [0,1] interval, and the influence of different indicator dimensions is eliminated: in, represents the dimensionless value of the target sequence after normalization, represents the dimensionless value after the comparison sequence is standardized. Represents the minimum value in the target sequence; Indicates the maximum value in the target sequence; Indicates The minimum value of the parameter, Indicates The maximum value of the parameters; The correlation coefficient is used to calculate the correlation between the target sequence and the comparison sequence: in, Indicates that the two sequences are The absolute value of the moment; represents the minimum absolute difference, Indicates the maximum value of the absolute difference; represents the resolution coefficient, ; For the The parameters in The correlation coefficient of the moment; Grey correlation calculation formula: in, Indicates The grey relational degree of the parameters, represents the number of data points for the reference and comparison sequences; According to the grey relational The parameters are sorted by their size. The parameters with higher correlation have more significant impact on the target sequence. The parameters with greater impact on thermal efficiency, exergy efficiency and energy consumption are identified as key parameters through the sorting results.

4. The process industry production system energy efficiency evaluation and intelligent diagnosis method according to claim 3 is characterized in that: The maximum and minimum values ​​of the absolute difference in the correlation coefficient are calculated as follows: in, Indicates that the two sequences are The absolute value of the moment; represents the minimum absolute difference, Indicates the maximum absolute difference.

5. The process industry production system energy efficiency evaluation and intelligent diagnosis method according to claim 1, characterized in that: The similarity analysis based K-Means clustering screens the benchmark working conditions, determines the optimal working conditions and the actual working conditions, takes energy consumption as the core evaluation target, and determines the optimal energy-saving strategy and production method, specifically including: Based on the benchmark working condition, continuous full-process data under similar production conditions is selected from the industrial production process database, and the full-process data is sorted from high to low, the production record with the lowest energy consumption is selected, and the corresponding production parameters are obtained as the optimal working condition; the full-process energy consumption index and its related production parameters under the current similar working condition are obtained from the real-time production data as the current actual working condition; Compare and analyze the thermal efficiency, exergy efficiency and energy consumption of the best working condition and the actual working condition, determine the key parameters that affect energy consumption, and compare the key parameters of the best working condition and the actual working condition with the primary and secondary influencing factors as references, calculate the absolute value and relative change rate of the deviation of the key parameters on the thermal efficiency, exergy efficiency and energy consumption of the equipment, process and different levels of the whole process, and quantify the contribution of the key parameters to the overall energy consumption; According to the calculation results of the contribution of the key parameters to the overall energy consumption, the key parameters at all levels are quantitatively ranked, and energy consumption is taken as the core evaluation target. Combined with thermal efficiency and exergy efficiency as goals, a comprehensive optimization plan covering equipment, processes and the entire process is formulated.

Images