Frequency modulation instruction distribution method for super-capacity electric storage in consideration of service life of unit
By combining artificial immune algorithms and quantum computing technology, the frequency modulation instruction allocation strategy is optimized, and the problems of unreasonable frequency modulation instruction allocation and short unit life in the existing technology are solved, achieving more efficient frequency modulation effects and longer equipment life.
Patent Information
- Application Number
- CN202411407555.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-10
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing frequency regulation strategy cannot fully consider the unit life, resulting in unreasonable frequency regulation instruction allocation, low frequency regulation efficiency, and short unit life, which affects the stable operation of the power grid and the service life of energy storage equipment.
Combining artificial immune algorithms and quantum computing technology, life management is carried out through self-organized mapping neural networks (SOM), frequency modulation instruction allocation strategy is optimized, quantum computing is used for parallel optimization, global optimal solution is found, and frequency modulation instruction allocation is optimized to extend the life of the unit.
It improves the rationality and efficiency of frequency modulation instruction allocation, extends the service life of ultra-capacitance electrical storage equipment, reduces maintenance costs, and improves the frequency modulation efficiency and stability of the power grid.
Smart Images

Figure CN118920516A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of frequency regulation instruction allocation for power plants, and in particular to a frequency regulation instruction allocation method for super-capacity power storage taking into account the life of a unit. Background Art
[0002] With the continuous development of the power system and the large-scale access of renewable energy, the demand for frequency regulation of the power grid is increasing. As a new type of energy storage technology, ultra-capacity energy storage has gradually become an important means of power grid frequency regulation due to its characteristics of rapid response and efficient energy storage. However, the existing frequency regulation strategies still have many problems in practical applications, such as the failure to fully consider the life of the unit, unreasonable allocation of frequency regulation instructions, and low frequency regulation efficiency. These problems not only affect the stable operation of the power grid, but also lead to excessive loss of energy storage equipment and shorten its service life. Therefore, how to optimize the frequency regulation instruction allocation strategy of ultra-capacity energy storage to improve the frequency regulation effect and extend the life of the unit has become a technical problem that needs to be solved urgently. Summary of the invention
[0003] In view of the above existing problems, the present invention is proposed.
[0004] Therefore, the present invention combines artificial immune algorithm and quantum computing technology to effectively solve the problems of unreasonable frequency modulation instruction allocation, low frequency modulation efficiency, short unit life and so on in the prior art.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for allocating frequency modulation instructions of super-capacity power storage considering the life of the unit, comprising: Collect multi-dimensional data of unit operation, pre-process the collected data, and input the processed data into the self-organizing map neural network SOM for training; based on the pre-processed data, use the self-organizing map neural network SOM for life management, input the pre-processed multi-dimensional data into the SOM network, the SOM network maps the high-dimensional data to a two-dimensional plane through competitive learning, and classifies the life status of the unit according to the feature map output by the SOM network; combine the artificial immune algorithm to optimize the frequency modulation instruction allocation strategy, generate an initial antibody group, each antibody represents a frequency modulation strategy, calculate the fitness of each antibody, evaluate it according to the frequency modulation effect, select antibodies for cloning, and generate new antibodies through mutation. The selected antibodies enter the next generation, and repeat the fitness evaluation, cloning, mutation and selection process until the optimal frequency modulation instruction allocation strategy is found; apply quantum computing for optimization, model the frequency modulation instruction allocation problem as an optimization problem, define the objective function and constraints, select the quantum algorithm, perform parallel computing, deploy the optimization algorithm on the quantum computing platform, perform iterative optimization, and find the global optimal solution.
[0006] As a preferred solution of the method for allocating frequency modulation instructions for supercapacitor storage taking into account the life of the unit as described in the present invention, the multi-dimensional data collected from the operation of the unit includes temperature, vibration, pressure, operating time, current, voltage and power factor parameters, which are collected in real time through temperature sensors, vibration sensors, pressure sensors, current sensors, voltage sensors and power factor sensors, and stored in a database.
[0007] As a preferred solution of the frequency modulation instruction allocation method of the ultra-capacity power storage considering the life of the unit described in the present invention, the preprocessing includes Gaussian filtering of each sample, calculating the preprocessed data by integration, and normalizing each dimension of each sample to obtain a normalized comprehensive index, averaging the comprehensive index of each sample to obtain a normalized final comprehensive index, which is as follows: ; in, is the final normalized comprehensive index, used as the input of the SOM model. is the sample size; is the input data vector of the i-th sample; are the upper and lower limits of the integral; is the preprocessed data function; is the Gaussian filter function, where is the standard deviation; is the number of data dimensions; is the j-th dimension data of the i-th sample; is the mean of the data in the jth dimension; is the standard deviation of the data in the jth dimension; is the kernel function of the data, where For reference data.
[0008] As a preferred solution of the frequency modulation instruction allocation method of the super-capacity power storage considering the life of the unit described in the present invention, wherein: the use of the self-organizing map neural network SOM for life management includes bringing Φ as input data into the life management model, calculating the distance between the weight vector of the SOM network and the sample data vector, using an exponential function for weighting, and obtaining the life management model, and obtaining the final life management index Ψ through comprehensive calculation of all samples: ; in, is the comprehensive index of the i-th sample; is the standard deviation of the i-th sample; is the mean of the i-th sample; is the comprehensive index of the jth dimension of the i-th sample; is the mean of the data in the jth dimension; is the standard deviation of the data in the jth dimension; is the weight vector of the jth neuron in the SOM network; is the vector of the i-th sample; is the learning rate parameter of the SOM network.
[0009] As a preferred solution of the frequency modulation instruction allocation method of the super-capacity storage considering the life of the unit described in the present invention, wherein: the classification of the life status of the unit includes: If Ψ≤0.3, the unit is in normal condition; when the unit is in normal condition, the unit is fully lubricated once a quarter, all fasteners are checked and re-tightened, all exposed mechanical parts and electrical connectors are cleaned, sensors and control systems are adjusted and calibrated, key parameters are continuously monitored, including temperature, vibration and current, and data is recorded once an hour using a remote monitoring system, and alarm thresholds are set; when parameters reach the threshold, maintenance personnel are immediately notified to conduct on-site inspections; If 0.3<Ψ≤0.6, the unit is in a mild warning state; when the unit is in a mild warning state, increase the inspection frequency to once a week, and the inspection content includes measuring and recording the wear of key components; the wear of key components includes the wear degree of bearings, gears and brushes; use vibration analyzers and infrared thermal imagers for detection, and perform preventive maintenance, replace filters and seals, calibrate equipment, adjust operating parameters according to monitoring data, reduce load operation time and increase no-load operation time, reduce mechanical stress and thermal stress of the unit, and ensure stable operation in a mild warning state; If 0.6<Ψ≤0.8, the unit is in a moderate warning state; when the unit is in a moderate warning state, it is necessary to disassemble and inspect all mechanical parts, check the connectivity and insulation of electrical wiring, detect the response time and accuracy of the control system, replace all worn parts, clean the cooling system and replace the coolant, re-lubricate all moving parts, reduce continuous operation time, increase intermittent rest time, adjust the operation strategy, and increase the monitoring frequency to once every half hour to ensure that potential problems are discovered and handled in a timely manner; If 0.8<Ψ≤1.0, the unit is in a severe warning state; when the unit is in a severe warning state, a comprehensive inspection shall be immediately carried out, including a detailed inspection of all mechanical, electrical and control systems, detection using a spectrum analyzer and a real-time monitoring system, and professional technicians shall be arranged to carry out centralized maintenance, fully dismantle and inspect components, repair or replace damaged components, reassemble and calibrate the system, strengthen operation monitoring, monitor key parameters in real time, and record data every 15 minutes; If Ψ>1.0, the unit is in a faulty state; when the unit is in a faulty state, it is necessary to shut down immediately and conduct a comprehensive fault diagnosis, using the Fault Tree Analysis (FTA) and Failure Mode and Effects Analysis (FMEA) to determine the cause of the fault; based on the diagnosis results, repair or replace the faulty parts, and after repair or replacement, conduct operation verification, including load testing, performance testing, and safety inspections, to ensure that all systems return to normal operation, and re-evaluate and update the maintenance plan.
[0010] As a preferred solution of the frequency modulation instruction allocation method of the super-capacity storage considering the life of the unit described in the present invention, wherein: the optimization of the frequency modulation instruction allocation strategy in combination with the artificial immune algorithm includes generating an initial antibody group: , in, is the number of antibodies, For the i-th antibody, i=1,2,…,L. Perform fitness calculation and define the fitness function as: ; Where T is the number of frequency modulation strategies, is the kth frequency modulation strategy effect value of the antibody, is the mean value of the kth frequency modulation strategy, is the standard deviation of the kth frequency modulation strategy, is the weight of the kth FM strategy.
[0011] As a preferred solution of the frequency modulation instruction allocation method of the super-capacity power storage considering the life of the unit described in the present invention, wherein: the optimization of the frequency modulation instruction allocation strategy in combination with the artificial immune algorithm includes cloning and mutation, selecting high-fitness antibodies in the clones and mutating them: .
[0012] Perform mutation operations: , in, is the variation that follows Gaussian distribution; is the ith antibody.
[0013] Antibodies with fitness higher than the preset standard are selected to enter the next generation, and antibodies with fitness lower than the preset standard are eliminated: .
[0014] Repeat the fitness calculation, cloning, mutation, and selection process until the stopping condition is met: , in, is the set convergence threshold, is the number of iterations, is the number of antibodies.
[0015] As a preferred solution of the frequency modulation instruction allocation method of the ultra-capacitive power storage considering the life of the unit described in the present invention, wherein: the optimization by applying quantum computing includes two parts, the first part is the square error and the weight term, and the second part is the Gaussian function and the regularization term; the objective function is set according to the two parts : ; in, Allocate vectors for frequency modulation instructions, and are the dimensions of the two different parts of the objective function, is the weight, is the mean, is the regularization parameter, is the weight of the second part, is the parameter mean, is the standard deviation.
[0016] Select the quantum annealing algorithm and define the Hamiltonian : , in, and are the expected values of quantum bits respectively.
[0017] Perform parallel computing and execute the Hamiltonian minimization process in parallel on the quantum computing platform, using the evolution formula of quantum annealing: , in, and is the corresponding time coefficient, is the initial Hamiltonian, is the Hamiltonian of the problem.
[0018] After iterative optimization, the global optimal solution is found and the optimal solution is used. Update frequency modulation instruction allocation strategy: , in, is the initial antibody group; is the ith antibody; is the fitness of the ith antibody; The antibody population selected for cloning; For the next generation of antibody groups.
[0019] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, steps of a method for allocating frequency modulation instructions for super-capacity power storage that takes into account the life of a unit are implemented.
[0020] 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 method for allocating frequency modulation instructions for super-capacity power storage taking into account the life of a unit are implemented.
[0021] Beneficial effects of the present invention: The present invention proposes a new method for allocating frequency modulation instructions for ultra-capacitor storage by combining artificial immune algorithm and quantum computing technology, which can fully consider the life of the unit and the frequency modulation effect. This method gradually optimizes the frequency modulation strategy through multiple rounds of fitness evaluation, cloning, mutation and selection processes, ensuring the rationality and efficiency of frequency modulation instruction allocation. At the same time, the use of quantum computing for global optimization can find the optimal solution in a wider solution space, further improving the frequency modulation effect. Through the optimized frequency modulation instruction allocation strategy, not only the frequency modulation efficiency and stability of the power grid are improved, but also the service life of the ultra-capacitor storage equipment is significantly extended, and the maintenance cost is reduced. It has important application value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0023] Figure 1 A flow chart of a method for allocating frequency modulation instructions for ultra-capacity power storage taking into account the life of a unit is provided as an embodiment of the present invention. DETAILED DESCRIPTION
[0024] 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.
[0025] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0026] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0027] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.
[0028] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0029] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0030] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a method for allocating frequency modulation instructions of a super-capacity power storage system taking into account the life of a unit, comprising: S1: Collect multi-dimensional data of unit operation and pre-process the collected data.
[0031] The processed data is input into the self-organizing map neural network SOM for training.
[0032] S2: Based on the preprocessed data, a self-organizing map neural network SOM is used for life management.
[0033] The preprocessed multidimensional data is input into the SOM network. The SOM network maps the high-dimensional data to a two-dimensional plane through competitive learning, and classifies the life status of the unit according to the feature map output by the SOM network.
[0034] S3: Optimize the frequency modulation instruction allocation strategy by combining the artificial immune algorithm until the optimal frequency modulation instruction allocation strategy is found.
[0035] Generate an initial population of antibodies, each antibody represents an FM strategy, calculate the fitness of each antibody, evaluate it based on the FM effect, select antibodies for cloning, and generate new antibodies through mutation. The selected antibodies enter the next generation and repeat the fitness evaluation, cloning, mutation and selection process.
[0036] S4: Apply quantum computing for optimization, model the frequency modulation instruction allocation problem as an optimization problem, define the objective function and constraints, select the quantum algorithm, perform parallel computing, deploy the optimization algorithm on the quantum computing platform, perform iterative optimization, and find the global optimal solution.
[0037] The multi-dimensional data collected about the operation of the unit include temperature, vibration, pressure, operation time, current, voltage and power factor parameters, which are collected in real time through temperature sensors, vibration sensors, pressure sensors, current sensors, voltage sensors and power factor sensors, and stored in a database.
[0038] The preprocessing includes performing Gaussian filtering on each sample, calculating the preprocessed data by integration, and normalizing each dimension of each sample to obtain a normalized comprehensive index, averaging the comprehensive index of each sample to obtain a normalized final comprehensive index, as follows: , in, is the final normalized comprehensive index, used as the input of the SOM model. is the sample size; is the input data vector of the i-th sample; are the upper and lower limits of the integral; is the preprocessed data function; is the Gaussian filter function, where is the standard deviation; is the number of data dimensions; is the j-th dimension data of the i-th sample; is the mean of the data in the jth dimension; is the standard deviation of the data in the jth dimension; is the kernel function of the data, where For reference data.
[0039] The use of the self-organizing map neural network SOM for life management includes bringing Φ as input data into the life management model, calculating the distance between the weight vector of the SOM network and the sample data vector, using an exponential function for weighting, and obtaining the life management model. By comprehensive calculation of all samples, the final life management index Ψ is obtained: , in, is the comprehensive index of the i-th sample; is the standard deviation of the i-th sample; is the mean of the i-th sample; is the comprehensive index of the jth dimension of the i-th sample; is the mean of the data in the jth dimension; is the standard deviation of the data in the jth dimension; is the weight vector of the jth neuron in the SOM network; is the vector of the i-th sample; is the learning rate parameter of the SOM network.
[0040] The classification of the life status of the unit includes: if Ψ≤0.3, the unit is in a normal state; when the unit is in a normal state, the unit is fully lubricated once a quarter, all fasteners are checked and retightened, all exposed mechanical parts and electrical connectors are cleaned, sensors and control systems are adjusted and calibrated, key parameters are continuously monitored, including temperature, vibration and current, a remote monitoring system is used to record data once an hour, and an alarm threshold is set; when the parameter reaches the threshold, the maintenance personnel are immediately notified to conduct an on-site inspection.
[0041] If 0.3<Ψ≤0.6, the unit is in a mild warning state; when the unit is in a mild warning state, increase the inspection frequency to once a week, and the inspection content includes measuring and recording the wear of key components; the wear of key components includes the degree of wear of bearings, gears and brushes; use vibration analyzers and infrared thermal imagers for detection, and perform preventive maintenance, replace filters and seals, calibrate equipment, adjust operating parameters according to monitoring data, reduce load operating time and increase no-load operating time, reduce the mechanical stress and thermal stress of the unit, and ensure stable operation in a mild warning state.
[0042] If 0.6<Ψ≤0.8, the unit is in a moderate warning state; when the unit is in a moderate warning state, it is necessary to disassemble and inspect all mechanical parts, check the connectivity and insulation of electrical wiring, detect the response time and accuracy of the control system, replace all worn parts, clean the cooling system and replace the coolant, re-lubricate all moving parts, reduce continuous operating time, increase intermittent rest time, adjust the operating strategy, and increase the monitoring frequency to once every half hour to ensure that potential problems are discovered and dealt with in a timely manner.
[0043] If 0.8<Ψ≤1.0, the unit is in a severe warning state; when the unit is in a severe warning state, a comprehensive inspection should be carried out immediately, including a detailed inspection of all mechanical, electrical and control systems, detection using a spectrum analyzer and a real-time monitoring system, and professional technicians should be arranged to carry out centralized maintenance, fully disassemble and inspect components, repair or replace damaged components, reassemble and calibrate the system, strengthen operation monitoring, monitor key parameters in real time, and record data every 15 minutes.
[0044] If Ψ>1.0, the unit is in a faulty state; when the unit is in a faulty state, it is necessary to shut down immediately and conduct a comprehensive fault diagnosis, using the Fault Tree Analysis (FTA) and Failure Mode and Effects Analysis (FMEA) to determine the cause of the fault; based on the diagnosis results, repair or replace the faulty parts, and after repair or replacement, conduct operation verification, including load testing, performance testing, and safety inspections, to ensure that all systems return to normal operation, and re-evaluate and update the maintenance plan.
[0045] The optimization of the frequency modulation instruction allocation strategy by combining the artificial immune algorithm includes generating an initial antibody group: , in, is the number of antibodies, For the i-th antibody, i=1,2,…,L. Perform fitness calculation and define the fitness function as: , Where T is the number of frequency modulation strategies, is the kth frequency modulation strategy effect value of the antibody, is the mean value of the kth frequency modulation strategy, is the standard deviation of the kth frequency modulation strategy, is the weight of the kth FM strategy.
[0046] The optimization of the frequency modulation instruction allocation strategy by combining the artificial immune algorithm includes cloning and mutation, selecting high fitness antibodies and mutating them: , Perform mutation operations: , in, is the variation that follows Gaussian distribution; is the ith antibody.
[0047] Antibodies with fitness higher than the preset standard are selected to enter the next generation, and antibodies with fitness lower than the preset standard are eliminated: , Repeat the fitness calculation, cloning, mutation, and selection process until the stopping condition is met: , in, is the set convergence threshold, is the number of iterations, is the number of antibodies.
[0048] The optimization using quantum computing includes two parts, the first part is the square error and weight term, the second part is the Gaussian function and regularization term; the objective function is set according to the two parts : ; in, Allocate vectors for frequency modulation instructions, and are the dimensions of the two different parts of the objective function, is the weight, is the mean, is the regularization parameter, is the weight of the second part, is the parameter mean, is the standard deviation.
[0049] Select the quantum annealing algorithm and define the Hamiltonian : , in, and are the expected values of quantum bits respectively.
[0050] Perform parallel computing and execute the Hamiltonian minimization process in parallel on the quantum computing platform, using the evolution formula of quantum annealing: ; in, and is the corresponding time coefficient, is the initial Hamiltonian, is the Hamiltonian of the problem.
[0051] After iterative optimization, the global optimal solution is found and the optimal solution is used. Update frequency modulation instruction allocation strategy: ; in, is the initial antibody group; is the ith antibody; is the fitness of the ith antibody; The antibody population selected for cloning; For the next generation of antibody groups.
[0052] 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.
[0053] Embodiment 2, the second embodiment of the present invention, is different from the previous embodiment in that: 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 to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments 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 codes.
[0054] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0055] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0056] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0057] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0058] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A frequency modulation instruction allocation method for super-capacity power storage considering the life of the unit, characterized by: include, Collect multi-dimensional data of unit operation, pre-process the collected data, and input the processed data into the self-organizing map neural network SOM for training; Based on the preprocessed data, a self-organizing map neural network (SOM) is used for life management. The preprocessed multi-dimensional data is input into the SOM network, which maps the high-dimensional data to a two-dimensional plane through competitive learning, and classifies the life status of the unit according to the feature map output by the SOM network. Combined with the artificial immune algorithm, the frequency modulation instruction allocation strategy is optimized to generate an initial antibody group. Each antibody represents a frequency modulation strategy. The fitness of each antibody is calculated, and the frequency modulation effect is evaluated. Antibodies are selected for cloning and new antibodies are generated through mutation. The selected antibodies enter the next generation and the fitness evaluation, cloning, mutation and selection process are repeated until the optimal frequency modulation instruction allocation strategy is found. Apply quantum computing for optimization, model the frequency modulation instruction allocation problem as an optimization problem, define the objective function and constraints, select the quantum algorithm, perform parallel computing, deploy the optimization algorithm on the quantum computing platform, perform iterative optimization, and find the global optimal solution.
2. A frequency modulation instruction allocation method for super-capacity power storage considering the life of the unit as claimed in claim 1, characterized in that: The multi-dimensional data collected about the operation of the unit include temperature, vibration, pressure, operation time, current, voltage and power factor parameters, which are collected in real time through temperature sensors, vibration sensors, pressure sensors, current sensors, voltage sensors and power factor sensors, and stored in a database.
3. A frequency modulation instruction allocation method for super-capacity power storage considering the life of the unit as claimed in claim 2, characterized in that: The preprocessing includes performing Gaussian filtering on each sample, calculating the preprocessed data by integration, and normalizing each dimension of each sample to obtain a normalized comprehensive index, averaging the comprehensive index of each sample to obtain a normalized final comprehensive index, as follows: , in, is the final normalized comprehensive index, used as the input of the SOM model. is the sample size; is the input data vector of the i-th sample; are the upper and lower limits of the integral; is the preprocessed data function; is the Gaussian filter function, where is the standard deviation; is the number of data dimensions; is the j-th dimension data of the i-th sample; is the mean of the data in the jth dimension; is the standard deviation of the data in the jth dimension; is the kernel function of the data, where For reference data.
4. A frequency modulation instruction allocation method for super-capacity power storage considering the life of the unit as claimed in claim 3, characterized in that: The use of the self-organizing map neural network SOM for life management includes bringing Φ as input data into the life management model, calculating the distance between the weight vector of the SOM network and the sample data vector, using an exponential function for weighting, and obtaining the life management model. By comprehensive calculation of all samples, the final life management index Ψ is obtained: , in, is the comprehensive index of the i-th sample; is the standard deviation of the i-th sample; is the mean of the i-th sample; is the j-th dimension comprehensive index of the i-th sample; is the mean of the data in the jth dimension; is the standard deviation of the data in the jth dimension; is the weight vector of the jth neuron in the SOM network; is the vector of the i-th sample; is the learning rate parameter of the SOM network.
5. The frequency modulation instruction allocation method of the super-capacity power storage considering the life of the unit as claimed in claim 4 is characterized by: The classification of the life status of the unit includes: If Ψ≤0.3, the unit is in normal condition; when the unit is in normal condition, the unit is fully lubricated once a quarter, all fasteners are checked and re-tightened, all exposed mechanical parts and electrical connectors are cleaned, sensors and control systems are adjusted and calibrated, key parameters are continuously monitored, including temperature, vibration and current, and data is recorded once an hour using a remote monitoring system, and alarm thresholds are set; when parameters reach the threshold, maintenance personnel are immediately notified to conduct on-site inspections; If 0.3<Ψ≤0.6, the unit is in a mild warning state; when the unit is in a mild warning state, increase the inspection frequency to once a week, and the inspection content includes measuring and recording the wear of key components; the wear of key components includes the wear degree of bearings, gears and brushes; use vibration analyzers and infrared thermal imagers for detection, and perform preventive maintenance, replace filters and seals, calibrate equipment, adjust operating parameters according to monitoring data, reduce load operation time and increase no-load operation time, reduce mechanical stress and thermal stress of the unit, and ensure stable operation in a mild warning state; If 0.6<Ψ≤0.8, the unit is in a moderate warning state; when the unit is in a moderate warning state, it is necessary to disassemble and inspect all mechanical parts, check the connectivity and insulation of electrical wiring, detect the response time and accuracy of the control system, replace all worn parts, clean the cooling system and replace the coolant, re-lubricate all moving parts, reduce continuous operation time, increase intermittent rest time, adjust the operation strategy, and increase the monitoring frequency to once every half hour to ensure that potential problems are discovered and handled in a timely manner; If 0.8<Ψ≤1.0, the unit is in a severe warning state; when the unit is in a severe warning state, a comprehensive inspection shall be immediately carried out, including a detailed inspection of all mechanical, electrical and control systems, detection using a spectrum analyzer and a real-time monitoring system, and professional technicians shall be arranged to carry out centralized maintenance, fully dismantle and inspect components, repair or replace damaged components, reassemble and calibrate the system, strengthen operation monitoring, monitor key parameters in real time, and record data every 15 minutes; If Ψ>1.0, the unit is in a faulty state; when the unit is in a faulty state, it is necessary to shut down immediately and conduct a comprehensive fault diagnosis, using the Fault Tree Analysis (FTA) and Failure Mode and Effects Analysis (FMEA) to determine the cause of the fault; based on the diagnosis results, repair or replace the faulty parts, and after repair or replacement, conduct operation verification, including load testing, performance testing, and safety inspections, to ensure that all systems return to normal operation, and re-evaluate and update the maintenance plan.
6. A frequency modulation instruction allocation method for super-capacity power storage considering the life of the unit as claimed in claim 5, characterized in that: The optimization of the frequency modulation instruction allocation strategy by combining the artificial immune algorithm includes generating an initial antibody group: , in, is the number of antibodies, For the i-th antibody, i=1,2,…,L; perform fitness calculation and define the fitness function as: , Where T is the number of frequency modulation strategies, is the kth frequency modulation strategy effect value of the antibody, is the mean value of the kth frequency modulation strategy, is the standard deviation of the kth frequency modulation strategy, is the weight of the kth FM strategy.
7. A frequency modulation instruction allocation method for super-capacity power storage considering the life of the unit as claimed in claim 6, characterized in that: The optimization of the frequency modulation instruction allocation strategy by combining the artificial immune algorithm includes cloning and mutation, selecting high fitness antibodies and mutating them: , Perform mutation operations: , in, is the variation that follows Gaussian distribution; is the ith antibody; Antibodies with fitness higher than the preset standard are selected to enter the next generation, and antibodies with fitness lower than the preset standard are eliminated: , Repeat the fitness calculation, cloning, mutation, and selection process until the stopping condition is met: , in, is the set convergence threshold, is the number of iterations, is the number of antibodies.
8. A frequency modulation instruction allocation method for super-capacity power storage considering the life of the unit as claimed in claim 7, characterized in that: The optimization using quantum computing includes measuring two different parts of objectives or constraints, the first part is the square error and the weight term, and the second part is the Gaussian function and the regularization term; setting the objective function : , in, Assign vectors to frequency modulation instructions, and are the dimensions of the two different parts of the objective function, is the weight, is the mean, is the regularization parameter, is the weight of the second part, is the parameter mean, is the standard deviation; Select the quantum annealing algorithm and define the Hamiltonian : , in, and are the expected values of quantum bits respectively; Perform parallel computing and execute the Hamiltonian minimization process in parallel on the quantum computing platform, using the evolution formula of quantum annealing: , in, and is the corresponding time coefficient, is the initial Hamiltonian, is the problem Hamiltonian; After iterative optimization, the global optimal solution is found and the optimal solution is used. Update frequency modulation instruction allocation strategy: , , is the initial antibody group; is the ith antibody; is the fitness of the ith antibody; The antibody population selected for cloning; For the next generation of antibody groups.
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 method for allocating frequency modulation instructions for ultra-capacity power storage taking into account the life of the unit as described in any one of claims 1 to 8 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 method for allocating frequency modulation instructions for ultra-capacity power storage taking into account the life of the unit as described in any one of claims 1 to 8 are implemented.
Citation Information
Patent Citations
Frequency modulation instruction scheduling method considering energy storage power station life attenuation and capacity balance bidding
CN110210709A
Fused salt energy storage capacity distribution method and system considering frequency modulation performance index
CN118214040A
Super capacitor coupling lithium battery energy storage method and system based on frequency modulation instruction prediction
CN118367573A
Super-capacity energy storage frequency modulation instruction distribution method and device considering service life of unit
CN118659410A
Adaptive variable-parameter frequency modulation method and device for doubly fed variable-speed pumped-storage unit
WO2024007465A1
Cited By
Distributed energy resource intelligent scheduling method based on Internet of Things
CN120373823A
