Intelligent power plant production period energy auditing and optimizing method and system

Abstract

The invention discloses an intelligent power plant production period energy auditing and optimizing method and system, and belongs to the technical field of energy management, and the method comprises the steps: collecting energy data from an intelligent power plant in real time through a sensor, carrying out the preprocessing, carrying out the multi-dimensional analysis, and generating an energy consumption analysis report; performing dynamic optimization on an energy use strategy in combination with historical data, and generating an optimal energy distribution and use scheme; and auditing the energy use data after the implementation of the scheme, generating a detailed energy auditing report, and comparing the energy auditing report with historical data to evaluate an optimization effect. According to the method, the regression model and the production objective function are constructed, the energy distribution of each device is dynamically adjusted, the energy efficiency output is maximized, and the energy consumption is minimized. Through a continuous energy auditing and feedback mechanism, a detailed auditing report is generated, the situation that the energy efficiency does not reach the standard can be found and corrected in time, it is ensured that the optimal state of energy use is continuously maintained, and the energy efficiency management level and the overall operation benefits of an intelligent power plant are improved.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and specifically to a method and system for energy auditing and optimization during the production period of a smart power plant. Background Art

[0002] The energy management methods of traditional power plants usually rely on fixed energy allocation strategies and manual monitoring, and scheduling decisions are mostly based on historical experience and static models. Due to the lack of dynamic analysis and feedback mechanism for real-time data, this management method shows obvious limitations in dealing with complex fluctuations in the production process. The aging of equipment performance, changes in load, and the impact of environmental conditions are often difficult to reflect in the energy management strategy in a timely manner, resulting in low energy efficiency and serious waste of resources. In addition, traditional energy management systems usually only consider single-dimensional energy consumption data, such as electricity consumption or fuel usage, and lack the ability to comprehensively analyze multi-dimensional data such as time, space, equipment type, and environmental factors.

[0003] Under the limitation of this single-dimensional analysis, power plants cannot effectively identify energy consumption hotspots in the production process, nor can they find energy consumption anomalies or potential optimization opportunities. For example, when a piece of equipment experiences an abnormal increase in energy consumption, traditional analysis methods may not be able to quickly identify and take corresponding measures, resulting in long-term energy waste. In addition, traditional methods usually rely on manual recording and analysis when conducting energy consumption audits, which is cumbersome and time-consuming. This method is not only inefficient, but also due to the lag in analysis, it is often difficult to detect and correct energy consumption anomalies in a timely manner, affecting the overall production economy.

[0004] With the expansion of modern power plants and the complexity of processes, traditional energy management methods can no longer meet actual needs. The rise of smart power plants has put forward higher requirements for energy management, and there is an urgent need for an intelligent energy management method that can monitor in real time, dynamically optimize, and continuously audit and adjust. This method must not only be able to process a large amount of real-time data, but also have the ability to perform multi-dimensional analysis, dynamically adjust energy allocation strategies based on real-time collected data, and continuously optimize the energy efficiency and resource utilization of power plants through continuous auditing and feedback mechanisms. Therefore, it has become an urgent need for the industry to develop an advanced energy management method based on smart power plants that can overcome the shortcomings of traditional methods and improve the energy efficiency and economy of power plants. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: how to overcome the limitations of traditional energy management methods and achieve more accurate and efficient optimization and auditing of energy usage in the production process in the energy management of smart power plants.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for energy audit and optimization during the production period of a smart power plant, which comprises the following steps:

[0008] Use sensors to collect energy data from each production link of the smart power plant in real time and perform preprocessing;

[0009] Perform multi-dimensional analysis based on pre-processed data and generate a preliminary energy consumption analysis report;

[0010] Based on the analysis results, combined with historical data and production goals, the energy use strategy is dynamically optimized to generate the optimal energy allocation and use plan;

[0011] Audit the energy usage data after the implementation of the plan, generate a detailed energy audit report, and compare it with historical data to evaluate the optimization effect.

[0012] As a preferred solution of the energy audit and optimization method for a smart power plant production period described in the present invention, the real-time energy data collected includes electric energy data, fuel consumption data, thermal energy data, equipment operation data and environmental data;

[0013] The preprocessing is to perform preliminary screening on the collected raw data, filter out abnormal values ​​and incomplete records, use a smoothing algorithm to denoise the data, eliminate abnormal data points, and use an interpolation method to fill in the missing data, unify the dimensions of different types of data, convert all energy data into the same unit, and eliminate the differences between different magnitudes through normalization;

[0014] Perform timestamp alignment on preprocessed data, synchronize data with different sampling frequencies through interpolation technology, set upper and lower limits and change rates of preprocessed data, detect and remove abnormal data points that exceed the set range, store the cleaned and processed data in a structured manner in the database, and back up them regularly.

[0015] As a preferred solution of the energy audit and optimization method for a smart power plant production period described in the present invention, wherein: the multi-dimensional analysis is to aggregate the pre-processed energy data according to the time period and classify them according to the equipment type and energy type;

[0016] Use the aggregated data to draw a time series graph of energy consumption, showing the energy consumption change curve in different time periods, mark the time points of the maximum and minimum energy consumption in the time series graph, and determine the peak and trough periods of energy consumption;

[0017] Based on the peak and trough time points marked in the time series graph, the energy consumption of each device in the time period is counted, the energy consumption of the device in the peak and trough periods is calculated, and the energy efficiency is evaluated;

[0018] The energy consumption data of the equipment will be associated with the physical location to generate a spatial distribution map of energy consumption, showing the energy consumption of each area in the power plant;

[0019] Based on the spatial distribution map, identify hot spots where energy consumption is concentrated and analyze whether the equipment or operating processes in the area need further optimization;

[0020] Conduct correlation analysis between environmental data and energy consumption data, calculate the impact coefficient of environmental factors on energy consumption, identify energy consumption anomalies under extreme environmental conditions, and preliminarily generate an energy consumption analysis report.

[0021] As a preferred solution of the energy audit and optimization method for a smart power plant during production period described in the present invention, the energy use strategy is dynamically optimized to generate the optimal energy allocation and use plan based on the analysis results in the preliminary generated energy consumption analysis report, combined with historical data of the same period for comparative analysis, to identify the difference between current energy consumption and historical consumption, to determine the historical trend of energy consumption, to identify historical change points and to perform correlation analysis on production events;

[0022] Construct a production objective function and fit it with historical energy consumption data to predict the energy distribution under different production conditions. Based on the regression model and production objective function, establish an energy distribution optimization model, and use a linear programming algorithm to dynamically adjust the energy distribution of each device to minimize total energy consumption and maximize energy efficiency.

[0023] As a preferred solution of the energy audit and optimization method for a smart power plant production period described in the present invention, the production objective function includes a gas turbine and steam turbine coupling model, a boiler and condenser thermal model, a power network model, and a model of the impact of environmental factors on equipment operation;

[0024] The gas turbine and steam turbine coupling model is expressed as:

[0025]

[0026] Among them, η GT is the gas turbine efficiency, is the fuel flow rate, LHV fuel is the lower calorific value of the fuel, P GT is the power output of the gas turbine, is the exhaust gas flow rate, C p is the specific heat capacity of the exhaust gas, T exhaust is the exhaust gas temperature, Tamb is the ambient temperature, η ST is the steam turbine efficiency, is the steam flow rate, Δh is the steam enthalpy difference, P ST is the power output of the steam turbine;

[0027] The thermal model of the boiler and condenser is expressed as:

[0028]

[0029] in, is the heat output of the boiler, C p is the specific heat capacity of water, is the water flow rate in the boiler, T out and T in are the outlet and inlet temperatures of the boiler, is the heat absorbed by the condenser, is the steam flow rate, Δh condensation is the condensation enthalpy difference of steam;

[0030] The power network model is expressed as:

[0031]

[0032] Among them, P ij is the active power from node i to node j, V i ,V j is the voltage amplitude between node i and node j, X ij is the reactance between node i and node j, θ i ,θ j are the voltage phase angles at node i and node j respectively;

[0033] The impact model of environmental factors on equipment operation is expressed as:

[0034] η GT =η0·(1-k·(T in -T ref ))

[0035] Among them, η GT is the gas turbine efficiency, η0 is the gas turbine efficiency at the reference temperature T ref Baseline efficiency under T in is the intake air temperature, T ref is the reference temperature, and k is the coefficient of the effect of temperature change on efficiency.

[0036] As a preferred solution of the energy audit and optimization method for a smart power plant during production period described in the present invention, the construction of a production objective function is fitted with historical energy consumption data to predict the energy distribution under different production conditions, which is to construct a regression model of energy consumption, and the expression is:

[0037]

[0038] Where E(t) is the total energy consumption at time t, β0 is a constant term, and X k (t) is the operating parameter of the equipment at time t, β k is the regression coefficient corresponding to each operating parameter, P ij (t) is the power transmitted at time t, γ i is the regression coefficient corresponding to each power transmission power, δ is the regression coefficient of ambient temperature, ∈ is the error term, T evn (t) is the effect of ambient temperature at time t, γ i is the regression coefficient of electric power transmission power;

[0039] Construct the production objective function, the expression is:

[0040]

[0041] Among them, η sys (t) is the comprehensive efficiency, C op (t) is the energy and maintenance cost during operation, λ is the penalty coefficient, t0 and t f are the starting point and end point of the time interval respectively;

[0042] Based on the regression model and production objective function, an energy allocation optimization model is established. The linear programming algorithm is used to dynamically adjust the energy allocation of each device, and the energy allocation plan is output with the purpose of minimizing total energy consumption and maximizing energy efficiency. The expression is:

[0043]

[0044] Among them, Z is the total optimization target, the total energy consumption of each device under the optimal energy efficiency, E k (t) is the energy consumption of the kth device, η k (t) is the energy efficiency of the kth device.

[0045] As a preferred solution of the energy audit and optimization method for the production period of a smart power plant described in the present invention, wherein: the audit of the energy usage data after the implementation of the plan is to obtain energy usage data from various equipment and production links after the smart power plant implements the energy allocation plan, and compare and analyze the data with the prediction results of the optimization model;

[0046] By matching the same time period and equipment category, the difference between the current energy consumption and the energy consumption predicted by the optimization model is calculated, the energy usage changes of each production link after the optimization scheme is implemented are quantified, the specific increase or decrease in energy consumption is determined, and whether the expected energy efficiency improvement goals are met is analyzed;

[0047] When the expected energy efficiency improvement target is not met, the production link or equipment with deviation is marked, the potential reasons for the energy efficiency failure are analyzed, and correction suggestions are generated. The correction suggestions are compared with the original energy allocation plan, and the relevant optimization parameters or strategies are adjusted to form a new energy allocation plan. The adjusted energy allocation plan is re-implemented, and the audit and comparative analysis process is repeated until the energy efficiency improvement target is met or the upper limit condition of the optimization adjustment is reached;

[0048] When the expected energy efficiency improvement target is met, an energy audit report is output, recording the comparative analysis results of energy use and storing them in a structured manner in the database.

[0049] Another purpose of the present invention is to provide a smart power plant production period energy audit and optimization system, which can realize real-time energy management of each production link of the power plant by integrating data collection, preprocessing, multi-dimensional analysis, dynamic optimization and energy audit modules, and can automatically collect and process real-time energy data, combine multi-dimensional analysis models to conduct comprehensive evaluation and dynamic optimization of energy consumption, and automatically generate energy audit reports through continuous audit and feedback mechanisms to ensure the efficiency and stability of energy use. The system effectively solves the problems of low energy management efficiency, inability to dynamically adjust and lack of multi-dimensional analysis capabilities in the prior art, and improves the overall energy efficiency and economy of smart power plants.

[0050] In order to solve the above technical problems, the present invention provides the following technical solutions: a smart power plant production period energy audit and optimization system, comprising: a data acquisition module, a data preprocessing module, a multi-dimensional analysis and modeling module, a dynamic optimization and control module, and an energy audit and report generation module;

[0051] The data acquisition module collects various energy-related data in real time from various production links of the smart power plant;

[0052] The data preprocessing module cleans and removes noise, normalizes, detects outliers, and interpolates and fills in missing data to standardize the collected raw data;

[0053] The multi-dimensional analysis and modeling module classifies and aggregates energy data by time, equipment type and energy type, and generates a time series diagram and a spatial distribution diagram of energy consumption. Based on the analysis results, a regression model of energy consumption is constructed, and a production objective function is set to predict energy distribution under different production conditions.

[0054] The dynamic optimization and control module is based on the output of the multi-dimensional analysis and modeling module, uses an optimization algorithm to dynamically adjust the energy allocation of each device to minimize the total energy consumption and maximize energy efficiency. During the production process, the deviation between the actual energy consumption and the predicted energy consumption is monitored in real time, and the parameters and strategies of the optimization model are adjusted according to the feedback;

[0055] The energy audit and report generation module audits the energy usage data after the implementation of the optimization plan, compares and analyzes the actual energy consumption with the predicted results of the optimization model, and generates an energy audit report, which records the details of energy usage, difference analysis results, and an evaluation of the optimization effect, and stores this information in a structured manner in a database.

[0056] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for energy audit and optimization during the production period of a smart power plant are implemented.

[0057] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for energy audit and optimization during the production period of a smart power plant.

[0058] Beneficial effects of the present invention: The present invention adopts a multi-dimensional analysis method to effectively identify abnormal points of energy consumption and optimization potential areas; by constructing a regression model and a production objective function, the energy distribution of each device is dynamically adjusted to maximize energy efficiency output and minimize energy consumption.

[0059] The present invention also generates detailed audit reports through a continuous energy audit and feedback mechanism, which can promptly discover and correct situations where energy efficiency does not meet standards, ensuring that the optimal state of energy use is continuously maintained, thereby significantly improving the energy efficiency management level and overall operational benefits of the smart power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0061] Figure 1 An overall flow chart of a smart power plant production period energy audit and optimization method provided for the first embodiment of the present invention;

[0062] Figure 2 A structural diagram of a smart power plant production period energy audit and optimization system provided for the second embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0064] Example 1, reference Figure 1 As an embodiment of the present invention, a method for energy audit and optimization during production period of a smart power plant is provided, comprising:

[0065] Use sensors to collect energy data from each production link of the smart power plant in real time and perform preprocessing;

[0066] Perform multi-dimensional analysis based on pre-processed data and generate a preliminary energy consumption analysis report;

[0067] Based on the analysis results, combined with historical data and production goals, the energy use strategy is dynamically optimized to generate the optimal energy allocation and use plan;

[0068] Audit the energy usage data after the implementation of the plan, generate a detailed energy audit report, and compare it with historical data to evaluate the optimization effect.

[0069] Real-time collection of energy data including electrical energy data, fuel consumption data, thermal energy data, equipment operation data and environmental data;

[0070] Perform preliminary screening of the collected raw data, filter out outliers and incomplete records, use smoothing algorithms to denoise the data, eliminate outlier data points, and use interpolation methods to fill in missing data. Unify the dimensions of different types of data, convert all energy data into the same unit, and eliminate differences between different magnitudes through normalization.

[0071] Perform timestamp alignment on preprocessed data, synchronize data with different sampling frequencies through interpolation technology, set upper and lower limits and change rates of preprocessed data, detect and remove abnormal data points that exceed the set range, store the cleaned and processed data in a structured manner in the database, and back up them regularly.

[0072] The preprocessed data is aggregated by time periods (such as minutes, hours, days, and months). For example, the electricity consumption data per minute is summarized into the total consumption per hour. The data is classified by equipment type and energy type, and the fuel consumption data of all boilers are classified into one category and the electricity consumption data of all generators are classified into another category to ensure clear classification of data on different equipment and energy types.

[0073] Through data aggregation and classification, the sorted data will be used to draw a time series graph to help identify the changing trends over time and the energy consumption of each device, laying the foundation for the next step of time dimension analysis.

[0074] Use the aggregated data to draw a time series graph of energy consumption, showing the energy consumption change curve in different time periods, mark the time points of the maximum and minimum energy consumption in the time series graph, and determine the peak and trough periods of energy consumption;

[0075] Combined with the results of the time dimension analysis, analyze the equipment that consumes the most energy during peak periods and calculate its efficiency per unit of energy output, such as the amount of fuel consumed per kilowatt-hour of electricity. Analyze the equipment that still maintains high energy consumption during off-peak periods to check whether these equipment have problems with inefficient operation. Compare the energy consumption performance of different equipment under the same conditions to identify less efficient equipment that may need optimization or maintenance. Through the equipment dimension analysis, the inefficient equipment or high-energy-consuming equipment identified will be used for spatial dimension analysis to determine whether the area where these equipment is located has a problem of excessive overall energy consumption.

[0076] Based on the peak and trough time points marked in the time series graph, the energy consumption of each device in the time period is counted, the energy consumption of the device in the peak and trough periods is calculated, and the energy efficiency is evaluated;

[0077] The energy consumption data of the equipment will be associated with the physical location to generate a spatial distribution map of energy consumption, showing the energy consumption of each area in the power plant;

[0078] Based on the spatial distribution map, identify hot spots where energy consumption is concentrated and analyze whether the equipment or operating processes in the area need further optimization;

[0079] Conduct correlation analysis between environmental data and energy consumption data, calculate the impact coefficient of environmental factors on energy consumption, identify energy consumption anomalies under extreme environmental conditions, and preliminarily generate an energy consumption analysis report.

[0080] It is further explained that:

[0081] The aggregation of time periods clearly shows that the data is aggregated by time period and then classified by device type and energy type, ensuring that the data is reasonably organized in the subsequent analysis. The changes in energy consumption are shown by drawing a time series graph, and the peak and trough periods are identified by marking the maximum and minimum values. Based on the key time points in the time series, the energy consumption of the equipment is calculated and its efficiency is evaluated, which clearly shows how time dimension analysis can be directly applied to the energy consumption evaluation of the equipment.

[0082] The spatial distribution map is generated by associating the equipment energy consumption data with the physical location to generate a spatial distribution map of the power plant's energy consumption, and on this basis, energy consumption hotspots are identified to analyze whether further optimization is needed.

[0083] Conduct correlation analysis between environmental data and energy consumption data, further calculate the impact of environmental factors on energy consumption, and identify energy consumption anomalies under extreme conditions, to ensure that the report content not only covers current data, but also takes into account the impact of external environmental factors.

[0084] Finally, through the above analysis steps, a preliminary energy consumption analysis report is generated to provide data support and decision-making basis for subsequent optimization.

[0085] Dynamically optimize the energy usage strategy and generate the optimal energy allocation and usage plan based on the analysis results in the preliminary energy consumption analysis report, combined with historical data for the same period for comparative analysis, identify the difference between current energy consumption and historical consumption, determine the historical trend of energy consumption, identify historical change points and conduct correlation analysis with production events;

[0086] Construct a production objective function and fit it with historical energy consumption data to predict the energy distribution under different production conditions. Based on the regression model and production objective function, establish an energy distribution optimization model, and use a linear programming algorithm to dynamically adjust the energy distribution of each device to minimize total energy consumption and maximize energy efficiency.

[0087] The production objective function includes the gas turbine and steam turbine coupling model, the boiler and condenser thermal model, the power network model, and the model of the impact of environmental factors on equipment operation;

[0088] The gas turbine and steam turbine coupling model is expressed as:

[0089]

[0090] Among them, η GT is the gas turbine efficiency, is the fuel flow rate, LHV fuel is the lower calorific value of the fuel, P GT is the power output of the gas turbine, is the exhaust gas flow rate, C p is the specific heat capacity of the exhaust gas, T exhaust is the exhaust gas temperature, T amb is the ambient temperature, η ST is the steam turbine efficiency, is the steam flow rate, Δh is the steam enthalpy difference, P ST is the power output of the steam turbine;

[0091] The thermal model of the boiler and condenser is expressed as:

[0092]

[0093] in, is the heat output of the boiler, C p is the specific heat capacity of water, is the water flow rate in the boiler, T out and T in are the outlet and inlet temperatures of the boiler, is the heat absorbed by the condenser, is the steam flow rate, Δh condensation is the condensation enthalpy difference of steam;

[0094] The power network model is expressed as:

[0095]

[0096] Among them, P ij is the active power from node i to node j, V i ,V j is the voltage amplitude between node i and node j, X ij is the reactance between node i and node j, θ i ,θ j are the voltage phase angles at node i and node j respectively;

[0097] The impact model of environmental factors on equipment operation is expressed as:

[0098] η GT =η0·(1-k·(T in -T ref ))

[0099] Among them, η GT is the gas turbine efficiency, η0 is the gas turbine efficiency at the reference temperature T ref Baseline efficiency under T in is the intake air temperature, T ref is the reference temperature, and k is the coefficient of the effect of temperature change on efficiency.

[0100] It is further explained that:

[0101] Constructing the production objective function and fitting it with the historical energy consumption data to predict the energy distribution under different production conditions is to construct a regression model of energy consumption, which is expressed as:

[0102]

[0103] Where E(t) is the total energy consumption at time t, β0 is a constant term, and X k (t) is the operating parameter of the equipment at time t, including is the fuel flow rate of the gas turbine, is the steam flow rate of the steam turbine, is the water flow rate in the boiler, is the exhaust gas flow rate, β k is the regression coefficient corresponding to each operating parameter, P ij (t) is the power transmitted at time t, including P ij (t) is the power transferred from node i to node j at time t, V i (t) and V j (t) are the voltages of node i and node j at time t, respectively, X ij is the inter-node reactance, θ i (t) and θ j (t) are the voltage phase angles between nodes at time t,

[0104] γ i is the regression coefficient corresponding to each power transmission power, δ is the regression coefficient of ambient temperature, ∈ is the error term, T evn (t) is the effect of ambient temperature at time t, including T exhaust (t) is the exhaust gas temperature, T amb (t) is the ambient temperature, γ i is the regression coefficient of electric power transmission power;

[0105] Construct the production objective function, the expression is:

[0106]

[0107] Among them, η sys (t) is the comprehensive efficiency, C op (t) is the energy and maintenance cost during operation, λ is the penalty coefficient, t0 and t f are the starting point and end point of the time interval respectively;

[0108] Based on the regression model and production objective function, the energy allocation optimization model is established, and the expression is:

[0109]

[0110] Among them, t0, t f They are the integration start time and the integration end time, that is, the time when the energy allocation strategy starts to be implemented and the time when the energy allocation strategy ends or is re-evaluated.

[0111] It should be further noted that in energy allocation optimization models, the focus is usually on minimizing energy consumption and operating costs by adjusting parameters. The error term ∈ simply represents the random noise predicted by the model, and assuming that these noises are independent and well-distributed, that is, they do not have a systematic impact on the optimization results, then the error term is usually not added separately in the optimization objective.

[0112] Optimization algorithms usually deal with the structural part of the model and optimize system performance by adjusting controllable parameters. Error terms are random and not controllable variables in the optimization process. Therefore, they can be regarded as background noise and are not directly included in the optimization target. Introducing error terms will increase the complexity of the optimization model. If the impact of the error term on the optimization result is negligible, retaining it may increase the computational complexity without actual optimization value.

[0113] The linear programming algorithm is used to dynamically adjust the energy allocation of each device, and the energy allocation plan is output with the purpose of minimizing total energy consumption and maximizing energy efficiency. The expression is:

[0114]

[0115] Among them, Z is the total optimization target, the total energy consumption of each device under the optimal energy efficiency, E k (t) is the energy consumption of the kth device, η k (t) is the energy efficiency of the kth device.

[0116] After implementing the energy allocation plan in the smart power plant, energy usage data is obtained from each equipment and production link, and the data is compared and analyzed with the prediction results of the optimization model;

[0117] By matching the same time period and equipment category, the difference between the current energy consumption and the energy consumption predicted by the optimization model is calculated, the energy usage changes of each production link after the optimization scheme is implemented are quantified, the specific increase or decrease in energy consumption is determined, and whether the expected energy efficiency improvement goals are met is analyzed;

[0118] When the expected energy efficiency improvement target is not met, the production link or equipment with deviation is marked, the potential reasons for the energy efficiency failure are analyzed, and correction suggestions are generated. The correction suggestions are compared with the original energy allocation plan, and the relevant optimization parameters or strategies are adjusted to form a new energy allocation plan. The adjusted energy allocation plan is re-implemented, and the audit and comparative analysis process is repeated until the energy efficiency improvement target is met or the upper limit condition of the optimization adjustment is reached;

[0119] When the expected energy efficiency improvement target is met, an energy audit report is output, recording the comparative analysis results of energy use and storing them in a structured manner in the database.

[0120] Example 2, reference Figure 2 , which is an embodiment of the present invention, provides a system for energy audit and optimization method during the production period of a smart power plant, including: a data acquisition module, a data preprocessing module, a multi-dimensional analysis and modeling module, a dynamic optimization and control module, and an energy audit and report generation module.

[0121] The data acquisition module collects various energy-related data in real time from each production link of the smart power plant.

[0122] The data preprocessing module cleans and denoises the collected raw data, normalizes it, detects outliers, and interpolates and fills in missing data for standardization.

[0123] The multi-dimensional analysis and modeling module classifies and aggregates energy data by time, equipment type and energy type, and generates time series graphs and spatial distribution graphs of energy consumption. Based on the analysis results, a regression model of energy consumption is constructed, and the production objective function is set to predict energy distribution under different production conditions.

[0124] The dynamic optimization and control module is based on the output of the multi-dimensional analysis and modeling module. It uses an optimization algorithm to dynamically adjust the energy distribution of each device to minimize total energy consumption and maximize energy efficiency. During the production process, it monitors the deviation between actual energy consumption and predicted energy consumption in real time, and adjusts the parameters and strategies of the optimization model based on feedback.

[0125] The energy audit and report generation module audits the energy usage data after the implementation of the optimization plan, compares and analyzes the actual energy consumption with the predicted results of the optimization model, and generates an energy audit report that records the details of energy usage, difference analysis results, and an evaluation of the optimization effect, and stores this information in a structured manner in the database.

[0126] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0127] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0128] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0129] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0130] Embodiment 3: In this embodiment, in order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments. This embodiment experiments the existing traditional method and the method of this embodiment respectively.

[0131] The environment of this simulation experiment is based on the production process of a smart power plant. The experiment simulates the energy usage of various equipment in the power plant, including core equipment such as gas turbines, steam turbines, boilers, and power distribution systems. The experiment uses an integrated energy management system that can collect energy consumption data, environmental data, and equipment operating status data of each device in real time, and perform dynamic optimization and energy auditing. The experiment will verify the beneficial effects of the present invention in improving energy efficiency, reducing energy consumption, and reducing resource waste by comparing traditional energy management methods with the energy audit and optimization method for smart power plants proposed in the present invention.

[0132] In this experiment, the traditional energy management method is defined as a static energy management method based on a fixed energy allocation strategy. This method mainly relies on historical experience and manual scheduling, and lacks a dynamic analysis and feedback mechanism for real-time data. Specifically, the traditional method does not consider real-time environmental changes and dynamic adjustments to equipment status. It only sets fixed energy allocation parameters at the beginning of production and conducts static energy consumption analysis by regularly manually auditing energy usage. Although this method is simple and easy to implement, it has obvious limitations and is difficult to adapt to the complex and changeable production environment of modern smart power plants.

[0133] Semi-automatic management method: In this method, the power plant monitors the operating status and energy consumption of the equipment through regular automated data collection, but still relies mainly on fixed energy allocation strategies. Although part of the data collection and monitoring process is automated, the process of adjusting energy allocation and handling energy consumption anomalies is still done manually. This method is an improvement over the traditional fully manual method, but due to the lack of a dynamic optimization mechanism, it still cannot adapt to the rapidly changing production environment and is difficult to maximize its effectiveness in energy efficiency management.

[0134] Table 1 Data comparison table

[0135]

[0136] It can be seen from the updated experimental data comparison table that the smart power plant energy audit and optimization method proposed in the present invention is significantly superior to the traditional static management method and semi-automatic management method in many aspects. In terms of energy distribution, both the traditional static management and semi-automatic management methods adopt fixed strategies. Although the semi-automatic management method adds some automated monitoring functions, its energy distribution still lacks flexibility. Through the dynamic optimization strategy, the present invention can adjust the energy distribution of each device in real time, better adapt to changes in the production environment, and significantly improve the efficiency of energy use.

[0137] In terms of data collection frequency, the static management method has a collection frequency of once an hour, which is obviously lagging behind. Although the semi-automatic management method increases the collection frequency, it still cannot compare with the real-time collection of the present invention. The present invention can collect data in real time and directly use this data for dynamic optimization and energy auditing, ensuring that energy management decisions are based on the latest production conditions and environmental conditions.

[0138] Regarding environmental data, traditional methods and semi-automatic management methods usually ignore the impact of environmental factors, while the present invention incorporates environmental data such as temperature and humidity into the optimization model, further improving energy efficiency.

[0139] The experimental results show that under the same production conditions, the average daily energy consumption of the power plant using the method of the present invention is 108,000 kWh, which is 10% and 6% lower than the static management method and the semi-automatic management method respectively; at the same time, the energy efficiency is increased to 92%, which is 7 and 5 percentage points higher than the traditional method and the semi-automatic management method respectively. In addition, the method of the present invention can detect energy consumption anomalies in real time and generate energy audit reports in a timely manner, while the traditional method and the semi-automatic management method are significantly lagging behind in this regard, resulting in more waste of resources and longer response time to failures.

[0140] In summary, the present invention not only significantly reduces the energy consumption and resource waste of power plants through real-time data collection, dynamic optimization and continuous auditing, but also greatly improves energy efficiency and shortens fault response time, thereby greatly improving the overall operational efficiency of smart power plants. Compared with traditional static management methods and semi-automatic management methods, the present invention shows obvious technical advantages and is suitable for application in the energy management system of modern smart power plants.

[0141] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for energy audit and optimization during the production period of a smart power plant, characterized in that: include: Use sensors to collect energy data from each production link of the smart power plant in real time and perform preprocessing; Perform multi-dimensional analysis based on pre-processed data and generate a preliminary energy consumption analysis report; Based on the analysis results, combined with historical data and production goals, the energy use strategy is dynamically optimized to generate the optimal energy allocation and use plan; Audit the energy usage data after the implementation of the plan, generate a detailed energy audit report, and compare it with historical data to evaluate the optimization effect.

2. The method for energy audit and optimization during production period of a smart power plant according to claim 1, characterized in that: The real-time collected energy data includes electric energy data, fuel consumption data, thermal energy data, equipment operation data and environmental data; The preprocessing is to perform preliminary screening on the collected raw data, filter out abnormal values ​​and incomplete records, use a smoothing algorithm to denoise the data, eliminate abnormal data points, and use an interpolation method to fill in the missing data, unify the dimensions of different types of data, convert all energy data into the same unit, and eliminate the differences between different magnitudes through normalization; Perform timestamp alignment on preprocessed data, synchronize data with different sampling frequencies through interpolation technology, set upper and lower limits and change rates of preprocessed data, detect and remove abnormal data points that exceed the set range, store the cleaned and processed data in a structured manner in the database, and back up them regularly.

3. The method for energy audit and optimization during production period of a smart power plant according to claim 2, characterized in that: The multi-dimensional analysis is to aggregate the pre-processed energy data by time period and classify them by equipment type and energy type; Use the aggregated data to draw a time series graph of energy consumption, showing the energy consumption change curve in different time periods, mark the time points of the maximum and minimum energy consumption in the time series graph, and determine the peak and trough periods of energy consumption; Based on the peak and trough time points marked in the time series graph, the energy consumption of each device in the time period is counted, the energy consumption of the device in the peak and trough periods is calculated, and the energy efficiency is evaluated; The energy consumption data of the equipment will be associated with the physical location to generate a spatial distribution map of energy consumption, showing the energy consumption of each area in the power plant; Based on the spatial distribution map, identify hot spots where energy consumption is concentrated and analyze whether the equipment or operating processes in the area need further optimization; Conduct correlation analysis between environmental data and energy consumption data, calculate the impact coefficient of environmental factors on energy consumption, identify energy consumption anomalies under extreme environmental conditions, and preliminarily generate an energy consumption analysis report.

4. The method for energy audit and optimization during production period of a smart power plant according to claim 3, characterized in that: The dynamic optimization of the energy usage strategy to generate the optimal energy allocation and usage plan is based on the analysis results in the preliminary generated energy consumption analysis report, combined with historical data for the same period for comparative analysis, identifying the difference between current energy consumption and historical consumption, determining the historical trend of energy consumption, identifying historical change points and correlating them with production events; Construct a production objective function and fit it with historical energy consumption data to predict the energy distribution under different production conditions. Based on the regression model and production objective function, establish an energy distribution optimization model, and use a linear programming algorithm to dynamically adjust the energy distribution of each device to minimize total energy consumption and maximize energy efficiency.

5. The method for energy audit and optimization during production period of a smart power plant according to claim 4, characterized in that: The production objective function includes a gas turbine and steam turbine coupling model, a boiler and condenser thermal model, a power network model, and a model of the impact of environmental factors on equipment operation; The gas turbine and steam turbine coupling model is expressed as: Among them, η GT is the gas turbine efficiency, is the fuel flow rate, LHV fuel is the lower calorific value of the fuel, P GT is the power output of the gas turbine, is the exhaust gas flow rate, C p is the specific heat capacity of the exhaust gas, T exhaust is the exhaust gas temperature, T amb is the ambient temperature, η ST is the steam turbine efficiency, is the steam flow rate, △h is the steam enthalpy difference, P ST is the power output of the steam turbine; The thermal model of the boiler and condenser is expressed as: in, is the heat output of the boiler, C p is the specific heat capacity of water, is the water flow rate in the boiler, T out and T in are the outlet and inlet temperatures of the boiler, is the heat absorbed by the condenser, is the steam flow rate, △h condensation is the condensation enthalpy difference of steam; The power network model is expressed as: Among them, P ij is the active power from node i to node j, V i , V j is the voltage amplitude between node i and node j, X ij is the reactance between node i and node j, θ i ,θ j are the voltage phase angles at node i and node j respectively; The impact model of environmental factors on equipment operation is expressed as: or GT =η0·(1-k·(T in -T ref )) Among them, η GT is the gas turbine efficiency, η0 is the gas turbine efficiency at the reference temperature T ref Baseline efficiency under T in is the intake air temperature, T ref is the reference temperature, and k is the coefficient of the effect of temperature change on efficiency.

6. A method for energy audit and optimization during production period of a smart power plant as claimed in claim 5, characterized in that: The construction of the production target function is fitted with the historical energy consumption data to predict the energy distribution under different production conditions, which is to construct a regression model of energy consumption, and the expression is: Where E(t) is the total energy consumption at time t, β0 is a constant term, and X k (t) is the operating parameter of the equipment at time t, β k is the regression coefficient corresponding to each operating parameter, P ij (t) is the power transmitted at time t, γ i is the regression coefficient corresponding to each power transmission power, δ is the regression coefficient of ambient temperature, ∈ is the error term, T evn (t) is the effect of ambient temperature at time t, γ i is the regression coefficient of electric power transmission power; Construct the production objective function, the expression is: Among them, η sys (t) is the comprehensive efficiency, C op (t) is the energy and maintenance cost during operation, λ is the penalty coefficient, t0 and t f are the starting point and end point of the time interval respectively; Based on the regression model and production objective function, an energy allocation optimization model is established. The linear programming algorithm is used to dynamically adjust the energy allocation of each device, and the energy allocation plan is output with the purpose of minimizing total energy consumption and maximizing energy efficiency. The expression is: Among them, Z is the total optimization target, the total energy consumption of each device under the optimal energy efficiency, E k (t) is the energy consumption of the kth device, η k (t) is the energy efficiency of the kth device.

7. A method for energy audit and optimization during production period of a smart power plant according to claim 6, characterized in that: The audit of energy usage data after the implementation of the plan is to obtain energy usage data from various equipment and production links after the smart power plant implements the energy allocation plan, and compare and analyze the data with the prediction results of the optimization model; By matching the same time period and equipment category, the difference between the current energy consumption and the energy consumption predicted by the optimization model is calculated, the energy usage changes of each production link after the optimization scheme is implemented are quantified, the specific increase or decrease in energy consumption is determined, and whether the expected energy efficiency improvement goals are met is analyzed; When the expected energy efficiency improvement target is not met, the production link or equipment with deviation is marked, the potential reasons for the energy efficiency failure are analyzed, and correction suggestions are generated. The correction suggestions are compared with the original energy allocation plan, and the relevant optimization parameters or strategies are adjusted to form a new energy allocation plan. The adjusted energy allocation plan is re-implemented, and the audit and comparative analysis process is repeated until the energy efficiency improvement target is met or the upper limit condition of the optimization adjustment is reached; When the expected energy efficiency improvement target is met, an energy audit report is output, recording the comparative analysis results of energy use and storing them in a structured manner in the database.

8. A system using a smart power plant production period energy audit and optimization method as claimed in any one of claims 1 to 7, characterized in that: It includes data acquisition module, data preprocessing module, multi-dimensional analysis and modeling module, dynamic optimization and control module, and energy audit and report generation module; The data acquisition module collects various energy-related data in real time from various production links of the smart power plant; The data preprocessing module cleans and removes noise, normalizes, detects outliers, and interpolates and fills in missing data to standardize the collected raw data; The multi-dimensional analysis and modeling module classifies and aggregates energy data by time, equipment type and energy type, and generates a time series diagram and a spatial distribution diagram of energy consumption. Based on the analysis results, a regression model of energy consumption is constructed, and a production objective function is set to predict energy distribution under different production conditions. The dynamic optimization and control module is based on the output of the multi-dimensional analysis and modeling module, uses an optimization algorithm to dynamically adjust the energy allocation of each device to minimize the total energy consumption and maximize energy efficiency. During the production process, the deviation between the actual energy consumption and the predicted energy consumption is monitored in real time, and the parameters and strategies of the optimization model are adjusted according to the feedback; The energy audit and report generation module audits the energy usage data after the implementation of the optimization plan, compares and analyzes the actual energy consumption with the predicted results of the optimization model, and generates an energy audit report, which records the details of energy usage, difference analysis results, and an evaluation of the optimization effect, and stores this information in a structured manner in a database.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a smart power plant production period energy audit and optimization method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a smart power plant production period energy audit and optimization method as described in any one of claims 1 to 7 are implemented.

Images