New energy power generation equipment accurate monitoring and operation data analysis method

Abstract

The invention relates to the technical field of power generation equipment data monitoring, in particular to a new energy power generation equipment accurate monitoring and operation data analysis method. Comprising the following steps: data acquisition and storage: deploying sensors at key nodes to acquire data; evaluating a running state, extracting key indexes such as equipment efficiency, energy consumption and environmental adaptability, and quantifying a scoring standard; an evaluation function is constructed, an analytic hierarchy process and an entropy weight method are combined to determine a weight, and a normalized weight value and a comprehensive evaluation value are calculated; carrying out anomaly detection and early warning, defining an early warning level based on the comprehensive evaluation value, and carrying out mean shift detection; early warning operation and emergency response are carried out, a feedback mechanism is established, and emergency measures under different early warning levels are formulated. According to the method, the equipment operation state monitoring accuracy, the data evaluation scientificity and the abnormity processing timeliness and effectiveness are improved, and stable operation and efficient power generation of the new energy power generation equipment are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power generation equipment data monitoring, and specifically designs a method for accurate monitoring and operation data analysis of new energy power generation equipment. Background Art

[0002] With the rapid development of new energy power generation technology, new energy power generation equipment (such as solar power generation equipment and wind power generation equipment) is being used more and more widely. However, the existing new energy power generation equipment monitoring and data analysis technology has some shortcomings:

[0003] Defects in operating status evaluation: Key indicators are not comprehensive, usually only a few indicators such as equipment efficiency are considered, and energy consumption and environmental adaptability are ignored. Energy consumption is related to power generation costs and sustainable operation, and environmental adaptability affects equipment performance in different environments. The lack of these indicators will lead to an incomplete evaluation of equipment operating status. The scoring criteria are unscientific, the scoring criteria are too simple and single, and the performance changes of equipment under different working conditions are not fully considered. Taking equipment efficiency as an example, the scoring is only based on a fixed threshold range, and the reasonable fluctuations of efficiency under conditions such as ambient temperature, light intensity, and wind speed are not considered, which can easily lead to misjudgment. Defects in evaluation function construction: Single weight determination, single method for determining indicator weights, often relying on expert experience or simple statistical analysis, unable to fully consider the complex relationship between indicators and data characteristics, resulting in unreasonable weight distribution, affecting the accuracy of the comprehensive evaluation value. No normalization processing, some technologies do not normalize the indicators when calculating the comprehensive evaluation value. Different indicators have large differences in dimensions and numerical ranges. Failure to normalize will cause certain indicators to dominate the comprehensive evaluation, affecting the objective evaluation of the overall performance of the equipment. Anomaly detection and early warning defects: The detection method is inaccurate. The anomaly detection method is simple and based on fixed threshold comparison, which cannot adapt to the complex changes in equipment operation data. The normal data range of the equipment changes in different seasons and operation stages. The existing method cannot dynamically adjust the threshold, which is prone to misjudgment and missed judgment. The early warning mechanism is imperfect, the early warning mechanism is not flexible and comprehensive enough, and the information transmission does not take into account the responsibilities and needs of personnel, resulting in untimely and inaccurate. The early warning level division is not detailed, and it cannot accurately reflect the degree of operation risk, which is not conducive to taking targeted measures. Early warning operation and emergency response defects: Early warning operation lacks pertinence, early warning operation is general, and targeted operations are not formulated according to the specific abnormalities and risks of the equipment, which cannot effectively alleviate the operation risk. Emergency response is not timely and effective, and there are problems such as long response time, lack of detailed process and effect evaluation. When equipment fails, it cannot be repaired quickly, affecting power generation efficiency and economic benefits.

[0004] To this end, we propose a method for accurate monitoring and operation data analysis of renewable energy power generation equipment. Summary of the invention

[0005] In view of the above deficiencies in the prior art, the purpose of the present invention is to overcome the deficiencies of existing new energy power generation equipment monitoring and data analysis technology, inaccurate operating status evaluation, unreasonable evaluation function construction, imperfect abnormality detection and early warning, and inefficient early warning operation and emergency response. The accuracy of equipment operating status monitoring, the scientific nature of data evaluation, the timeliness and effectiveness of abnormality handling are improved, and the stable operation and efficient power generation of new energy power generation equipment are guaranteed.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solutions:

[0007] A method for accurate monitoring and operation data analysis of new energy power generation equipment, comprising:

[0008] S1. Data collection and storage: deploy multifunctional sensors at key nodes of the new energy power generation system to collect equipment operation data in real time and store it in the database;

[0009] S2. Operation status evaluation, extracting key performance indicators such as equipment efficiency, energy consumption and environmental adaptability, defining and quantifying the scoring criteria and evaluation grade standards for operation performance indicators;

[0010] S3. Construct an evaluation function according to the scoring criteria and evaluation grade criteria of S2, calculate the normalized weight value of each operating performance indicator, and obtain a comprehensive evaluation value;

[0011] S4. Anomaly detection and warning: Based on the comprehensive evaluation value obtained in S3, define the level standard of abnormal warning, quantify the value range of the warning level, compare the comprehensive evaluation value with the value of the warning level, and execute the warning operation if it falls within the abnormal value range;

[0012] S5. Early warning operation and emergency response: when the comprehensive evaluation value indicates potential operational risks, the preset early warning operation is automatically executed.

[0013] Furthermore, the operation data in S1 includes a voltage sensor, a current sensor, a temperature sensor, a light intensity sensor, etc.

[0014] Furthermore, in S2, the equipment efficiency includes photovoltaic cell conversion efficiency, inverter efficiency, and battery charge and discharge efficiency, etc.

[0015] Among them, the conversion efficiency of photovoltaic cells is ηp, Po,p is the output power of the photovoltaic panel, A is the area of ​​the photovoltaic panel, and Q is the solar radiation intensity;

[0016] The inverter efficiency is ηi, P o,i is the output power of the inverter, P i,iis the input power of the inverter;

[0017] The charge and discharge efficiency of the battery is η b , E o,b is the energy output by the battery, E i,b is the energy input from the battery.

[0018] Furthermore, in S2, energy consumption is the total energy consumption of the analyzed equipment and the energy consumption distribution of different equipment components under different operating conditions. The total energy consumption E is expressed as: P(t) is the power consumption of the device at time t 1 and t 2 is the start and end time of the time interval; if the device has n components, the energy consumption of component i is E i , then the energy consumption ratio Pi of the components is:

[0019] Furthermore, in S2, environmental adaptability is to measure the adaptability of the device to different environmental conditions using the environmental adaptability coefficient A;

[0020] Environmental adaptability coefficient A for solar power generation equipment d for:

[0021] Environmental adaptability coefficient A′ for wind power generation equipment d for:

[0022] Among them, η pa (T 1 ,S 1 ) is in the environment condition (T 1 ,S 1 ) is the efficiency of the photovoltaic panel, the denominator η pa (T 0 ,S 0 ) is in the environment condition (T 0 ,S 0 ) when the photovoltaic panel is at 100°C; the ratio of the two is used to measure the change in efficiency of the equipment under different environmental conditions, thereby reflecting the equipment's ability to adapt to the environment;

[0023] W 0 and W 1 Represents different wind speed conditions, P o,w (W 1 ) indicates that the wind speed is W 1 The output power of wind power generation equipment at η w (W 0 ) indicates that the wind speed is W 0The formula measures the adaptability of wind power generation equipment to different wind speed environments through the ratio of output power to performance indicators under different wind speed conditions.

[0024] Furthermore, in S2, the method of quantifying the scoring criteria and evaluation grade criteria of the operating performance indicators is:

[0025] The rating of equipment efficiency is S η , according to the efficiency interval [η l ,η h ] Set the scoring criteria, where ηl is the set low efficiency threshold and ηh is the set high efficiency threshold;

[0026] When the equipment efficiency η satisfies η ≥ η l When S η =90→100;

[0027] When η low ≤η<η l When S η =80→90, etc.

[0028] Energy consumption and environmental adaptability scores are classified in the same way as equipment efficiency scores;

[0029] At the same time, combined with the equipment efficiency score S η , Energy Consumption Score i , Environmental adaptability score S d The weight coefficient is used for comprehensive scoring, and the comprehensive scoring formula is:

[0030] S c =ω 1 S η +ω 2 S i +ω 3 S d ;

[0031] Among them, ω 1 is the weight coefficient of equipment efficiency score, ω 2 is the weight coefficient of energy consumption score, ω 3 is the weight coefficient of environmental adaptability score, and ω 1 +ω 2 +ω 3 =1.

[0032] Further, the S3 includes:

[0033] S31. Determine the weights by combining the analytic hierarchy process (AHP) and the entropy weight method.

[0034] In the hierarchical analysis method, the judgment matrix A is constructed as follows: ij ) n×n , a ij Indicates the importance of index i relative to index j, by calculating the maximum eigenvalue λ of the judgment matrix max and the corresponding eigenvector W = (ω 1 ,ω 2 …ω n ), and obtain the weight vector ω determined by the hierarchical analysis method A ; Among them, the maximum eigenvalue λ max and the corresponding eigenvector W = (ω 1 ,ω 2 …ω n ) is calculated using mathematical software such as MATLAB's eig function;

[0035] In the entropy weight method, there are m evaluation objects, n evaluation indicators, and the indicator value is x. ij , x ij Including equipment efficiency rating S η , Energy Consumption Score i and environmental adaptability score S d ; First, calculate the information entropy Ej of index j, The relative importance pij, represents the relative importance of the i-th indicator in the j-th evaluation object; the coefficient of information entropy k, Information entropy is used to measure the uncertainty of an indicator. The larger the information entropy of an indicator, the smaller the amount of information it provides, and the smaller its weight should be.

[0036] Then calculate the entropy weight ωj of indicator j, The entropy weight reflects the weight of each indicator determined according to the characteristics of the data itself;

[0037] The final weight is calculated using the formula ω f =αω A +(1-α)ω e Determine, where α is the weight coefficient, the value is between [0,1]; where, ω A is the weight vector determined by the AHP method, ω e is the weight vector obtained by the entropy weight method;

[0038] S32. Calculate the normalized weight value of each operating performance indicator:

[0039] For equipment efficiency η, its maximum efficiency under ideal conditions is η max , normalized value of equipment efficiency

[0040] For energy consumption E, the energy consumption of the equipment in the best energy-saving state is E min, energy consumption normalized value

[0041] For environmental adaptability A, it is assumed that the environmental adaptability of the equipment under the most suitable environmental conditions is A d-max , normalized value

[0042] The original weights of equipment efficiency, energy consumption and environmental adaptability are ω η ,ω E ,ω A , the normalized weight values ​​are ω η ' η ,ω′ E ,ω′ A ;

[0043]

[0044] In the formula, ωj represents the weight value involved in determining the normalized weight value; nj is the normalization factor corresponding to the weight value ωj;

[0045] S33. Calculate the comprehensive evaluation value by weighted summation, that is:

[0046]

[0047] Among them, S is the comprehensive evaluation value; ω i ′ is the normalized weight value of index i, S ci is the comprehensive score of indicator i (obtained according to S2).

[0048] Further, the S4 includes:

[0049] S41. Definition of abnormal warning level: Considering the timeliness of warning, the abnormal change rate is used To measure, where St-i represents the comprehensive evaluation value at time ti, St-i-1 is the comprehensive evaluation value at the previous time ti; St-1 represents the comprehensive evaluation value at time t-1, ωi is the weight coefficient related to different time intervals, ωi decreases as the time interval increases, and

[0050] When the abnormal change rate exceeds a certain threshold, the warning level needs to be increased, which means that the equipment operation status is rapidly deteriorating. The warning level L(r) determined by the abnormal change rate is expressed as:

[0051]

[0052] Among them, r is the abnormal change rate, r t1 、r t2 and r t3Different thresholds are set according to actual conditions;

[0053] S42. Anomaly detection, using mean shift detection based on statistical analysis, the data sequence is X = {x 1 , x 2 , …, x n}, with the current data point x i The set of data points in the sphere with radius r as the center is D i , then the mean shift vector m(x i )for:

[0054]

[0055] If the mean shift vector m(x i ) is greater than the threshold, it is judged as an abnormal point and a warning signal is issued.

[0056] Furthermore, the S5 includes:

[0057] S51. Establish a feedback mechanism for early warning operation, record the changes in equipment operation data after the early warning operation is executed, and after the early warning operation is executed, the equipment operation data vector is X′={x1′,x′2,…,x′n}, which is different from the data sequence X={x 1 , x 2 , …, x n}, and evaluate the effect of the early warning operation by analyzing the data changes; if the key performance indicators are significantly improved after executing a certain early warning operation, it means that the early warning operation is effective; on the contrary, if the key performance indicators continue to deteriorate, the early warning operation strategy needs to be further adjusted;

[0058] S52. Formulate emergency response measures, formulate a set of emergency response measures E = {e1, e2, ..., en} under different warning levels, and when the warning level is i, execute the corresponding emergency response measure ei.

[0059] In summary, due to the adoption of the above technical solution, the beneficial technical effects of the invention are:

[0060] A method for accurate monitoring and operation data analysis of new energy power generation equipment changes the incomplete situation of key performance indicators in existing technologies by extracting key performance indicators such as equipment efficiency, energy consumption and environmental adaptability. These three indicators reflect the operating status of the equipment from different angles, making the evaluation of the equipment operation more comprehensive and accurate. The scoring criteria and evaluation grade criteria of the operating performance indicators are defined and quantified through key performance indicators such as equipment efficiency, energy consumption and environmental adaptability, taking into account the changes in equipment performance under different working conditions, and solving the problem of unscientific scoring criteria in existing technologies. For example, for equipment efficiency, the scoring is no longer based solely on a fixed threshold range, but the impact of environmental factors on efficiency is comprehensively considered, which improves the accuracy and rationality of the scoring and reduces the possibility of misjudgment.

[0061] In terms of evaluation function construction: the weights are determined by combining the analytic hierarchy process and the entropy weight method, which avoids the problem of a single weight determination method in the existing technology. This combination method fully considers the complex relationship between indicators and the characteristics of the data itself, making the weight distribution more reasonable, thereby improving the accuracy of the comprehensive evaluation value.

[0062] Enhanced objectivity of comprehensive evaluation: Normalization of indicators such as equipment efficiency, energy consumption and environmental adaptability solves the problem that the existing technology does not consider normalization. Normalization makes indicators of different dimensions and numerical ranges comparable in comprehensive evaluation, avoids the situation where some indicators unreasonably dominate the comprehensive evaluation, and enhances the objectivity of comprehensive evaluation.

[0063] Abnormal detection and early warning: The use of methods such as mean drift detection based on statistical analysis can adapt to the complex change patterns of equipment operation data, dynamically adjust the detection threshold, and overcome the inaccuracy of the existing abnormal detection methods. This improves the accuracy of abnormal detection, reduces misjudgments and missed judgments, and can detect abnormalities in equipment operation more promptly.

[0064] Improved effectiveness of early warning mechanism: A detailed early warning level standard has been established to solve the problem of imperfect early warning mechanism of existing technology. This can make the early warning information transmission more timely and accurate, and relevant personnel can take more effective measures based on the early warning information, thus improving the effectiveness of the early warning mechanism.

[0065] Early warning operation and emergency response: According to the specific abnormal conditions and operation risks of the equipment, targeted early warning operations are formulated, which changes the lack of targetedness of the existing technical early warning operations. This enables early warning operations to more effectively alleviate the operation risks of the equipment and improve the stability of equipment operation.

[0066] Improved emergency response efficiency: By establishing a feedback mechanism for early warning operations and formulating emergency response measures at different early warning levels, the problem of ineffective and untimely emergency response in existing technologies has been solved. The effectiveness of early warning operations and emergency responses can be evaluated in a timely manner and adjusted as needed, which improves the efficiency of emergency response, reduces equipment downtime, and ensures power generation efficiency and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a flow chart of a method for accurate monitoring and operation data analysis of new energy power generation equipment;

[0068] Figure 2 A flowchart of a method for constructing an evaluation function;

[0069] Figure 3 A flow chart of the method for anomaly detection and early warning;

[0070] Figure 4 The figure is a flow chart of the method of early warning operation and emergency response. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the invention more clear, the invention is further described in detail below in combination with the embodiments. It should be understood that the specific embodiments described here are only used to explain the invention and are not used to limit the invention.

[0072] like Figure 1 As shown, a method for accurate monitoring and operation data analysis of new energy power generation equipment includes:

[0073] S1. Data collection and storage: deploy multifunctional sensors at key nodes of the new energy power generation system to collect equipment operation data in real time and store it in the database;

[0074] S2. Operation status evaluation, extracting key performance indicators such as equipment efficiency, energy consumption and environmental adaptability, defining and quantifying the scoring criteria and evaluation grade standards for operation performance indicators;

[0075] S3. Construct an evaluation function according to the scoring criteria and evaluation grade criteria of S2, calculate the normalized weight value of each operating performance indicator, and obtain a comprehensive evaluation value;

[0076] S4. Anomaly detection and warning: Based on the comprehensive evaluation value obtained in S3, define the level standard of abnormal warning, quantify the value range of the warning level, compare the comprehensive evaluation value with the value of the warning level, and execute the warning operation if it falls within the abnormal value range;

[0077] S5. Early warning operation and emergency response: when the comprehensive evaluation value indicates potential operational risks, the preset early warning operation is automatically executed.

[0078] The operation data in S1 include voltage sensors, current sensors, temperature sensors, light intensity sensors, etc.; the equipment efficiency includes photovoltaic cell conversion efficiency, inverter efficiency, and battery charge and discharge efficiency, etc.,

[0079] The conversion efficiency of photovoltaic cells is ηp, Po,p is the output power of the photovoltaic panel, A is the area of ​​the photovoltaic panel, and Q is the solar radiation intensity;

[0080] The inverter efficiency is P o,i is the output power of the inverter, P i,i is the input power of the inverter;

[0081] Battery charge and discharge efficiency η b , E o,b is the energy output by the battery, E i,b is the energy input from the battery.

[0082] In S2, energy consumption refers to the total energy consumption of the analyzed equipment and the energy consumption distribution of different equipment components under different operating conditions. The total energy consumption E is expressed as: P(t) is the power consumption of the device at time t 1 and t 2 is the start and end time of the time interval; if the device has n components, the energy consumption of component i is E i , then the energy consumption ratio Pi of the components is:

[0083]

[0084] In S2, environmental adaptability is to measure the adaptability of the equipment to different environmental conditions using the environmental adaptability coefficient A;

[0085] Environmental adaptability coefficient A for solar power generation equipment d for:

[0086] Environmental adaptability coefficient A′ for wind power generation equipment d for:

[0087] Among them, η pa (T 1 ,S 1 ) is in the environment condition (T 1 ,S 1 ) is the efficiency of the photovoltaic panel, the denominator η pa (T 0 ,S 0 ) is in the environment condition (T 0,S 0 ) when the photovoltaic panel is at 100°C; the ratio of the two is used to measure the change in efficiency of the equipment under different environmental conditions, thereby reflecting the equipment's ability to adapt to the environment;

[0088] W 0 and W 1 Represents different wind speed conditions, P o,w (W 1 ) indicates that the wind speed is W 1 The output power of wind power generation equipment at η w (W 0 ) indicates that the wind speed is W 0 The formula measures the adaptability of wind power generation equipment to different wind speed environments through the ratio of output power to performance indicators under different wind speed conditions.

[0089] In S2, the method of quantifying the scoring criteria and evaluation grade criteria of the operating performance indicators is:

[0090] A combination of quantitative and qualitative scoring methods is used to ensure the comprehensiveness and accuracy of the scoring criteria. For equipment efficiency, specific efficiency ranges are set to correspond to different scoring values, and equipment efficiency scoring, energy consumption scoring, and environmental adaptability scoring are comprehensively scored.

[0091] Specifically:

[0092] The rating of equipment efficiency is S η , according to the efficiency interval [η l ,η h ] Set the scoring criteria, where ηl is the set low efficiency threshold and ηh is the set high efficiency threshold;

[0093] When the equipment efficiency η satisfies η ≥ ηh, S η =90→100;

[0094] When ηl≤η<ηh, S η =80→90;

[0095] When η≤ηl, Sη=70→80, etc.

[0096] Energy consumption and environmental adaptability scores are classified in the same way as equipment efficiency scores;

[0097] At the same time, combined with the equipment efficiency score S η , Energy Consumption Score i , Environmental adaptability score S d The weight coefficient is used for comprehensive scoring, and the comprehensive scoring formula is:

[0098] S c=ω 1 S η +ω 2 S i +ω 3 S d ;

[0099] Among them, ω 1 is the weight coefficient of equipment efficiency score, ω 2 is the weight coefficient of energy consumption score, ω 3 is the weight coefficient of environmental adaptability score, and ω 1 +ω 2 +ω 3 =1.

[0100] like Figure 2 As shown, the S3 includes:

[0101] S31. Construct an evaluation function to determine the weight, using the analytic hierarchy process (AHP) and entropy weight

[0102] The combination of law

[0103] The weight is determined by

[0104] In the hierarchical analysis method, the judgment matrix A is constructed as follows: ij ) n×n , a ij Indicates the importance of index i relative to index j, by calculating the maximum eigenvalue λ of the judgment matrix max and the corresponding eigenvector W = (ω 1 ,ω 2 …ω n ), and obtain the weight vector ω determined by the hierarchical analysis method A ; Among them, the maximum eigenvalue λ max and the corresponding eigenvector W = (ω 1 ,ω 2 …ω n ) is calculated using mathematical software such as MATLAB's eig function;

[0105] In the entropy weight method, there are m evaluation objects, n evaluation indicators, and the indicator value is x. ij , x ij Including equipment efficiency rating S η , Energy Consumption Score i and environmental adaptability score S d ; First, calculate the information entropy Ej of index j, The relative importance pij, Indicates the relative importance of the i-th indicator in the j-th evaluation object; the coefficient of information entropy k, Information entropy is used to measure the uncertainty of an indicator. The larger the information entropy of an indicator, the smaller the amount of information it provides, and the smaller its weight should be.

[0106] Then calculate the entropy weight of indicator j The entropy weight reflects the weight of each indicator determined according to the characteristics of the data itself;

[0107] The final weight is calculated using the formula ω f =αω A +(1-α)ω e Determine, where α is the weight coefficient, the value is between [0,1]; where, ω A is the weight vector determined by the AHP method, ω e is the weight vector obtained by the entropy weight method;

[0108] S32. Calculate the normalized weight value of each operating performance indicator:

[0109] For equipment efficiency η, its maximum efficiency under ideal conditions is η max , normalized value of equipment efficiency

[0110] For energy consumption E, the energy consumption of the equipment in the best energy-saving state is E min , energy consumption normalized value

[0111] For environmental adaptability A, it is assumed that the environmental adaptability of the equipment under the most suitable environmental conditions is A d-max , normalized value

[0112] The original weights of equipment efficiency, energy consumption and environmental adaptability are ω η ,ω E ,ω A , the normalized weight values ​​are ω η ′、ω′ E ,ω′ A ;

[0113]

[0114] In the formula, ωj represents the weight value involved in determining the normalized weight value; nj is the normalization factor corresponding to the weight value ωj;

[0115] S33. Calculate the comprehensive evaluation value by weighted summation, that is:

[0116]

[0117] Among them, S is the comprehensive evaluation value; ω i ′ is the normalized weight value of index i, Sci is the comprehensive score of indicator i (obtained according to S2).

[0118] like Figure 3 As shown, the S4 includes:

[0119] S41. Definition of abnormal warning level: Considering the timeliness of warning, the abnormal change rate is used To measure, where St-i represents the comprehensive evaluation value at time ti, St-i-1 is the comprehensive evaluation value at the previous time ti; St-1 represents the comprehensive evaluation value at time t-1, ωi is the weight coefficient related to different time intervals, ωi decreases as the time interval increases, and

[0120] When the abnormal change rate exceeds a certain threshold, the warning level needs to be increased, which means that the equipment operation status is rapidly deteriorating. The warning level L(r) determined by the abnormal change rate is expressed as:

[0121]

[0122] Among them, r is the abnormal change rate, r t1 、r t2 and r t3 Different thresholds are set according to actual conditions;

[0123] S42. Anomaly detection, using mean shift detection based on statistical analysis, the data sequence is X = {x 1 , x 2 , …, x n}, with the current data point x i The set of data points in the sphere with radius r as the center is D i , then the mean shift vector m(x i )for:

[0124]

[0125] If the mean shift vector m(x i ) is greater than the threshold, it is judged as an abnormal point and a warning signal is issued.

[0126] like Figure 4 As shown, the S5 comprises:

[0127] S51. Establish a feedback mechanism for early warning operation, record the changes in equipment operation data after the early warning operation is executed, and after the early warning operation is executed, the equipment operation data vector is X′={x1′,x′2,…,x′n}, which is different from the data sequence X={x 1 , x 2 , …, x n}, and evaluate the effect of the early warning operation by analyzing the data changes; if the key performance indicators (such as equipment efficiency) are significantly improved after executing a certain early warning operation, it means that the early warning operation is effective; on the contrary, if the key performance indicators continue to deteriorate, the early warning operation strategy needs to be further adjusted;

[0128] S52. Formulate emergency response measures, formulate a set of emergency response measures E = {e1, e2, ..., en} under different warning levels, and when the warning level is i, execute the corresponding emergency response measure ei.

[0129] The above description is a preferred embodiment of the invention and is not intended to limit the invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the invention should be included in the protection scope of the invention.

Claims

1. A method for accurate monitoring and operation data analysis of new energy power generation equipment, characterized in that: include: S1. Data collection and storage: deploy multifunctional sensors at key nodes of the new energy power generation system to collect equipment operation data in real time and store it in the database; S2. Operation status evaluation, extracting key performance indicators, and defining and quantifying the scoring criteria and evaluation grade criteria for operation performance indicators; S3. Construct an evaluation function according to the scoring criteria and evaluation grade criteria of S2, calculate the normalized weight value of each operating performance indicator, and obtain a comprehensive evaluation value; S4. Anomaly detection and warning: Based on the comprehensive evaluation value obtained in S3, define the level standard of abnormal warning, quantify the value range of the warning level, compare the comprehensive evaluation value with the value of the warning level, and execute the warning operation if it falls within the abnormal value range; S5. Early warning operation and emergency response: when the comprehensive evaluation value indicates potential operational risks, the preset early warning operation is automatically executed.

2. A method for accurate monitoring and operation data analysis of new energy power generation equipment according to claim 1, characterized in that: The operation data in S1 includes a voltage sensor, a current sensor, a temperature sensor, and a light intensity sensor.

3. The method for accurate monitoring and operation data analysis of new energy power generation equipment according to claim 1 is characterized in that: Key performance indicators include: equipment efficiency, energy consumption and environmental adaptability.

4. The method for accurate monitoring and operation data analysis of new energy power generation equipment according to claim 1, characterized in that: In S2, the equipment efficiency includes the photovoltaic cell conversion efficiency, the inverter efficiency and the battery charging and discharging efficiency. Among them, the conversion efficiency of photovoltaic cells is η p , P o,p is the output power of the photovoltaic panel, A is the area of ​​the photovoltaic panel, and Q is the solar radiation intensity; The inverter efficiency is P o,i is the output power of the inverter, P i,i is the input power of the inverter; The charge and discharge efficiency of the battery is η b , E o,b is the energy output by the battery, E i,b is the energy input from the battery.

5. The method for accurate monitoring and operation data analysis of new energy power generation equipment according to claim 1 is characterized in that: In S2, energy consumption refers to the total energy consumption of the analyzed equipment and the energy consumption distribution of different equipment components under different operating conditions. The total energy consumption E is expressed as: P(t) is the power consumption of the device at time, t1 and t2 are the start and end times of the time interval; if the device has n components, the energy consumption of component i is E i , then the energy consumption ratio of the component is P i , 6. The method for accurate monitoring and operation data analysis of new energy power generation equipment according to claim 1, characterized in that: In S2, environmental adaptability is to measure the adaptability of the equipment to different environmental conditions using the environmental adaptability coefficient A; Environmental adaptability coefficient A for solar power generation equipment d for: Environmental adaptability coefficient A′ for wind power generation equipment d for: Among them, η pa (T1, S1) is the efficiency of the photovoltaic panel when the environmental conditions are (T1, S1), and the denominator η pa (T0, S0) is the efficiency of the photovoltaic panel when the environmental condition is (T0, S0); the ratio of the two is used to measure the change in the efficiency of the equipment under different environmental conditions, thereby reflecting the adaptability of the equipment to the environment; W0 and W1 represent different wind speed conditions, P o,w (W1) represents the output power of the wind power generation equipment when the wind speed is W1; η w (W0) represents the performance index related to the wind energy utilization efficiency of the wind power generation equipment when the wind speed is W0; the formula measures the adaptability of the wind power generation equipment to different wind speed environments through the ratio of the output power to the performance index under different wind speed conditions.

7. A method for accurate monitoring and operation data analysis of new energy power generation equipment according to claim 1, characterized in that: In S2, the method of quantifying the scoring criteria and evaluation grade criteria of the operating performance indicators is: The rating of equipment efficiency is S η , according to the efficiency interval [η l ,η h ] Set the scoring criteria, where η l is the set low efficiency threshold, η h is the high efficiency threshold set; When the equipment efficiency η satisfies η ≥ η l When S η =90→100; When η low ≤ η < η l , S η = 80 → 90; Energy consumption and environmental adaptability scores are classified in the same way as equipment efficiency scores; At the same time, combined with the equipment efficiency score S η , Energy Consumption Score i , Environmental adaptability score S d The weight coefficient is used for comprehensive scoring, and the comprehensive scoring formula is: S c =ω1S η +ω2S i +ω3S d ; Among them, ω1 is the weight coefficient of the equipment efficiency score, ω2 is the weight coefficient of the energy consumption score, ω3 is the weight coefficient of the environmental adaptability score, and ω1+ω2+ω3=1.

8. The method for accurate monitoring and operation data analysis of new energy power generation equipment according to claim 1, characterized in that: The S3 includes: S31. Construct an evaluation function to determine the weight, and use a combination of analytic hierarchy process and entropy weight method to determine the weight. In the hierarchical analysis method, the judgment matrix A is constructed as follows: ij ) n×n , a ij Indicates the importance of index i relative to index j, by calculating the maximum eigenvalue λ of the judgment matrix max and the corresponding eigenvector W = (ω1,ω2…ω n ), and obtain the weight vector ω determined by the hierarchical analysis method A ; Among them, the maximum eigenvalue λ max and the corresponding eigenvector W = (ω1,ω2…ω n ) is calculated using mathematical software such as MATLAB's eig function; In the entropy weight method, there are m evaluation objects, n evaluation indicators, and the indicator value is x. ij , x ij Including equipment efficiency rating S η , Energy Consumption Score i and environmental adaptability score S d ; First calculate the information entropy E of index j j , The relative importance p ij , represents the relative importance of the i-th indicator in the j-th evaluation object; the coefficient of information entropy k, Information entropy is used to measure the uncertainty of an indicator. The larger the information entropy of an indicator, the smaller the amount of information it provides, and the smaller its weight should be. Then calculate the entropy weight of indicator j The entropy weight reflects the weight of each indicator determined according to the characteristics of the data itself; The final weight is calculated using the formula ω f =αω A +(1-α)ω e Determine, where α is the weight coefficient, the value is between [0,1]; where, ω A is the weight vector determined by the AHP method, ω e is the weight vector obtained by the entropy weight method; S32. Calculate the normalized weight value of each operating performance indicator: For equipment efficiency η, its maximum efficiency under ideal conditions is η max , normalized value of equipment efficiency For energy consumption E, the energy consumption of the equipment in the best energy-saving state is E min , energy consumption normalized value For environmental adaptability A, it is assumed that the environmental adaptability of the equipment under the most suitable environmental conditions is A d-max , normalized value The original weights of equipment efficiency, energy consumption and environmental adaptability are ω η ,ω E ,ω A , the normalized weight values ​​are ω′ η ,ω′ E ,ω′ A ; In the formula, ω j Represents the weight value involved in determining the normalized weight value; n j is the weight value ω j The corresponding normalization factor; S33. Calculate the comprehensive evaluation value by weighted summation, that is: Among them, S is the comprehensive evaluation value; ω′ i is the normalized weight value of index i, S ci is the comprehensive score of indicator i.

9. The method for accurate monitoring and operation data analysis of new energy power generation equipment according to claim 1, characterized in that: The S4 includes: S41. Definition of abnormal warning level: Considering the timeliness of warning, the abnormal change rate is used To measure, where S t-i represents the comprehensive evaluation value at time ti, S t-i-1 is the comprehensive evaluation value at the previous moment ti; S t-1 represents the comprehensive evaluation value at time t-1, ω i is the weight coefficient associated with different time intervals, ω i As the time interval increases, it decreases, and When the abnormal change rate exceeds a certain threshold, the warning level needs to be increased, which means that the equipment operation status is rapidly deteriorating. The warning level L(r) determined by the abnormal change rate is expressed as: Among them, r is the abnormal change rate, r t1 、r t2 and r t3 Different thresholds are set according to actual conditions; S42. Anomaly detection, using mean shift detection based on statistical analysis, the data sequence is X = {x1, x2, ..., x n }, with the current data point x i The set of data points in the sphere with radius r as the center is D i , then the mean shift vector m(x i )for: If the mean shift vector m(x i ) is greater than the threshold, it is judged as an abnormal point and a warning signal is issued.

10. A method for accurate monitoring and operation data analysis of new energy power generation equipment according to claim 1, characterized in that: The S5 includes: S51. Establish a feedback mechanism for early warning operations, record the changes in equipment operation data after the early warning operation is executed, and after the early warning operation is executed, the equipment operation data vector is X′={x′1,x′2,…,x′ n }, and the data sequence before the early warning operation is executed X = {x1, x2, ..., x n }, and evaluate the effect of the early warning operation by analyzing the data changes; if the key performance indicators are significantly improved after executing a certain early warning operation, it means that the early warning operation is effective; on the contrary, if the key performance indicators continue to deteriorate, the early warning operation strategy needs to be further adjusted; S52. Formulate emergency response measures and formulate emergency response measures set E = {e1, e2, ..., e n }, when the warning level is i, execute the corresponding emergency response measure e i .

Images