An apparatus and process energy efficiency carbon efficiency optimization method and related devices

Abstract

The application provides a kind of equipment and process energy efficiency carbon efficiency optimization method and related device, which first obtains multi-source time series metering data set, carries out process electricity tracing based on the preset binding mapping relationship of branch intelligent electric meter and process flow, realizes the leap of electricity data from factory statistics to process splitting;Subsequently, a three-dimensional electric-carbon coupling feature matrix is constructed using ridge regression weighting algorithm, quantifying the dynamic linkage law of power, fuel and carbon emission data, breaking the traditional static statistical mode of electric-carbon data fragmentation;On this basis, the dynamic carbon emission factor is used to calculate the energy efficiency and carbon emission of each process, so that each branch electric meter data can be traced back to the corresponding process carbon emission;Further, two-level hierarchical optimization is carried out according to the order of optimizing electricity-using equipment first and then optimizing process flow, eliminating the cross interference of electric-carbon parameters through variable locking mechanism to ensure the stability of energy saving and carbon reduction effect;Finally, control instructions are issued to the field execution mechanism according to the optimization control strategy.

Description

Technical Field

[0001] This invention belongs to the field of industrial energy efficiency and carbon efficiency optimization technology, specifically relating to a method and related apparatus for optimizing the energy efficiency and carbon efficiency of equipment and processes. Background Technology

[0002] Against the backdrop of new power system construction, the synergy between electricity and fossil energy, as well as refined energy and carbon management, has become a major focus in the industrial sector. With the continuous development of energy metering technology, energy and carbon management is gradually transforming from extensive plant-wide statistics to refined management at the process and equipment levels. There is an urgent need to build a full-chain technology system covering monitoring, accounting, traceability, optimization, and control to achieve comprehensive improvement in energy efficiency and carbon efficiency.

[0003] In the industrial sector, numerous electrical and fuel / gas-fuel coupled devices exist, with multiple independent processes operating in parallel, resulting in a deep linkage between electricity and fossil fuel consumption. The electrical operating conditions of these devices directly impact fuel combustion efficiency and carbon emissions, while fuel operating conditions conversely constrain electricity load distribution, creating a significant electricity-carbon coupling characteristic. In this scenario, deploying smart meters and fuel / gas meters to acquire multi-dimensional time-series operating parameters has become a crucial means of deconstructing the dynamic relationship between electricity, gas, and carbon, and supporting collaborative management.

[0004] In existing technologies, multi-source metering data are usually stored independently and only statically correlated. They lack in-depth analysis of the dynamic linkage between electricity and fossil energy, making it impossible to accurately decompose process-level indirect carbon emissions based on actual measured electricity and other operational data. This makes it difficult to support refined carbon traceability and energy-carbon synergistic optimization under dynamic operating conditions. Summary of the Invention

[0005] Based on this, it is necessary to provide a method and related apparatus for optimizing the energy and carbon efficiency of equipment and processes to address the above-mentioned technical problems. This would solve the problems in the existing technology where multi-source electrical carbon data is fragmented and lacks in-depth analysis of dynamic coupling laws, resulting in the lack of accurate carbon accounting at the process level and unstable energy-carbon synergistic optimization effects.

[0006] In a first aspect, the present invention provides a method for optimizing the energy efficiency and carbon efficiency of equipment and processes, comprising the following steps: Obtain multi-source time-series econometric datasets; By utilizing multi-source time-series metering datasets, and based on the pre-defined binding mapping relationship between branch smart meters and process flow, the electricity consumption of each process is traced, and the time-of-use electricity consumption data and fuel / gas consumption data of each process are obtained. By combining the time-of-use electricity data and fuel and gas consumption data of each process, a three-dimensional electric-carbon coupling feature matrix is ​​constructed using the ridge regression weighting algorithm to obtain the quantitative results of the electric-carbon coupling law at the process level. The three-dimensional electric-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that quantifies the energy-carbon linkage law within the process by using three types of multi-source data, namely electricity, fuel and carbon emissions, as input and adaptive weight allocation through ridge regression weighting. Based on the dynamic carbon emission factor, the energy efficiency and carbon emissions of each process are calculated to obtain the process-level energy efficiency and carbon efficiency calculation results; Combining the quantitative results of the process-level electro-carbon coupling law with the process-level energy efficiency and carbon efficiency accounting results, a two-level hierarchical optimization is carried out in the order of first optimizing the power equipment and then optimizing the process flow, so as to obtain the optimization and control strategy of equipment and process. Based on the optimized control strategy, control instructions are issued to the on-site execution agencies.

[0007] Furthermore, by utilizing multi-source time-series metering datasets and based on the pre-defined binding mapping relationship between branch smart meters and the process flow, the electricity consumption of each process is traced, yielding time-of-use electricity data and fuel / gas consumption data for each process, including: Preprocessing of multi-source time-series metrology datasets yields effective metrology data; Based on the pre-established one-to-one binding mapping relationship between the branch smart meters and each process flow, the time-of-use data of the meter in the effective metering data is split according to the process flow to obtain the time-of-use electricity data of each process flow. Based on the measured data of fuel and gas meters for each process, the fuel and gas consumption data for each process are matched.

[0008] Furthermore, by combining the time-of-use electricity data and fuel / gas consumption data of each process, a three-dimensional electro-carbon coupling feature matrix is ​​constructed using a ridge regression weighting algorithm, yielding quantitative results of the process-level electro-carbon coupling law, including: Using the time-series electricity load sequence, fuel consumption sequence, and carbon emission sequence of each process as input data, the ridge regression weighting algorithm is used to adaptively assign weights to the three types of input data to obtain the electricity-carbon coupling weights of each process. Based on the electrocarbon coupling weight, calculate the time-series correlation coefficient, operating condition response delay, and energy consumption linkage ratio; A three-dimensional electro-carbon coupling feature matrix for a single process is constructed by time-series correlation coefficient, operating condition response delay, and energy consumption linkage ratio, and the coupling strength level is divided by the carbon coupling feature matrix.

[0009] Furthermore, based on dynamic carbon emission factors, the energy efficiency and carbon emissions of each process are calculated to obtain process-level energy efficiency and carbon efficiency calculation results, including: The system obtains the grid dynamic carbon emission factor, which is updated in real time with the green electricity ratio and time-of-use electricity price in the linked area, as well as the fuel dynamic carbon emission factor, which is updated with the fuel type and combustion conditions. Multiply the measured electricity of the branch smart meter by the grid dynamic carbon emission factor to obtain the indirect carbon emissions of each process. Multiply the fuel and gas meter consumption by the fuel dynamic carbon emission factor to obtain the direct carbon emissions of each process. The total carbon emissions of a process are obtained by adding the indirect carbon emissions and direct carbon emissions of the process. The carbon efficiency of the process is calculated by combining the effective output of the process, and the comprehensive energy efficiency of the process is calculated by combining the total energy input of the process.

[0010] Furthermore, in the two-level hierarchical optimization process, which follows the order of first optimizing electrical equipment and then optimizing the process flow, the first-level electrical equipment optimization stage includes: Keep all process parameters and fuel / gas supply parameters unchanged, and optimize the electrical equipment used in each process. With the optimization objectives of maximizing energy efficiency in a single process and minimizing carbon emissions between processes, electrical safety thresholds, equipment rated parameters, and power grid power quality requirements are set as constraints. An intelligent iterative algorithm is used for optimization. When the fluctuation of the power consumption efficiency of the process is lower than the preset threshold or the maximum number of iterations is reached, it is determined that the power consumption condition has converged to the optimal steady state and the optimal power consumption parameters are output.

[0011] Furthermore, in the two-level hierarchical optimization process, which follows the order of first optimizing electrical equipment and then optimizing the process flow, the second-level process flow optimization stage includes: Start after the electrical equipment reaches its optimal steady state, and lock the optimal power consumption parameters of the first stage output unchanged; The optimization targets are fuel supply, combustion conditions, equipment linkage timing and the entire process flow, with multiple objectives including maximizing comprehensive energy efficiency, optimizing carbon efficiency and minimizing operating costs. Based on the coupling strength level in the quantitative results of the process-level electro-carbon coupling law, the adjustment step size of the parameter is adjusted, and fuel supply limits, equipment safety conditions, carbon emission quotas and process production requirements are superimposed as constraints to obtain the global optimal process control strategy.

[0012] Secondly, the present invention provides an energy efficiency and carbon efficiency optimization device for equipment and processes, comprising: The multi-source data acquisition module is used to acquire multi-source time-series metrology datasets; The process power consumption traceability module is used to trace process power consumption based on the preset binding mapping relationship between branch smart meters and process flow using multi-source time-series metering datasets, and obtain time-of-use power consumption data and fuel / gas consumption data for each process. The three-dimensional electro-carbon coupling analysis module is used to combine the time-of-use electricity data and fuel and gas consumption data of each process, and to construct a three-dimensional electro-carbon coupling feature matrix using the ridge regression weighting algorithm to obtain the quantitative results of the process-level electro-carbon coupling law. The three-dimensional electro-carbon coupling feature matrix takes electricity, fuel and carbon emissions as inputs, and performs adaptive weight allocation through ridge regression weighting to quantify the multi-dimensional coupling matrix of the energy-carbon linkage law within the process. The process-level energy and carbon accounting module is used to calculate the energy efficiency and carbon emissions of each process based on the dynamic carbon emission factor, and obtain the process-level energy and carbon efficiency accounting results. The two-level hierarchical optimization module is used to combine the quantitative results of the process-level electro-carbon coupling law with the energy efficiency and carbon efficiency accounting results, and to perform two-level hierarchical optimization in the order of first optimizing the power equipment and then optimizing the process flow, so as to obtain the optimization and control strategy of equipment and process. The optimization execution module is used to issue control commands to the field actuators based on the optimization control strategy.

[0013] Thirdly, the present invention provides a computer device, the device including a processor and a memory: The memory is used to store computer programs and send the instructions of the computer programs to the processor; The processor executes the following steps according to the instructions of the computer program: Obtain multi-source time-series econometric datasets; By utilizing multi-source time-series metering datasets, and based on the pre-defined binding mapping relationship between branch smart meters and process flow, the electricity consumption of each process is traced, and the time-of-use electricity consumption data and fuel / gas consumption data of each process are obtained. By combining the time-of-use electricity data and fuel and gas consumption data of each process, a three-dimensional electric-carbon coupling feature matrix is ​​constructed using the ridge regression weighting algorithm to obtain the quantitative results of the electric-carbon coupling law at the process level. The three-dimensional electric-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that quantifies the energy-carbon linkage law within the process by using three types of multi-source data, namely electricity, fuel and carbon emissions, as input and adaptive weight allocation through ridge regression weighting. Based on the dynamic carbon emission factor, the energy efficiency and carbon emissions of each process are calculated to obtain the process-level energy efficiency and carbon efficiency calculation results; Combining the quantitative results of the process-level electro-carbon coupling law with the process-level energy efficiency and carbon efficiency accounting results, a two-level hierarchical optimization is carried out in the order of first optimizing the power equipment and then optimizing the process flow, so as to obtain the optimization and control strategy of equipment and process. Based on the optimized control strategy, control instructions are issued to the on-site execution agencies.

[0014] Fourthly, the present invention provides a computer-readable storage medium on which a computer program is stored, and when executed by a processor, the computer program performs the following steps: Obtain multi-source time-series econometric datasets; By utilizing multi-source time-series metering datasets, and based on the pre-defined binding mapping relationship between branch smart meters and process flow, the electricity consumption of each process is traced, and the time-of-use electricity consumption data and fuel / gas consumption data of each process are obtained. By combining the time-of-use electricity data and fuel and gas consumption data of each process, a three-dimensional electric-carbon coupling feature matrix is ​​constructed using the ridge regression weighting algorithm to obtain the quantitative results of the electric-carbon coupling law at the process level. The three-dimensional electric-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that quantifies the energy-carbon linkage law within the process by using three types of multi-source data, namely electricity, fuel and carbon emissions, as input and adaptive weight allocation through ridge regression weighting. Based on the dynamic carbon emission factor, the energy efficiency and carbon emissions of each process are calculated to obtain the process-level energy efficiency and carbon efficiency calculation results; Combining the quantitative results of the process-level electro-carbon coupling law with the process-level energy efficiency and carbon efficiency accounting results, a two-level hierarchical optimization is carried out in the order of first optimizing the power equipment and then optimizing the process flow, so as to obtain the optimization and control strategy of equipment and process. Based on the optimized control strategy, control instructions are issued to the on-site execution agencies.

[0015] Fifthly, the present invention provides a computer program product, including a computer program that, when executed by a processor, performs the following steps: Obtain multi-source time-series econometric datasets; By utilizing multi-source time-series metering datasets, and based on the pre-defined binding mapping relationship between branch smart meters and process flow, the electricity consumption of each process is traced, and the time-of-use electricity consumption data and fuel / gas consumption data of each process are obtained. By combining the time-of-use electricity data and fuel and gas consumption data of each process, a three-dimensional electric-carbon coupling feature matrix is ​​constructed using the ridge regression weighting algorithm to obtain the quantitative results of the electric-carbon coupling law at the process level. The three-dimensional electric-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that quantifies the energy-carbon linkage law within the process by using three types of multi-source data, namely electricity, fuel and carbon emissions, as input and adaptive weight allocation through ridge regression weighting. Based on the dynamic carbon emission factor, the energy efficiency and carbon emissions of each process are calculated to obtain the process-level energy efficiency and carbon efficiency calculation results; Combining the quantitative results of the process-level electro-carbon coupling law with the process-level energy efficiency and carbon efficiency accounting results, a two-level hierarchical optimization is carried out in the order of first optimizing the power equipment and then optimizing the process flow, so as to obtain the optimization and control strategy of equipment and process. Based on the optimized control strategy, control instructions are issued to the on-site execution agencies.

[0016] In summary, this invention provides a method and related apparatus for optimizing the energy and carbon efficiency of equipment and processes. The method first acquires a multi-source time-series metering dataset and traces the electricity consumption of each process based on a pre-defined binding mapping relationship between branch smart meters and the process flow, achieving a leap from plant-wide statistics to process-specific data. Then, a ridge regression weighting algorithm is used to construct a three-dimensional electricity-carbon coupling feature matrix, quantifying the dynamic linkage patterns of electricity, fuel, and carbon emissions, breaking the traditional static statistical model of fragmented electricity-carbon data. Based on this, dynamic carbon emission factors are used to calculate the energy efficiency and carbon emissions of each process, enabling the traceability of carbon emissions from each branch meter data point to the corresponding process. Furthermore, a two-level hierarchical optimization is performed, prioritizing the optimization of electrical equipment before optimizing the process flow. A variable locking mechanism eliminates cross-interference of electricity-carbon parameters, ensuring stable energy-saving and carbon-reduction effects. Finally, control commands are issued to the field actuators according to the optimized control strategy, solving the problems of fragmented multi-source electricity-carbon data and lack of in-depth analysis of dynamic coupling patterns in existing technologies, leading to a lack of accurate carbon accounting at the process level and unstable energy-carbon synergistic optimization effects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic flowchart of a method for optimizing the energy efficiency and carbon efficiency of equipment and processes according to one embodiment of the present invention; Figure 2 This is a block diagram of a device and process energy efficiency and carbon efficiency optimization apparatus according to one embodiment of the present invention; Figure 3 This is a block diagram of a computer device according to one embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] It should be noted that the user information (including but not limited to user images, user portrait information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with relevant regulations.

[0022] To accurately understand the technical solution of this invention and to standardize the expression of technical terminology, the relevant technical terms involved in this application are first defined and explained.

[0023] Fuel and gas meters: Intelligent metering terminals deployed in fuel and gas pipelines collect real-time data on fossil energy such as instantaneous flow rate, cumulative consumption, medium pressure, and temperature. They are the basic metering equipment for fuel energy consumption and direct carbon emissions.

[0024] Electricity consumption characteristics: These parameters cover all dimensions of power operation, including load curves, power factor, power loss, time-of-use electricity consumption, load fluctuations, and equipment start-up and shutdown. They are the core basis for judging electricity consumption patterns and calculating indirect carbon emissions.

[0025] Branch-circuit smart meters: precision metering devices deployed according to independent process flows and equipment circuits, enabling accurate time-of-use electricity collection for single processes and single equipment, supporting process-level carbon separation.

[0026] Process flow: The independent production processes such as air supply, water supply, combustion, power output, and flue gas treatment, which are matched with industrial boilers, gas turbines, fuel-fired generator sets, etc., are the basic units for carbon control.

[0027] Electricity-carbon coupling refers to the inherent law of the interrelation and dynamic linkage between the energy consumption, operating conditions and carbon emissions of two types of energy, namely electricity and fuel / gas, in the operation of equipment and processes. It includes the dual connotations of electricity-gas energy consumption coupling and electricity-carbon emission coupling.

[0028] Electricity-carbon coupling feature matrix: A multi-dimensional quantitative matrix constructed based on multi-source metering data, with time-series correlation coefficient, operating condition response delay, and energy consumption linkage ratio as core indicators, deeply deconstructing the dynamic relationship between electricity, gas, and carbon.

[0029] Electricity consumption-carbon emission mapping model: Following relevant carbon emission accounting standards and electricity-carbon coordination standards, a quantitative mapping relationship between measured electricity consumption and indirect carbon emissions is established to realize the direct conversion of electricity meter data into process carbon emissions.

[0030] Dynamic carbon emission factor: Unlike fixed statistical factors, it is dynamically updated according to fuel type, combustion conditions, the proportion of green electricity in the regional power grid, and time-of-use electricity price, and is fully aligned with the requirements of relevant dynamic carbon accounting systems.

[0031] Energy efficiency: The ratio of effective output energy to total input energy, divided into equipment energy efficiency, single process energy efficiency, and system comprehensive energy efficiency, is a core assessment indicator for dual control of energy consumption.

[0032] Carbon efficiency: The amount of carbon emissions corresponding to a unit of effective output. The lower the value, the higher the level of low carbon emissions. It is a core evaluation indicator for power grid carbon synergy and carbon asset management.

[0033] Process-level energy and carbon traceability: Based on the measured data of branch electricity meters and fuel gas meters, the energy consumption and carbon emissions of each process are broken down to identify high energy-consuming and high-carbon-emission links.

[0034] Two-level hierarchical optimization: Following the laws of industrial operation and the energy and carbon control logic of the Southern Power Grid user side, priority is given to optimizing power equipment and then optimizing the overall process flow. Variable locking rules are set in the optimization process to avoid cross-interference of parameters.

[0035] Ridge Regression Weighted Coupling Model: The ridge regression algorithm is used to adaptively weight multi-source carbon dioxide data to improve the accuracy of coupling relationship analysis and trend prediction.

[0036] Closed-loop iterative self-learning: Based on on-site operation and optimization feedback data, the coupled model, carbon factor, and optimization algorithm are continuously updated to achieve adaptive evolution of the system.

[0037] In one embodiment, such as Figure 1 As shown, a method for optimizing the energy efficiency and carbon efficiency of equipment and processes is provided, including the following steps: S101: Obtain multi-source time-series econometric datasets.

[0038] Among them, the multi-source time-series metering dataset refers to a multi-dimensional time-series operational data set that is synchronously collected from fuel and gas meters, main power meters, branch smart meters, and environmental power grid monitoring terminals and aligned with a unified timestamp.

[0039] In this step, the system simultaneously collects four types of measured data: fuel and gas metering data, total power consumption data, branch smart meter data, and environmental power grid data, with consistent granularity and time alignment. Fuel and gas metering data is collected from pipeline smart meters, including instantaneous flow rate, cumulative consumption, medium pressure, and temperature. Total power consumption data is collected from the plant's main meter, including plant load, total electricity consumption, and power factor. Branch smart meter data is deployed independently according to the process flow, collecting time-of-use electricity consumption and real-time load. Environmental power grid data includes regional temperature, humidity, regional green electricity ratio, and time-of-use electricity price, providing auxiliary data for dynamic carbon emission factors and coupled analysis.

[0040] S102: Using multi-source time-series metering datasets, trace the electricity consumption of each process based on the preset binding mapping relationship between branch smart meters and process flow, and obtain the time-of-use electricity consumption data and fuel / gas consumption data of each process.

[0041] Among them, process power consumption traceability refers to the process of splitting the measured time-of-use data of the meter into process steps based on the preset binding mapping relationship between the branch smart meter and the process flow, and obtaining the time-of-use power consumption data and fuel gas consumption data of each process.

[0042] This step utilizes a multi-source time-series metering dataset. Based on the one-to-one binding mapping relationship between branch smart meters and each process flow, the actual time-of-use data of the meters in the effective metering data is split by process flow, and the actual measured data of fuel and gas meters corresponding to each process flow are matched, realizing the leap from plant-wide statistics to process-level breakdown of electricity consumption data.

[0043] S103: Combining the time-of-use electricity data and fuel / gas consumption data of each process, a three-dimensional electric-carbon coupling feature matrix is ​​constructed using the ridge regression weighting algorithm to obtain the quantitative results of the process-level electric-carbon coupling law. The three-dimensional electric-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that uses three types of multi-source data—electricity, fuel, and carbon emissions—as input and performs adaptive weight allocation through ridge regression weighting to quantify the energy-carbon linkage law within the process.

[0044] Among them, the quantitative result of the process-level electro-carbon coupling law refers to the quantitative data output by the three-dimensional electro-carbon coupling feature matrix, which reflects the degree of dynamic linkage between electricity and fossil energy in each process.

[0045] This step combines time-of-use electricity data and fuel / gas consumption data from each process, and uses a ridge regression weighting algorithm to adaptively assign weights to the three types of input data. It constructs a three-dimensional electric-carbon coupling feature matrix, quantifies the time-series correlation coefficient, operating condition response delay, and energy consumption linkage ratio, and obtains the quantitative results of the process-level electric-carbon coupling law.

[0046] S104: Based on the dynamic carbon emission factor, calculate the energy efficiency and carbon emissions of each process to obtain the process-level energy efficiency and carbon efficiency calculation results.

[0047] Among them, the dynamic carbon emission factor refers to the carbon emission accounting coefficient that is dynamically updated according to fuel type, combustion conditions, the proportion of green electricity in the regional power grid, and time-of-use electricity price, which is different from the traditional fixed statistical factor. The process-level energy efficiency carbon efficiency accounting result refers to the set of accounting data for the indirect carbon emissions, direct carbon emissions, total carbon emissions, carbon efficiency, and comprehensive energy efficiency of each process.

[0048] This step uses the dynamic carbon emission factor to calculate the indirect carbon emissions by multiplying the measured electricity of the branch smart meters by the dynamic carbon emission factor of the power grid, and multiplying the fuel consumption by the fuel dynamic carbon emission factor to obtain the direct carbon emissions. These are then combined to obtain the total carbon emissions of the process. Finally, carbon efficiency is calculated by combining the effective output of the process with the total energy input of the process to calculate the comprehensive energy efficiency.

[0049] S105: Combining the quantitative results of the process-level electro-carbon coupling law with the process-level energy efficiency and carbon efficiency accounting results, a two-level hierarchical optimization is carried out in the order of first optimizing the power equipment and then optimizing the process flow to obtain the optimization and control strategy of equipment and process.

[0050] Two-level hierarchical optimization refers to an optimization method that first optimizes the electrical equipment and then optimizes the process flow, locking in non-controllable variables for hierarchical solution. The optimized control strategy refers to the set of solutions output by the two-level hierarchical optimization, which includes the optimal parameters of the electrical equipment and the globally optimal control strategy for the process flow.

[0051] This step combines the quantitative results of the process-level electro-carbon coupling law with the energy efficiency and carbon efficiency calculation results. First, the process parameters and fuel / gas supply parameters are kept constant, and the first-level optimization is carried out with the electrical equipment as the optimization object. After the power consumption conditions converge to the optimal steady state, the optimal power consumption parameters are kept constant, and the second-level multi-objective optimization is carried out with the process flow as the optimization object, so as to obtain the optimization and control strategy of equipment and process.

[0052] S106: Based on the optimized control strategy, issue control instructions to the field actuators.

[0053] Among them, control commands refer to specific instructions generated according to the optimized control strategy, which are used to control the field actuators to adjust the parameters of electrical equipment and process flow.

[0054] Based on the optimized control strategy, this step sequentially sends the control commands generated by the two-level optimization to the field controller and actuator, automatically adjusting the parameters of the electrical equipment and process flow. The entire process is unattended, and the execution log and parameter changes are recorded synchronously.

[0055] This embodiment provides a method for optimizing the energy and carbon efficiency of equipment and processes. First, it acquires a multi-source time-series metering dataset and traces the electricity consumption of each process based on a pre-defined binding mapping relationship between branch smart meters and the process flow, achieving a refined leap from plant-wide statistics to process-specific data. Then, it uses a ridge regression weighting algorithm to construct a three-dimensional electricity-carbon coupling feature matrix, quantifying the dynamic linkage patterns of electricity, fuel, and carbon emissions, breaking the traditional static statistical model of fragmented electricity and carbon data. Based on this, it calculates the energy efficiency and carbon emissions of each process using dynamic carbon emission factors, enabling traceability of carbon emissions from each branch meter data point to the corresponding process. Next, it performs two-level hierarchical optimization, first optimizing the electrical equipment and then the process flow, eliminating cross-interference of electricity and carbon parameters through a variable locking mechanism to ensure stable energy-saving and carbon-reduction effects. Finally, it issues control commands to the field actuators based on the optimized control strategy, solving the problems of fragmented multi-source electricity and carbon data and lack of in-depth analysis of dynamic coupling patterns in existing technologies, leading to a lack of accurate carbon accounting at the process level and unstable energy-carbon synergistic optimization effects.

[0056] In an exemplary embodiment, a multi-source time-series metering dataset is used to trace the electricity consumption of each process based on a pre-defined binding mapping relationship between branch smart meters and the process flow, obtaining time-of-use electricity consumption data and fuel / gas consumption data for each process, including: S201: Preprocess the multi-source time-series metrology dataset to obtain valid metrology data.

[0057] Preprocessing refers to the process of cleaning, denoising, imputing missing values, and normalizing the dimensions of multi-source time-series metrology datasets, removing anomalous data jumps from sensors, and ensuring the validity of the metrology data. Valid metrology data refers to time-series metrology data that meets quality requirements after preprocessing.

[0058] In practice, the data cleaning process identifies and removes invalid data caused by abnormal sensor jumps, exceeding range limits, and communication interruptions; the noise reduction process uses moving average or Kalman filtering methods to smooth data fluctuations; the missing value completion process fills in missing values ​​based on interpolation of data from adjacent time periods or backfilling with historical data from the same period; and the dimension normalization process converts data such as electricity, flow, and temperature of different dimensions into a unified standard dimension space.

[0059] S202: Based on the pre-established one-to-one binding mapping relationship between the branch smart meters and each process flow, the actual time-of-use data of the meters in the effective metering data is split according to the process flow to obtain the time-of-use electricity data of each process flow.

[0060] Among them, the binding mapping relationship refers to the pre-established one-to-one correspondence between branch smart meters and each process flow, which is the basis for tracing the electricity consumption of each process. Time-of-use electricity data refers to the electricity consumption and load data of each process in different time periods after being broken down by process.

[0061] For example, based on the one-to-one binding mapping relationship between the branch smart meters and each process flow, the actual time-of-use data measured by the meters in the effective metering data is automatically split by process flow, so as to independently extract the electricity consumption and load fluctuation patterns of each process flow. It can be understood that when multiple processes share the branch smart meters, the electricity consumption can be split based on the load time-series curve characteristics of each process, and the traceability and carbon accounting logic remains unchanged.

[0062] S203: Match the fuel and gas consumption data of each process with the actual measured data of the fuel and gas meter corresponding to each process.

[0063] Among them, fuel consumption data refers to the fuel consumption data measured by fuel meters and matched to each process.

[0064] Specifically, based on the measured data from the fuel and gas meters corresponding to each process, fossil energy data such as instantaneous flow rate, cumulative consumption, medium pressure, and temperature are matched to the corresponding process, forming the basic input for process-level electro-carbon analysis together with time-of-use electricity data. It should be noted that all data are aligned with a unified timestamp, achieving spatiotemporal linkage between electricity, gas, and carbon data.

[0065] This embodiment obtains effective metering data by preprocessing multi-source time-series metering datasets. Based on the binding mapping relationship between branch smart meters and process flow, the meter data is split into time-of-use electricity data by process, and fuel and gas consumption data of each process are matched, realizing a refined leap from plant-wide statistics to process-specific breakdown of electricity data.

[0066] In an exemplary embodiment, by combining time-of-use electricity data and fuel / gas consumption data for each process, a three-dimensional electro-carbon coupling feature matrix is ​​constructed using a ridge regression weighting algorithm to obtain the quantitative results of process-level electro-carbon coupling patterns, including: S301: Using the time-series electricity load sequence, fuel consumption sequence, and carbon emission sequence of each process as input data, the ridge regression weighting algorithm is used to adaptively assign weights to the three types of input data to obtain the electricity-carbon coupling weights of each process.

[0067] Among them, the ridge regression weighting algorithm refers to a regression algorithm that adaptively assigns weights to three types of multi-source data: electricity, fuel, and carbon emissions. It avoids the error problem of traditional equal-weight calculation by introducing a regularization term. The electricity-carbon coupling weight refers to the weight coefficients output by the ridge regression weighting algorithm, which reflect the relative contributions of the three types of data: electricity consumption, fuel consumption, and carbon emissions in each process.

[0068] For example, time-series samples of electricity consumption, fuel consumption, and carbon emissions for each process are collected at a uniform time step of 15 minutes and normalized to the [0,1] interval. The time-series electricity load sequence for each process is then used. E Fuel consumption sequence F and carbon emission sequenceC For the input data, a multivariate linear fitting model is constructed, and an L2 regularization term is introduced to eliminate multicollinearity of multi-source data. The expression for its loss function is:

[0069] The initial value of the regularization coefficient is set to λ = 0.05. The adaptive weights for electricity and fuel consumption are solved by minimizing the loss function through matrix operations. The weight calculation formula for the ridge regression weighting algorithm is as follows:

[0070] in, This is the coupling weight vector, which includes electricity consumption weight and fuel weight; The input sample matrix consists of an electricity load sequence and a fuel consumption sequence. This is the carbon emission sequence for the process timing; It is the identity matrix. It should be noted that, compared to the traditional least squares method, ridge regression effectively suppresses multicollinearity among multiple data sources by introducing an L2 regularization term, thus improving the stability of the coupled weight solution.

[0071] S302: Calculate the time-series correlation coefficient, operating condition response delay, and energy consumption linkage ratio based on the electro-carbon coupling weight.

[0072] Among them, the time-series correlation coefficient is a statistical measure characterizing the degree of synchronization between changes in electricity consumption and changes in fuel and carbon emissions. Operating condition response delay refers to the delay time at which another type of energy and carbon emissions respond in tandem after a change in electricity or fuel parameters. Energy consumption linkage ratio refers to the magnitude of change in the consumption or carbon emissions of another type of energy corresponding to a unit change in electricity or fuel consumption.

[0073] Specifically, three types of coupling indices are calculated based on the electrocarbon coupling weights. Time-series correlation coefficient. R The Pearson correlation coefficient is used to quantify the linear correlation between electricity consumption series and fuel series, carbon emission series; operating condition response delay. T d Cross-correlation analysis was used to determine the time offset between changes in electricity load and changes in fuel consumption and carbon emissions; energy consumption linkage ratio. K Regression analysis is used to quantify the changes in fuel consumption and carbon emissions corresponding to changes in unit electricity consumption. The formula for calculating the coupling index is:

[0074] in, R The Pearson correlation coefficient is used. ρ For the correlation coefficient function, T d For operating condition response delay, K Energy consumption linkage ratio, EThis is the electrical load sequence for the process. F This represents the time-series fuel consumption sequence for a specific process. For example, the time-series correlation coefficient between the electricity load and fuel consumption of a particular process. R =0.85, indicating a high positive correlation between the two; operating condition response delay T d =2min, indicating that fuel consumption lags behind changes in electricity load by approximately 2 minutes; energy consumption linkage ratio K =1.3, meaning that for every 1 kWh increase in electricity consumption, fuel consumption increases by 1.3 units. It is understandable that the above three types of coupling indicators characterize the electro-carbon coupling features of the process from three dimensions: synchronicity, timeliness, and sensitivity, which differs from traditional single correlation coefficient analysis.

[0075] S303: A three-dimensional electro-carbon coupling feature matrix for a single process is composed of timing correlation coefficient, operating condition response delay and energy consumption linkage ratio, and the carbon coupling feature matrix is ​​used to classify the coupling strength level.

[0076] Among them, the single-process three-dimensional electro-carbon coupling characteristic matrix refers to a multi-dimensional quantification matrix composed of time-series correlation coefficients, operating condition response delays, and energy consumption linkage ratios, which deeply deconstructs the dynamic correlation between electricity, gas, and carbon. The coupling strength level refers to the three levels of strong coupling, medium coupling, and weak coupling, which are divided according to the coupling characteristic matrix.

[0077] In specific implementation, a three-dimensional electro-carbon coupling characteristic matrix for a single process is constructed using the time-series correlation coefficient, operating condition response delay, and energy consumption linkage ratio. This coupling characteristic matrix is ​​then used to classify the coupling strength levels. Preferably, the coupling level classification rule is: R ≥ 0.7 and... T d ≤30min is considered strong coupling; 0.3≤ R <0.7 and 30min < T d If the time is ≤120 min, it is considered as medium coupling; R <0.3 and T d A timeframe of ≥120 min indicates weak coupling. It should be noted that the power consumption of strongly coupled processes significantly impacts fuel consumption and carbon emissions, and should be a key focus of control in two-level hierarchical optimization, employing a smaller adjustment step size for fine-grained search. Weakly coupled processes have a weaker correlation between power consumption and fuel consumption, and can be optimized independently to reduce the solution dimensionality, using a larger adjustment step size to accelerate convergence.

[0078] This embodiment employs a ridge regression weighting algorithm to adaptively allocate weights to multi-source data, calculates three types of coupling indicators—time-series correlation coefficient, operating condition response delay, and energy consumption linkage ratio—and constructs a three-dimensional electric-carbon coupling feature matrix for a single process, classifying the coupling strength levels. This achieves in-depth analysis of the three-dimensional dynamic linkage patterns of electricity, fuel / gas, and carbon emissions, which differs from traditional two-dimensional static energy consumption statistical analysis. It provides a quantitative basis for coupling patterns in energy efficiency and carbon efficiency accounting and two-level hierarchical optimization.

[0079] In an exemplary embodiment, based on the dynamic carbon emission factor, the energy efficiency and carbon emissions of each process are calculated to obtain process-level energy efficiency and carbon efficiency calculation results, including: S401: Obtain the grid dynamic carbon emission factor updated in real time with the green electricity ratio and time-of-use electricity price in the linked area, as well as the fuel dynamic carbon emission factor updated with fuel type and combustion conditions.

[0080] Among them, the grid dynamic carbon emission factor refers to the grid carbon emission accounting coefficient updated in real time based on the proportion of green electricity in the linked region and the time-of-use electricity price. The fuel dynamic carbon emission factor refers to the fuel carbon emission accounting coefficient updated according to the fuel type and combustion conditions.

[0081] Specifically, the dynamic carbon emission factor of the power grid differs from traditional fixed statistical factors. It is linked to the green electricity ratio of the regional power grid and the time-of-use electricity price, and is updated in real time, fully aligning with the requirements of the dynamic carbon accounting system. The dynamic carbon emission factor of fuel is updated dynamically according to the fuel type (such as natural gas, diesel, heavy oil, etc.) and combustion conditions (such as combustion efficiency, air-fuel ratio, etc.).

[0082] For example, the formula for calculating the dynamic carbon emission factor of the power grid is:

[0083] in, As the dynamic carbon emission factor of the power grid, As a benchmark carbon emission factor for the regional power grid, for t The percentage of green electricity in the regional power grid at any given time. for t Time-of-use electricity pricing factor This is a time-of-use correction factor for grid carbon emissions. For example, when the proportion of green electricity in a region... At that time, the grid dynamic carbon emission factor decreased by about 40% compared to the benchmark factor, reflecting the carbon emission reduction effect of clean energy consumption; when the time-of-use electricity price is during peak hours, As the load increases, the power grid carbon emission correction coefficient is adjusted accordingly, reflecting the indirect impact of load peaks and valleys on carbon emissions.

[0084] S402: Multiply the measured electricity of the branch smart meter by the grid dynamic carbon emission factor to obtain the indirect carbon emissions of each process.

[0085] Indirect carbon emissions refer to the carbon emissions generated by the electricity used in the process, calculated by multiplying the measured electricity from the branch smart meter by the grid dynamic carbon emission factor.

[0086] For example, the indirect carbon emissions of each process are obtained by multiplying the measured electricity of the branch smart meter by the grid dynamic carbon emission factor. The calculation formula is as follows:

[0087] in, For process i Indirect carbon emissions For process i Branch meter t Electricity consumption during a given time period.

[0088] S403: Multiply the fuel gas consumption by the fuel dynamic carbon emission factor to obtain the direct carbon emissions of each process.

[0089] Direct carbon emissions refer to the carbon emissions generated by the combustion of fuel in the process, calculated by multiplying the fuel consumption by the fuel dynamic carbon emission factor.

[0090] For example, the formula for calculating the fuel dynamic carbon emission factor is as follows:

[0091] in, fuel m Dynamic carbon emission factors fuel m Theoretical baseline carbon emission factor for t Real-time fuel combustion efficiency This is a correction constant for combustion conditions. The direct carbon emissions of each process are obtained by multiplying the fuel gas consumption by the fuel dynamic carbon emission factor. The calculation formula is as follows:

[0092] in, For process i Direct carbon emissions For process i fuel m Consumption. It should be noted that the dynamic carbon emission factor of fuel is updated in real time according to fuel type and combustion conditions, replacing the traditional fixed factor, which greatly improves the accuracy of carbon accounting and policy compliance. For example, the benchmark carbon factor of natural gas is lower than that of diesel, and the direct carbon emission accounting result is even lower under the same operating conditions; when the combustion efficiency decreases, the carbon factor is adjusted upward accordingly to reflect the increase in carbon emissions caused by incomplete combustion.

[0093] S404: The total carbon emissions of a process are obtained by adding the indirect carbon emissions and direct carbon emissions of the process. The carbon efficiency of the process is calculated by combining the effective output of the process, and the comprehensive energy efficiency of the process is calculated by combining the total energy input of the process.

[0094] The total carbon emissions from a process refer to the total carbon emissions from the process, obtained by adding indirect and direct carbon emissions. Process carbon efficiency refers to the carbon emissions per unit of effective output; the lower the value, the higher the level of low carbon emissions. Overall process energy efficiency is the ratio of effective output to total energy input.

[0095] In practice, the total carbon emissions of a process are obtained by adding the indirect carbon emissions from the process to the direct carbon emissions. The calculation formula is as follows:

[0096] in, For process i Total carbon emissions. The carbon efficiency of a process is calculated by combining the effective output of that process with the following formula:

[0097] in, For process carbon efficiency, This represents the effective output of the process. The overall energy efficiency of the process is calculated by combining the total energy input of the process with the following formula:

[0098] in, For the overall energy efficiency of the process, This represents the total electricity consumption of the process. This refers to the calorific value of the fuel. It is understandable that this step allows for the traceability of carbon emissions from each branch meter to the corresponding process, meeting the requirements for process-level carbon verification, carbon trading, and dual control of energy consumption.

[0099] This embodiment obtains the grid dynamic carbon emission factor based on the proportion of green electricity in the linked area and the time-of-use electricity price, as well as the fuel dynamic carbon emission factor updated with fuel type and combustion conditions. It calculates the indirect and direct carbon emissions of each process, and superimposes them to obtain the total carbon emissions of the process. It also calculates carbon efficiency and comprehensive energy efficiency, thus constructing a process-level refined energy and carbon accounting system driven by dynamic factors. This breaks through the accuracy bottleneck of traditional fixed-factor static accounting, making branch meters the main data source for carbon traceability and carbon verification.

[0100] In an exemplary embodiment, in a two-level hierarchical optimization process that first optimizes electrical equipment and then optimizes the process flow, the first-level electrical equipment optimization stage includes: S501: Lock all process parameters and fuel / gas supply parameters unchanged, and optimize the electrical equipment used in each process.

[0101] Herein, variable locking refers to a mechanism that keeps the parameters of non-current-level regulation objects unchanged at a certain level of optimization stage to prevent cross-interference of power and carbon parameters. The optimal steady state refers to the optimization termination state where convergence is determined when the energy efficiency fluctuation of power-consuming equipment is lower than a preset threshold.

[0102] Specifically, following the hierarchical logic of optimizing power-consuming units first, all process flow parameters and fuel, gas supply parameters are kept locked throughout the whole process, and power-consuming equipment such as supporting motors, fans, water pumps, and frequency converters in each process are taken as optimization objects. It can be understood that the variable locking mechanism ensures that the first-level optimization only adjusts the parameters of power-consuming equipment, does not involve changes in process flow and fuel supply parameters, and eliminates cross-interference of power and carbon parameters, which is an innovation different from the traditional synchronous parameter adjustment optimization method.

[0103] S502: Taking maximizing the power consumption energy efficiency of a single process and minimizing the indirect carbon emission of the process as optimization objectives, and setting electrical safety thresholds, equipment rated parameters and power grid power quality requirements as constraint conditions.

[0104] Herein, maximizing power consumption energy efficiency refers to the optimization direction targeting the optimal energy efficiency ratio of the power-consuming equipment in a single process. Minimizing indirect carbon emission refers to the optimization objective of reducing the indirect carbon emission of the process by optimizing the operating parameters of power-consuming equipment.

[0105] Exemplarily, taking maximizing the power consumption energy efficiency of a single process and minimizing the indirect carbon emission of the process as optimization objectives, and setting electrical safety thresholds, equipment rated parameters and power grid power quality requirements as constraint conditions. In specific implementation, the calculation formula of the first-level power consumption optimization fitness function is:

[0106] Herein, is the first-level power consumption optimization fitness function, is the total energy consumption of adjustable power-consuming equipment.

[0107] S503: An intelligent iterative algorithm is adopted for optimization search. When the power consumption energy efficiency fluctuation of the process is lower than a preset threshold or the maximum number of iterations is reached, it is determined that the power consumption working condition converges to the optimal steady state, and the optimal power consumption parameters are output.

[0108] Herein, the intelligent iterative algorithm refers to a method for parameter optimization search using heuristic algorithms such as genetic algorithm, particle swarm algorithm or ant colony algorithm. The preset threshold refers to the upper limit of energy efficiency fluctuation tolerance for judging the convergence of power consumption working conditions.

[0109] In practice, an intelligent iterative algorithm is used for optimization. When the energy efficiency fluctuation of the process is lower than a preset threshold or the maximum number of iterations is reached, the power consumption condition is determined to have converged to the optimal steady state, and the optimal power consumption parameters are output. It should be noted that if convergence is not achieved, the current level of iteration continues without entering the second-level process optimization stage, ensuring the reliability of the equipment optimization results. Preferably, the iterative algorithm can be replaced by a similar heuristic algorithm such as a genetic algorithm or ant colony algorithm, while the two-level hierarchical structure and variable locking rules remain unchanged. The convergence condition can be set to 20 consecutive iterations. Fit 1. Fluctuation is less than 0.5%.

[0110] This embodiment locks the process parameters and fuel / gas supply parameters unchanged, performs single-objective optimization with electrical equipment as the optimization target, and configures iterative convergence judgment rules to achieve priority optimization of electrical equipment energy efficiency and effective avoidance of parameter cross-interference, providing a stable basis for optimal power parameters for the second-level process optimization.

[0111] In an exemplary embodiment, in a two-level hierarchical optimization process that first optimizes electrical equipment and then optimizes the process flow, the second-level process flow optimization stage includes: S601: Starts after the electrical equipment reaches its optimal steady state, locking the optimal power consumption parameters of the first-stage output unchanged.

[0112] Among them, the optimal power consumption parameters refer to the set of operating parameters output by the first-level optimization, which are the parameters when the power-consuming equipment reaches its optimal steady state.

[0113] Specifically, the second-stage process optimization only begins after the electrical equipment reaches its optimal steady state. Throughout the process, the optimal electrical parameters output from the first stage remain unchanged, ensuring that the second-stage optimization only adjusts the process flow and fuel supply parameters without altering the already converged operating state of the electrical equipment. In essence, the variable locking mechanisms in the two optimization stages complement each other: the first stage locks process parameters to optimize the electrical equipment, while the second stage locks electrical parameters to optimize the process flow. This resolves the issue of cross-interference between electrical and carbon parameters, ensuring that the energy-saving and carbon-reducing effects do not rebound.

[0114] S602: The optimization targets are fuel supply, combustion conditions, equipment linkage timing and the entire process flow, with the goal of maximizing comprehensive energy efficiency, optimizing carbon efficiency and minimizing operating costs.

[0115] Among them, multi-objective optimization refers to an optimization method that simultaneously considers the three dimensions of maximizing comprehensive energy efficiency, optimizing carbon efficiency, and minimizing operating costs.

[0116] For example, the optimization targets are fuel supply, combustion conditions, equipment linkage timing, and the entire process flow, with the goals of maximizing overall energy efficiency, optimizing carbon efficiency, and minimizing operating costs. In specific implementation, the calculation formula for the second-level multi-objective optimization function is as follows:

[0117] in, It is a second-order multi-objective optimization function. The combined operating cost of fuel and electricity For comprehensive energy efficiency weighting, As carbon efficiency weight, This is the weight for operating costs. It should be noted that the weighting is constrained. The default benchmark weights can be adjusted according to the range of control requirements. The first priority is to maximize comprehensive energy efficiency, the second priority is to optimize carbon efficiency, and the third priority is to minimize operating costs, which aligns with the business orientation of electricity-carbon collaborative trading and comprehensive energy efficiency control.

[0118] S603: Adjust the step size of the parameter based on the coupling strength level in the quantitative results of the process-level electro-carbon coupling law, and superimpose fuel supply limits, equipment safety conditions, carbon emission quotas and process production requirements as constraints to obtain the global optimal process control strategy.

[0119] Among them, the coupling strength level refers to the strong coupling, medium coupling, and weak coupling levels divided by the three-dimensional electro-carbon coupling characteristic matrix, which is used to guide the differentiated setting of parameter adjustment step size in process optimization. The global optimal process control strategy refers to the multi-objective optimization solution result that comprehensively considers fuel supply, combustion conditions, equipment linkage timing, and process flow.

[0120] In practice, the adjustment step size of parameters is adjusted based on the coupling strength level in the quantification results of the process-level electro-carbon coupling law: For strongly coupled processes, a smaller adjustment step size is used for fine-tuning to avoid large fluctuations in carbon emissions caused by minor parameter changes; for weakly coupled processes, a larger adjustment step size can be used to accelerate convergence and improve optimization efficiency. By overlaying fuel supply limits, equipment safety conditions, carbon emission quotas, and process production requirements as constraints, the globally optimal process control strategy is obtained. The convergence condition can be set to 30 consecutive iterations. Fit 2. Fluctuations are less than or equal to 0.3%. It is understandable that the electro-carbon coupling matrix output in step 3 is used to predict the linkage effects of parameters, ensuring that the optimization strategy adapts to the coupling characteristics of the processes. It should be noted that the coupling level-driven differentiated step size adjustment mechanism is one of the innovations of this invention, enabling the optimization process to fully consider the differences in electro-carbon linkage between processes and avoiding the rebound in optimization effects caused by a one-size-fits-all parameter adjustment.

[0121] This embodiment starts and locks the optimal power consumption parameters after the power equipment reaches the optimal steady state, performs multi-objective optimization with the process flow as the optimization object, and adjusts the parameter adjustment step size according to the difference in coupling strength level. It realizes precise control driven by multi-objective optimization of electricity and carbon reduction and coupling law, and ensures the stability and sustainability of energy saving and carbon reduction effect.

[0122] It should be noted that after the optimization instructions are executed on-site, the system collects all optimized data, including fuel and gas consumption, branch electricity meters, load, energy efficiency, carbon emissions, and coupling characteristics, to form a closed-loop feedback dataset for model iteration. In practice, the feedback data covers all processes, all metering terminals, and the entire optimization cycle to ensure the data integrity of the closed-loop iteration.

[0123] For example, feedback data is used to complete iterative upgrades, and the standardization and correction of three types of parameters are performed simultaneously: (1) Ridge regression weight gradient correction:

[0124] in, For the updated ridge regression weights, For the old weight, A fixed learning rate (with a value of 0.02) is used. This is the gradient of the loss function based on the latest feedback samples. This formula updates the weights through gradient descent, optimizing the weighting coefficients of the ridge regression.

[0125] (2) The update formula for the three-dimensional electrocarbon coupling characteristic matrix is:

[0126] in, For the updated coupling feature matrix, This is the old coupling characteristic matrix. This is the latest sample coupling index matrix. The forgetting factor is 1. This formula is used to balance historical operating conditions with the latest sample data, update the three-dimensional electro-carbon coupling feature matrix and time-series linkage parameters, and adapt to long-term operating condition changes such as equipment aging, seasonal load, and fuel replacement.

[0127] (3) The update formula for the dynamic carbon emission factor is:

[0128] in, For the updated dynamic carbon emission factor, To optimize the measured carbon efficiency, To optimize the carbon efficiency prediction of the model before optimization, it is understood that when the measured carbon efficiency is better than the predicted value, the carbon factor is corrected downward; when the measured carbon efficiency is worse than the predicted value, the carbon factor is corrected upward. The optimized measured carbon efficiency is used to correct the prediction bias of the model, and the carbon emission factors of the power grid and fuel are dynamically corrected to fit the seasonal, fuel, and green electricity ratio changes.

[0129] It is understood that the coupling algorithm in the above embodiments can be replaced by a similar multi-source regression algorithm or a random forest weighting algorithm instead of the ridge regression algorithm, while the three-dimensional electricity-carbon coupling matrix architecture and index calculation logic remain unchanged; the optimization algorithm can be replaced by a genetic algorithm or an ant colony algorithm instead of the particle swarm algorithm, while the two-level hierarchical structure, variable locking, and multi-objective rules remain unchanged; the carbon emission factor update rules can be fine-tuned according to the green electricity and electricity price linkage logic based on the different regional power grid rules, while the core mechanism of dynamic factors remains unchanged. The convergence condition can be three consecutive rounds of learning, with the matrix change less than or equal to 1% and the carbon factor correction less than or equal to 0.8%. It should be noted that when multiple processes share a branch meter, the electricity consumption of the process can be split based on the load time series curve, while the source tracing and carbon accounting logic remain unchanged; the coupling dimension can be expanded to include auxiliary dimensions such as meteorology and pollution, while the three-dimensional coupling architecture of electricity-fuel-carbon remains unchanged.

[0130] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0131] Based on the same inventive concept, this application also provides an apparatus for implementing the above-described method for optimizing the energy and carbon efficiency of equipment and processes. The solution provided by this system is similar to the solution described in the above method; therefore, the specific limitations in the embodiments of the apparatus for optimizing the energy and carbon efficiency of equipment and processes provided below can be found in the limitations of the method described above, and will not be repeated here.

[0132] Please see Figure 2 This invention provides an energy efficiency and carbon efficiency optimization device for equipment and processes, comprising: The multi-source data acquisition module is used to acquire multi-source time-series metrology datasets; The process power consumption traceability module is used to trace process power consumption based on the preset binding mapping relationship between branch smart meters and process flow using multi-source time-series metering datasets, and obtain time-of-use power consumption data and fuel / gas consumption data for each process. The three-dimensional electro-carbon coupling analysis module is used to combine the time-of-use electricity data and fuel and gas consumption data of each process, and construct a three-dimensional electro-carbon coupling feature matrix using the ridge regression weighting algorithm to obtain the quantitative results of the process-level electro-carbon coupling law. The three-dimensional electro-carbon coupling feature matrix takes electricity, fuel and carbon emissions as inputs, and performs adaptive weight allocation through ridge regression weighting to quantify the multi-dimensional coupling matrix of the energy-carbon linkage law within the process. The process-level energy and carbon accounting module is used to calculate the energy efficiency and carbon emissions of each process based on the dynamic carbon emission factor, and obtain the process-level energy and carbon efficiency accounting results. The two-level hierarchical optimization module is used to combine the quantitative results of the process-level electro-carbon coupling law with the energy efficiency and carbon efficiency accounting results, and to perform two-level hierarchical optimization in the order of first optimizing the power equipment and then optimizing the process flow, so as to obtain the optimization and control strategy of equipment and process. The optimization execution module is used to issue control commands to the field actuators based on the optimization control strategy.

[0133] 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 merely 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 system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0134] Reference Figure 3 This invention also provides a computer device, including: a memory and a processor, and a computer program stored in the memory. When the computer program is executed on the processor, it performs the following steps: Obtain multi-source time-series econometric datasets; By utilizing multi-source time-series metering datasets, and based on the pre-defined binding mapping relationship between branch smart meters and process flow, the electricity consumption of each process is traced, and the time-of-use electricity consumption data and fuel / gas consumption data of each process are obtained. By combining the time-of-use electricity data and fuel and gas consumption data of each process, a three-dimensional electric-carbon coupling feature matrix is ​​constructed using the ridge regression weighting algorithm to obtain the quantitative results of the electric-carbon coupling law at the process level. The three-dimensional electric-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that uses three types of multi-source data, namely electricity, fuel and carbon emissions, as input and performs adaptive weight allocation through ridge regression weighting to quantify the energy-carbon linkage law within the process. Based on the dynamic carbon emission factor, the energy efficiency and carbon emissions of each process are calculated to obtain the process-level energy efficiency and carbon efficiency calculation results; Combining the quantitative results of the process-level electro-carbon coupling law with the process-level energy efficiency and carbon efficiency accounting results, a two-level hierarchical optimization is carried out in the order of first optimizing the power equipment and then optimizing the process flow to obtain the optimization and control strategy of equipment and process. Based on the optimized control strategy, control instructions are issued to the on-site execution agencies.

[0135] The computer device may be a desktop computer, laptop, handheld computer, or cloud server, etc. This computer device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that... Figure 3 The examples of computer devices are merely examples and do not constitute a limitation on computer devices. They may include more or fewer components than shown in the illustration, or combinations of certain components, or different components. For example, they may also include input / output devices, network access devices, etc.

[0136] The processor referred to can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0137] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard drive or RAM. In other embodiments, the memory may be an external storage device of the computer device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory may include both internal and external storage units of the computer device. The memory is used to store the operating system, applications, boot loader, data, and other programs, such as the program code of the computer program. The memory can also be used to temporarily store data that has been output or will be output.

[0138] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the following steps: Obtain multi-source time-series econometric datasets; By utilizing multi-source time-series metering datasets, and based on the pre-defined binding mapping relationship between branch smart meters and process flow, the electricity consumption of each process is traced, and the time-of-use electricity consumption data and fuel / gas consumption data of each process are obtained. By combining the time-of-use electricity data and fuel and gas consumption data of each process, a three-dimensional electric-carbon coupling feature matrix is ​​constructed using the ridge regression weighting algorithm to obtain the quantitative results of the electric-carbon coupling law at the process level. The three-dimensional electric-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that uses three types of multi-source data, namely electricity, fuel and carbon emissions, as input and performs adaptive weight allocation through ridge regression weighting to quantify the energy-carbon linkage law within the process. Based on the dynamic carbon emission factor, the energy efficiency and carbon emissions of each process are calculated to obtain the process-level energy efficiency and carbon efficiency calculation results; Combining the quantitative results of the process-level electro-carbon coupling law with the process-level energy efficiency and carbon efficiency accounting results, a two-level hierarchical optimization is carried out in the order of first optimizing the power equipment and then optimizing the process flow to obtain the optimization and control strategy of equipment and process. Based on the optimized control strategy, control instructions are issued to the on-site execution agencies.

[0139] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, 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 computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0140] This invention provides a computer program product, including a computer program that, when executed by a processor, performs the following steps: Obtain multi-source time-series econometric datasets; By utilizing multi-source time-series metering datasets, and based on the pre-defined binding mapping relationship between branch smart meters and process flow, the electricity consumption of each process is traced, and the time-of-use electricity consumption data and fuel / gas consumption data of each process are obtained. By combining the time-of-use electricity data and fuel and gas consumption data of each process, a three-dimensional electric-carbon coupling feature matrix is ​​constructed using the ridge regression weighting algorithm to obtain the quantitative results of the electric-carbon coupling law at the process level. The three-dimensional electric-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that uses three types of multi-source data, namely electricity, fuel and carbon emissions, as input and performs adaptive weight allocation through ridge regression weighting to quantify the energy-carbon linkage law within the process. Based on the dynamic carbon emission factor, the energy efficiency and carbon emissions of each process are calculated to obtain the process-level energy efficiency and carbon efficiency calculation results; Combining the quantitative results of the process-level electro-carbon coupling law with the process-level energy efficiency and carbon efficiency accounting results, a two-level hierarchical optimization is carried out in the order of first optimizing the power equipment and then optimizing the process flow to obtain the optimization and control strategy of equipment and process. Based on the optimized control strategy, control instructions are issued to the on-site execution agencies.

[0141] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0142] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0143] In the embodiments disclosed in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0144] The above 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.

Claims

1. A method for optimizing the energy efficiency and carbon efficiency of equipment and processes, characterized in that, Includes the following steps: Obtain multi-source time-series econometric datasets; Using the multi-source time-series metering dataset, the power consumption of each process is traced based on the preset binding mapping relationship between the branch smart meters and the process flow, and the time-of-use power consumption data and fuel / gas consumption data of each process are obtained. By combining the time-of-use electricity data and fuel / gas consumption data of each process, a three-dimensional electric-carbon coupling feature matrix is ​​constructed using a ridge regression weighting algorithm to obtain the quantitative results of the process-level electric-carbon coupling law. The three-dimensional electric-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that quantifies the energy-carbon linkage law within the process by using three types of multi-source data (electricity, fuel, and carbon emissions) as input and adaptive weight allocation through ridge regression weighting. Based on the dynamic carbon emission factor, the energy efficiency and carbon emissions of each process are calculated to obtain the process-level energy efficiency and carbon efficiency calculation results; Combining the quantitative results of the process-level electro-carbon coupling law with the process-level energy efficiency and carbon efficiency calculation results, a two-level hierarchical optimization is carried out in the order of first optimizing the power equipment and then optimizing the process flow to obtain the optimization and control strategy for equipment and process. Based on the optimized control strategy, control commands are issued to the field actuators.

2. The method for optimizing the energy efficiency and carbon efficiency of equipment and processes according to claim 1, characterized in that, Using the aforementioned multi-source time-series metering dataset, and based on the preset binding mapping relationship between branch smart meters and the process flow, the electricity consumption of each process is traced to obtain time-of-use electricity data and fuel / gas consumption data for each process, including: The multi-source time-series metering dataset is preprocessed to obtain valid metering data; Based on the pre-established one-to-one binding mapping relationship between the branch smart meters and each process flow, the actual time-of-use data of the meters in the effective metering data is split according to the process flow to obtain the time-of-use electricity data of each process flow. Based on the measured data of fuel and gas meters for each process, the fuel and gas consumption data for each process are matched.

3. The method for optimizing the energy efficiency and carbon efficiency of equipment and processes according to claim 1, characterized in that, Combining the time-of-use electricity data and fuel / gas consumption data of each process, a three-dimensional electro-carbon coupling feature matrix is ​​constructed using a ridge regression weighting algorithm to obtain the quantitative results of the process-level electro-carbon coupling law, including: Using the time-series electricity load sequence, fuel consumption sequence, and carbon emission sequence of each process as input data, the ridge regression weighting algorithm is used to adaptively assign weights to the three types of input data to obtain the electricity-carbon coupling weights of each process. Based on the aforementioned electrocarbon coupling weights, calculate the time-series correlation coefficient, operating condition response delay, and energy consumption linkage ratio. The time-series correlation coefficient, operating condition response delay, and energy consumption linkage ratio constitute a three-dimensional electro-carbon coupling feature matrix for a single process, and the carbon coupling feature matrix is ​​used to classify the coupling strength level.

4. The method for optimizing the energy efficiency and carbon efficiency of equipment and processes according to claim 1, characterized in that, Based on dynamic carbon emission factors, the energy efficiency and carbon emissions of each process are calculated to obtain process-level energy efficiency and carbon efficiency calculation results, including: The system obtains the grid dynamic carbon emission factor, which is updated in real time with the green electricity ratio and time-of-use electricity price in the linked area, as well as the fuel dynamic carbon emission factor, which is updated with the fuel type and combustion conditions. Multiply the measured electricity of the branch smart meter by the grid dynamic carbon emission factor to obtain the indirect carbon emissions of each process. Multiply the fuel and gas meter consumption by the fuel dynamic carbon emission factor to obtain the direct carbon emissions of each process. The total carbon emissions of a process are obtained by adding the indirect carbon emissions and direct carbon emissions of the process. The carbon efficiency of the process is calculated by combining the effective output of the process, and the comprehensive energy efficiency of the process is calculated by combining the total energy input of the process.

5. The method for optimizing the energy efficiency and carbon efficiency of equipment and processes according to claim 1, characterized in that, In the two-level hierarchical optimization process, which follows the order of first optimizing electrical equipment and then optimizing the process flow, the first level of electrical equipment optimization includes: Keep all process parameters and fuel / gas supply parameters unchanged, and optimize the electrical equipment used in each process. With the optimization objectives of maximizing the energy efficiency of a single process and minimizing the carbon emissions between processes, electrical safety thresholds, equipment rated parameters, and power grid power quality requirements are set as constraints. An intelligent iterative algorithm is used for optimization. When the fluctuation of the power consumption efficiency of the process is lower than the preset threshold or the maximum number of iterations is reached, it is determined that the power consumption condition has converged to the optimal steady state and the optimal power consumption parameters are output.

6. The method for optimizing the energy efficiency and carbon efficiency of equipment and processes according to claim 5, characterized in that, In the two-level hierarchical optimization process, which follows the order of first optimizing electrical equipment and then optimizing the process flow, the second-level process flow optimization stage includes: Start after the electrical equipment reaches its optimal steady state, and lock the optimal power consumption parameters of the first stage output unchanged; The optimization targets are fuel supply, combustion conditions, equipment linkage timing and the entire process flow, with multiple objectives including maximizing comprehensive energy efficiency, optimizing carbon efficiency and minimizing operating costs. Based on the coupling strength level in the quantitative results of the process-level electro-carbon coupling law, the adjustment step size of the parameter is adjusted, and fuel supply limits, equipment safety conditions, carbon emission quotas and process production requirements are superimposed as constraints to obtain the global optimal process control strategy.

7. A device for optimizing energy efficiency and carbon efficiency in equipment and processes, characterized in that, include: The multi-source data acquisition module is used to acquire multi-source time-series metrology datasets; The process power consumption traceability module is used to trace the process power consumption based on the multi-source time-series metering dataset and the preset binding mapping relationship between the branch smart meters and the process flow, so as to obtain the time-of-use power consumption data and fuel gas consumption data of each process. The three-dimensional electro-carbon coupling analysis module is used to combine the time-of-use electricity consumption data and fuel and gas consumption data of each process, and construct a three-dimensional electro-carbon coupling feature matrix using the ridge regression weighting algorithm to obtain the quantitative results of the process-level electro-carbon coupling law. The three-dimensional electro-carbon coupling feature matrix is ​​a multi-dimensional coupling matrix that uses three types of multi-source data, namely electricity consumption, fuel and carbon emissions, as input, and performs adaptive weight allocation through ridge regression weighting to quantify the energy-carbon linkage law within the process. The process-level energy and carbon accounting module is used to calculate the energy efficiency and carbon emissions of each process based on the dynamic carbon emission factor, and obtain the process-level energy and carbon efficiency accounting results. The two-level hierarchical optimization module is used to combine the quantitative results of the process-level electro-carbon coupling law with the energy efficiency and carbon efficiency calculation results, and to perform two-level hierarchical optimization in the order of first optimizing the power equipment and then optimizing the process flow, so as to obtain the optimization and control strategy of equipment and process. The optimization execution module is used to issue control commands to the field actuators according to the optimization control strategy.

8. A computer device, characterized in that, The device includes a processor and a memory: The memory is used to store computer programs and send the instructions of the computer programs to the processor; The processor executes, according to the instructions of the computer program, a method for optimizing the energy and carbon efficiency of an equipment and process as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for optimizing the energy efficiency and carbon efficiency of an equipment and process as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements a method for optimizing the energy and carbon efficiency of an equipment and process as described in any one of claims 1-6.

Images