10kV electrical equipment temperature and humidity monitoring system

Abstract

The invention discloses a 10kV electrical equipment temperature and humidity monitoring system, and the system comprises an obtaining module which is used for obtaining historical temperature and humidity data and historical feature state parameters of each piece of electrical equipment; the construction module is used for analyzing the historical feature state parameters to obtain historical feature state evaluation values, and constructing a temperature and humidity-feature state evaluation model according to the historical feature state evaluation values and the historical temperature and humidity data; the monitoring module is used for obtaining a predicted feature state evaluation value corresponding to the real-time temperature and humidity data, and generating a risk coefficient according to the predicted feature state evaluation value; the alarm module is used for determining the predicted temperature and humidity data and a second predicted feature state evaluation value, setting a correction coefficient according to the relationship between the second predicted feature state evaluation value and the predicted feature state evaluation value, correcting the risk coefficient, and judging whether to generate an alarm signal according to the corrected risk coefficient; the accuracy and timeliness of the monitoring system are improved, and the service life of electrical equipment is prolonged.

Description

Technical Field

[0001] The present application relates to the technical field, and in particular to a 10kV electrical equipment temperature and humidity monitoring system. Background Art

[0002] Electrical equipment is a general term for equipment such as generators, transformers, power lines and circuit breakers. The safe operation of electrical equipment is the top priority of power supply work. Therefore, temperature and humidity sensors are usually used to monitor the temperature and humidity changes of electrical equipment during the operation of electrical equipment. However, the operating status of electrical equipment cannot be accurately judged based only on the temperature and humidity changes around the electrical equipment, which leads to errors in the monitoring results, poses a major safety hazard, and reduces the service life of electrical equipment. Therefore, there is an urgent need for a 10kV electrical equipment temperature and humidity monitoring system that comprehensively analyzes the status parameters of electrical equipment with temperature and humidity data to improve the accuracy of monitoring results. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides a 10kV electrical equipment temperature and humidity monitoring system, which determines the historical characteristic state evaluation value through the historical characteristic state parameters corresponding to the historical temperature and humidity data of each electrical equipment, and constructs a temperature and humidity-characteristic state evaluation model for each electrical equipment, determines the predicted characteristic state evaluation value and risk coefficient of the real-time temperature and humidity data, sets a correction coefficient according to the relationship between the second predicted characteristic state evaluation value and the predicted characteristic state evaluation value, and corrects the risk coefficient. According to the corrected risk coefficient, the operating state of the electrical equipment is determined and it is judged whether to send an alarm signal. By screening out the characteristic state parameters associated with the temperature and humidity data and the operating state of the electrical equipment, a comprehensive analysis of the characteristic state parameters and the temperature and humidity data is performed, thereby improving the accuracy and timeliness of the monitoring system and increasing the service life of the electrical equipment.

[0004] In some embodiments of the present application, a 10kV electrical equipment temperature and humidity monitoring system is provided, comprising:

[0005] An acquisition module is used to acquire historical temperature and humidity data and historical characteristic state parameters of each electrical device;

[0006] A construction module is used to analyze the historical characteristic state parameters to obtain the historical characteristic state evaluation value, and to construct a temperature and humidity-characteristic state evaluation model according to the historical characteristic state evaluation value and the corresponding historical temperature and humidity data;

[0007] A monitoring module is used to monitor real-time temperature and humidity data, obtain the predicted characteristic state evaluation value corresponding to the real-time temperature and humidity data based on the temperature and humidity-characteristic state evaluation model, and generate the risk coefficient of the real-time temperature and humidity data according to the predicted characteristic state evaluation value;

[0008] The alarm module is used to determine the predicted temperature and humidity data of the real-time temperature and humidity data in the future time period and the second predicted characteristic state evaluation value, set the correction coefficient according to the relationship between the second predicted characteristic state evaluation value and the predicted characteristic state evaluation value, and correct the risk coefficient, and determine whether to generate an alarm signal based on the corrected risk coefficient.

[0009] In some embodiments of the present application, obtaining historical temperature and humidity data and historical characteristic state parameters of each electrical device includes:

[0010] Acquire historical operating parameters of the electrical equipment, calculate the degree of correlation between the historical operating parameters and the operating status of the corresponding electrical equipment, and set the historical operating parameters whose correlation degree is greater than a preset correlation degree threshold as the historical operating status parameters of the corresponding electrical equipment;

[0011] Acquire historical temperature and humidity data of electrical equipment within a historical period, and divide the historical temperature and humidity data into multiple historical temperature and humidity data groups based on days as time units, analyze the historical temperature and humidity data in the same historical temperature and humidity data group, determine the historical time nodes at which the fluctuation amount of the historical temperature and humidity data is greater than a preset fluctuation amount threshold, and set the adjacent preset time period of each historical time node as the focus time interval of the corresponding historical temperature and humidity data group;

[0012] Obtaining historical operating status parameters for a number of time intervals of interest, and calculating change characteristics of the historical operating status parameters for the corresponding time intervals of interest;

[0013] Based on the number of times the change characteristics in the focus time interval of the historical temperature and humidity data group are greater than the preset standard change characteristics, and the feature difference amount of the change characteristics greater than the preset standard change characteristics, the degree of correlation between the historical temperature and humidity data and the corresponding historical operating status parameters is determined, and the historical operating status parameters with a correlation degree greater than the preset correlation degree threshold are set as the historical characteristic status parameters of the corresponding electrical equipment.

[0014] In some embodiments of the present application, determining the degree of correlation between historical temperature and humidity data and corresponding historical operating status parameters includes:

[0015] The calculation formula for the correlation between the historical temperature and humidity data and the corresponding historical operating status parameters is:

[0016]

[0017] Among them, K is the degree of correlation between the historical operating status parameters and the historical temperature and humidity data, △gi,r is the characteristic difference of the historical operating status parameters in the i-th focus time interval of the r-th historical temperature and humidity data group, nr is the number of times the change characteristics in the focus time interval of the r-th historical temperature and humidity data group are greater than the preset standard change characteristics, Mr is the total number of focus time intervals of the r-th historical temperature and humidity data group, c is the total number of historical temperature and humidity data groups, i = 1, 2, ..., n, r = 1, 2, ..., c.

[0018] 4. The 10kV electrical equipment temperature and humidity monitoring system according to claim 3, characterized in that the historical characteristic state parameters are analyzed to obtain the historical characteristic state evaluation value, including:

[0019] An objective function is constructed according to the operation state stability and the performance state efficiency, and based on the objective function, a preset standard state parameter interval is divided into a plurality of standard state parameter sub-intervals, and a corresponding state evaluation coefficient is configured for each standard state parameter sub-interval;

[0020] Compare the historical characteristic state parameters of each electrical device with the corresponding preset standard state parameter interval, and determine the standard state parameter sub-interval in which the historical characteristic state parameter is located and the corresponding state evaluation coefficient according to the comparison result;

[0021] A historical characteristic state evaluation value of the historical characteristic state parameter is generated according to the state evaluation coefficient.

[0022] In some embodiments of the present application, a temperature and humidity-characteristic state evaluation model is constructed according to the historical characteristic state evaluation value and the corresponding historical temperature and humidity data, including:

[0023] Construct training data sets and test data sets based on the historical characteristic status evaluation value of each electrical device and the corresponding historical temperature and humidity data;

[0024] According to the historical temperature and humidity data in the training data set as input items, the historical characteristic state evaluation values ​​corresponding to the historical temperature and humidity data are used as output items, and the neural network training is performed to obtain the initial temperature and humidity-characteristic state evaluation model of the corresponding electrical equipment;

[0025] Generate the initial temperature and humidity-characteristic state based on the test data set to evaluate the accuracy of the model;

[0026] Preset accuracy threshold;

[0027] If the accuracy is less than the accuracy threshold, the training data set is iteratively trained and the initial temperature and humidity-feature state evaluation model is reconstructed;

[0028] If the accuracy is greater than the accuracy threshold, the initial temperature and humidity-feature state evaluation model is set as the temperature and humidity-feature state evaluation model.

[0029] In some embodiments of the present application, the risk coefficient of real-time temperature and humidity data is generated according to the predicted characteristic state evaluation value, including:

[0030] Presetting a first preset state evaluation value interval, a second preset state evaluation value interval, a third preset state evaluation value interval and a fourth preset state evaluation value interval;

[0031] When the predicted characteristic state evaluation value is within the first preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to a fourth preset risk coefficient w4;

[0032] When the predicted characteristic state evaluation value is in the second preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to the third preset risk coefficient w3;

[0033] When the predicted characteristic state evaluation value is in the third preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to the second preset risk coefficient w2;

[0034] When the predicted characteristic state evaluation value is in the fourth preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to the first preset risk coefficient w1;

[0035] Among them, w1<w2<w3<w4.

[0036] In some embodiments of the present application, determining predicted temperature and humidity data of real-time temperature and humidity data in a future period and a second predicted characteristic state evaluation value includes:

[0037] Construct a real-time temperature and humidity change curve based on the real-time temperature and humidity data in chronological order;

[0038] Analyze the real-time temperature and humidity change curve to obtain the temperature fluctuation and humidity fluctuation of the real-time temperature and humidity change curve within multiple preset time periods;

[0039] Constructing multiple historical temperature and humidity change curves according to the corresponding time sequence according to multiple historical temperature and humidity data groups;

[0040] Analyze multiple historical temperature and humidity change curves to obtain historical temperature fluctuations and historical humidity fluctuations of the historical temperature and humidity change curves in corresponding multiple preset time periods;

[0041] Compare the temperature fluctuation and humidity fluctuation of the real-time temperature and humidity change curve in multiple preset time periods with the historical temperature fluctuation and humidity fluctuation of each historical temperature and humidity change curve in the corresponding preset time period to obtain the temperature fluctuation difference and humidity fluctuation difference in multiple preset time periods;

[0042] Generate a similarity coefficient between the corresponding historical temperature and humidity change curve and the real-time temperature and humidity change curve according to the temperature fluctuation difference and humidity fluctuation difference in multiple preset time periods in the same historical temperature and humidity change curve;

[0043] The calculation formula of the similarity coefficient is:

[0044]

[0045] Wherein, H is the similarity coefficient between the corresponding historical temperature and humidity change curve and the real-time temperature and humidity change curve, b is the conversion coefficient, u is the number of preset time periods, △Q1v is the temperature fluctuation difference within the vth preset time period, and △Q2v is the humidity fluctuation difference within the vth preset time period;

[0046] Arrange the similarity coefficients of multiple historical temperature and humidity change curves in order of magnitude, and set the first historical temperature and humidity change curve as the similarity curve of the real-time temperature and humidity change curve;

[0047] Determine predicted temperature and humidity data of the real-time temperature and humidity change curve in the future period based on the similarity curve, and determine a second predicted characteristic state evaluation value of the predicted temperature and humidity data based on the temperature and humidity-characteristic state evaluation model;

[0048] A correction coefficient of the risk coefficient is set according to a comparison result and a change rate between the second predicted feature state evaluation value and the predicted feature state evaluation value.

[0049] In some embodiments of the present application, setting a correction factor of the risk factor includes:

[0050] According to the comparison result and the change rate of the second predicted characteristic state evaluation value and the predicted characteristic state evaluation value, a correction coefficient of the risk coefficient is set;

[0051] Presetting a first preset change rate interval, a second preset change rate interval and a third preset change rate interval;

[0052] If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the first preset change rate interval, the correction coefficient of the risk coefficient is set to the sixth preset correction coefficient f6, and the corrected risk coefficient is wj*f6;

[0053] If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the second preset change rate interval, the correction coefficient of the risk coefficient is set to the fifth preset correction coefficient, and the corrected risk coefficient is wj*f5;

[0054] If the third predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the third preset change rate interval, the correction coefficient of the risk coefficient is set to the fourth preset correction coefficient, and the corrected risk coefficient is wj*f4;

[0055] If the second predicted characteristic state evaluation value is greater than the predicted characteristic state evaluation value and the change rate is within the first preset change rate interval, the correction coefficient of the risk coefficient is set to the third preset correction coefficient, and the corrected risk coefficient is wj*f3;

[0056] If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the second preset change rate interval, the correction coefficient of the risk coefficient is set to the second preset correction coefficient, and the corrected risk coefficient is wj*f2;

[0057] If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the third preset change rate interval, the correction coefficient of the risk coefficient is set to the first preset correction coefficient, and the corrected risk coefficient is wj*f1;

[0058] Among them, j=1, 2, 3, 4, 0.75<f1<f2<f3<1<f4<f5<f6<1.25.

[0059] In some embodiments of the present application, determining whether to generate an alarm signal according to the corrected risk factor includes:

[0060] Pre-set risk factor thresholds;

[0061] When the corrected risk factor is less than the risk factor threshold, no alarm signal is sent;

[0062] When the corrected risk factor is greater than the preset risk factor threshold, an alarm signal is sent, and the alarm signal includes the location information and risk level of the corresponding electrical equipment.

[0063] Compared with the prior art, the 10kV electrical equipment temperature and humidity monitoring system of the present application has the following beneficial effects:

[0064] The historical characteristic state evaluation value is determined by the historical characteristic state parameters corresponding to the historical temperature and humidity data of each electrical equipment, and a temperature and humidity-characteristic state evaluation model is constructed for each electrical equipment to determine the predicted characteristic state evaluation value and the risk coefficient of the real-time temperature and humidity data. The correction coefficient is set according to the relationship between the second predicted characteristic state evaluation value and the predicted characteristic state evaluation value, and the risk coefficient is corrected. The operating state of the electrical equipment is determined according to the corrected risk coefficient and it is judged whether to send an alarm signal. By screening out the characteristic state parameters associated with the temperature and humidity data and the operating state of the electrical equipment, a comprehensive analysis of the characteristic state parameters and the temperature and humidity data is performed to improve the accuracy and timeliness of the monitoring system and to increase the service life of the electrical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic diagram of a 10kV electrical equipment temperature and humidity monitoring system in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0066] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0067] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0068] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0069] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0070] like Figure 1 As shown, a 10kV electrical equipment temperature and humidity monitoring system according to a preferred embodiment of the present application includes:

[0071] An acquisition module is used to acquire historical temperature and humidity data and historical characteristic state parameters of each electrical device;

[0072] A construction module is used to analyze the historical characteristic state parameters to obtain the historical characteristic state evaluation value, and to construct a temperature and humidity-characteristic state evaluation model according to the historical characteristic state evaluation value and the corresponding historical temperature and humidity data;

[0073] A monitoring module is used to monitor real-time temperature and humidity data, obtain the predicted characteristic state evaluation value corresponding to the real-time temperature and humidity data based on the temperature and humidity-characteristic state evaluation model, and generate the risk coefficient of the real-time temperature and humidity data according to the predicted characteristic state evaluation value;

[0074] The alarm module is used to determine the predicted temperature and humidity data of the real-time temperature and humidity data in the future time period and the second predicted characteristic state evaluation value, set the correction coefficient according to the relationship between the second predicted characteristic state evaluation value and the predicted characteristic state evaluation value, and correct the risk coefficient, and determine whether to generate an alarm signal based on the corrected risk coefficient.

[0075] In some embodiments of the present application, obtaining historical temperature and humidity data and historical characteristic state parameters of each electrical device includes:

[0076] Acquire historical operating parameters of the electrical equipment, calculate the degree of correlation between the historical operating parameters and the operating status of the corresponding electrical equipment, and set the historical operating parameters whose correlation degree is greater than a preset correlation degree threshold as the historical operating status parameters of the corresponding electrical equipment;

[0077] Acquire historical temperature and humidity data of electrical equipment within a historical period, and divide the historical temperature and humidity data into multiple historical temperature and humidity data groups based on days as time units, analyze the historical temperature and humidity data in the same historical temperature and humidity data group, determine the historical time nodes at which the fluctuation amount of the historical temperature and humidity data is greater than a preset fluctuation amount threshold, and set the adjacent preset time period of each historical time node as the focus time interval of the corresponding historical temperature and humidity data group;

[0078] Obtaining historical operating status parameters for a number of time intervals of interest, and calculating change characteristics of the historical operating status parameters for the corresponding time intervals of interest;

[0079] Based on the number of times the change characteristics in the focus time interval of the historical temperature and humidity data group are greater than the preset standard change characteristics, and the feature difference amount of the change characteristics greater than the preset standard change characteristics, the degree of correlation between the historical temperature and humidity data and the corresponding historical operating status parameters is determined, and the historical operating status parameters with a correlation degree greater than the preset correlation degree threshold are set as the historical characteristic status parameters of the corresponding electrical equipment.

[0080] In this embodiment, historical operating status parameters associated with the operating status of the electrical equipment are extracted, and historical characteristic status parameters associated with the temperature and humidity data are extracted from the historical operating status parameters, so as to subsequently obtain the operating status of the electrical equipment under different temperature and humidity data based on the historical characteristic status evaluation values ​​of the historical characteristic status parameters, thereby improving the accuracy of the monitoring system and increasing the service life of the electrical equipment.

[0081] In this embodiment, the daily historical temperature and humidity data are regarded as a historical temperature and humidity data group, and the focus time interval of each historical temperature and humidity data group is determined. According to the change characteristics of the corresponding historical operating state parameters in the corresponding focus time interval, the correlation degree between the historical characteristic state parameters and the historical temperature and humidity data is determined, so as to screen out the historical characteristic state parameters, lay the foundation for the subsequent formulation of a temperature and humidity-characteristic state evaluation model based on the relationship between the historical characteristic state parameters and the historical temperature and humidity data, ensure the timeliness of the monitoring system, quickly determine the risk factor of electrical equipment, and improve the service life of electrical equipment.

[0082] In some embodiments of the present application, determining the degree of correlation between historical temperature and humidity data and corresponding historical operating status parameters includes:

[0083] The calculation formula for the correlation between the historical temperature and humidity data and the corresponding historical operating status parameters is:

[0084]

[0085] Among them, K is the degree of correlation between the historical operating status parameters and the historical temperature and humidity data, △gi,r is the characteristic difference of the historical operating status parameters in the i-th focus time interval of the r-th historical temperature and humidity data group, nr is the number of times the change characteristics in the focus time interval of the r-th historical temperature and humidity data group are greater than the preset standard change characteristics, Mr is the total number of focus time intervals of the r-th historical temperature and humidity data group, c is the total number of historical temperature and humidity data groups, i = 1, 2, ..., n, r = 1, 2, ..., c.

[0086] In this embodiment, the historical period is at least 30 days. The historical temperature and humidity data within the last 30 days are divided into multiple historical temperature and humidity data groups according to the daily time unit, and the focus time interval of each historical temperature and humidity data group is determined. The focus time interval refers to the 15 minutes before and after the time node when the historical temperature and humidity data within a single day fluctuates greatly.

[0087] In this embodiment, based on the change characteristics of the historical operating status parameters within the time interval of interest of each historical temperature and humidity data group, the degree of correlation between the corresponding historical operating status parameters and the historical temperature and humidity data group is obtained, thereby screening out the historical characteristic status parameters, laying a data foundation for the subsequent analysis of the operating status of the electrical equipment by the temperature and humidity data, reducing the amount of data processing, and improving the timeliness and accuracy of monitoring.

[0088] In some embodiments of the present application, the historical feature state parameters are analyzed to obtain the historical feature state evaluation value, including:

[0089] An objective function is constructed according to the operation state stability and the performance state efficiency, and based on the objective function, a preset standard state parameter interval is divided into a plurality of standard state parameter sub-intervals, and a corresponding state evaluation coefficient is configured for each standard state parameter sub-interval;

[0090] Compare the historical characteristic state parameters of each electrical device with the corresponding preset standard state parameter interval, and determine the standard state parameter sub-interval in which the historical characteristic state parameter is located and the corresponding state evaluation coefficient according to the comparison result;

[0091] A historical characteristic state evaluation value of the historical characteristic state parameter is generated according to the state evaluation coefficient.

[0092] In this embodiment, a state evaluation coefficient-characteristic state evaluation value mapping table is pre-set. The larger the state evaluation coefficient, the larger the corresponding historical characteristic state evaluation value, that is, the better the operating state of the electrical equipment under the corresponding historical temperature and humidity data.

[0093] In some embodiments of the present application, a temperature and humidity-characteristic state evaluation model is constructed according to the historical characteristic state evaluation value and the corresponding historical temperature and humidity data, including:

[0094] Construct training data sets and test data sets based on the historical characteristic status evaluation value of each electrical device and the corresponding historical temperature and humidity data;

[0095] According to the historical temperature and humidity data in the training data set as input items, the historical characteristic state evaluation values ​​corresponding to the historical temperature and humidity data are used as output items, and the neural network training is performed to obtain the initial temperature and humidity-characteristic state evaluation model of the corresponding electrical equipment;

[0096] Generate the initial temperature and humidity-characteristic state based on the test data set to evaluate the accuracy of the model;

[0097] Preset accuracy threshold;

[0098] If the accuracy is less than the accuracy threshold, the training data set is iteratively trained and the initial temperature and humidity-feature state evaluation model is reconstructed;

[0099] If the accuracy is greater than the accuracy threshold, the initial temperature and humidity-feature state evaluation model is set as the temperature and humidity-feature state evaluation model.

[0100] In some embodiments of the present application, the risk coefficient of real-time temperature and humidity data is generated according to the predicted characteristic state evaluation value, including:

[0101] Presetting a first preset state evaluation value interval, a second preset state evaluation value interval, a third preset state evaluation value interval and a fourth preset state evaluation value interval;

[0102] When the predicted characteristic state evaluation value is within the first preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to a fourth preset risk coefficient w4;

[0103] When the predicted characteristic state evaluation value is in the second preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to the third preset risk coefficient w3;

[0104] When the predicted characteristic state evaluation value is in the third preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to the second preset risk coefficient w2;

[0105] When the predicted characteristic state evaluation value is in the fourth preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to the first preset risk coefficient w1;

[0106] Among them, w1<w2<w3<w4.

[0107] In this embodiment, when the predicted characteristic state evaluation value is smaller, it means that the operating state of the electrical equipment under the influence of the real-time temperature and humidity data is worse, and the risk coefficient is higher.

[0108] In this embodiment, by screening out historical characteristic state parameters that are highly correlated with real-time temperature and humidity data and calculating the corresponding historical characteristic state evaluation values, a temperature and humidity-characteristic state evaluation model is constructed, and the predicted characteristic state evaluation values ​​of real-time temperature and humidity data can be quickly obtained, thereby determining the risk factor of electrical equipment, ensuring the timeliness and accuracy of the monitoring system, and promptly discovering and formulating response strategies to increase the service life of electrical equipment.

[0109] In some embodiments of the present application, determining predicted temperature and humidity data of real-time temperature and humidity data in a future period and a second predicted characteristic state evaluation value includes:

[0110] Construct a real-time temperature and humidity change curve based on the real-time temperature and humidity data in chronological order;

[0111] Analyze the real-time temperature and humidity change curve to obtain the temperature fluctuation and humidity fluctuation of the real-time temperature and humidity change curve within multiple preset time periods;

[0112] Constructing multiple historical temperature and humidity change curves according to the corresponding time sequence according to multiple historical temperature and humidity data groups;

[0113] Analyze multiple historical temperature and humidity change curves to obtain historical temperature fluctuations and historical humidity fluctuations of the historical temperature and humidity change curves in corresponding multiple preset time periods;

[0114] Compare the temperature fluctuation and humidity fluctuation of the real-time temperature and humidity change curve in multiple preset time periods with the historical temperature fluctuation and humidity fluctuation of each historical temperature and humidity change curve in the corresponding preset time period to obtain the temperature fluctuation difference and humidity fluctuation difference in multiple preset time periods;

[0115] Generate a similarity coefficient between the corresponding historical temperature and humidity change curve and the real-time temperature and humidity change curve according to the temperature fluctuation difference and humidity fluctuation difference in multiple preset time periods in the same historical temperature and humidity change curve;

[0116] The calculation formula of the similarity coefficient is:

[0117]

[0118] Wherein, H is the similarity coefficient between the corresponding historical temperature and humidity change curve and the real-time temperature and humidity change curve, b is the conversion coefficient, u is the number of preset time periods, △Q1v is the temperature fluctuation difference within the vth preset time period, and △Q2v is the humidity fluctuation difference within the vth preset time period;

[0119] Arrange the similarity coefficients of multiple historical temperature and humidity change curves in order of magnitude, and set the first historical temperature and humidity change curve as the similarity curve of the real-time temperature and humidity change curve;

[0120] Determine predicted temperature and humidity data of the real-time temperature and humidity change curve in the future period based on the similarity curve, and determine a second predicted characteristic state evaluation value of the predicted temperature and humidity data based on the temperature and humidity-characteristic state evaluation model;

[0121] A correction coefficient of the risk coefficient is set according to a comparison result and a change rate between the second predicted feature state evaluation value and the predicted feature state evaluation value.

[0122] In this embodiment, the preset time period is set according to the time length of the real-time temperature and humidity data. The longer the time length, the larger the preset time period. For example, if the time length of the real-time temperature and humidity data is 3 hours, the preset time period is set to 15 minutes, that is, the temperature fluctuation and humidity fluctuation are calculated once every 15 minutes. The temperature fluctuation refers to the difference between the maximum and minimum temperature values ​​within 15 minutes, and the humidity fluctuation refers to the difference between the maximum and minimum humidity values ​​within 15 minutes.

[0123] In this embodiment, the predicted temperature and humidity data of the real-time temperature and humidity data in the future time period can be predicted based on the similarity curve, thereby determining the second predicted characteristic state evaluation value of the future time period, and evaluating and predicting the operating state of the corresponding electrical equipment in the future time period based on the second predicted characteristic state evaluation value, so as to timely discover electrical equipment failure problems and improve the service life of the electrical equipment.

[0124] In some embodiments of the present application, setting a correction factor of the risk factor includes:

[0125] According to the comparison result and the change rate of the second predicted characteristic state evaluation value and the predicted characteristic state evaluation value, a correction coefficient of the risk coefficient is set;

[0126] Presetting a first preset change rate interval, a second preset change rate interval and a third preset change rate interval;

[0127] If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the first preset change rate interval, the correction coefficient of the risk coefficient is set to the sixth preset correction coefficient f6, and the corrected risk coefficient is wj*f6;

[0128] If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the second preset change rate interval, the correction coefficient of the risk coefficient is set to the fifth preset correction coefficient, and the corrected risk coefficient is wj*f5;

[0129] If the third predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the third preset change rate interval, the correction coefficient of the risk coefficient is set to the fourth preset correction coefficient, and the corrected risk coefficient is wj*f4;

[0130] If the second predicted characteristic state evaluation value is greater than the predicted characteristic state evaluation value and the change rate is within the first preset change rate interval, the correction coefficient of the risk coefficient is set to the third preset correction coefficient, and the corrected risk coefficient is wj*f3;

[0131] If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the second preset change rate interval, the correction coefficient of the risk coefficient is set to the second preset correction coefficient, and the corrected risk coefficient is wj*f2;

[0132] If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the third preset change rate interval, the correction coefficient of the risk coefficient is set to the first preset correction coefficient, and the corrected risk coefficient is wj*f1;

[0133] Among them, j=1, 2, 3, 4, 0.75<f1<f2<f3<1<f4<f5<f6<1.25.

[0134] In this embodiment, a comparison between the second predicted characteristic state evaluation value and the predicted characteristic state evaluation value is obtained according to the comparison result. When the second predicted characteristic state evaluation value is greater than the predicted characteristic state evaluation value, it means that the predicted temperature and humidity data in the future time period will improve the operating state of the corresponding power equipment. The faster the rate of change, the larger the second predicted characteristic state evaluation value of the electrical equipment is, and the lower the risk factor is. When the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value, it means that the predicted temperature and humidity data in the future time period will reduce the operating state of the corresponding power equipment. The faster the rate of change, the smaller the second predicted characteristic state evaluation value of the electrical equipment is, and the higher the risk factor is.

[0135] In this embodiment, a similarity curve is determined based on the similarity coefficient between the real-time temperature and humidity change curve and the historical temperature and humidity change curve, and the predicted temperature and humidity data for the future time period and the second predicted characteristic state evaluation value are obtained, so as to correct the risk coefficient, improve the accuracy of the risk coefficient, predict the operating status of the corresponding electrical equipment, and improve the monitoring efficiency and the service life of the electrical equipment.

[0136] In some embodiments of the present application, determining whether to generate an alarm signal according to the corrected risk factor includes:

[0137] Pre-set risk factor thresholds;

[0138] When the corrected risk factor is less than the risk factor threshold, no alarm signal is sent;

[0139] When the corrected risk factor is greater than the preset risk factor threshold, an alarm signal is sent, and the alarm signal includes the location information and risk level of the corresponding electrical equipment.

[0140] In this embodiment, the risk level is determined based on the corrected risk coefficient. The larger the corrected risk coefficient is, the higher the risk level is. After receiving the alarm signal, a reasonable response strategy is formulated based on the location information of the electrical equipment and the corresponding alarm level, thereby increasing the service life of the electrical equipment.

[0141] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A 10kV electrical equipment temperature and humidity monitoring system, characterized in that: include: An acquisition module is used to acquire historical temperature and humidity data and historical characteristic state parameters of each electrical device; A construction module is used to analyze the historical characteristic state parameters to obtain the historical characteristic state evaluation value, and to construct a temperature and humidity-characteristic state evaluation model according to the historical characteristic state evaluation value and the corresponding historical temperature and humidity data; A monitoring module is used to monitor real-time temperature and humidity data, obtain the predicted characteristic state evaluation value corresponding to the real-time temperature and humidity data based on the temperature and humidity-characteristic state evaluation model, and generate the risk coefficient of the real-time temperature and humidity data according to the predicted characteristic state evaluation value; The alarm module is used to determine the predicted temperature and humidity data of the real-time temperature and humidity data in the future time period and the second predicted characteristic state evaluation value, set the correction coefficient according to the relationship between the second predicted characteristic state evaluation value and the predicted characteristic state evaluation value, and correct the risk coefficient, and determine whether to generate an alarm signal based on the corrected risk coefficient.

2. The 10kV electrical equipment temperature and humidity monitoring system according to claim 1, characterized in that: Obtain the historical temperature and humidity data and historical characteristic status parameters of each electrical device, including: Acquire historical operating parameters of the electrical equipment, calculate the degree of correlation between the historical operating parameters and the operating status of the corresponding electrical equipment, and set the historical operating parameters whose correlation degree is greater than a preset correlation degree threshold as the historical operating status parameters of the corresponding electrical equipment; Acquire historical temperature and humidity data of electrical equipment within a historical period, and divide the historical temperature and humidity data into multiple historical temperature and humidity data groups based on days as time units, analyze the historical temperature and humidity data in the same historical temperature and humidity data group, determine the historical time nodes at which the fluctuation amount of the historical temperature and humidity data is greater than a preset fluctuation amount threshold, and set the adjacent preset time period of each historical time node as the focus time interval of the corresponding historical temperature and humidity data group; Obtaining historical operating status parameters for a number of time intervals of interest, and calculating change characteristics of the historical operating status parameters for the corresponding time intervals of interest; Based on the number of times the change characteristics in the focus time interval of the historical temperature and humidity data group are greater than the preset standard change characteristics, and the feature difference amount of the change characteristics greater than the preset standard change characteristics, the degree of correlation between the historical temperature and humidity data and the corresponding historical operating status parameters is determined, and the historical operating status parameters with a correlation degree greater than the preset correlation degree threshold are set as the historical characteristic status parameters of the corresponding electrical equipment.

3. The 10kV electrical equipment temperature and humidity monitoring system according to claim 2, characterized in that: Determine the degree of correlation between historical temperature and humidity data and corresponding historical operating status parameters, including: The calculation formula for the correlation between the historical temperature and humidity data and the corresponding historical operating status parameters is: Among them, K is the degree of correlation between the historical operating status parameters and the historical temperature and humidity data, △gi,r is the characteristic difference of the historical operating status parameters in the i-th focus time interval of the r-th historical temperature and humidity data group, nr is the number of times the change characteristics in the focus time interval of the r-th historical temperature and humidity data group are greater than the preset standard change characteristics, Mr is the total number of focus time intervals of the r-th historical temperature and humidity data group, c is the total number of historical temperature and humidity data groups, i = 1, 2, ..., n, r = 1, 2, ..., c.

4. The 10kV electrical equipment temperature and humidity monitoring system according to claim 3, characterized in that: Analyze the historical characteristic state parameters to obtain historical characteristic state evaluation values, including: An objective function is constructed according to the operation state stability and the performance state efficiency, and based on the objective function, a preset standard state parameter interval is divided into a plurality of standard state parameter sub-intervals, and a corresponding state evaluation coefficient is configured for each standard state parameter sub-interval; Compare the historical characteristic state parameters of each electrical device with the corresponding preset standard state parameter interval, and determine the standard state parameter sub-interval in which the historical characteristic state parameter is located and the corresponding state evaluation coefficient according to the comparison result; A historical characteristic state evaluation value of the historical characteristic state parameter is generated according to the state evaluation coefficient.

5. The 10kV electrical equipment temperature and humidity monitoring system according to claim 4, characterized in that: A temperature and humidity-characteristic state evaluation model is constructed based on the historical characteristic state evaluation value and the corresponding historical temperature and humidity data, including: Construct training data sets and test data sets based on the historical characteristic status evaluation value of each electrical device and the corresponding historical temperature and humidity data; According to the historical temperature and humidity data in the training data set as input items, the historical characteristic state evaluation values ​​corresponding to the historical temperature and humidity data are used as output items, and the neural network training is performed to obtain the initial temperature and humidity-characteristic state evaluation model of the corresponding electrical equipment; Generate the initial temperature and humidity-characteristic state based on the test data set to evaluate the accuracy of the model; Preset accuracy threshold; If the accuracy is less than the accuracy threshold, the training data set is iteratively trained and the initial temperature and humidity-feature state evaluation model is reconstructed; If the accuracy is greater than the accuracy threshold, the initial temperature and humidity-feature state evaluation model is set as the temperature and humidity-feature state evaluation model.

6. The 10kV electrical equipment temperature and humidity monitoring system according to claim 5, characterized in that: Generate risk factors for real-time temperature and humidity data based on the predicted characteristic state evaluation values, including: Presetting a first preset state evaluation value interval, a second preset state evaluation value interval, a third preset state evaluation value interval and a fourth preset state evaluation value interval; When the predicted characteristic state evaluation value is within the first preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to a fourth preset risk coefficient w4; When the predicted characteristic state evaluation value is in the second preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to the third preset risk coefficient w3; When the predicted characteristic state evaluation value is in the third preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to the second preset risk coefficient w2; When the predicted characteristic state evaluation value is in the fourth preset state evaluation value interval, the risk coefficient of the real-time temperature and humidity data is set to the first preset risk coefficient w1; Among them, w1<w2<w3<w4.

7. The 10kV electrical equipment temperature and humidity monitoring system according to claim 6, characterized in that: Determining predicted temperature and humidity data of real-time temperature and humidity data in a future period and a second predicted characteristic state evaluation value, including: Construct a real-time temperature and humidity change curve based on the real-time temperature and humidity data in chronological order; Analyze the real-time temperature and humidity change curve to obtain the temperature fluctuation and humidity fluctuation of the real-time temperature and humidity change curve within multiple preset time periods; Constructing multiple historical temperature and humidity change curves according to the corresponding time sequence according to multiple historical temperature and humidity data groups; Analyze multiple historical temperature and humidity change curves to obtain historical temperature fluctuations and historical humidity fluctuations of the historical temperature and humidity change curves in corresponding multiple preset time periods; Compare the temperature fluctuation and humidity fluctuation of the real-time temperature and humidity change curve in multiple preset time periods with the historical temperature fluctuation and humidity fluctuation of each historical temperature and humidity change curve in the corresponding preset time period to obtain the temperature fluctuation difference and humidity fluctuation difference in multiple preset time periods; Generate a similarity coefficient between the corresponding historical temperature and humidity change curve and the real-time temperature and humidity change curve according to the temperature fluctuation difference and humidity fluctuation difference in multiple preset time periods in the same historical temperature and humidity change curve; The calculation formula of the similarity coefficient is: Wherein, H is the similarity coefficient between the corresponding historical temperature and humidity change curve and the real-time temperature and humidity change curve, b is the conversion coefficient, u is the number of preset time periods, △Q1v is the temperature fluctuation difference within the vth preset time period, and △Q2v is the humidity fluctuation difference within the vth preset time period; Arrange the similarity coefficients of multiple historical temperature and humidity change curves in order of magnitude, and set the first historical temperature and humidity change curve as the similarity curve of the real-time temperature and humidity change curve; Determine predicted temperature and humidity data of the real-time temperature and humidity change curve in the future period based on the similarity curve, and determine a second predicted characteristic state evaluation value of the predicted temperature and humidity data based on the temperature and humidity-characteristic state evaluation model; A correction coefficient of the risk coefficient is set according to a comparison result and a change rate between the second predicted feature state evaluation value and the predicted feature state evaluation value.

8. The 10kV electrical equipment temperature and humidity monitoring system according to claim 7, characterized in that: Set the correction factor for the risk factor, including: According to the comparison result and the change rate of the second predicted characteristic state evaluation value and the predicted characteristic state evaluation value, a correction coefficient of the risk coefficient is set; Presetting a first preset change rate interval, a second preset change rate interval and a third preset change rate interval; If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the first preset change rate interval, the correction coefficient of the risk coefficient is set to the sixth preset correction coefficient f6, and the corrected risk coefficient is wj*f6; If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the second preset change rate interval, the correction coefficient of the risk coefficient is set to the fifth preset correction coefficient, and the corrected risk coefficient is wj*f5; If the third predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the third preset change rate interval, the correction coefficient of the risk coefficient is set to the fourth preset correction coefficient, and the corrected risk coefficient is wj*f4; If the second predicted characteristic state evaluation value is greater than the predicted characteristic state evaluation value and the change rate is within the first preset change rate interval, the correction coefficient of the risk coefficient is set to the third preset correction coefficient, and the corrected risk coefficient is wj*f3; If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the second preset change rate interval, the correction coefficient of the risk coefficient is set to the second preset correction coefficient, and the corrected risk coefficient is wj*f2; If the second predicted characteristic state evaluation value is less than the predicted characteristic state evaluation value and the change rate is within the third preset change rate interval, the correction coefficient of the risk coefficient is set to the first preset correction coefficient, and the corrected risk coefficient is wj*f1; Among them, j=1, 2, 3, 4, 0.75<f1<f2<f3<1<f4<f5<f6<1.

25.

9. The 10kV electrical equipment temperature and humidity monitoring system according to claim 8, characterized in that: Determine whether to generate an alarm signal based on the corrected risk factor, including: Pre-set risk factor thresholds; When the corrected risk factor is less than the risk factor threshold, no alarm signal is sent; When the corrected risk factor is greater than the preset risk factor threshold, an alarm signal is sent, and the alarm signal includes the location information and risk level of the corresponding electrical equipment.

Images