Industrial high energy consuming system energy efficiency optimization system, method, device and medium

Abstract

The application relates to the technical field of industrial control. An industrial high-energy-consumption system energy efficiency optimization system, method, device and medium are disclosed. The system comprises an acquisition module for acquiring main process equipment state parameters and auxiliary process equipment state parameters; a first generation module for generating a system coupling topology graph according to the main process equipment state parameters and the auxiliary process equipment state parameters; a path determination module for determining a key coupling path according to the system coupling topology graph; and a second generation module for generating an optimization instruction according to the key coupling path. The application can cognize and quantify the complex coupling interaction relationship between the main process dynamic production demand and the auxiliary process energy supply from the system level by constructing the system coupling topology graph, can accurately locate the key bottleneck path of the low overall energy efficiency of the system by generating the optimization instruction for the key coupling path, and can generate the targeted optimization instruction to perform the global energy efficiency optimization of the main process and the auxiliary process of the system.

Description

Technical Field

[0001] This application relates to the field of industrial control technology, and more specifically, to an energy efficiency optimization system, method, equipment, and medium for high-energy-consuming industrial systems. Background Technology

[0002] High-energy-consuming industrial systems, such as typical production facilities in chemical and metallurgical fields, usually consist of a main process that undertakes the core production tasks and auxiliary processes that provide energy such as power, compressed gas, and circulating water. For a long time, the main process and auxiliary processes have been relatively isolated at the operational optimization level, forming information silos.

[0003] Traditional energy efficiency optimization technologies mostly focus on local aspects, either optimizing only the process parameters of the main process or improving the operating efficiency of a single auxiliary process device. Existing local optimization methods cannot understand and quantify the complex coupling and interaction between the dynamic production demand of the main process and the energy supply of the auxiliary process at the system level. Lacking insight into this dynamic coupling relationship, it is difficult to accurately locate the key bottlenecks causing low overall system energy efficiency, and the optimization measures are somewhat blind. Summary of the Invention

[0004] In view of the above situation, this application provides an energy efficiency optimization system, method, device and medium for industrial high energy consumption systems, which aims to solve the above problems or at least partially solve the above problems.

[0005] In a first aspect, this application provides an energy efficiency optimization system for industrial high-energy-consuming systems, including: main process equipment and auxiliary process equipment; The acquisition module is used to acquire the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The first generation module is used to generate a system coupled topology diagram based on a pre-set topology diagram generation model, according to the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The system coupled topology diagram includes equipment nodes and energy flow edges connecting the equipment nodes, as well as flux fluctuation indicators, phase lag indicators and correlation indicators marked on each energy flow edge. The path determination module is used to determine the key coupling paths based on a pre-set topology graph analysis model and the system coupling topology graph. The second generation module is used to generate optimization instructions based on a pre-set instruction generation model and according to the key coupling path. The optimization instructions include main process optimization instructions and / or auxiliary process optimization instructions. The main process optimization instructions are sent to the main process device, and the auxiliary process optimization instructions are sent to the auxiliary process device.

[0006] For example, the first generation module is further configured to determine the state parameters of the two target device nodes corresponding to the target energy flow edge within a preset analysis period based on the main process device state parameters and the auxiliary process device state parameters. The first generation module is also used to determine the status parameters of the main process equipment node within a preset analysis period based on the status parameters of the main process equipment. The first generation module is also used to determine the throughput fluctuation index, the phase lag index, and the correlation index based on a pre-set index calculation model and according to the status parameters of the main process equipment node and the status parameters of the two target equipment nodes.

[0007] For example, the indicator calculation model includes a first indicator calculation model, a second indicator calculation model, and a third indicator calculation model; The first generation module is further configured to, based on the first index calculation model, determine the energy flux time series of the target energy flow edge according to the state parameters of the two target device nodes corresponding to the target energy flow edge, and calculate the flux fluctuation index according to the standard deviation and average value of the energy flux time series of the target energy flow edge; The first generation module is also used to determine the main process characteristic time point based on the second index calculation model and the state parameters of the main process equipment node, and to determine the auxiliary process characteristic time point in the energy flux time series of the target energy flow edge based on the main process characteristic time point, and to calculate the phase lag index based on the main process characteristic time point and the auxiliary process characteristic time point. The first generation module is also used to calculate the correlation index based on the third index calculation model, according to the flux fluctuation index and the phase lag index.

[0008] For example, the key coupling path includes a weakly coupled path; The path determination module is also used to parse the correlation index of each energy flow edge based on the topology graph analysis model and the coupled topology graph of the system. The path determination module is also used to compare the correlation index of each energy flow edge with the first preset threshold based on the first preset threshold in the topology graph analysis model, and determine the weakly coupled path according to the comparison result.

[0009] For example, the second generation module is also used to parse the first energy flux time series of the weakly coupled path based on the system coupling topology graph according to the pre-set topology graph analysis model; The second generation module is also used to generate the theoretical demand curve of the main process equipment in the instruction generation model based on the instruction, and to identify the energy gap period and the energy sufficient period of the first auxiliary process according to the first energy flux time series. The second generation module is also used to generate main process optimization instructions based on the main process instruction generation model in the instruction generation model, according to the first auxiliary process energy gap period and the first auxiliary process energy sufficient period.

[0010] For example, the key coupling path includes an unstable path; The path determination module is also used to parse the correlation index of each energy flow edge within multiple preset analysis periods based on the topology graph analysis model and the system coupling topology graph. The path determination module is also used to perform statistical analysis on the correlation index of the target energy flow edge within multiple preset analysis periods to obtain the correlation fluctuation rate of each energy flow edge. The path determination module is also used to compare the correlation volatility of each energy flow edge with the second preset threshold based on the second preset threshold in the topology graph analysis model, and determine the unstable path according to the comparison result.

[0011] For example, the second generation module is further configured to parse the second energy flux time series of the unstable path based on the pre-set topology graph analysis model and the unstable path. The second generation module is also used to generate the theoretical operating curve of the auxiliary process equipment in the instruction generation model based on the instruction, and to identify the energy gap period and the energy sufficient period of the second auxiliary process according to the second energy flux time series. The second generation module is also used to generate auxiliary process optimization instructions based on the main process instruction generation model in the instruction generation model, according to the energy gap period of the second auxiliary process and the energy sufficient period of the second auxiliary process.

[0012] Secondly, this application provides a method for optimizing the energy efficiency of industrial high-energy-consuming systems, used in the industrial high-energy-consuming system energy efficiency optimization system as described in the first aspect, the method comprising: Obtain the status parameters of the main process equipment and the auxiliary process equipment; Based on a pre-set topology generation model, a system coupled topology is generated according to the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The system coupled topology includes equipment nodes and energy flow edges connecting the equipment nodes, as well as flux fluctuation indicators, phase lag indicators and correlation indicators marked on each energy flow edge. Based on the pre-set topology diagram analysis model, the key coupling paths are determined according to the system coupling topology diagram; Based on a pre-set instruction generation model, optimized instructions are generated according to the key coupling path. The optimized instructions include main process optimization instructions and / or auxiliary process optimization instructions. The main process optimization instructions are sent to the main process device, and the auxiliary process optimization instructions are sent to the auxiliary process device.

[0013] Thirdly, this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the energy efficiency optimization method for industrial high-energy-consuming systems as described in the second aspect.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the energy efficiency optimization method for high-energy-consuming industrial systems as described in the second aspect.

[0015] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: This application constructs a system coupling topology diagram, enabling the understanding and quantification of the complex coupling interaction between the dynamic production demands of the main process and the energy supply of the auxiliary process at the system level. Based on the system coupling topology diagram, this application parses out key coupling paths and generates optimization instructions for these paths. This achieves insight into the dynamic coupling relationship between the main and auxiliary processes, accurately pinpointing key bottleneck paths leading to low overall system energy efficiency, and generating targeted optimization instructions for global energy efficiency optimization of both the main and auxiliary processes. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a schematic diagram of an application environment for an energy efficiency optimization method for industrial high-energy-consuming systems according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating an energy efficiency optimization method for industrial high-energy-consuming systems according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a system coupling topology in one embodiment of the present invention; Figure 4 yes Figure 2 A flowchart illustrating a specific implementation method of step S2; Figure 5 This is a schematic flowchart of a specific implementation of a weakly coupled path in one embodiment of the present invention; Figure 6This is a schematic flowchart illustrating a specific implementation of the unstable path in one embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an energy efficiency optimization system for high-energy-consuming industrial systems according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention; Figure 9 This is another structural schematic diagram of a computer device according to one embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such use can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the term "comprising" and its variations should be interpreted as open-ended terms meaning "including but not limited to."

[0019] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0020] As mentioned earlier, current local optimization methods cannot understand and quantify the complex coupling and interaction between the dynamic production needs of the main process and the energy supply of the auxiliary process at the system level. Lacking insight into this dynamic coupling, they struggle to accurately pinpoint the key bottlenecks causing overall low system energy efficiency, and their optimization measures are somewhat arbitrary. To address this technical problem, this application provides an energy efficiency optimization system for high-energy-consuming industrial systems.

[0021] In one embodiment, an energy efficiency optimization system for high-energy-consuming industrial systems is provided, such as... Figure 7 As shown, the energy efficiency optimization system for this high-energy-consuming industrial system includes main process equipment, auxiliary process equipment, acquisition module 101, first generation module 102, path determination module 103, and second generation module 104. Detailed descriptions of each functional module are as follows: The acquisition module 101 is used to acquire the status parameters of the main process equipment and the status parameters of the auxiliary process equipment; The first generation module 102 is used to generate a system coupled topology diagram based on a pre-set topology diagram generation model, according to the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The system coupled topology diagram includes equipment nodes and energy flow edges connecting the equipment nodes, as well as flux fluctuation index, phase lag index and correlation index marked on each energy flow edge. The path determination module 103 is used to determine the key coupling paths based on the system coupling topology graph according to the pre-set topology graph analysis model. The second generation module 104 is used to generate optimization instructions based on a pre-set instruction generation model and according to the key coupling path. The optimization instructions include main process optimization instructions and / or auxiliary process optimization instructions. The main process optimization instructions are sent to the main process device, and the auxiliary process optimization instructions are sent to the auxiliary process device.

[0022] This invention provides an energy efficiency optimization device for high-energy-consuming industrial systems. By constructing a system coupling topology diagram, this application can understand and quantify the complex coupling interaction between the dynamic production needs of the main process and the energy supply of the auxiliary process at the system level. Based on the system coupling topology diagram, this application parses out key coupling paths and generates optimization instructions for these paths. This achieves insight into the dynamic coupling relationship between the main and auxiliary processes, accurately locates the key bottleneck paths leading to low overall system energy efficiency, and generates targeted optimization instructions for global energy efficiency optimization of both the main and auxiliary processes.

[0023] Specifically, in one embodiment, the status parameters of the main process equipment are measured by measuring devices in the industrial high-energy-consuming system. The main process equipment status parameters are the status parameters of the equipment located in the main process of the industrial high-energy-consuming system. There are multiple pieces of equipment in the main process of the industrial high-energy-consuming system, and the status parameters of each piece of equipment are set and collected according to requirements. For example, the main process equipment includes furnaces, reactors, processing equipment, etc., and the status parameters of the main process equipment are as follows: the status parameter of the furnace is the material throughput rate, the status parameter of the reactor is the critical process temperature, and the status parameter of the processing equipment is the equipment operating frequency.

[0024] In one embodiment, the status parameters of the auxiliary process equipment are measured by measuring devices in the industrial high-energy-consuming system. The status parameters of the auxiliary process equipment refer to the status parameters of the equipment located in the auxiliary process of the industrial high-energy-consuming system. There are multiple pieces of equipment in the auxiliary process of the industrial high-energy-consuming system, and the status parameters of each piece of equipment are set and collected according to requirements. For example, the auxiliary process equipment includes air compressor units, energy storage tanks, circulating water systems, pump sets, cooling towers, etc. The status parameters of the auxiliary process equipment are as follows: the status parameter of the air compressor unit is the compressed air pressure; the status parameter of the energy storage tank is the energy storage tank pressure; the status parameter of the circulating water system is the circulating water flow rate; the status parameter of the pump set is the pump set speed; and the status parameter of the cooling tower is the inlet water temperature.

[0025] It should be noted that the status parameters of the main process equipment or the auxiliary process equipment are set according to the system characteristics of the industrial high-energy-consuming system. Each piece of equipment must have at least one type of status parameter. If the same piece of equipment has two or more status parameters, all status parameters are obtained. This embodiment uses one type of status parameter for the same equipment as an example. No specific limitations are made here.

[0026] In one embodiment, both the main process equipment and the auxiliary process equipment have unique equipment identifiers. The topology graph generation model includes topology graph generation rules, which include generating equipment nodes, determining energy flow edges between equipment nodes, and calculating flux fluctuation, phase lag, and correlation indices for each energy flow edge. Generating equipment nodes involves obtaining the equipment identifiers of the main process equipment and the auxiliary process equipment, generating equipment nodes based on the equipment identifiers, and establishing a mapping relationship between equipment nodes and equipment identifiers. Determining energy flow edges between equipment nodes involves determining the energy flow edges between equipment nodes based on a preset energy flow relationship between the equipment. The generation of equipment nodes and the determination of energy flow edges between equipment nodes in the first generation module 102 can also be performed before the acquisition module 101 acquires the status parameters of the main process equipment and the auxiliary process equipment, without specific limitations. The status parameters of the main process equipment and the auxiliary process equipment acquired by the acquisition module 101 both include equipment identifiers and their status parameter values. Based on the mapping relationship between equipment nodes and equipment identifiers, the status parameter values ​​are mapped to the equipment nodes. For example... Figure 3 The equipment nodes include auxiliary process equipment nodes and main process equipment nodes. The main process equipment nodes include heating furnace nodes, reactor nodes, and processing equipment nodes. The auxiliary process equipment nodes include air compressor unit nodes, energy storage tank nodes, circulating water system nodes, pump unit nodes, and cooling tower nodes. The energy flow edges between equipment nodes are shown as solid lines in the figure.

[0027] In one embodiment, the first generation module 102 is used to calculate the flux fluctuation index, phase lag index and correlation index on each energy flow edge based on the status parameters of the main process equipment and the status parameters of the auxiliary process equipment.

[0028] Specifically, the first generation module 102 is also used to determine the status parameters of the two target device nodes corresponding to the target energy flow edge within a preset analysis period based on the status parameters of the main process equipment and the status parameters of the auxiliary process equipment.

[0029] In one embodiment, the preset analysis period is a time period that can characterize a complete main process unit production cycle.

[0030] In one embodiment, each energy flow edge in the system coupled topology graph needs to have its flux fluctuation index, phase lag index, and correlation index calculated. Therefore, the target energy flow edge is a single energy flow edge when performing a traversal analysis of all energy flow edges in the system coupled topology graph; that is, the target energy flow edge is any single energy flow edge. For example, the energy flow edge between the air compressor unit and the energy storage tank, or the energy flow edge between the circulating water system and the heater, or the energy flow edge between the circulating water system and the pump unit, etc.

[0031] In one embodiment, when determining the device status parameters corresponding to the two connected device nodes based on the target energy flow edge, the two connected device nodes are first determined based on the target energy flow edge, and then the device status parameters are determined based on the mapping relationship between device nodes and device identifiers. The status parameters of the two target device nodes corresponding to the target energy flow edge may be two auxiliary process device status parameters, or one main process device status parameter and one auxiliary process device status parameter. For example, when the target energy flow edge is the energy flow edge between the circulating water system and the pump group, the status parameters of the two target device nodes corresponding to the target energy flow edge are the circulating water system status parameter and the pump group status parameter; when the target energy flow edge is the energy flow edge between the circulating water system and the heater, the status parameters of the two target device nodes corresponding to the target energy flow edge are the circulating water system status parameter and the heater status parameter.

[0032] Specifically, the first generation module 102 is also used to determine the status parameters of the main process equipment node within a preset analysis period based on the status parameters of the main process equipment.

[0033] In one embodiment, the status parameters of the main process equipment nodes are determined based on the mapping relationship between the main process equipment status parameters, equipment identifiers, and equipment nodes. For example, the status parameters of the main process equipment nodes include the status parameters of the heater—material throughput rate, the status parameters of the reactor—critical process temperature, and the status parameters of the processing equipment—equipment operating frequency.

[0034] Specifically, the first generation module 102, based on a pre-set index calculation model, determines the throughput fluctuation index, the phase lag index, and the correlation index according to the status parameters of the main process equipment node and the status parameters of the two target equipment nodes.

[0035] Specifically, the indicator calculation model includes a first indicator calculation model, a second indicator calculation model, and a third indicator calculation model.

[0036] Specifically, the first generation module 102 is further configured to determine the energy flux time series of the target energy flow edge based on the first index calculation model and the state parameters of the two target device nodes corresponding to the target energy flow edge, and calculate the flux fluctuation index based on the standard deviation and average value of the energy flux time series of the target energy flow edge.

[0037] In one embodiment, determining the energy flux time series of the target energy flow edge based on the state parameters of the two target device nodes corresponding to the target energy flow edge includes: within the preset analysis period, slicing the state parameters of the two target device nodes corresponding to the target energy flow edge into data slices to obtain two target device state time series; converting the target device state time series into corresponding equivalent energy flux quantum sequences based on a pre-set energy conversion coefficient for each device; and performing a weighted summation of the two equivalent energy flux quantum sequences based on a pre-set device conversion weight to obtain the energy flux time series of the target energy flow edge. Then, the standard deviation and mean of the energy flux time series of the target energy flow edge are calculated, and the flux fluctuation index is calculated based on the standard deviation and mean.

[0038] In one embodiment, the size of the data slice is set according to requirements. It can be sliced ​​based on time or the number of samples. For example, if the sampling point for the main process equipment status parameters and auxiliary process equipment status parameters is 1 second, the data slice can be set at 1-second intervals or at 10-second intervals. When slicing by 1 second, one slice of the target equipment status time series contains one status parameter value; when slicing by 10 seconds, one slice contains ten status parameter values. Similarly, if the sampling point for the main process equipment status parameters and auxiliary process equipment status parameters is 1 second, the data slice can be set at one sampling point or at ten sampling points. When slicing by one sampling point, one slice of the target equipment status time series contains one status parameter value; when slicing by ten sampling points, one slice contains ten status parameter values. It is important to note that the size of the data slices for the status parameters of all equipment must be consistent to ensure the accuracy of subsequent calculations. When a slice contains two or more state parameter values, the average value of the state parameter values ​​in this slice needs to be calculated before proceeding to subsequent steps. This ensures that one slice in the target device state time series corresponds to one data point, and that the two target device state time series can be weighted and summed based on time alignment for subsequent sequence values.

[0039] In one embodiment, each device is pre-set with an energy conversion coefficient, and a mapping relationship is established between the energy conversion coefficient and the device identifier for easy calculation. Each device is also pre-set with a device conversion weight, and a mapping relationship is established between the device conversion weight and the device identifier for easy calculation. It can be understood that a device can be any device in the main process or any device in the auxiliary process.

[0040] In one embodiment, the energy conversion coefficient is a physical proportionality coefficient that converts the state parameters (instantaneous values) of the auxiliary process equipment into their corresponding power consumption or equivalent energy flux expressed in power. The energy conversion coefficient can be a fixed value, where each value in the target equipment's state time series is multiplied by this energy conversion coefficient to obtain an equivalent energy flux quantum sequence. Alternatively, the energy conversion coefficient can be a set of coefficients corresponding to the target equipment's state time series, where the values ​​in the target equipment's state time series are multiplied by their corresponding coefficient values ​​in the energy conversion coefficient to obtain an equivalent energy flux quantum sequence.

[0041] Since the time series of each equipment status represents the operating status of different energy media or power equipment in the auxiliary process during the production cycle, and they are not the same original sequence, this application converts the time series of each equipment status into the corresponding equivalent energy flux quantum sequence by preset energy conversion coefficient, and obtains the energy flux time series by weighted summation of each equivalent energy flux quantum sequence, which can realize a unified representation of the comprehensive energy supply status of the auxiliary process.

[0042] For example, when the target energy flow edge is the energy flow edge between the circulating water system and the pump set, the state parameters of the two target device nodes corresponding to the target energy flow edge are the state parameters of the circulating water system and the state parameters of the pump set, namely the circulating water flow rate and the pump set speed. Within a preset analysis period, data slices are performed on the circulating water flow rate and pump speed to obtain two target equipment state time series: the circulating water flow rate time series and the pump speed time series. Based on the energy conversion coefficient of the circulating water system, the circulating water flow rate time series is converted into its corresponding circulating water flow rate equivalent energy flux quantum sequence. Based on the pump speed conversion coefficient, the pump speed time series is converted into its corresponding pump equivalent energy flux quantum sequence. Based on the equipment conversion weights of the circulating water system and the pumps, the value in each circulating water flow rate equivalent energy flux quantum sequence is multiplied by the equipment conversion weight of the circulating water system to obtain the circulating water flow rate equivalent energy flux weight sequence. The value in each pump equivalent energy flux quantum sequence is multiplied by the pump equivalent energy flux weight to obtain the pump equivalent energy flux weight sequence. Finally, the corresponding values ​​in the circulating water flow rate equivalent energy flux weight sequence and the pump equivalent energy flux weight sequence are added to obtain the energy flux time series E(t) of the target energy flow edge. This process is repeated for each energy flow edge to obtain its corresponding energy flux time series E(t). Based on the above example, the process of obtaining the energy flux time series E(t) of the target energy flow edge for the same device with two or more state parameters is illustrated below: In the above content, the circulating water system state parameters only include circulating water flow rate. If the circulating water system state parameters also include water temperature, the calculation process should also include converting the circulating water temperature time series into its corresponding circulating water temperature equivalent energy flux sequence based on the circulating water system's energy conversion coefficient, obtaining the circulating water temperature equivalent energy flux weight sequence based on the device conversion weights of the circulating water system, and then adding the corresponding values ​​from the circulating water flow rate equivalent energy flux weight sequence, the circulating water temperature equivalent energy flux weight sequence, and the pump group equivalent energy flux weight sequence to obtain the energy flux time series E(t) of the target energy flow edge. It can be understood that the energy conversion coefficient and device conversion weights can be set according to the types of state parameters.

[0043] In one embodiment, a flux fluctuation index is used to quantify flux fluctuation in order to characterize the stability of energy supply to the auxiliary process.

[0044] In one embodiment, within a preset analysis period, the energy flux time series E(t) of the target energy flow edge is obtained, and the energy flux time series E(t) of the target energy flow edge includes the energy flux corresponding to N data slices. Calculate the average value for N energy fluxes. Then calculate its standard deviation. Finally, the ratio of the standard deviation to the absolute value of the mean was used as an indicator of flux fluctuation. The calculation formula is as follows: ;in, Indicates flux fluctuation index; This represents the average value of the time series of energy flux along the target energy flow edge within a preset analysis period T: ; The standard deviation of the time series of energy flux of the target energy flow edge within the preset analysis period T is: ; This represents a very small positive number set to prevent the denominator from being zero. The larger the value, the more pronounced the fluctuation in the energy supply status of the auxiliary process corresponding to the target energy flow edge within the production cycle. The smaller the value, the more stable the energy supply of the auxiliary process corresponding to the target energy flow edge.

[0045] It should be noted that the flux fluctuation index is calculated in the first generation module 102. The description is based on the target energy flow edge, which represents the flux fluctuation index of other energy flow edges in the system's coupled topology graph. The calculation process is based on the above content and will not be repeated here.

[0046] Specifically, the first generation module 102 is also used to determine the main process characteristic time point based on the second index calculation model and the state parameters of the main process equipment node, and to determine the auxiliary process characteristic time point in the energy flux time series of the target energy flow edge based on the main process characteristic time point, and to calculate the phase lag index based on the main process characteristic time point and the auxiliary process characteristic time point.

[0047] In one embodiment, the status parameters of the main process equipment nodes within a preset analysis period T are obtained, and the throughput fluctuation index is calculated accordingly. Data slices are performed synchronously with the data slice size to obtain the state time series of each main process device. The state time series of each main process device is then normalized to obtain a normalized time series of the state parameters for each main process device. Based on pre-set device transformation weights, a weighted sum is performed on the normalized time series of the state parameters of all main process devices to obtain the main process load characterization sequence. ; Calculate the main process load characterization sequence The difference between adjacent values ​​is the load change rate. , k≥2; load change rate With preset load step threshold The comparison is performed, and the main process characteristic time point is determined based on the comparison results. The difference between adjacent values ​​in the energy flux time series of the target energy flow edge that are located after the main process characteristic time point is calculated as the energy flux change rate. , k≥2; the rate of change of energy flux With preset energy step threshold A comparison is made, and the characteristic time points of the auxiliary process are determined based on the comparison results. The difference between the characteristic time points of the main process and the characteristic time points of the auxiliary process is calculated to obtain the phase lag index τ.

[0048] In one embodiment, the maximum and minimum values ​​during normalization can be preset or obtained from the state time series of each main process device.

[0049] In one embodiment, each device is pre-set with a corresponding device conversion weight, and a mapping relationship is established between the device conversion weight and the device identifier for easy calculation. It can be understood that a device is any device in the main process.

[0050] For example, the main process equipment status parameters within a preset analysis period T are obtained, including the furnace status parameter - material throughput rate, the reactor status parameter - critical process temperature, and the processing equipment status parameter - equipment operating frequency. After data slicing, the material throughput rate time series, critical process temperature time series, and equipment operating frequency time series are obtained. The material throughput rate time series, critical process temperature time series, and equipment operating frequency time series are then normalized to obtain normalized material throughput rate time series, normalized critical process temperature time series, and normalized equipment operating frequency time series, respectively. Based on the furnace equipment rotation... The equivalent weight sequence for the heating furnace is obtained by multiplying the normalized material throughput rate time series value by the heating furnace equipment conversion weight, the equivalent weight sequence for the reactor equipment conversion weight, and the equivalent weight sequence for the processing equipment equipment conversion weight. The equivalent weight sequence for the processing equipment is obtained by multiplying the normalized key process temperature time series value by the reactor equipment conversion weight, and the equivalent weight sequence for the processing equipment equipment conversion weight. Finally, the corresponding values ​​from the equivalent weight sequences for the heating furnace, reactor, and processing equipment are summed to obtain the main process load characterization sequence. Based on the above examples, if the same device has two or more state parameters, then the main process load characterization sequence should be obtained. During the process, each state parameter needs to be normalized, and after normalization, it participates in the subsequent weighted summation based on the corresponding device transformation weight.

[0051] In one embodiment, the load change rate With preset load step threshold When making comparisons, when multiple consecutive load change rates first appear... Greater than or equal to the preset load step threshold When, it will be greater than or equal to the preset load step threshold. The first load change rate The corresponding time point is determined as the main process characteristic time point t. k Understandably, determining the characteristic time points of the main process requires three conditions to be met simultaneously. The first condition is the load change rate. Greater than or equal to the preset load step threshold The second condition is the first occurrence of multiple consecutive load change rates. Greater than or equal to the preset load step threshold The third condition is that it is greater than or equal to the preset load step threshold. The number of consecutive occurrences satisfies the preset number.

[0052] In one embodiment, the rate of change of energy flux With preset energy step threshold When comparing, the first one that is greater than or equal to a preset energy step threshold will be selected. rate of change of energy flux The corresponding time points are determined as the characteristic time points of the auxiliary process.

[0053] In one embodiment, the load change rate Used to identify load step changes in the main process status parameters. Fluctuation index. The phase lag index τ is used to characterize the stability of the auxiliary process energy supply at the amplitude level. The phase lag index τ is used to characterize the time-level response lag of the auxiliary process energy supply to changes in the main process load.

[0054] It should be noted that the calculation of the phase lag index τ in the first generation module 102 is based on one energy flow edge of the target energy flow edge. The calculation process of the phase lag index τ of other energy flow edges in the system coupling topology graph is based on this and will not be elaborated further.

[0055] Specifically, the first generation module 102 is also used to calculate the correlation index based on the third index calculation model, according to the flux fluctuation index and the phase lag index.

[0056] In one embodiment, the third indicator calculation model presets the maximum and minimum values ​​of the flux fluctuation indicator based on historical data, and then calculates the flux fluctuation indicator. Normalization is performed to map the flux fluctuation index of the target energy flow edge acquired in real time to the interval [0,1] to obtain the fluctuation coefficient.

[0057] In one embodiment, the third index calculation model presets the maximum and minimum values ​​of the phase lag index based on historical data, normalizes the phase lag index τ, and maps the phase lag index of the target energy flow edge acquired in real time to the interval [0,1] to obtain the lag coefficient.

[0058] In one embodiment, the volatility coefficient and lag coefficient are used as inputs and substituted into the correlation function of the third indicator calculation model for calculation. The specific calculation formula is as follows: Where R represents the correlation index; This represents the fluctuation coefficient, which is obtained after normalization of the flux fluctuation index. This represents the lag coefficient, which is obtained after normalization of the phase lag index. and This indicates the preset weighting coefficient.

[0059] Therefore, a correlation index R can be output for each directed edge of energy flow in the system coupling topology graph. The correlation index R ranges from [0, 1]. A high R value indicates a good matching degree and a relatively ideal coupling strength, while a low R value indicates a poor matching degree and a high risk of energy efficiency bottleneck.

[0060] It should be noted that the correlation index R in the first generation module 102 is described based on the target energy flow edge. The calculation process of the correlation index R of other energy flow edges in the system coupling topology graph is based on this and will not be elaborated.

[0061] In one embodiment, the topology graph analysis model in the path determination module 103 is pre-trained. The analysis system couples each device node and each energy flow edge in the topology graph using the topology graph analysis model, extracting the starting device node, ending device node, corresponding energy medium type, and the energy flux time series, flux fluctuation index, phase lag index, and correlation index of each energy flow edge within a preset analysis period. For example, for any energy flow edge... Where i represents the starting device node, This represents the endpoint device node, and the energy flux time series E corresponding to this energy flow edge. ij (t), the calculated flux fluctuation index Phase lag index Relevance index R ijTherefore, the analytical results of the system coupling topology graph do not only yield three unified indicators, but also form a set of edge weight features for each energy flow edge. These edge weight features include at least flux fluctuation indicators, phase lag indicators, and correlation indicators.

[0062] Specifically, the path determination module 103 is also used to parse the correlation index of each energy flow edge based on the topology graph analysis model and the system coupling topology graph.

[0063] Specifically, the path determination module 103 is also used to compare the correlation index of each energy flow edge with the first preset threshold based on the first preset threshold in the topology graph analysis model, and determine the weakly coupled path according to the comparison result.

[0064] In one embodiment, the first preset threshold is obtained through statistical learning based on a large amount of data from historically optimal energy efficiency operating conditions. Specifically, the system first operates within a reference time period deemed to have excellent energy efficiency. This reference time period is typically determined by domain experts based on actual energy consumption data and product unit consumption indicators. Within this reference time period, the correlation degree index of all energy flow edges in the system coupling topology graph is continuously calculated and recorded, thereby forming a correlation degree sample set representing a healthy coupling state. Subsequently, statistical analysis is performed on this sample set, and the correlation degree value of a specific low quantile in the set is taken as the first preset threshold.

[0065] In one embodiment, each energy flow edge in the system's coupled topology graph is evaluated edge-by-edge based on the resolved correlation index. For any energy flow edge... The corresponding correlation index is ,in This indicates the starting device node of the energy flow edge. This represents the endpoint device node of the energy flow edge. It's an affinity index. An energy flow edge in the corresponding system coupling topology graph Energy flow edges can serve as the smallest granularity coupling paths. When a certain energy flow edge... correlation index When the energy flow edge is below a first preset threshold, it is marked as a weakly coupled edge and treated as a weakly coupled path with the smallest granularity. When the correlation index of multiple energy flow edges is below the first preset threshold, each energy flow edge below the preset threshold is a weakly coupled edge. If multiple weakly coupled edges are continuously connected in the system coupling topology graph and together form the same energy transfer link or response link, the multiple weakly coupled edges are merged and marked as a single weakly coupled path. In this case, the weakly coupled path includes multiple energy flow edges and is a composite path, such as... Figure 3 The weakly coupled path is indicated by the dashed line.

[0066] Specifically, the path determination module 103 is also used to parse the correlation index of each energy flow edge within multiple preset analysis periods based on the topology graph analysis model and the system coupling topology graph.

[0067] Specifically, the path determination module 103 is also used to perform statistical analysis on the correlation index of the target energy flow edge within multiple preset analysis periods to obtain the correlation fluctuation rate of each energy flow edge.

[0068] Specifically, the path determination module 103 is also used to compare the correlation fluctuation rate of each energy flow edge with the second preset threshold based on the second preset threshold in the topology graph analysis model, and determine the unstable path according to the comparison result.

[0069] In one embodiment, a second preset threshold is established by quantifying the volatility characteristics of the correlation index over time. The system operates within a reference time period (containing multiple analysis cycles) deemed to have excellent energy efficiency. This reference time period is typically determined by domain experts based on actual energy consumption data and product unit consumption indicators. Within this reference time period, the correlation index of all energy flow edges in the system coupling topology graph is continuously calculated and recorded. The correlation volatility of each energy flow edge is calculated over multiple consecutive analysis cycles. This correlation volatility is typically defined as the standard deviation or coefficient of variation of the correlation index within these analysis cycles. This yields a volatility sample set representing a normal stable level. Statistical analysis is performed on this set, and the correlation volatility at a specific high quantile is taken as the second preset threshold.

[0070] In one embodiment, the standard deviation or coefficient of variation of the correlation index of the same energy flow edge over multiple preset analysis periods is calculated as the correlation volatility of that energy flow edge. The correlation volatility of each energy flow edge is then compared with a second preset threshold. If a certain energy flow edge... If the correlation volatility of an energy flow edge exceeds the second preset threshold, this energy flow edge is recorded as an unstable edge. If this unstable edge is an independent energy flow edge and is connected to the main process equipment node in the system coupling topology graph, then the unstable edge is an unstable path. If the correlation volatility of multiple energy flow edges all exceeds the second preset threshold, each energy flow edge exceeding the second preset threshold is an unstable edge. If multiple unstable edges are continuously connected in the system coupling topology graph and are connected to the main process equipment node in the system coupling topology graph, forming the same energy transfer link or response link, the multiple unstable edges are merged and marked as one unstable path. At this time, the unstable path includes multiple energy flow edges and is a composite path, such as... Figure 3 The instability path is shown by the dashed line.

[0071] Weakly coupled paths are used to characterize energy interaction paths where the matching degree between primary and secondary processes is insufficient in the long term, while unstable paths are used to characterize energy interaction paths where the matching state between primary and secondary processes fluctuates significantly with the production cycle and lacks operational stability. Therefore, both weakly coupled paths and unstable paths are critical coupling paths.

[0072] For example, such as Figure 3 As shown in the system coupling topology diagram, if the energy flow edge corresponding to "air compressor unit to energy storage tank" is... correlation index If the correlation index of the energy flow edge is below the first preset threshold, it can be marked as a weakly coupled path. If the correlation index of the two continuous energy flow edges, "air compressor unit to energy storage tank" and "energy storage tank to reactor", is below the first preset threshold, they can be merged into a composite weakly coupled path, "air compressor unit - energy storage tank - reactor". For example, if the correlation index of the energy flow edge "pump unit to cooling tower" fluctuates across multiple consecutive analysis periods, and its statistical correlation volatility exceeds the second preset threshold, this energy flow edge is marked as an unstable edge. However, since the energy flow edge "pump unit to cooling tower" is not connected to the main process equipment node, this energy flow edge cannot be defined as an unstable path. However, if the energy flow edge correlation volatility of "pump set to circulating water system" and "circulating water system to heater" also exceeds the second preset threshold, since the energy flow edges of "pump set to cooling tower," "pump set to circulating water system," and "circulating water system to heater" are continuously connected in the system coupling topology and connected to the main process equipment node (heater equipment node) in the system coupling topology, the three can ultimately be merged into a composite unstable path of "heater—circulating water system—pump set—cooling tower." This unstable path is used to characterize the periodic fluctuations in the cooling, heat exchange, or temperature regulation support capability of the circulating water auxiliary process for the main process equipment, indicating insufficient operational stability.

[0073] In one embodiment, a main process optimization instruction is generated based on a weakly coupled path in the critical coupling path, and the main process equipment is optimized and adjusted according to the main process optimization instruction; an auxiliary process optimization instruction is generated based on an unstable path in the critical coupling path, and the auxiliary process equipment is optimized and adjusted according to the auxiliary process optimization instruction.

[0074] Specifically, the second generation module 104 is also used to parse the first energy flux time series of the weakly coupled path based on the system coupling topology graph according to the pre-set topology graph analysis model.

[0075] Specifically, the second generation module 104 is also used to generate the theoretical demand curve of the main process equipment in the instruction generation model, and to identify the energy gap period and the energy sufficient period of the first auxiliary process according to the first energy flux time series.

[0076] Specifically, the second generation module 104 is also used to generate main process optimization instructions based on the main process instruction generation model in the instruction generation model, according to the first auxiliary process energy gap period and the first auxiliary process energy sufficient period.

[0077] In one embodiment, for the weakly coupled path, the first energy flux time series of the weakly coupled path within a preset analysis period and the corresponding main process equipment node are extracted. Based on the main process equipment node, the corresponding theoretical energy demand curve of the main process equipment is extracted from a preset main process equipment theoretical energy demand curve library. The first energy flux time series of the weakly coupled path within the preset analysis period is compared with the theoretical energy demand curve of the main process equipment to identify the energy gap period and the energy sufficient period of the first auxiliary process, and further generate main process optimization instructions. Further, when the weakly coupled path is not connected to a main process equipment node, the corresponding main process equipment node is all main process equipment nodes; when the weakly coupled path is connected to a main process equipment node, the corresponding main process equipment node is the connected main process equipment node. The first energy flux time series is the actual energy flux time series of the auxiliary processes transmitted to the main process equipment in the weakly coupled path.

[0078] In one embodiment, the first energy flux time series is obtained from the energy flux time series of the energy flow edge corresponding to the weakly coupled path in the aforementioned system coupled topology graph.

[0079] In one embodiment, when the weakly coupled path includes a single energy flow edge, the first energy flux time series is the energy flux time series E(t) corresponding to that energy flow edge.

[0080] In one embodiment, when a weakly coupled path includes two or more energy flow edges, the weakly coupled path is a composite path. Based on the energy flux time series of each energy flow edge in the composite path and their transmission relationships, the equivalent energy flux time series that can actually act on the main process equipment at the end of the composite path can be determined as the first energy flux time series. Specifically, the energy flux time series corresponding to each energy flow edge is obtained. Then, based on the pre-set mapping relationship between each energy flow edge and its corresponding energy weight, the energy weight of each energy flow edge is determined. The energy flux time series corresponding to each energy flow edge is then weighted and summed with its corresponding energy weight to obtain the final first energy flux time series.

[0081] In one embodiment, the theoretical energy demand curve of the main process equipment is a baseline demand curve pre-established based on the main process equipment's technological tasks, set process parameters, historical stable operating data, or rated energy consumption model. This curve characterizes the theoretical energy demand required for the main process equipment to complete the corresponding production task within a unit production cycle. There is a mapping relationship between the theoretical energy demand curve of the main process equipment and the nodes of the main process equipment. The nodes of the main process equipment are identified based on equipment identifiers.

[0082] In one embodiment, the second generation module 104 is further configured to determine the first energy flow gap time series based on the theoretical demand curve of the main process equipment and the first energy flux time series.

[0083] In one embodiment, within a single preset analysis period T, based on the time series of the aforementioned data slices, N data points are acquired according to the first energy flux time series, at any given time point. The specific formula for calculating the energy flow gap value is as follows: ;in, express The energy flow gap value at any given time; express The energy value on the theoretical energy demand curve of the main process equipment at any given moment; express Energy flux values ​​in the actual energy flux time series of the auxiliary process; This indicates that a positive energy flow gap value is recorded only when there is insufficient energy supply; when the supply is sufficient, the energy flow gap value is 0.

[0084] Through the above calculations, the first energy flow gap time series G1(t) within the preset analysis period T is obtained. Through the first energy flow gap time series G1(t), the energy gap period and the energy sufficient period of the first auxiliary process are identified, and the total energy flow gap, gap intensity and gap distribution time series are quantitatively analyzed.

[0085] In one embodiment, the first auxiliary process energy gap period is a period of time that meets a preset time length and in which the energy flow gap value exceeds the first preset gap value.

[0086] In one embodiment, the second generation module 104 is further configured to traverse the first energy flow gap time series G1(t), compare each energy flow gap value with the first preset gap value, and mark all energy flow gap values ​​as two states according to the comparison result: over-threshold state or normal state. Then, the continuous energy flow gap values ​​in the over-threshold state and their time periods are divided into an independent candidate gap time series.

[0087] In one embodiment, the second generation module 104 is further configured to calculate the duration of each candidate gap time series, compare the duration with a first preset time length, and when the duration of a candidate gap time series is greater than or equal to the first preset time length, the candidate gap time series is the first auxiliary process energy gap period. In one embodiment, the second generation module 104 is further configured to output a list of all identified first auxiliary process energy gap periods. The list includes the start time, end time, and statistical information such as the average energy flow gap value or the maximum gap value within each first auxiliary process energy gap period. Finally, by summing the durations of all first auxiliary process energy gap periods, the total duration of the first auxiliary process energy gap periods in the entire analysis cycle can be obtained.

[0088] In one embodiment, the first auxiliary process energy sufficient period is a period of time that meets the preset time length and in which the energy flow gap value is 0.

[0089] In one embodiment, the second generation module 104 is further configured to traverse the first energy flow gap time series G1(t), mark all energy flow gap values ​​of 0 as sufficient states, and then divide the continuous energy flow gap values ​​in sufficient states and their time periods into an independent candidate sufficient time series. In one embodiment, the second generation module 104 is further configured to calculate the duration of each candidate sufficient time series, compare the duration with a second preset time series, and when the duration of a candidate sufficient time series is greater than or equal to the second preset time series, the candidate sufficient time series is the first auxiliary process energy sufficient period. In one embodiment, the second generation module 104 is further configured to output a list of all identified energy-sufficient periods of the first auxiliary process. The list includes statistical information such as the start time, end time, and average energy flow gap value of each energy-sufficient period of the first auxiliary process. Finally, by summing the durations of all energy-sufficient periods of the first auxiliary process, the total duration of the energy-sufficient periods of the first auxiliary process in the entire analysis cycle can be obtained.

[0090] Therefore, the identification of the energy gap period and the energy sufficient period of the first auxiliary process is not manually specified, but determined based on the aforementioned energy flow gap time series.

[0091] Subsequently, a main process optimization instruction is generated based on the energy shortage period and the energy sufficient period of the first auxiliary process, and the main process optimization instruction is sent to the main process equipment to adjust the process operating parameters or operating phase arrangement of the main process equipment.

[0092] In one embodiment, the main process optimization instruction includes at least one or more of the following: target main process equipment identifier, control period, operation phase adjustment method, target temperature curve, heating rate, holding temperature, phase start and end time, and allowable energy consumption limit. The main process optimization instruction can be determined jointly based on the energy deficit period and the energy sufficient period of the first auxiliary process, as well as manually input instructions. Alternatively, the main process optimization instruction can be automatically generated based on a pre-set instruction template, the energy deficit period and the energy sufficient period of the first auxiliary process.

[0093] In one embodiment, the target main process equipment identifier is determined based on the main process equipment node corresponding to the weakly coupled path; the control period is determined based on the energy shortage period and the energy sufficient period of the first auxiliary process; the operation stage adjustment method is determined based on the process stage attributes, energy demand intensity, and process constraints of the target main process equipment during the control period; the target temperature curve is determined based on the target main process equipment identifier and its process task; the heating rate, holding temperature, stage start and end time, and allowable energy consumption upper limit are jointly determined based on the target temperature curve, the energy shortage period of the first auxiliary process, the energy sufficient period of the first auxiliary process, and equipment safety operation constraints. Process stage attributes, energy demand intensity, process constraints, process tasks, and equipment safety operation constraints are preset.

[0094] Specifically, when the high-energy-consuming process stage of the target main process equipment overlaps with the energy shortage period of the first auxiliary process, there is a period of sufficient energy in the first auxiliary process, and the high-energy-consuming process stage is allowed to be adjusted in time, the main process optimization instruction includes adjusting the high-energy-consuming process stage from the energy shortage period of the first auxiliary process to the period of sufficient energy in the first auxiliary process, and determining the start and end times of the adjusted stage. The high-energy-consuming process stage includes rapid heating stage, pressurization stage, accelerated operation stage, high-load reaction stage, or other process stages with high energy requirements.

[0095] When the high-energy-consuming process stage of the target main process equipment does not allow for time adjustment, the main process optimization instructions include reducing the equipment heating rate, reducing the equipment operating frequency, reducing the material handling rate, limiting the upper limit of allowable energy consumption during this period, extending the duration of the low-load transition stage, or adjusting the local slope of the target temperature curve to reduce the instantaneous demand of the main process equipment on the energy supply of the auxiliary process during this period.

[0096] When the duration of the energy gap period in the first auxiliary process is greater than or equal to the preset energy gap time length, and the average energy flow gap value within the energy gap period of the first auxiliary process... Or maximum energy flow gap value When the preset energy flow gap threshold is exceeded, the main process optimization instructions include pausing the rapid heating phase, delaying the batch start time, postponing the high-load production phase, switching the equipment to the heat preservation operation state, or controlling the main process equipment to maintain operation within the preset safe process parameter range.

[0097] When a period of sufficient energy is identified in the first auxiliary process, the main process optimization instructions include starting the main process equipment in advance or centrally arranging rapid heating, pressurization, accelerated operation, high-load response, or other high-energy-consuming process stages to improve the utilization rate of the spare energy supply capacity of the auxiliary process.

[0098] Therefore, the main process optimization instructions are not limited to adjusting the rapid heating phase to the period when the first auxiliary process has sufficient energy, but include one or more of the following: operation phase shift, operation parameter adjustment, energy intensity reduction, production cycle adjustment, heat preservation, and energy consumption upper limit constraint. These instructions are used to make targeted adjustments to the operation curve, operation parameters, and operation phase arrangement of the main process equipment based on the energy shortage period and the energy sufficient period of the first auxiliary process.

[0099] For example, such as Figure 3 As shown, for the composite weakly coupled path of "air compressor unit - energy storage tank - reactor", the target main process equipment identifier is determined based on the main process equipment node in the weakly coupled path, and thus the main process equipment is determined to be the reactor. In subsequent adjustment cycles, if the rapid heating phase of the reactor overlaps with the energy gap period of the first auxiliary process, there is a period of sufficient energy in the first auxiliary process, and the rapid heating phase of the reactor is allowed to be adjusted in time, the main process optimization instruction may include adjusting the rapid heating phase of the reactor to be executed during the period of sufficient energy in the first auxiliary process, and setting the adjusted heating rate and phase start and end time according to the target temperature curve of the reactor. If the rapid heating phase of the reactor is constrained by process continuity and cannot be adjusted in time, the main process optimization instruction may include reducing the reactor heating rate, adjusting the local slope of the target temperature curve, limiting the upper limit of allowable energy consumption of the reactor in this period, or extending the duration of the low load transition phase. If the duration of the energy gap period of the first auxiliary process is longer than the preset energy gap time length, and the average energy flow gap value within the energy gap period of the first auxiliary process is... Or maximum energy flow gap value If the preset energy flow deficit threshold is exceeded, the main process optimization instructions may also include pausing the rapid heating phase, postponing the high-load operation phase of the reactor, or switching the reactor to the heat preservation operation state, and setting the corresponding heat preservation temperature and heat preservation duration according to the reactor target temperature curve.

[0100] Specifically, the second generation module 104 is also used to parse the second energy flux time series of the unstable path based on the pre-set topology graph analysis model and the unstable path.

[0101] Specifically, the second generation module 104 is also used to generate the theoretical operating curve of the auxiliary process equipment in the instruction generation model, and to identify the energy gap period and the energy sufficient period of the second auxiliary process according to the second energy flux time series.

[0102] Specifically, the second generation module 104 is also used to generate auxiliary process optimization instructions based on the main process instruction generation model in the instruction generation model, according to the energy gap period of the second auxiliary process and the energy sufficient period of the second auxiliary process.

[0103] In one embodiment, such as Figure 6 As shown, the second generation module 104 for unstable paths generates optimized instructions based on a pre-set instruction generation model and the key coupling path.

[0104] Specifically, the second generation module 104 is also used to parse the second energy flux time series of the unstable path based on the pre-set topology graph analysis model and the unstable path.

[0105] Specifically, the second generation module 104 is also used to generate the theoretical operating curve of the auxiliary process equipment in the instruction generation model, and to identify the energy gap period and the energy sufficient period of the second auxiliary process according to the second energy flux time series.

[0106] Specifically, the second generation module 104 is also used to generate auxiliary process optimization instructions based on the main process instruction generation model in the instruction generation model, according to the energy gap period of the second auxiliary process and the energy sufficient period of the second auxiliary process.

[0107] In one embodiment, based on the device nodes in the unstable path, the auxiliary process device corresponding to the device node is determined through the mapping relationship between the device node and the device identifier.

[0108] In one embodiment, for the unstable path, the second energy flux time series of the unstable path within a preset analysis period and the corresponding auxiliary process equipment node are extracted. Based on the auxiliary process equipment node, the corresponding theoretical operating energy curve of the auxiliary process equipment is extracted from a preset auxiliary process equipment theoretical operating energy curve library. The second energy flux time series of the unstable path within the preset analysis period is compared with the theoretical operating energy curve of the auxiliary process equipment to identify the second auxiliary process energy gap period and the second auxiliary process energy sufficient period, and further generate auxiliary process optimization instructions.

[0109] In one embodiment, the second energy flux time series is obtained from the energy flux time series of the energy flow edge corresponding to the unstable path in the aforementioned system coupling topology graph.

[0110] In one embodiment, when the unstable path includes a single energy flow edge, the second energy flux time series is the energy flux time series E(t) corresponding to that energy flow edge, and the corresponding auxiliary process device is the device corresponding to the auxiliary process device node on that energy flow edge.

[0111] In one embodiment, when an unstable path includes two or more energy flow edges, the unstable path is a composite path. Based on the energy flux time series of each energy flow edge in the composite path and their transmission relationships, the energy flux time series that the composite path can actually affect each auxiliary process device can be determined as the second energy flux time series. Specifically, starting from the main process device node in the unstable path, the energy flux time series of each energy flow edge and the corresponding auxiliary process device are determined. The energy flux time series of this energy flow edge is the second energy flux time series. Based on the corresponding auxiliary process device, its theoretical operating energy curve is determined, thereby determining the second auxiliary process energy gap period and the second auxiliary process energy sufficient period corresponding to that auxiliary process device, and generating optimization instructions for that auxiliary process device. For example... Figure 3 The complex instability path in the middle, "cooling tower → pump set → circulating water system → heating furnace", according to the energy transfer relationship, starts from the main process equipment heating furnace, and the energy flow side "circulating water system → heating furnace" The corresponding energy flux time series is Based on the corresponding auxiliary process nodes, the auxiliary process equipment is identified as the circulating water system. The theoretical operating energy curve of the circulating water system is determined based on the auxiliary process equipment. Furthermore, the energy gap period and the energy sufficient period of the second auxiliary process corresponding to the circulating water system are determined, generating optimization instructions for the circulating water system. The energy flow edge "pump set → circulating water system" is used to... The corresponding energy flux time series is Based on the corresponding auxiliary process nodes, the auxiliary process equipment is determined to be a pump set. The theoretical operating energy curve of the pump set is then determined based on the auxiliary process equipment. Furthermore, the energy gap period and the energy sufficient period of the second auxiliary process corresponding to the pump set are determined, and optimization instructions for the pump set are generated. The energy flow edge "cooling tower → pump set" is... The corresponding energy flux time series is The system identifies the auxiliary process equipment as a cooling tower based on the corresponding auxiliary process node. It then determines the theoretical operating energy curve of the cooling tower based on the auxiliary process equipment, further identifying the energy gap period and the energy sufficient period for the second auxiliary process corresponding to the cooling tower, and generates optimization instructions for the cooling tower. The auxiliary process equipment corresponding to each energy flow edge is the upstream equipment of that energy flow edge.

[0112] In one embodiment, the theoretical operating energy curve of the auxiliary process equipment is a baseline operating energy curve pre-established based on the auxiliary process equipment's process task, set process parameters, historical stable operating data, or rated energy consumption model. This curve characterizes the theoretical operating energy requirement of the auxiliary process equipment to complete the corresponding production task within a unit production cycle. There is a mapping relationship between the theoretical operating energy curve of the auxiliary process equipment and the nodes of the auxiliary process equipment. The nodes of the auxiliary process equipment are identified based on equipment identifiers.

[0113] In one embodiment, the second generation module 104 is further configured to obtain the corresponding second auxiliary process energy gap period and the second auxiliary process energy sufficient period based on the second energy flux time series corresponding to each energy flow edge and its corresponding auxiliary process equipment.

[0114] Specifically, the second generation module 104 is also used to determine the second energy flow gap time series based on the theoretical operating energy curve of the auxiliary process equipment and the second energy flux time series.

[0115] In one embodiment, within a single preset analysis period T, based on the time series of the aforementioned data slices, N data points are acquired according to the second energy flux time series, at any given time point. The specific formula for calculating the energy flow gap value is as follows: ;in, express The energy flow gap value at any given time; express Energy values ​​on the theoretical operating energy curve of the auxiliary process equipment at any given time; express The energy flux value in the second energy flux time series at time point; This indicates that a positive energy flow gap value is recorded only when there is insufficient energy supply; when the supply is sufficient, the energy flow gap value is 0.

[0116] Through the above calculations, the second energy flow gap time series G2(t) within the preset analysis period T is obtained. Through the second energy flow gap time series G2(t), the subsequent energy gap period of the second auxiliary process and the energy sufficient period of the second auxiliary process are identified, and the total energy flow gap, gap intensity and gap distribution time series are quantitatively analyzed.

[0117] In one embodiment, the second auxiliary process energy gap period is a period of time that meets a preset time length and in which the energy flow gap value exceeds the second preset gap value.

[0118] Specifically, the second generation module 104 is also used to traverse the second energy flow gap time series G2(t), compare each energy flow gap value with the second preset gap value, and mark all energy flow gap values ​​as two states according to the comparison results: over-threshold state or normal state. Then, the continuous energy flow gap values ​​in the over-threshold state and their time periods are divided into an independent candidate gap time series. Specifically, the second generation module 104 is also used to calculate the duration of each candidate gap time series, compare this duration with a third preset time length, and when the duration of a candidate gap time series is greater than or equal to the third preset time length, the candidate gap time series is the energy gap period of the second auxiliary process. Specifically, the second generation module 104 is also used to output a list of all identified energy gap periods of the second auxiliary process. This list includes the start time, end time, and statistical information such as the average energy flow gap value or the maximum gap value within each energy gap period of the second auxiliary process. Finally, by summing the durations of all energy gap periods of the second auxiliary process, the total duration of the energy gap periods of the second auxiliary process in the entire analysis cycle can be obtained.

[0119] In one embodiment, the second auxiliary process energy-sufficient period is a period of time that meets a preset time length and in which the energy flow gap value is 0.

[0120] Specifically, the second generation module 104 is also used to traverse the second energy flow gap time series G2(t), mark all energy flow gap values ​​of 0 as sufficient states, and then divide the continuous energy flow gap values ​​in sufficient states and their time periods into an independent candidate sufficient time series. Specifically, the second generation module 104 is also used to calculate the duration of each candidate sufficient time series, compare this duration with the fourth preset time length, and when the duration of a candidate sufficient time series is greater than or equal to the fourth preset time length, the candidate sufficient time series is the energy sufficient period of the second auxiliary process. Specifically, the second generation module 104 is also used to output a list of all identified energy-sufficient periods of the second auxiliary process. This list includes the start time, end time, and average energy flow gap value of each energy-sufficient period of the second auxiliary process. Finally, by summing the durations of all energy-sufficient periods of the second auxiliary process, the total duration of the energy-sufficient periods of the second auxiliary process in the entire analysis cycle can be obtained.

[0121] Therefore, the identification of the energy gap period and the energy sufficient period of the second auxiliary process is not manually specified, but determined based on the aforementioned energy flow gap time series.

[0122] Subsequently, auxiliary process optimization instructions are generated based on the energy gap period and the energy sufficient period of the second auxiliary process, and corresponding auxiliary process optimization instructions are sent to the auxiliary process equipment to adjust the process operation parameters or operation phase arrangement of the auxiliary process equipment.

[0123] Furthermore, the auxiliary process optimization instruction includes at least one or more of the following: target auxiliary process equipment identifier, execution period, equipment operating mode, equipment operating parameters, and parameter adjustment range. The equipment operating parameters include one or more of the following: equipment speed, equipment output flow rate, equipment output pressure, equipment output power, equipment operating frequency, equipment start / stop status, and equipment switching status. The target auxiliary process equipment identifier is determined through the auxiliary process equipment node, and then the target auxiliary process equipment is identified through the auxiliary process equipment node. The execution period is determined through the auxiliary process energy shortage period and the auxiliary process sufficient energy supply period. The parameter adjustment range is adjusted based on a pre-set adjustment logic.

[0124] In one embodiment, the auxiliary process optimization instruction can be determined based on a preset instruction template, the auxiliary process equipment node corresponding to the unstable path, the auxiliary process energy gap period, the auxiliary process energy sufficient period, and the auxiliary process equipment operating status. Alternatively, it can be determined based on the auxiliary process equipment node, the auxiliary process equipment operating status, the auxiliary process energy gap period, the auxiliary process energy sufficient period, and manually input instructions.

[0125] Specifically, the instruction generation model first determines the target auxiliary process equipment based on the auxiliary process equipment nodes in the unstable path; then, based on the operating status parameters, equipment capacity constraints, adjustment range, and backup resource configuration of the target auxiliary process equipment during the auxiliary process energy shortage period and the auxiliary process sufficient energy supply period, it determines the equipment adjustment strategy; finally, it generates auxiliary process optimization instructions based on the target auxiliary process equipment and the equipment adjustment strategy.

[0126] Specifically, when the unstable path corresponding to the target auxiliary process equipment is in a period of energy shortage in the auxiliary process, the auxiliary process optimization instructions include one or more of the following: increasing the operating power of the auxiliary process equipment, increasing the output flow rate of the auxiliary process equipment, increasing the rotation speed of the auxiliary process equipment, increasing the output pressure of the auxiliary process equipment, adding backup auxiliary process equipment to the operation, adjusting the control parameters of the auxiliary process equipment, and switching the backup power supply unit. When the unstable path corresponding to the target auxiliary process equipment is in a period of sufficient energy supply in the auxiliary process, the auxiliary process optimization instructions include one or more of the following: reducing the operating load of the auxiliary process equipment, reducing the operating frequency of the auxiliary process equipment, reducing the output flow rate of the auxiliary process equipment, stopping the operation of the backup auxiliary process equipment, or maintaining the current operating state, in order to reduce the overall operating energy consumption of the auxiliary process.

[0127] For example, such as Figure 3As shown, for the composite instability path of "cooling tower → pump set → circulating water system → heater", when this instability path is identified, the corresponding instability cause is usually a decrease in the cooling capacity of the cooling tower, leading to insufficient energy supply capacity of the circulating water system, and further causing an energy flow gap in the heater during the corresponding period. The target auxiliary process equipment can be identified as the circulating water system, pump set, and cooling tower. When the subsequent period corresponding to this instability path falls within the calculated energy gap period for the cooling tower auxiliary process, the auxiliary process optimization instruction can include increasing the cooling tower fan speed. During the pump set auxiliary process energy gap period, the auxiliary process optimization instruction can include increasing the pump set speed and increasing the circulating water flow rate. During the circulating water system auxiliary process energy gap period, the auxiliary process optimization instruction can include activating the backup cooling unit or increasing the operating power of the circulating water system to enhance the energy supply capacity of the auxiliary process. Typically, the energy gap periods for the cooling tower auxiliary process, pump set auxiliary process, and circulating water system auxiliary process on an instability path are consistent. If the subsequent period falls within a period of sufficient power supply for the auxiliary process, the auxiliary process optimization instructions can include reducing the operating power of the cooling tower, reducing the circulating water flow rate, reducing the pump speed, disabling standby equipment operation, or resuming normal operation mode to reduce the energy consumption of the auxiliary process. Therefore, the auxiliary process optimization instructions do not merely represent the optimization result of "eliminating instability risks," but rather specific equipment control instructions generated for the auxiliary process equipment in the instability path, used to improve the auxiliary process's power supply capacity and restore the system to a stable operating state.

[0128] The instruction generation model can be a neural network model trained based on historical system operation data.

[0129] This invention provides an energy efficiency optimization device for high-energy-consuming industrial systems. By constructing a system coupling topology diagram, this application can understand and quantify the complex coupling interaction between the dynamic production needs of the main process and the energy supply of the auxiliary process at the system level. Based on the system coupling topology diagram, this application parses out key coupling paths and generates optimization instructions for these paths. This achieves insight into the dynamic coupling relationship between the main and auxiliary processes, accurately locates the key bottleneck paths leading to low overall system energy efficiency, and generates targeted optimization instructions for global energy efficiency optimization of both the main and auxiliary processes.

[0130] Each module in the aforementioned energy efficiency optimization system for high-energy-consuming industrial systems can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0131] In one embodiment, the energy efficiency optimization method for high-energy-consuming industrial systems can be applied to, for example... Figure 1In this application environment, the device communicates with the server via a network. The server can obtain the status parameters of the main process equipment and the auxiliary process equipment through the device. Based on a pre-set topology graph generation model, a system coupling topology graph is generated according to the status parameters of the main process equipment and the auxiliary process equipment. The system coupling topology graph includes device nodes and energy flow edges connecting the device nodes, as well as flux fluctuation indicators, phase lag indicators, and correlation indicators marked on each energy flow edge. Based on a pre-set topology graph parsing model, key coupling paths are determined according to the system coupling topology graph. Based on a pre-set instruction generation model, optimization instructions are generated according to the key coupling paths. This application, by constructing a system coupling topology graph, can understand and quantify the complex coupling interaction between the dynamic production demand of the main process and the energy supply of the auxiliary process at the system level. This application parses the key coupling paths from the system coupling topology graph and generates optimization instructions for the key coupling paths, realizing insight into the dynamic coupling relationship between the main and auxiliary processes. It can accurately locate the key bottleneck paths with low overall system energy efficiency and generate targeted optimization instructions for global energy efficiency optimization of the main and auxiliary processes. The device side can include, but is not limited to, various sensors installed on the main process equipment and auxiliary process equipment. The server side can be implemented using a standalone server or a server cluster consisting of multiple servers. The invention will now be described in detail through specific embodiments.

[0132] Please see Figure 2 As shown, Figure 2 A flowchart illustrating the energy efficiency optimization method for industrial high-energy-consuming systems provided in this embodiment of the invention includes the following steps: S1: Obtain the status parameters of the main process equipment and the status parameters of the auxiliary process equipment.

[0133] S2: Based on the pre-set topology generation model, a system coupled topology is generated according to the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The system coupled topology includes equipment nodes and energy flow edges connecting the equipment nodes, as well as flux fluctuation index, phase lag index and correlation index marked on each energy flow edge.

[0134] In one embodiment, such as Figure 4 As shown, step S2 generates a system coupled topology diagram based on a pre-set topology diagram generation model, according to the status parameters of the main process equipment and the status parameters of the auxiliary process equipment, including: S21: Based on the status parameters of the main process equipment and the status parameters of the auxiliary process equipment, determine the status parameters of the two target equipment nodes corresponding to the target energy flow edge within a preset analysis period.

[0135] S22: Based on the status parameters of the main process equipment, determine the status parameters of the main process equipment node within a preset analysis period.

[0136] S23: Based on the pre-set index calculation model, determine the throughput fluctuation index, the phase lag index, and the correlation index according to the status parameters of the main process equipment node and the status parameters of the two target equipment nodes.

[0137] In one embodiment, step S23, based on a pre-set index calculation model, determines the throughput fluctuation index, the phase lag index, and the correlation index according to the status parameters of the main process equipment node and the status parameters of the two target equipment nodes, including: S231: Based on the first index calculation model, the energy flux time series of the target energy flow edge is determined according to the state parameters of the two target device nodes corresponding to the target energy flow edge, and the flux fluctuation index is calculated according to the standard deviation and average value of the energy flux time series of the target energy flow edge.

[0138] S232: Based on the second index calculation model, determine the main process characteristic time point according to the state parameters of the main process equipment node, and determine the auxiliary process characteristic time point in the energy flux time series of the target energy flow edge according to the main process characteristic time point. Calculate the phase lag index based on the main process characteristic time point and the auxiliary process characteristic time point.

[0139] S233: Based on the third indicator calculation model, calculate the correlation index according to the flux fluctuation index and the phase lag index.

[0140] S3: Based on the pre-set topology diagram analysis model, determine the key coupling paths according to the system coupling topology diagram.

[0141] In one embodiment, such as Figure 5 As shown, the critical coupling paths include weakly coupled paths. Step S3, based on a pre-set topology diagram analysis model, determines the critical coupling paths according to the system coupling topology diagram, including: S31: Based on the topology graph analysis model, the correlation index of each energy flow edge is analyzed according to the coupled topology graph of the system; S32: Based on the first preset threshold in the topology graph analysis model, the correlation index of each energy flow edge is compared with the first preset threshold, and the weakly coupled path is determined according to the comparison result.

[0142] In one embodiment, such as Figure 6As shown, the critical coupling path includes the unstable path. Step S3, based on a pre-set topology graph analysis model and according to the system coupling topology graph, determines the critical coupling path, and further includes: S31': Based on the topology graph analysis model, according to the system coupling topology graph, the correlation index of each energy flow edge within multiple preset analysis periods is analyzed; S32': Perform statistical analysis on the correlation index of the target energy flow edge within multiple preset analysis periods to obtain the correlation fluctuation rate of each energy flow edge; S33': Based on the second preset threshold in the topology graph analysis model, the correlation volatility of each energy flow edge is compared with the second preset threshold, and the unstable path is determined according to the comparison result.

[0143] S4: Based on the pre-set instruction generation model, generate optimization instructions according to the key coupling path. The optimization instructions include main process optimization instructions and / or auxiliary process optimization instructions. The main process optimization instructions are sent to the main process device, and the auxiliary process optimization instructions are sent to the auxiliary process device.

[0144] In one embodiment, a main process optimization instruction is generated based on a weakly coupled path in the critical coupling path, and the main process equipment is optimized and adjusted according to the main process optimization instruction; an auxiliary process optimization instruction is generated based on an unstable path in the critical coupling path, and the auxiliary process equipment is optimized and adjusted according to the auxiliary process optimization instruction.

[0145] In one embodiment, such as Figure 5 As shown, for the weakly coupled path step S4, based on the pre-set instruction generation model, optimization instructions are generated according to the key coupled path, including: S41: Based on the pre-set topology graph analysis model, the first energy flux time series of the weakly coupled path is analyzed according to the system coupling topology graph; S42: Based on the theoretical demand curve of the main process equipment in the instruction generation model, identify the energy gap period and the energy sufficient period of the first auxiliary process according to the first energy flux time series; S43: Based on the main process instruction generation model in the instruction generation model, generate main process optimization instructions according to the first auxiliary process energy gap period and the first auxiliary process energy sufficient period.

[0146] In one embodiment, step S42 includes: S421: Determine the first energy flow gap time series based on the theoretical demand curve of the main process equipment and the first energy flux time series.

[0147] In one embodiment, the first auxiliary process energy gap period is a period that meets a preset time length and where the energy flow gap value exceeds a first preset gap value throughout this period. The identification process specifically includes the following steps: S422a: Traverse the first energy flow gap time series G1(t), compare each energy flow gap value with the first preset gap value, and mark all energy flow gap values ​​as two states: over-threshold state or normal state according to the comparison result. Then, divide the continuous energy flow gap values ​​in the over-threshold state and their time periods into an independent candidate gap time series. S423a: Calculate the duration of each candidate gap time series, compare this duration with the first preset time length, and when the duration of a candidate gap time series is greater than or equal to the first preset time length, the candidate gap time series is the first auxiliary process energy gap period. S424a: Output a list of all identified energy gap periods for the first auxiliary process. This list includes the start time, end time, and statistical information such as the average or maximum energy gap value for each energy gap period. Finally, the total duration of the energy gap periods for the first auxiliary process is obtained by summing the durations of all energy gap periods for the first auxiliary process throughout the entire analysis period.

[0148] In one embodiment, the first auxiliary process energy-sufficient period is a period that meets a preset time length and during which the energy flow gap value is 0. The identification process specifically includes the following steps: S422b: Traverse the first energy flow gap time series G1(t), mark all energy flow gap values ​​of 0 as sufficient states, and then divide the continuous energy flow gap values ​​in sufficient states and their time periods into an independent candidate sufficient time series. S423b: Calculate the duration of each candidate sufficient time series, compare this duration with the second preset time length, and when the duration of a candidate sufficient time series is greater than or equal to the second preset time length, the candidate sufficient time series is the first auxiliary process energy sufficient period. S424b: Output a list of all identified energy-sufficient periods of the first auxiliary process. This list includes the start time, end time, and average energy flow deficit value of each energy-sufficient period. Finally, the total duration of the energy-sufficient periods of the first auxiliary process is obtained by summing the durations of all energy-sufficient periods of the first auxiliary process throughout the entire analysis period.

[0149] Subsequently, a main process optimization instruction is generated based on the energy shortage period and the energy sufficient period of the first auxiliary process, and the main process optimization instruction is sent to the main process equipment to adjust the process operating parameters or operating phase arrangement of the main process equipment.

[0150] In one embodiment, the main process optimization instruction includes at least one or more of the following: target main process equipment identifier, control period, operation phase adjustment method, target temperature curve, heating rate, holding temperature, phase start and end time, and allowable energy consumption limit. The main process optimization instruction can be determined jointly based on the energy deficit period and the energy sufficient period of the first auxiliary process, as well as manually input instructions. Alternatively, the main process optimization instruction can be automatically generated based on a pre-set instruction template, the energy deficit period and the energy sufficient period of the first auxiliary process.

[0151] In one embodiment, the target main process equipment identifier is determined based on the main process equipment node corresponding to the weakly coupled path; the control period is determined based on the energy shortage period and the energy sufficient period of the first auxiliary process; the operation stage adjustment method is determined based on the process stage attributes, energy demand intensity, and process constraints of the target main process equipment during the control period; the target temperature curve is determined based on the target main process equipment identifier and its process task; the heating rate, holding temperature, stage start and end time, and allowable energy consumption upper limit are jointly determined based on the target temperature curve, the energy shortage period of the first auxiliary process, the energy sufficient period of the first auxiliary process, and equipment safety operation constraints. Process stage attributes, energy demand intensity, process constraints, process tasks, and equipment safety operation constraints are preset.

[0152] Specifically, when the high-energy-consuming process stage of the target main process equipment overlaps with the energy shortage period of the first auxiliary process, there is a period of sufficient energy in the first auxiliary process, and the high-energy-consuming process stage is allowed to be adjusted in time, the main process optimization instruction includes adjusting the high-energy-consuming process stage from the energy shortage period of the first auxiliary process to the period of sufficient energy in the first auxiliary process, and determining the start and end times of the adjusted stage. The high-energy-consuming process stage includes rapid heating stage, pressurization stage, accelerated operation stage, high-load reaction stage, or other process stages with high energy requirements.

[0153] When the high-energy-consuming process stage of the target main process equipment does not allow for time adjustment, the main process optimization instructions include reducing the equipment heating rate, reducing the equipment operating frequency, reducing the material handling rate, limiting the upper limit of allowable energy consumption during this period, extending the duration of the low-load transition stage, or adjusting the local slope of the target temperature curve to reduce the instantaneous demand of the main process equipment on the energy supply of the auxiliary process during this period.

[0154] When the duration of the energy gap period in the first auxiliary process is greater than or equal to the preset energy gap time length, and the average energy flow gap value within the energy gap period of the first auxiliary process... Or maximum energy flow gap value When the preset energy flow gap threshold is exceeded, the main process optimization instructions include pausing the rapid heating phase, delaying the batch start time, postponing the high-load production phase, switching the equipment to the heat preservation operation state, or controlling the main process equipment to maintain operation within the preset safe process parameter range.

[0155] When a period of sufficient energy is identified in the first auxiliary process, the main process optimization instructions include starting the main process equipment in advance or centrally arranging rapid heating, pressurization, accelerated operation, high-load response, or other high-energy-consuming process stages to improve the utilization rate of the spare energy supply capacity of the auxiliary process.

[0156] Therefore, the main process optimization instructions are not limited to adjusting the rapid heating phase to the period when the first auxiliary process has sufficient energy, but include one or more of the following: operation phase shift, operation parameter adjustment, energy intensity reduction, production cycle adjustment, heat preservation, and energy consumption upper limit constraint. These instructions are used to make targeted adjustments to the operation curve, operation parameters, and operation phase arrangement of the main process equipment based on the energy shortage period and the energy sufficient period of the first auxiliary process.

[0157] In one embodiment, such as Figure 6 As shown, for the unstable path step S4, based on the pre-set instruction generation model, optimization instructions are generated according to the key coupling path, including: S41': Based on a pre-set topology graph analysis model, the second energy flux time series of the unstable path is analyzed according to the unstable path; S42': Based on the theoretical operating curve of the auxiliary process equipment in the instruction generation model, identify the energy gap period and the energy sufficient period of the second auxiliary process according to the second energy flux time series; S43': Based on the main process instruction generation model in the instruction generation model, generate auxiliary process optimization instructions according to the energy gap period and the energy sufficient period of the second auxiliary process.

[0158] In one embodiment, step S42', which involves obtaining the corresponding second auxiliary process energy gap period and second auxiliary process energy sufficient period based on the second energy flux time series corresponding to each energy flow edge and its corresponding auxiliary process equipment, includes: S421': Determine the second energy flow gap time series based on the theoretical operating energy curve of the auxiliary process equipment and the second energy flux time series.

[0159] In one embodiment, the second auxiliary process energy gap period is a period that meets a preset time length and where the energy flow gap value exceeds a second preset gap value throughout this period. The identification process specifically includes the following steps: S422a´: Traverse the second energy flow gap time series G2(t), compare each energy flow gap value with the second preset gap value, and mark all energy flow gap values ​​as two states: over-threshold state or normal state according to the comparison result. Then, divide the continuous energy flow gap values ​​in the over-threshold state and their time periods into an independent candidate gap time series. S423a´: Calculate the duration of each candidate gap time series, compare this duration with the third preset time length, and when the duration of a candidate gap time series is greater than or equal to the third preset time length, the candidate gap time series is the second auxiliary process energy gap period; S424a´: Outputs a list of all identified energy gap periods for the second auxiliary process. This list includes the start and end times of each energy gap period, as well as statistical information such as the average or maximum energy gap value within that period. Finally, the total duration of the energy gap periods for the second auxiliary process is obtained by summing the durations of all energy gap periods for the second auxiliary process throughout the entire analysis period.

[0160] In one embodiment, the second auxiliary process energy-sufficient period is a period that meets a preset time length and during which the energy flow gap value is 0. The identification process specifically includes the following steps: S422b´: Traverse the second energy flow gap time series G2(t), mark all energy flow gap values ​​of 0 as sufficient states, and then divide the continuous energy flow gap values ​​in sufficient states and their time periods into an independent candidate sufficient time series. S423b´: Calculate the duration of each candidate sufficient time series, compare this duration with the fourth preset time length, and when the duration of a candidate sufficient time series is greater than or equal to the fourth preset time length, the candidate sufficient time series is the energy sufficient period of the second auxiliary process; S424b´: Outputs a list of all identified energy-sufficient periods in the secondary auxiliary process. This list includes the start and end times of each energy-sufficient period, as well as statistical information such as the average energy flow deficit value within that period. Finally, the total duration of the energy-sufficient periods in the secondary auxiliary process is obtained by summing the durations of all energy-sufficient periods in the secondary auxiliary process throughout the entire analysis period.

[0161] Therefore, the identification of the energy gap period and the energy sufficient period of the second auxiliary process is not manually specified, but determined based on the aforementioned energy flow gap time series.

[0162] Subsequently, auxiliary process optimization instructions are generated based on the energy gap period and the energy sufficient period of the second auxiliary process, and corresponding auxiliary process optimization instructions are sent to the auxiliary process equipment to adjust the process operation parameters or operation phase arrangement of the auxiliary process equipment.

[0163] Furthermore, the auxiliary process optimization instruction includes at least one or more of the following: target auxiliary process equipment identifier, execution period, equipment operating mode, equipment operating parameters, and parameter adjustment range. The equipment operating parameters include one or more of the following: equipment speed, equipment output flow rate, equipment output pressure, equipment output power, equipment operating frequency, equipment start / stop status, and equipment switching status. The target auxiliary process equipment identifier is determined through the auxiliary process equipment node, and then the target auxiliary process equipment is identified through the auxiliary process equipment node. The execution period is determined through the auxiliary process energy shortage period and the auxiliary process sufficient energy supply period. The parameter adjustment range is adjusted based on a pre-set adjustment logic.

[0164] In one embodiment, the auxiliary process optimization instruction can be determined based on a preset instruction template, the auxiliary process equipment node corresponding to the unstable path, the auxiliary process energy gap period, the auxiliary process energy sufficient period, and the auxiliary process equipment operating status. Alternatively, it can be determined based on the auxiliary process equipment node, the auxiliary process equipment operating status, the auxiliary process energy gap period, the auxiliary process energy sufficient period, and manually input instructions.

[0165] Specifically, the instruction generation model first determines the target auxiliary process equipment based on the auxiliary process equipment nodes in the unstable path; then, based on the operating status parameters, equipment capacity constraints, adjustment range, and backup resource configuration of the target auxiliary process equipment during the auxiliary process energy shortage period and the auxiliary process sufficient energy supply period, it determines the equipment adjustment strategy; finally, it generates auxiliary process optimization instructions based on the target auxiliary process equipment and the equipment adjustment strategy.

[0166] Specifically, when the unstable path corresponding to the target auxiliary process equipment is in a period of energy shortage in the auxiliary process, the auxiliary process optimization instructions include one or more of the following: increasing the operating power of the auxiliary process equipment, increasing the output flow rate of the auxiliary process equipment, increasing the rotation speed of the auxiliary process equipment, increasing the output pressure of the auxiliary process equipment, adding backup auxiliary process equipment to the operation, adjusting the control parameters of the auxiliary process equipment, and switching the backup power supply unit. When the unstable path corresponding to the target auxiliary process equipment is in a period of sufficient energy supply in the auxiliary process, the auxiliary process optimization instructions include one or more of the following: reducing the operating load of the auxiliary process equipment, reducing the operating frequency of the auxiliary process equipment, reducing the output flow rate of the auxiliary process equipment, stopping the operation of the backup auxiliary process equipment, or maintaining the current operating state, in order to reduce the overall operating energy consumption of the auxiliary process.

[0167] The instruction generation model can be a neural network model trained based on historical system operation data.

[0168] As can be seen, in the above-mentioned scheme, this application, by constructing a system coupling topology diagram, can understand and quantify the complex coupling interaction between the dynamic production needs of the main process and the energy supply of the auxiliary process at the system level. Based on the system coupling topology diagram, this application parses out the key coupling paths, generates optimization instructions for these paths, and achieves insight into the dynamic coupling relationship between the main and auxiliary processes. It can accurately locate the key bottleneck paths leading to low overall system energy efficiency and generate targeted optimization instructions for global energy efficiency optimization of both the main and auxiliary processes.

[0169] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0170] For specific limitations on energy efficiency optimization methods for high-energy-consuming industrial systems, please refer to the limitations on energy efficiency optimization systems for high-energy-consuming industrial systems in the text, which will not be repeated here.

[0171] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used for communication with external devices via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a server-side method for optimizing energy efficiency in an industrial high-energy-consuming system.

[0172] In one embodiment, a computer device is provided, which may be a device terminal, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements the functions or steps of an energy efficiency optimization method for an industrial high-energy-consuming system on the device side.

[0173] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: Obtain the status parameters of the main process equipment and the auxiliary process equipment; Based on a pre-set topology generation model, a system coupled topology is generated according to the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The system coupled topology includes equipment nodes and energy flow edges connecting the equipment nodes, as well as flux fluctuation indicators, phase lag indicators and correlation indicators marked on each energy flow edge. Based on the pre-set topology diagram analysis model, the key coupling paths are determined according to the system coupling topology diagram; Based on a pre-set instruction generation model, optimized instructions are generated according to the key coupling path.

[0174] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Obtain the status parameters of the main process equipment and the auxiliary process equipment; Based on a pre-set topology generation model, a system coupled topology is generated according to the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The system coupled topology includes equipment nodes and energy flow edges connecting the equipment nodes, as well as flux fluctuation indicators, phase lag indicators and correlation indicators marked on each energy flow edge. Based on the pre-set topology diagram analysis model, the key coupling paths are determined according to the system coupling topology diagram; Based on a pre-set instruction generation model, optimized instructions are generated according to the key coupling path.

[0175] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and device side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0176] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0177] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0178] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. An energy efficiency optimization system for high-energy-consuming industrial systems, characterized in that, include: Main process equipment, auxiliary process equipment; The acquisition module is used to acquire the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The first generation module is used to generate a system coupled topology diagram based on a pre-set topology diagram generation model, according to the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The system coupled topology diagram includes equipment nodes and energy flow edges connecting the equipment nodes, as well as flux fluctuation indicators, phase lag indicators and correlation indicators marked on each energy flow edge. The path determination module is used to determine the key coupling paths based on a pre-set topology graph analysis model and the system coupling topology graph. The second generation module is used to generate optimization instructions based on a pre-set instruction generation model and according to the key coupling path. The optimization instructions include main process optimization instructions and / or auxiliary process optimization instructions. The main process optimization instructions are sent to the main process device, and the auxiliary process optimization instructions are sent to the auxiliary process device.

2. The energy efficiency optimization system for high-energy-consuming industrial systems according to claim 1, characterized in that, The first generation module is also used to determine the status parameters of the two target device nodes corresponding to the target energy flow edge within a preset analysis period based on the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The first generation module is also used to determine the status parameters of the main process equipment node within a preset analysis period based on the status parameters of the main process equipment. The first generation module is also used to determine the throughput fluctuation index, the phase lag index, and the correlation index based on a pre-set index calculation model and according to the status parameters of the main process equipment node and the status parameters of the two target equipment nodes.

3. The energy efficiency optimization system for high-energy-consuming industrial systems according to claim 2, characterized in that, The indicator calculation model includes a first indicator calculation model, a second indicator calculation model, and a third indicator calculation model; The first generation module is further configured to, based on the first index calculation model, determine the energy flux time series of the target energy flow edge according to the state parameters of the two target device nodes corresponding to the target energy flow edge, and calculate the flux fluctuation index according to the standard deviation and average value of the energy flux time series of the target energy flow edge; The first generation module is also used to determine the main process characteristic time point based on the second index calculation model and the state parameters of the main process equipment node, and to determine the auxiliary process characteristic time point in the energy flux time series of the target energy flow edge based on the main process characteristic time point, and to calculate the phase lag index based on the main process characteristic time point and the auxiliary process characteristic time point. The first generation module is also used to calculate the correlation index based on the third index calculation model, according to the flux fluctuation index and the phase lag index.

4. The energy efficiency optimization system for high-energy-consuming industrial systems according to claim 1, characterized in that, The key coupling paths include weakly coupled paths; The path determination module is also used to parse the correlation index of each energy flow edge based on the topology graph analysis model and the coupled topology graph of the system. The path determination module is also used to compare the correlation index of each energy flow edge with the first preset threshold based on the first preset threshold in the topology graph analysis model, and determine the weakly coupled path according to the comparison result.

5. The energy efficiency optimization system for high-energy-consuming industrial systems according to claim 4, characterized in that, The second generation module is also used to parse the first energy flux time series of the weakly coupled path based on the system coupled topology graph according to the pre-set topology graph analysis model; The second generation module is also used to generate the theoretical demand curve of the main process equipment in the instruction generation model based on the instruction, and to identify the energy gap period and the energy sufficient period of the first auxiliary process according to the first energy flux time series. The second generation module is also used to generate main process optimization instructions based on the main process instruction generation model in the instruction generation model, according to the first auxiliary process energy gap period and the first auxiliary process energy sufficient period.

6. The energy efficiency optimization system for high-energy-consuming industrial systems according to claim 1, characterized in that, The key coupling paths include unstable paths; The path determination module is also used to parse the correlation index of each energy flow edge within multiple preset analysis periods based on the topology graph analysis model and the system coupling topology graph. The path determination module is also used to perform statistical analysis on the correlation index of the target energy flow edge within multiple preset analysis periods to obtain the correlation fluctuation rate of each energy flow edge. The path determination module is also used to compare the correlation volatility of each energy flow edge with the second preset threshold based on the second preset threshold in the topology graph analysis model, and determine the unstable path according to the comparison result.

7. The energy efficiency optimization system for high-energy-consuming industrial systems according to claim 6, characterized in that, The second generation module is also used to parse the second energy flux time series of the unstable path based on the pre-set topology graph analysis model and the unstable path. The second generation module is also used to generate the theoretical operating curve of the auxiliary process equipment in the instruction generation model based on the instruction, and to identify the energy gap period and the energy sufficient period of the second auxiliary process according to the second energy flux time series. The second generation module is also used to generate auxiliary process optimization instructions based on the main process instruction generation model in the instruction generation model, according to the energy gap period of the second auxiliary process and the energy sufficient period of the second auxiliary process.

8. A method for optimizing the energy efficiency of a high-energy-consuming industrial system, characterized in that, The method, used in the energy efficiency optimization system for industrial high-energy-consuming systems as described in any one of claims 1 to 7, comprises: Obtain the status parameters of the main process equipment and the auxiliary process equipment; Based on a pre-set topology generation model, a system coupled topology is generated according to the status parameters of the main process equipment and the status parameters of the auxiliary process equipment. The system coupled topology includes equipment nodes and energy flow edges connecting the equipment nodes, as well as flux fluctuation indicators, phase lag indicators and correlation indicators marked on each energy flow edge. Based on the pre-set topology diagram analysis model, the key coupling paths are determined according to the system coupling topology diagram; Based on a pre-set instruction generation model, optimized instructions are generated according to the key coupling path. The optimized instructions include main process optimization instructions and / or auxiliary process optimization instructions. The main process optimization instructions are sent to the main process device, and the auxiliary process optimization instructions are sent to the auxiliary process device.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the energy efficiency optimization method for industrial high-energy-consuming systems as described in claim 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the energy efficiency optimization method for industrial high-energy-consuming systems as described in claim 8.

Images