Generator set peak capacity dynamic analysis method and system based on information entropy
By improving the information entropy method, dynamically analyzing the peak capabilities of the generator sets, solving the problem that time series analysis cannot be performed in the existing technology, achieving accurate assessment of the current and future peak capabilities of the generator sets, and providing effective analysis rules.
Patent Information
- Application Number
- CN202411064963.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-15
AI Technical Summary
The existing technology fails to effectively analyze the dynamic peak capability of the generator set in the time series, resulting in the inability to accurately grasp the changes in the current and future peak capability of the generator set.
Using a method based on improved information entropy, we collect and normalize the effectiveness index data of the generator set and calculate dynamic weights to realize dynamic analysis of the peak capability of the generator set, considering the index changes and offset trends at different moments.
The dynamic analysis of the peak capability of the generator set is realized, providing accurate assessment of current and future trends, solving the problem of object distance that cannot be sorted in traditional methods, and improving the effectiveness and accuracy of the analysis.
Smart Images

Figure CN118966898A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of dynamic analysis of peak power capacity of a generator set, and in particular to a method and system analysis of peak power capacity of a generator set based on information entropy. Background Art
[0002] The peak power supply is related to the normal development of the social economy. With the continuous economic recovery, the continuous improvement of people's quality of life and the frequent occurrence of extreme climate phenomena, power supply gaps occur from time to time and the peak power supply pressure is huge. It is of great significance to analyze the peak capacity of power generating sets.
[0003] CN117973848A constructs an index system for evaluating the peak resilience of power systems from the time dimension, space dimension and power system characteristic dimension; uses a combined weighting method to solve the weights of the index system for evaluating the peak resilience of power systems under extreme risk events, and scores the peak resilience.
[0004] CN117764307A formulates peak decisions during the meteorological disaster warning stage from the perspectives of meteorological disaster prediction, power peak decision generation, and digital twin simulation.
[0005] CN117728418A is a method for optimizing the peak capacity of an electric power system based on integrated decision-making of sources, grids, loads and storage, and proposes feasible supporting wind power, photovoltaic power and energy storage capacities under different power generation scales.
[0006] CN116154867A proposed a dynamic piecewise linear ramping model, which more accurately evaluated the real-time ramping capability of the unit, obtained a more realistic and feasible day-ahead unit scheduling table, and simulated a realistic and feasible generator unit scheduling plan.
[0007] CN117895544A constructs a model for regulating power supply to promote peak saturation effect, thereby improving the rationality of power system scheduling.
[0008] The above patent does not involve the dynamic peak capacity analysis of generator sets in time series. The peak capacity of generator sets at different times will change greatly, which is not only reflected in the peak capacity at a certain moment, but also related to the peak capacity at different times. Conducting dynamic analysis of generator sets and solving the peak analysis problem of units under time series will help to grasp the peak capacity of generator sets at present and at different times and understand future development trends.
[0009] Therefore, there is an urgent need for a dynamic analysis method of the peak capacity of a generator set, which can realize the dynamic analysis of the peak capacity of a generator set by allocating corresponding dynamic weights. Summary of the invention
[0010] In order to solve the deficiencies in the prior art, the present invention provides a method for dynamic analysis of the peak capacity of a generator set based on information entropy. Corresponding weights are assigned by the amount of indicator information, and changes in indicators at different times are considered. By assigning corresponding dynamic weights, dynamic analysis of the peak capacity of the generator set is achieved.
[0011] The present invention adopts the following technical solution.
[0012] A method for dynamic analysis of peak capacity of a generator set based on improved information entropy comprises the following steps:
[0013] Step 1: Collect the performance index data of each generator set at a set time in the area to form a performance index data matrix;
[0014] Step 2: Normalize the performance indicator data at the set time and the offset values of the performance indicator data between adjacent time points to obtain a performance indicator normalization matrix and an offset performance indicator normalization matrix respectively;
[0015] Step 3: Calculate the weights of each performance indicator and the offset performance indicator to obtain the performance indicator standard matrix and the offset performance indicator standard matrix;
[0016] Step 4: Calculate the peak capacity of each performance index and offset performance index of the generator set;
[0017] Step 5: Based on the performance indicator obtained in step 4 and the peak capacity of the offset performance indicator, calculate the fused peak capacity of the generator set.
[0018] The present invention further includes the following preferred embodiments:
[0019] In step 1, the performance indicators include peak efficiency of generator sets, power generation contribution rate, peak average load rate, peak available hours, coal inventory target completion rate, available coal storage days, fuel health, boiler equipment health, steam turbine equipment health, thermal system health and electrical equipment health.
[0020] In step 3, the calculation formula for the weight of each performance indicator and the offset performance indicator is as follows:
[0021]
[0022] Where i = 1, 2, ..., m, j = 1, 2, ..., n, v = 1, 2, ..., V, where m, n, V represent the number of generator sets, the number of evaluation indicators and the number of different time points, respectively. v represents the vth moment; α j (t v ),α′ j (t v ) represent the tth vThe jth performance indicator and the weight of the offset performance indicator at the time; r ij (t v ) represents the jth evaluation index of the i-th generator set at t v Normalized value at time; r′ ij (t v ) represents the offset value of the jth evaluation index of the i-th generator set at t v Normalized value at time.
[0023] In step 4, the calculation formula for the peak capacity of each performance index and offset performance index of the generator set is as follows:
[0024]
[0025] α i (t v ), α′ i (t v ) represent the tth v The peak capacity of the efficiency index and the peak capacity of the offset efficiency index of the i-th generator group at the time, Respectively t v The performance indicators of the i-th generator set at the time, Respectively t v The distance between each offset performance index of the i-th generator set at the moment and the positive and negative ideal solutions of the offset.
[0026] The calculation formula of the improved information entropy between the effectiveness index of each generator set and the positive and negative ideal solutions of the effectiveness index is as follows:
[0027]
[0028] in, Respectively t v The information entropy of each performance index of the i-th generator set and the positive and negative ideal solutions; The positive and negative ideal solutions of the j-th performance indicator respectively.
[0029] The calculation formula of the improved information entropy between the offset performance index of each generator set and the positive and negative ideal solutions of the offset performance index is as follows:
[0030]
[0031] in, Respectively t v The improved information entropy of each offset performance index of the i-th generator set at the moment and the positive and negative ideal solutions of the offset; The positive and negative ideal solutions of the j-th offset performance indicator are given respectively.
[0032] In step 5, the combined peak capacity of the generator set is calculated as follows:
[0033] Z i (t v )=δ(t v )α i (t v )+ε(t v )α′ i (t v )
[0034] Among them, δ(t v ), ε(t v )∈[0,1] are the weight coefficients of the effect and offset effect, δ(t v )+ε(t v )=1,Z i (t v ) represents the tth v The integrated peak capacity of the i-th generator set at the moment, α i (t v ), α′ i (t v ), respectively representing the tth v The peak capacity of the efficiency index and offset efficiency index of each generator set at time i.
[0035] At the same time, the present invention also provides a generator set peak capacity dynamic analysis system based on improved information entropy, including a data acquisition module, a data processing module, a static and dynamic peak capacity calculation module and a fusion peak capacity calculation module;
[0036] The data acquisition module is used to collect the performance index data of each generator set at each time in the region to form a performance index data matrix;
[0037] The data processing module is used to normalize the performance indicator data at each moment and the dynamic changes of each performance indicator data between different moments to obtain normalized matrices respectively;
[0038] The static and dynamic peak capacity calculation module is used to calculate the static and dynamic analysis peak capacity of each performance index of the generator set;
[0039] The fused peak capacity calculation module is used to calculate the fused peak capacity of each performance indicator of the generator set.
[0040] A terminal comprises a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of any one of the methods.
[0041] A computer-readable storage medium stores a computer program, which implements the steps of any one of the methods when executed by a processor.
[0042] The beneficial effect of the present invention lies in that, compared with the prior art, the present invention uses the peak capacity index of the generator set at different times, assigns corresponding weights according to the amount of index information, and considers improving information entropy to solve the problem that two objects with equal distances in traditional information entropy cannot be evaluated and ranked. Based on the improved information entropy calculation of the performance index at the same moment and at different moments, the dynamic analysis of the peak capacity of the generator set is realized by assigning corresponding dynamic weights at different moments. The present invention not only considers the peak capacity analysis at a certain moment, but also dynamically analyzes the deviation trend at different moments, provides effective analysis rules for the power peak of the generator set, grasps the peak capacity of the generator set at present and at different moments, and verifies the effectiveness of the indicators and analysis methods of the present invention through data. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 It is a flow chart of a method for dynamic analysis of peak capacity of a generator set based on information entropy in the present invention;
[0044] Figure 2 It is a block diagram of a system for dynamically analyzing the peak capacity of a generator set based on information entropy in the present invention. DETAILED DESCRIPTION
[0045] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.
[0046] The present invention provides a method for dynamic analysis of peak capacity of a generator set based on information entropy, such as Figure 1 The figure shows a flow chart of a method for dynamic analysis of peak capacity of a generator set based on information entropy in the present invention, the method comprising the following steps:
[0047] Step 1: Collect the performance index data of each generator set at a set time in the area to form a performance index data matrix;
[0048] In one embodiment of the present invention, in step 1, the performance indicators include the peak efficiency of the generator set, the power generation contribution rate, the peak average load rate, the peak available hours for supply guarantee, the power coal inventory target completion rate, the available coal storage days, the fuel health, the boiler equipment health, the steam turbine equipment health, the thermal system health and the electrical equipment health.
[0049] In this embodiment, the efficiency index data of each generator set at each time in the region are collected, and the indicators T1, T2, T3, and T4 of m=7 generator sets at each time are calculated, totaling n=4 indicators. The time is 2020.01.01, 2020.05.01, 2020.09.01, and 2020.12.01, totaling V=4, and the V*m row and n column data matrix X={x ij (t v )}(i=1,2,…N,j=1,2,…,M,v=1,2,…,V),x ij (t v ) represents the tth v The performance indicator data in the i-th row and j-th column at the time is shown in Table 1.1, and the unit represents the generating unit.
[0050] Table 1.1 Performance indicator data
[0051]
[0052]
[0053] From the original data, four time points and four indicators are selected. At the same time point, each unit has only one indicator changed compared to the previous unit, and the indicators of unit 5 are the best, and the indicator data of unit 6 and unit 4, unit 7 and unit 3 are the same; at different time points, each unit increases one indicator compared to the previous moment; the data size of the four indicators is divided into multiple orders of magnitude.
[0054] Step 2: Normalize the performance indicator data at the set time and the offset values of the performance indicator data between adjacent time points to obtain a performance indicator normalization matrix and an offset performance indicator normalization matrix respectively;
[0055] In one embodiment of the present invention, in step 2, the calculation formula of the performance indicator normalization matrix is as follows:
[0056] R = {r ij}
[0057]
[0058] Among them, x ij (t v ), r ij (t v ) represent the jth evaluation index of the i-th generator set at t v The original value and normalized value at the time, i = 1, 2, ..., m, j = 1, 2, ..., n, v = 1, 2, ..., V, where m, n, V represent the number of generator sets, the number of evaluation indicators and the number of different time points, respectively, t v represents the vth moment.
[0059] Considering that, for example, a positive indicator is 1 The value of the time is (10,20,30) T , the result after processing by range transformation method is (0,0.5,1) T , at t 2 The time value is (20,40,60) T , the result after processing using the range transformation method is also (0,0.5,1) T Similarly, after using the linear proportional transformation method, t 1 and t 2 The results at all times are (0, 0.333, 0.667) T ; The normalization method is used for processing, and the results after processing are (0.167, 0.333, 0.5) T The above dimensionless process increment information is lost. This problem also exists when other commonly used static dimensionless methods are used for processing. Therefore, this paper uses the data at each moment and the dynamic changes of the data at different moments for normalization.
[0060] In one embodiment of the present invention, in step 2, the calculation of the dynamic normalization matrix of performance indicator data changes includes:
[0061] In step 2, the calculation of the dynamic normalization matrix of performance indicator data changes includes:
[0062] Step S201: Calculate the offset matrix of the performance indicator data matrix:
[0063] x′ ij (t v )=x ij (t v )-x ij (t v-1 )
[0064] Among them, x′ ij (t v ) represents each generator set at t v The offset value of each performance indicator at the time is defined as x′ ij (t V ) = x′ ij (t V-1 );
[0065] Step S202: Calculate the weight of each value in the offset matrix obtained in step S201 to obtain a normalized matrix of the offset matrix.
[0066] R′={r′ ij}
[0067]
[0068] r′ ij (t v ) represents the offset value of the jth evaluation index of the i-th generator set at t v Normalized value at time.
[0069] In this embodiment, Table 1.2 shows the normalized matrix at each moment, and Table 1.3 shows the offset normalized matrix between different moments.
[0070] Table 1.2 Normalized matrix at each moment
[0071]
[0072]
[0073] Table 1.3 Normalized matrix of offsets at different times
[0074]
[0075]
[0076] Step 3: Calculate the weights of each performance indicator and the offset performance indicator to obtain the performance indicator standard matrix and the offset performance indicator standard matrix.
[0077] In one embodiment of the present invention, the calculation formula of the weight of each performance indicator and the offset performance indicator is as follows:
[0078]
[0079] Where i = 1, 2, ..., m, j = 1, 2, ..., n, v = 1, 2, ..., V, where m, n, V represent the number of generator sets, the number of evaluation indicators and the number of different time points, respectively. v represents the vth moment; α j (t v ),α′ j (t v ) represent the tth v The jth performance indicator and the weight of the offset performance indicator at the time; r ij (t v ) represents the jth evaluation index of the i-th generator set at t v Normalized value at time; r′ ij (t v ) represents the offset value of the jth evaluation index of the i-th generator set at t v The normalized value of the moment, the calculation results are shown in Table 1.4.
[0080] Table 1.4 Weights of performance indicators and deviation performance indicators
[0081] time Index value and weight T1 T2 T3 T4 2020.01.01 Performance indicator value 0.723 0.572 0.58 0.572 2020.01.01 Performance indicator weight 0.295 0.234 0.237 0.234 2020.01.01 Offset performance indicator value 0.669 0.88 1.0 0.822 2020.01.01 Offset performance weight 0.199 0.261 0.297 0.244 2020.05.01 Performance indicator value 0.619 0.572 0.58 0.572 2020.05.01 Performance indicator weight 0.264 0.244 0.247 0.244 2020.05.01 Offset performance indicator value 0.835 0.911 1.0 0.822 2020.05.01 Offset performance weight 0.234 0.255 0.28 0.23 2020.09.01 Performance indicator value 0.529 0.572 0.58 0.572 2020.09.01 Performance indicator weight 0.235 0.254 0.257 0.254 2020.09.01 Offset performance indicator value 0.835 0.911 1.0 0.822 2020.09.01 Offset performance weight 0.234 0.255 0.28 0.23 2020.12.01 Performance indicator value 0.45 0.572 0.58 0.572 2020.12.01 Performance indicator weight 0.207 0.263 0.267 0.263 2020.12.01 Offset performance indicator value 0.835 0.911 1.0 0.822 2020.12.01 Offset performance weight 0.234 0.255 0.28 0.23
[0082] Step 4: Calculate the peak capacity of each performance index and offset performance index of the generator set;
[0083] In one embodiment of the present invention, the calculation formulas for the peak capacity of each performance index and the offset performance index of the generator set are as follows:
[0084]
[0085] α i (t v ), α′ i (t v ) represent the tth v The peak capacity of the efficiency index and the peak capacity of the offset efficiency index of the i-th generator group at the time, Respectively t v The performance indicators of the i-th generator set at the time, Respectively t v The distance between each offset performance index of the i-th generator set at the moment and the positive and negative ideal solutions of the offset.
[0086] Preferably, the calculation formula of the improved information entropy between the efficiency index of each generator set and the positive and negative ideal solutions of the efficiency index is as follows:
[0087]
[0088] in, Respectively t v The distance between the performance indicators of the i-th generator set at the moment and the positive and negative ideal solutions; take the maximum and minimum values of each column indicator in Table 1.2 respectively, and get r j + =[0.053,0.036,0.05,0.043], r j - =[0.011,0.034,0.025,0.034] are the positive and negative ideal solutions of the j-th performance indicator respectively.
[0089] Preferably, the calculation formula of the improved information entropy between the offset performance index of each generator set and the positive and negative ideal solutions of the offset performance index is as follows:
[0090]
[0091] in, Respectively t v The distance between the offset performance index of the i-th generator set at the moment and the positive and negative ideal solutions of the offset; take the maximum and minimum values of each column index in Table 1.3 respectively, and get rj + ′=[0.2,0.938,1,1]、r j - ′=[0,-0.062,-1,-0.25] are the positive and negative ideal solutions of the j-th offset performance indicator respectively.
[0092] Information entropy is an asymmetric measure of the distance between two probability distributions and does not satisfy the triangle inequality, so it can solve the defect that the points on the perpendicular bisectors at both ends cannot be effectively sorted. However, the logarithmic function in the relative entropy formula requires that the data value is positive, so on the basis of the original formula, the real number is added with the absolute value, and 10 is added to the numerator and denominator at the same time. -10 It has almost no impact on the calculation results and can ensure normal calculation when there is zero-value data. As shown in Table 1.3, Unit 3 on January 1, 2020 and Unit 1 on May 1, 2020 will not be able to obtain differential ranking values. This paper adopts improved information entropy to solve the defect that the points on the midpoints at both ends cannot be effectively sorted, and the effective sorting results are shown in Table 1.6. The ranking value of Unit 3 on January 1, 2020 is 0.1, and the ranking value of Unit 1 on May 1, 2020 is 0.102.
[0093] Step 5: Based on the performance indicator obtained in step 4 and the peak capacity of the offset performance indicator, calculate the fused peak capacity of the generator set.
[0094] In one embodiment of the present invention, the calculation formula for the fusion peak capacity of the generator set is as follows:
[0095] Z i (t v )=δ(t v )α i (t v )+ε(t v )α′ i (t v )
[0096] Among them, δ(t v ), ε(t v )∈[0,1] are the weight coefficients of the effect and offset effect, δ(t v )+ε(t v )=1,Z i (t v ) represents the tth v The integrated peak capacity of the i-th generator set at the moment, Respectively represent the t v The ranking results of the efficiency index of the i-th generator group at the moment and the peak capacity of the offset efficiency index are taken as δ(t v )=ε(t v)=0.5,v=1,2,…,V=4; the performance index ranking results, offset performance index ranking results and final fusion ranking results are shown in Table 1.5, Table 1.6 and Table 1.7 respectively.
[0097] Table 1.5 Ranking results of performance indicators
[0098] Unit Name 2020.01.01 2020.05.01 2020.09.01 2020.12.01 Unit 1 0.061 0.067 0.071 0.073 Unit 2 0.069 0.073 0.076 0.078 Unit 3 0.07 0.075 0.078 0.079 Unit 4 0.085 0.089 0.092 0.093 Unit 5 0.09 0.094 0.097 0.098 Unit 6 0.085 0.089 0.092 0.093 Unit 7 0.07 0.075 0.078 0.079
[0099] Table 1.6 Ranking results of deviation effectiveness indicators
[0100]
[0101]
[0102] It should be noted that the "2020.05.01" column indicates the data change from 2020.01.01 to 2020.05.01, and the same applies to the others. The "2020.01.01" column represents itself.
[0103] Table 1.7 Final fusion sorting results
[0104] Unit Name 2020.01.01 2020.05.01 2020.09.01 2020.12.01 Unit 1 0.076 0.085 0.091 0.096 Unit 2 0.083 0.092 0.098 0.103 Unit 3 0.085 0.094 0.1 0.105 Unit 4 0.105 0.114 0.12 0.125 Unit 5 0.111 0.12 0.126 0.131 Unit 6 0.105 0.114 0.12 0.125 Unit 7 0.085 0.094 0.1 0.105
[0105] From the selection characteristics of the original data, it can be seen that at the same time, the peak capacity ranking value should gradually increase from unit 1 to unit 5, and then gradually decrease to unit 7, and the results of unit 7, unit 3, unit 6 and unit 4 should be consistent; at different times, the index value of the same unit is gradually increasing, and its peak capacity ranking value should gradually increase; the order of magnitude of different indicators is different, and the change of peak capacity ranking value should not be affected by the change of dimension. From the result table 1.7, it can be seen that the results all meet the above characteristics, verifying the correctness and rationality of the algorithm.
[0106] In another embodiment of the present invention, 11 performance index data of 5 units are used to illustrate the effectiveness of the algorithm. The performance indicators include peak effectiveness of generator sets, power generation contribution rate, peak average load rate, peak available hours, coal inventory target completion rate, available coal storage days, fuel health, boiler equipment health, steam turbine equipment health, thermal system health and electrical equipment health. The original data is shown in Table 1.8, the static and dynamic information entropy and weight results are shown in Table 1.9, and the final sorting results are shown in Table 1.10.
[0107] Table 1.8 Original data
[0108]
[0109]
[0110]
[0111] Table 1.9 Static and dynamic information entropy and weights
[0112]
[0113]
[0114]
[0115] Table 1.10 Comprehensive ranking results based on information entropy
[0116]
[0117] On 2020.01.01, most of the indicators of unit 1 were higher than those of unit 3. On 2020.05.01, many indicators of the unit decreased, and the changes at the two time points further aggravated its peak capacity to continue to be at the bottom. On 2020.09.01 and 2020.12.01, the peak capacity of unit 1 gradually increased, and the ranking results of unit 1 fluctuated greatly, which was related to the fluctuation of the indicators of its own indicators at different time points. The above results verify the effectiveness of the proposed method for the dynamic analysis of the peak capacity of the unit.
[0118] The above examples have demonstrated the rationality and effectiveness of the analysis method.
[0119] At the same time, the present invention also realizes a dynamic analysis system of the peak capacity of the generator set based on improved information entropy, such as Figure 2 The figure shows a block diagram of a generator set peak capacity dynamic analysis system based on information entropy in the present invention, the system includes a data acquisition module, a data processing module, a static and dynamic peak capacity calculation module and a fusion peak capacity calculation module;
[0120] The data acquisition module is used to collect the performance index data of each generator set at each time in the region to form a performance index data matrix;
[0121] The data processing module is used to normalize the performance indicator data at each moment and the dynamic changes of each performance indicator data between different moments to obtain normalized matrices respectively;
[0122] The static and dynamic peak capacity calculation module is used to calculate the static and dynamic analysis peak capacity of each performance index of the generator set;
[0123] The fused peak capacity calculation module is used to calculate the fused peak capacity of each performance indicator of the generator set.
[0124] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.
[0125] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.
[0126] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.
[0127] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.
[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A dynamic analysis method of peak capacity of power generation units based on improved information entropy, It is characterized in that The method comprises the following steps: Step 1: collecting effectiveness index data of each generator set at a set time in a region to form an effectiveness index data matrix; Step 2: Normalize the performance indicator data at the set time and the offset values of the performance indicator data between adjacent time points to obtain a performance indicator normalization matrix and an offset performance indicator normalization matrix respectively; Step 3: Calculate the weights of each performance indicator and the offset performance indicator to obtain the performance indicator standard matrix and the offset performance indicator standard matrix; Step 4: Calculate the peak capacity of each performance index and offset performance index of the generator set; Step 5: Based on the performance indicator obtained in step 4 and the peak capacity of the offset performance indicator, calculate the fused peak capacity of the generator set.
2. According to claim 1, a method for dynamic analysis of peak capacity of a generator set based on improved information entropy, Features: In step 1, the performance indicators include peak efficiency of generator sets, power generation contribution rate, peak average load rate, peak available hours, coal inventory target completion rate, available coal storage days, fuel health, boiler equipment health, steam turbine equipment health, thermal system health and electrical equipment health.
3. According to claim 1, a method for dynamic analysis of peak capacity of a generator set based on improved information entropy, Features: In step 3, the calculation formula for the weight of each performance indicator and the offset performance indicator is as follows: Where i = 1, 2, ..., m, j = 1, 2, ..., n, v = 1, 2, ..., V, where m, n, V represent the number of generator sets, the number of evaluation indicators and the number of different time points, respectively. v represents the vth moment; α j (t v ),α' j (t v ) represent the tth v The jth performance indicator and the weight of the offset performance indicator at the time; r ij (t v ) represents the jth evaluation index of the i-th generator set at t v Normalized value at the moment; r' ij (t v ) represents the offset value of the jth evaluation index of the i-th generator set at t v Normalized value at time.
4. According to claim 1, a method for dynamic analysis of peak capacity of a generator set based on improved information entropy, Features: In step 4, the calculation formula for the peak capacity of each performance index and offset performance index of the generator set is as follows: α i (t v ), α' i (t v ) represent the tth v The peak capacity of the efficiency index and the peak capacity of the offset efficiency index of the i-th generator group at the time, Respectively t v The performance indicators of the i-th generator set at the time, Respectively t v The distance between each offset performance index of the i-th generator set at the moment and the positive and negative ideal solutions of the offset.
5. According to claim 4, a method for dynamic analysis of peak capacity of a generator set based on improved information entropy, Features: The calculation formula of the improved information entropy between the effectiveness index of each generator set and the positive and negative ideal solutions of the effectiveness index is as follows: in, Respectively t v The information entropy of each performance index of the i-th generator set and the positive and negative ideal solutions; The positive and negative ideal solutions of the j-th performance indicator respectively.
6. A method for dynamic analysis of peak capacity of a generator set based on improved information entropy according to claim 6, Features: The calculation formula of the improved information entropy between the offset performance index of each generator set and the positive and negative ideal solutions of the offset performance index is as follows: in, Respectively t v The improved information entropy of each offset performance index of the i-th generator set at the moment and the positive and negative ideal solutions of the offset; The positive and negative ideal solutions of the j-th offset performance indicator are given respectively.
7. According to claim 1, a method for dynamic analysis of peak capacity of a generator set based on improved information entropy, Features: In step 5, the combined peak capacity of the generator set is calculated as follows: Z i (t v )=δ(t v )a i (t v )+ε(t v )a' i (t v ) Among them, δ(t v ), ε(t v )∈[0,1] are the weight coefficients of the effect and offset effect, δ(t v )+ε(t v )=1,Z i (t v ) represents the tth v The integrated peak capacity of the i-th generator set at the moment, α i (t v ), α' i (t v ), respectively representing the tth v The peak capacity of the efficiency index and offset efficiency index of each generator set at time i.
8. A system for analyzing the peak capacity of a generator set based on improved information entropy using the method according to any one of claims 1 to 7, comprising a data acquisition module, a data processing module, a static and dynamic peak capacity calculation module, and a fusion peak capacity calculation module, Features: The data acquisition module is used to collect the performance index data of each generator set at each time in the region to form a performance index data matrix; The data processing module is used to normalize the performance indicator data at each moment and the dynamic changes of each performance indicator data between different moments to obtain normalized matrices respectively; The static and dynamic peak capacity calculation module is used to calculate the static and dynamic analysis peak capacity of each performance index of the generator set; The fused peak capacity calculation module is used to calculate the fused peak capacity of each performance indicator of the generator set.
9. A terminal comprising a processor and a storage medium; Features: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-7.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Information entropy-based dynamic peak capacity analysis method and system for generator sets
WO2026031432A1
