Substation automation equipment operation and maintenance management system based on regulation and control cloud

Abstract

The invention relates to the technical field of substation equipment operation and maintenance management, and discloses a substation automation equipment operation and maintenance management system based on regulation and control cloud.The substation automation equipment operation and maintenance management system comprises a data acquisition module, a preprocessing module, a feature extraction module, a state evaluation module and a result display module.The method comprises the steps that firstly, key data are collected through the data acquisition module, and a foundation is laid for follow-up analysis; the preprocessing module can remove abnormal values of key data, guarantee data quality and avoid wrong analysis and decision; the feature extraction module can extract multiple key features, and the state evaluation module calculates a health state index and judges the fault hidden danger and degree according to the features, accurately evaluates the equipment state, facilitates targeted operation and maintenance, predicts the future state through a linear regression algorithm based on historical data, and facilitates fault prevention in advance. The result display module realizes information visualization and assists in scientific decision making; the intelligent level of operation and maintenance can be improved, and stable operation of equipment is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of substation equipment operation and maintenance management, and in particular to a substation automation equipment operation and maintenance management system based on a control cloud. Background Art

[0002] In the operation and management of substations, there are many automated devices in the substations and the types are complicated. The traditional operation and maintenance management model faces many severe challenges. Traditional operation and maintenance management often relies on manual regular inspections and experience judgment. Manual inspections have obvious limitations. On the one hand, the inspection cycle is relatively fixed, and it is difficult to monitor the operation status of the equipment in real time and continuously. This makes it difficult to detect some intermittent or sudden faults in time, which may cause the equipment to continue to operate without being discovered, thereby increasing the risk of failures, and may even cause power accidents, posing a serious threat to the safety of the power grid. On the other hand, manual recording and analysis of data are prone to errors and omissions, and when faced with massive equipment operation data, it is difficult to conduct comprehensive, in-depth and accurate analysis, and it is impossible to efficiently extract valuable information from complex data to accurately evaluate the status of the equipment.

[0003] In addition, the lack of effective data processing and analysis methods has resulted in the failure to fully utilize key data during the operation of the equipment. However, in the traditional mode, data is simply recorded without in-depth exploration of its internal connections and changing trends, making it difficult to predict possible equipment failures in advance and to effectively prevent failures. Furthermore, due to the lack of a scientific and systematic evaluation system, the determination of whether the equipment has hidden faults and the extent of the fault is often not accurate and timely. This may lead to excessive maintenance, a waste of manpower, material and time resources; or untimely maintenance, causing the equipment to operate with "diseases", reducing the service life of the equipment, increasing operation and maintenance costs and affecting the reliability of the power system.

[0004] To sum up, in order to overcome the defects of the traditional substation automation equipment operation and maintenance management mode and improve the efficiency, accuracy and intelligence level of operation and maintenance management, there is an urgent need for a substation automation equipment operation and maintenance management system based on the control cloud, which can timely detect fault hazards and predict equipment operation trends, thereby ensuring the reliable operation of substation automation equipment. Summary of the invention

[0005] The purpose of the present invention is to provide a substation automation equipment operation and maintenance management system based on a control cloud, which solves the technical problems raised in the background technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] Substation automation equipment operation and maintenance management system based on control cloud, including:

[0008] A data acquisition module is used to collect key data of various automation devices in the substation, including but not limited to multiple key parameters corresponding to actual load current, actual power, actual temperature, and actual insulation resistance;

[0009] The preprocessing module is used to preprocess the key data and remove abnormal values ​​in the key data through preprocessing;

[0010] A feature extraction module is used to extract multiple key features from the key data corresponding to each automation device within the observation period;

[0011] The status assessment module is used to perform status assessment and analysis on each automation device based on the extraction of multiple key features, and obtain the health status index of each automation device through the status assessment and analysis, and then determine whether each automation device has potential faults and the degree of faults when faults occur based on the health status index;

[0012] The result display module is used to display the results obtained by the feature extraction module and the state assessment module to relevant personnel.

[0013] As a further solution of the present invention: the pretreatment method is as follows:

[0014] Step Y1, taking a key parameter corresponding to a feature in an automation device as an example;

[0015] Define an observation period and divide it into several collection time nodes;

[0016] Step Y2: extract the key parameters of the feature in the automation equipment at each acquisition time node during the observation period and mark them as G i , i = 1, 2, ... n, n represents the number of acquisition time nodes;

[0017] Step Y3, calculate all G i The average value of , and mark it as Gp;

[0018] At the same time, calculate all G i The standard deviation of , and label it as Gb;

[0019] Then through:

[0020]

[0021] Calculate the key parameters G i Grubbs statistic Gg i ;

[0022] Step Y4, then Gg i Compare with the preset Grubbs critical value Gg1 and determine the abnormal parameters;

[0023] The specific method is as follows:

[0024] If Gg i ≤Gg1, then the corresponding Gg i The corresponding G i Determined as abnormal parameters;

[0025] If Gg i >Gg1, then the corresponding Gg i The corresponding G i Determined as abnormal parameters;

[0026] Step Y5, when the corresponding G i If it is judged as an abnormal parameter, G i The corresponding collection time node is recorded as T i , T represents the number of collection time nodes:

[0027] Then according to the collection time node T i Get the adjacent acquisition time node T i-1 and T i+1 , and its corresponding key parameter G i-1 and G i+1 ;

[0028] Among them, T i-1 Indicates the acquisition time node T i The adjacent previous acquisition time node, G i-1 Indicates the acquisition time node T i The key parameters at the previous adjacent acquisition time node, T i+1 Indicates the acquisition time node T i The next adjacent acquisition time node, G i+1 Indicates the acquisition time node T i The key parameters at the next adjacent acquisition time node;

[0029] Then pass:

[0030]

[0031] Calculate the parameter G that is judged to be abnormal during the observation period i Replacement value G0 i .

[0032] As a further solution of the present invention: the feature extraction module is as follows:

[0033] Select an automation equipment;

[0034] Step T1: Extraction of actual load current characteristics:

[0035] Extract the actual load current during the observation period and mark it as SL i ;

[0036] At the same time, the preset rated current is extracted and marked as EL;

[0037] Then through:

[0038]

[0039] Calculate the load factor index Z of the automation equipment during the observation period SL ;

[0040] Step T2: Extracting actual temperature features:

[0041] Extract the actual temperature during the observation period and mark it as SW i ;

[0042] Then through:

[0043]

[0044] Calculate the temperature rise rate WS of the automation equipment during the observation period;

[0045] Then, the preset temperature rise rate warning value is extracted and marked as SWy; then:

[0046]

[0047] Calculate the temperature rise rate index Z of the automation equipment during the observation period SW ;

[0048] Step T3: actual power feature extraction:

[0049] Extract the actual power during the observation period and mark it as SP i ;

[0050] At the same time, the preset rated power is extracted and marked as EP;

[0051] Then through:

[0052]

[0053] Calculate the power deviation rate index Z of the automation equipment during the observation period SP ;

[0054] Step T4: Extraction of actual insulation resistance characteristics:

[0055] Extract the actual insulation resistance during the observation period and mark it as SR i ;

[0056] At the same time, the preset qualified lower limit value of the insulation resistance is extracted and marked as R min ;

[0057] And extract the insulation resistance corresponding to the preset ideal maximum value and mark it as R max ;

[0058] Then through:

[0059]

[0060] Calculate the insulation resistance index Z of the automation equipment during the observation period SR .

[0061] As a further solution of the present invention: the state assessment analysis method is as follows:

[0062] Select an automation equipment;

[0063] Step P1: Extraction of key indicators of automation equipment:

[0064] Extract the load rate index Z of the automation equipment SL , Temperature rise rate index Z SW , power deviation rate index Z SP , Insulation resistance index Z SR ;

[0065] Step P2: Calculation of health status index:

[0066] pass:

[0067]

[0068] Calculate the health status index ZT of the automation equipment;

[0069] In the formula, α SL , α SW , α SP , α SR They are respectively the preset weight coefficients corresponding to the load rate index, the temperature rise rate index, the power deviation rate index, and the insulation resistance index;

[0070] Step P3: Fault potential assessment and determination:

[0071] The health status index ZT of each automation device is combined with the preset assessment judgment threshold ZTy to perform fault potential analysis, and then determine whether the automation device has fault potential and the degree of fault when it exists within the observation period.

[0072] As a further solution of the present invention: in step P3, the method for determining the potential faults within the observation period is as follows:

[0073] If ZT>ZTy, the automation equipment is judged to be in good condition;

[0074] If ZTy≥ZT>0.8×ZTy, the automation equipment is judged to be in a slight fault state;

[0075] If 0.8×ZTy≥ZT>0.5×ZTy, the automation equipment is judged to be in a moderate fault state;

[0076] If ZT≤0.5×ZTy, the automation equipment is determined to be in a severe fault state.

[0077] As a further solution of the present invention: the state assessment module is also used to perform short-term trend prediction based on multiple key features corresponding to multiple observation periods in history.

[0078] As a further solution of the present invention: the short-term trend prediction method is as follows:

[0079] Step G1: Historical observation period mark:

[0080] Mark multiple observation periods in history as LT j , j = 1, 2, ... m, m represents the number of observation periods in the history;

[0081] Step G2: Extraction of historical data of specific indicators:

[0082] Taking the load factor as an example, we extract the load factor indicators in multiple observation periods in history and mark them as Z. SL，j ;

[0083] Step G3: Linear regression model construction:

[0084] Combined with the linear regression algorithm, a linear regression model formula of the load rate index and multiple observation periods in history is proposed, and the linear regression model formula is as follows:

[0085] Z SL，j =a×LT j +b;

[0086] Among them, a and b in the linear regression model formula are obtained by least squares fitting;

[0087] The specific method is as follows:

[0088]

[0089] Step G4: Prediction of the load factor index for the next cycle:

[0090] Get the next observation period after the current time node;

[0091] Then substitute it into the linear regression model formula and obtain the load factor index predicted in the next observation period;

[0092] Step G5: Multi-index prediction expansion:

[0093] According to the method of step G2 to step G4, the predicted temperature rise rate index, power deviation rate index, and insulation resistance index in the next observation period are calculated in sequence;

[0094] Step G6: Calculation of predicted health status index:

[0095] Combine the result of step G5 with the method of step P2 to calculate the predicted health status index of the automation equipment in the next observation period and record it as ZT m+1 ;

[0096] Among them, m+1 represents the next observation period after the current time node;

[0097] Step G7: Predicting potential faults and evaluating their impact:

[0098] The predicted health status index of the automation equipment in the next observation cycle is combined with the preset evaluation judgment threshold ZTy to perform fault potential analysis, and then predict whether the automation equipment has fault potential and the degree of fault when it exists in the next observation cycle.

[0099] As a further solution of the present invention: in step G7, the prediction method of the potential fault in the next observation period is as follows:

[0100] The method is as follows:

[0101] If ZT m+1 >ZTy, the prediction result of the automation equipment in the next observation period is judged to be in good condition;

[0102] If ZTy≥ZT m+1 >0.8×ZTy, the prediction result of the automation equipment in the next observation period is judged to be a slight fault state;

[0103] If 0.8×ZTy≥ZT m+1 >0.5×ZTy, the prediction result of the automation equipment in the next observation period is determined to be a moderate fault state;

[0104] If ZT m+1 ≤0.5×ZTy, the prediction result of the automation equipment in the next observation period is judged to be a severe fault state.

[0105] Beneficial effects of the present invention:

[0106] Improved data accuracy: By preprocessing key data through the preprocessing module and using the Grubbs criterion to identify and process outliers, the accuracy and reliability of the data are effectively improved, providing a more accurate data basis for subsequent analysis and evaluation, and reducing misjudgments and wrong decisions caused by abnormal data.

[0107] Comprehensive assessment of equipment status: The feature extraction module can extract comprehensive features of automation equipment from load rate, temperature rise rate, power deviation rate, insulation resistance, etc. The status assessment module calculates the health status index based on these key features and preset weight coefficients, thereby achieving a comprehensive quantitative assessment of the equipment status. It can accurately determine whether the equipment has hidden faults and the degree of the fault, which helps operation and maintenance personnel to understand the equipment operation status in a timely manner and take targeted measures.

[0108] Fault prediction and prevention: The status assessment module performs short-term trend prediction based on key features corresponding to multiple historical observation cycles. It can predict the health status index of the equipment in the future observation cycle and possible fault hazards and fault severity, so that operation and maintenance personnel can plan maintenance strategies in advance, prevent faults in advance, reduce losses caused by sudden equipment failures, and improve the safety and stability of substation operation.

[0109] Visualization and decision support: The result display module displays the feature extraction and status assessment results to relevant personnel, making the operation and maintenance information intuitive, which is convenient for operation and maintenance personnel, managers, etc. to grasp the equipment status in time, and provide strong data support for their decision-making on operation and maintenance plans, resource allocation, etc., thus improving the efficiency and scientificity of operation and maintenance management. BRIEF DESCRIPTION OF THE DRAWINGS

[0110] The present invention will be further described below in conjunction with the accompanying drawings.

[0111] Figure 1 It is a system block diagram of the substation automation equipment operation and maintenance management system based on the control cloud of the present invention.

[0112] Figure 2 It is a flow chart of the feature extraction module in the substation automation equipment operation and maintenance management system based on the control cloud of the present invention.

[0113] Figure 3 This is a schematic diagram of the process of the state assessment module in the substation automation equipment operation and maintenance management system based on the control cloud of the present invention. Figure 1 .

[0114] Figure 4 This is a schematic diagram of the process of the state assessment module in the substation automation equipment operation and maintenance management system based on the control cloud of the present invention. Figure 2 . DETAILED DESCRIPTION

[0115] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0116] Embodiment 1

[0117] See also Figure 1 , Figure 2 , Figure 3 , Figure 4 As shown, the present invention is a substation automation equipment operation and maintenance management system based on a control cloud, comprising:

[0118] A data acquisition module is used to collect key data of various automation devices in the substation, including but not limited to multiple key parameters corresponding to actual load current, actual power, actual temperature, and actual insulation resistance;

[0119] A feature extraction module is used to extract multiple key features from the key data corresponding to each automation device within the observation period;

[0120] Take an automation device as an example, the specific method is as follows:

[0121] Step T1: Extraction of actual load current characteristics:

[0122] Extract the actual load current during the observation period and mark it as SL i ;

[0123] At the same time, the preset rated current is extracted and marked as EL;

[0124] Then through:

[0125]

[0126] Calculate the load factor index Z of the automation equipment during the observation period SL ;

[0127] Step T2: Extracting actual temperature features:

[0128] Extract the actual temperature during the observation period and mark it as SW i ;

[0129] Then through:

[0130]

[0131] Calculate the temperature rise rate WS of the automation equipment during the observation period;

[0132] Then the preset temperature rise rate warning value is extracted and marked as SWy;

[0133] Afterwards via:

[0134]

[0135] Calculate the temperature rise rate index Z of the automation equipment during the observation period SW ;

[0136] Step T3: actual power feature extraction:

[0137] Extract the actual power during the observation period and mark it as SP i ;

[0138] At the same time, the preset rated power is extracted and marked as EP;

[0139] Then through:

[0140]

[0141] Calculate the power deviation rate index Z of the automation equipment during the observation period SP ;

[0142] Step T4: Extraction of actual insulation resistance characteristics:

[0143] Extract the actual insulation resistance during the observation period and mark it as SR i ;

[0144] At the same time, the preset qualified lower limit value of the insulation resistance is extracted and marked as R min ;

[0145] And extract the insulation resistance corresponding to the preset ideal maximum value and mark it as R max ;

[0146] Then through:

[0147]

[0148] Calculate the insulation resistance index Z of the automation equipment during the observation period SR ;

[0149] The status assessment module is used to perform status assessment and analysis on each automation device based on the extraction of multiple key features, and obtain the health status index of each automation device through the status assessment and analysis, and then determine whether each automation device has potential faults and the degree of faults when faults occur based on the health status index;

[0150] Take an automation device as an example, the specific method is as follows:

[0151] Step P1: Extract the load rate index Z of the automation equipment SL , Temperature rise rate index Z SW , power deviation rate index Z SP , Insulation resistance index Z SR ;

[0152] Step P2, by:

[0153]

[0154] Calculate the health status index ZT of the automation equipment;

[0155] In the formula, α SL , α SW , α SP , α SR They are respectively the preset weight coefficients corresponding to the load rate index, the temperature rise rate index, the power deviation rate index, and the insulation resistance index;

[0156] Step P3, combining the health status index ZT of each automation device with the preset assessment threshold ZTy to identify potential fault hazards;

[0157] The potential faults are as follows:

[0158] If ZT>ZTy, the automation equipment is judged to be in good condition;

[0159] If ZTy≥ZT>0.8×ZTy, the automation equipment is judged to be in a slight fault state;

[0160] If 0.8×ZTy≥ZT>0.5×ZTy, the automation equipment is judged to be in a moderate fault state;

[0161] If ZT≤0.5×ZTy, the automation equipment is judged to be in a severe fault state;

[0162] The result display module is used to display the results obtained by the feature extraction module and the state evaluation module to relevant personnel, so that relevant personnel can operate and maintain the automation equipment according to different degrees of fault status.

[0163] This embodiment uses the feature extraction module to extract features from key data such as actual load current, actual temperature, actual power and actual insulation resistance, and calculates the corresponding load rate index, temperature rise rate index, power deviation rate index and insulation resistance index. The state assessment module then calculates the health status index based on these key features and preset weight coefficients, which can accurately determine whether the equipment has hidden faults and the degree of fault, and provide quantitative and accurate equipment status information for operation and maintenance personnel, which helps them to carry out operation and maintenance work in a targeted manner, improve operation and maintenance efficiency and reduce failure risks. The result display module intuitively presents the feature extraction and status assessment results to relevant personnel, making it convenient for operation and maintenance personnel and managers to grasp the equipment status in a timely and comprehensive manner, so as to reasonably plan operation and maintenance strategies and allocate resources based on different fault states of the equipment, making operation and maintenance decisions more scientific and efficient.

[0164] Embodiment 2

[0165] See also Figure 1 , Figure 2 , Figure 3 , Figure 4 As shown, as the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of this embodiment is different from that of the first embodiment only in that:

[0166] The state assessment module is also used to make short-term trend predictions based on multiple key features corresponding to multiple observation periods in history;

[0167] The specific method is as follows:

[0168] Step G1: Mark multiple observation periods in history as LT j , j = 1, 2, ... m, m represents the number of observation periods in the history;

[0169] Step G2: Take the load factor index as an example, extract the load factor index in multiple observation periods in history, and then mark it as Z SL，j ;

[0170] Step G3: Combined with the linear regression algorithm, a linear regression model formula of the load factor index and multiple observation periods in history is formulated, and the linear regression model formula is as follows:

[0171] Z SL，j =a×LT j +b;

[0172] in,

[0173] The a and b in the linear regression model formula are obtained by fitting using the least squares method;

[0174] The specific method is as follows:

[0175]

[0176] Step G4, obtaining the next observation period after the current time node;

[0177] Then substitute it into the linear regression model formula and obtain the load factor index predicted in the next observation period;

[0178] Step G5, according to the method of step G2 to step G4, calculate the predicted temperature rise rate index, power deviation rate index, and insulation resistance index in the next observation period in sequence;

[0179] Step G6: Combine the result of step G5 with the method of step P2 to calculate the predicted health status index of the automation equipment in the next observation period, and record it as ZT m+1 ;

[0180] Among them, m+1 represents the next observation period after the current time node;

[0181] Step G7, combining the predicted health status index of the automation equipment in the next observation period with the preset assessment threshold ZTy to identify potential fault hazards;

[0182] The method is as follows:

[0183] If ZT m+1 >ZTy, the prediction result of the automation equipment in the next observation period is judged to be in good condition;

[0184] If ZTy≥ZT m+1 >0.8×ZTy, the prediction result of the automation equipment in the next observation period is judged to be a slight fault state;

[0185] If 0.8×ZTy≥ZT m+1 >0.5×ZTy, the prediction result of the automation equipment in the next observation period is determined to be a moderate fault state;

[0186] If ZT m+1 ≤0.5×ZTy, the prediction result of the automation equipment in the next observation period is judged to be a severe fault state.

[0187] Based on the first embodiment, the state assessment module of this embodiment adds a short-term trend prediction function. Based on the key feature data of multiple historical observation periods, a linear regression algorithm is used to build a model to predict the key indicators in the future observation period, and then the predicted health status index is calculated and the potential fault hazards are determined. This enables operation and maintenance personnel to know in advance the possible state changes of the equipment in the future, and take preventive measures in advance, such as preparing maintenance resources in advance, adjusting operation plans, etc., effectively reducing the interference of sudden equipment failures on the operation of the power system, improving the reliability and stability of the power supply, and also helping to optimize the full life cycle management of the equipment and reduce operation and maintenance costs.

[0188] Embodiment 3

[0189] See also Figure 1 , Figure 2 , Figure 3 , Figure 4 As shown, as the third embodiment of the present invention, when the present application is implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments, and the difference between the technical solution of this embodiment and the first and second embodiments is that in this embodiment, it also includes:

[0190] The preprocessing module is used to preprocess the key data and remove abnormal values ​​in the key data through preprocessing;

[0191] The specific method is as follows:

[0192] Step Y1, taking a key parameter corresponding to a feature in an automation device as an example;

[0193] Define an observation period and divide it into several collection time nodes;

[0194] Step Y2: extract the key parameters of the feature in the automation equipment at each acquisition time node during the observation period and mark them as G i , i = 1, 2, ... n, n represents the number of acquisition time nodes;

[0195] Step Y3, calculate all G i The average value of , and mark it as Gp;

[0196] At the same time, calculate all G i The standard deviation of , and label it as Gb;

[0197] Then through:

[0198]

[0199] Calculate the key parameters G iGrubbs statistic Gg i ;

[0200] Step Y4, then Gg i Compare with the preset Grubbs critical value Gg1 and determine the abnormal parameters;

[0201] The specific method is as follows:

[0202] If Gg i ≤Gg1, then the corresponding Gg i The corresponding G i Determined as abnormal parameters;

[0203] If Gg i >Gg1, then the corresponding Gg i The corresponding G i Determined as abnormal parameters;

[0204] Step Y5, when the corresponding G i If it is judged as an abnormal parameter, G i The corresponding collection time node is recorded as T i , T represents the number of collection time nodes:

[0205] Then according to the collection time node T i Get the adjacent acquisition time node T i-1 and T i+1 , and its corresponding key parameter G i-1 and G i+1 ;

[0206] Among them, T i-1 Indicates the acquisition time node T i The adjacent previous acquisition time node, G i-1 Indicates the acquisition time node T i The key parameters at the previous adjacent acquisition time node, T i+1 Indicates the acquisition time node T i The next adjacent acquisition time node, G i+1 Indicates the acquisition time node T i The key parameters at the next adjacent acquisition time node;

[0207] Then pass:

[0208]

[0209] Calculate the parameter G that is judged to be abnormal during the observation period i Replacement value G0 i ;

[0210] Compared with Embodiments 1 and 2, the added preprocessing module of this embodiment uses the Grubbs statistic method to preprocess key data. By calculating the mean, standard deviation and Grubbs statistic, and comparing with the preset critical value to identify and process outliers, the accuracy and reliability of the data can be effectively improved. Accurate data is the basis for subsequent feature extraction, status assessment and trend prediction, which can avoid erroneous analysis and decision-making caused by abnormal data, further improve the performance and reliability of the entire operation and maintenance management system, and ensure the accuracy of equipment status assessment and prediction.

[0211] Embodiment 4

[0212] See also Figure 1 , Figure 2 , Figure 3 , Figure 4 As shown, as the fourth embodiment of the present invention, when the present application is implemented specifically, compared with the first, second and third embodiments, the technical solution of this embodiment is to combine and implement the solutions of the above-mentioned first, second, third and fourth embodiments.

[0213] This embodiment integrates all the functions and advantages of embodiments one, two, and three, and realizes a complete and optimized operation and maintenance management process from data collection, preprocessing, feature extraction, state evaluation to result display and short-term trend prediction. It can not only evaluate the current status of the equipment in real time and accurately, but also predict the future operation trend of the equipment prospectively, while ensuring the reliability of data quality. It comprehensively improves the intelligent level of operation and maintenance management of substation automation equipment, guarantees the stable operation of substation automation equipment to the greatest extent, improves the safety, reliability and economy of power system operation, reduces the labor and time costs of operation and maintenance, and improves the overall benefits and efficiency of operation and maintenance management.

[0214] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0215] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The substation automation equipment operation and maintenance management system based on the control cloud is characterized by: include: A data acquisition module is used to collect key data of various automation devices in the substation, including but not limited to multiple key parameters corresponding to actual load current, actual power, actual temperature, and actual insulation resistance; The preprocessing module is used to preprocess the key data and remove abnormal values ​​in the key data through preprocessing; A feature extraction module is used to extract multiple key features from the key data corresponding to each automation device within the observation period; The status assessment module is used to perform status assessment and analysis on each automation device based on the extraction of multiple key features, and obtain the health status index of each automation device through the status assessment and analysis, and then determine whether each automation device has potential faults and the degree of faults when faults occur based on the health status index; The result display module is used to display the results obtained by the feature extraction module and the state assessment module to relevant personnel.

2. The substation automation equipment operation and maintenance management system based on the control cloud according to claim 1 is characterized in that: The feature extraction module is as follows: Select an automation equipment; Step T1: Extraction of actual load current characteristics: Extract the actual load current during the observation period and mark it as SL i ; At the same time, the preset rated current is extracted and marked as EL; Then through: Calculate the load factor index Z of the automation equipment during the observation period SL ; Step T2: Extracting actual temperature features: Extract the actual temperature during the observation period and mark it as SW i ; Then through: Calculate the temperature rise rate WS of the automation equipment during the observation period; Then, the preset temperature rise rate warning value is extracted and marked as SWy; then: Calculate the temperature rise rate index Z of the automation equipment during the observation period SW ; Step T3: actual power feature extraction: Extract the actual power during the observation period and mark it as SP i ; At the same time, the preset rated power is extracted and marked as EP; Then through: Calculate the power deviation rate index Z of the automation equipment during the observation period SP ; Step T4: Extraction of actual insulation resistance characteristics: Extract the actual insulation resistance during the observation period and mark it as SR i ; At the same time, the preset qualified lower limit value of the insulation resistance is extracted and marked as R min ; and extract the insulation resistance corresponding to the preset ideal maximum value and mark it as R max ; followed by: Calculate the insulation resistance index Z of the automation equipment during the observation period SR .

3. The substation automation equipment operation and maintenance management system based on the control cloud according to claim 2 is characterized in that: The status assessment analysis method is as follows: Select an automation equipment; Step P1: Extract the load rate index Z of the automation equipment SL , Temperature rise rate index Z SW , power deviation rate index Z SP , Insulation resistance index Z SR ; Step P2, by: Calculate the health status index ZT of the automation equipment; In the formula, α SL , α SW , α SP , α SR They are respectively the preset weight coefficients corresponding to the load rate index, the temperature rise rate index, the power deviation rate index, and the insulation resistance index; Step P3: Combine the health status index ZT of each automation device with the preset evaluation judgment threshold ZTy to perform fault potential analysis, and then determine whether the automation device has fault potential and the degree of fault when a fault exists within the observation period.

4. The substation automation equipment operation and maintenance management system based on the control cloud according to claim 3 is characterized in that: In step P3, the fault potential within the observation period is determined as follows: If ZT>ZTy, the automation equipment is judged to be in good condition; If ZTy≥ZT>0.8×ZTy, the automation equipment is judged to be in a slight fault state; If 0.8×ZTy≥ZT>0.5×ZTy, the automation equipment is judged to be in a moderate fault state; If ZT≤0.5×ZTy, the automation equipment is determined to be in a severe fault state.

5. The substation automation equipment operation and maintenance management system based on the control cloud according to claim 3 is characterized in that: The state assessment module is also used to perform short-term trend prediction based on multiple key features corresponding to multiple observation periods in history.

6. The substation automation equipment operation and maintenance management system based on the control cloud according to claim 5 is characterized in that: The short-term trend forecast method is as follows: Step G1: Mark multiple observation periods in history as LT j , j = 1, 2, ... m, m represents the number of observation periods in the history; Step G2: Take the load factor index as an example, extract the load factor index in multiple observation periods in history, and then mark it as Z SL，j ; Step G3: Combined with the linear regression algorithm, a linear regression model formula of the load factor index and multiple observation periods in history is formulated, and the linear regression model formula is as follows: Z SL，j =a×LT j +b; Step G4, obtaining the next observation period after the current time node; Then substitute it into the linear regression model formula and obtain the load factor index predicted in the next observation period; Step G5, according to the method of step G2 to step G4, calculate the predicted temperature rise rate index, power deviation rate index, and insulation resistance index in the next observation period in sequence; Step G6: Combine the result of step G5 with the method of step P2 to calculate the predicted health status index of the automation equipment in the next observation period, and record it as ZT m+1 ; Among them, m+1 represents the next observation period after the current time node; Step G7: Combine the predicted health status index of the automation equipment in the next observation period with the preset assessment threshold ZTy to perform fault potential analysis, and then predict whether the automation equipment has fault potential and the degree of fault when it exists in the next observation period.

7. The substation automation equipment operation and maintenance management system based on the control cloud according to claim 6 is characterized in that: In step G3, a and b in the linear regression model formula are obtained by least squares fitting; The specific method is as follows:

8. The substation automation equipment operation and maintenance management system based on the control cloud according to claim 6 is characterized in that: In step G7, the prediction method of potential faults in the next observation period is as follows: The method is as follows: If ZT m+1 >ZTy, the prediction result of the automation equipment in the next observation period is judged to be in good condition; If ZTy ≥ ZT m+1 >0.8×ZTy, the prediction result of the automation equipment in the next observation period is judged to be a slight fault state; If 0.8×ZTy≥ZT m+1 >0.5×ZTy, the prediction result of the automation equipment in the next observation period is determined to be a moderate fault state; If ZT m+1 ≤0.5×ZTy, the prediction result of the automation equipment in the next observation period is judged to be a severe fault state.

9. The substation automation equipment operation and maintenance management system based on the control cloud according to claim 1 is characterized in that: The preprocessing method is as follows: Step Y1, taking a key parameter corresponding to a feature in an automation device as an example; Define an observation period and divide it into several collection time nodes; Step Y2: extract the key parameters of the feature in the automation equipment at each acquisition time node during the observation period and mark them as G i , i = 1, 2, ... n, n represents the number of acquisition time nodes; Step Y3, calculate all G i The average value of , and mark it as Gp; At the same time, calculate all G i The standard deviation of , and label it as Gb; Then through: Calculate the key parameters G i Grubbs statistic Gg i ; Step Y4, then Gg i Compare with the preset Grubbs critical value Gg1 and determine the abnormal parameters; Step Y5, when the corresponding G i If it is judged as an abnormal parameter, G i The corresponding collection time node is recorded as T i , T represents the number of collection time nodes: Then according to the collection time node T i Get the adjacent acquisition time node T i-1 and T i+1 , and its corresponding key parameter G i-1 and G i+1 ; Among them, T i-1 Indicates the acquisition time node T i The adjacent previous acquisition time node, G i-1 Indicates the acquisition time node T i The key parameters at the previous adjacent acquisition time node, T i+1 Indicates the acquisition time node T i The next adjacent acquisition time node, G i+1 Indicates the acquisition time node T i The key parameters at the next adjacent acquisition time node; Then pass: Calculate the parameter G that is judged to be abnormal during the observation period i Replacement value G0 i .

10. The substation automation equipment operation and maintenance management system based on the control cloud according to claim 9 is characterized in that: Abnormal parameters are determined as follows: If Gg i ≤Gg1, then the corresponding Gg i The corresponding G i Determined as abnormal parameters; If Gg i >Gg1, then the corresponding Gg i The corresponding G i Determined to be an abnormal parameter.

Images