Electric power engineering field security management system and method based on big data

Abstract

The invention relates to the technical field of security and protection management of big data, and particularly discloses an electric power engineering field security and protection management system and method based on big data. Temperature data of electric power equipment is collected in real time through an infrared thermal imaging instrument, and temperature prediction is performed by using a Gaussian process regression model in combination with environmental data; in consideration of the influence of an air attenuation coefficient on infrared thermal imaging data, the invention provides a correction method based on temperature deviation analysis, high-deviation equipment temperature data is accurately corrected by calculating the air attenuation coefficient and a temperature correction factor, and further, the temperature of the equipment is accurately corrected based on the corrected temperature data. Temperature abnormity of the equipment is identified by using a temperature fluctuation rate analysis technology, and real-time early warning and accurate positioning of equipment faults are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of security management of big data, and in particular to a power engineering site security management system and method based on big data. Background Art

[0002] With the rapid development of power engineering around the world, the scale and operating load of power equipment are constantly increasing. Ensuring the safe and stable operation of power equipment has become the most important link in modern power systems. If potential hidden dangers such as overheating, aging, and electrical failures of equipment are not discovered in time in the early stages, they will often cause large-scale power outages or equipment damage, causing huge economic losses and safety hazards. At present, traditional equipment monitoring methods rely on manual inspections and regular inspections, which often face problems such as long cycles, delayed responses, and missed hidden dangers, making it difficult to achieve real-time and accurate monitoring of equipment status. In addition, although infrared thermal imaging technology has been widely used in power equipment monitoring and can efficiently detect temperature anomalies on the surface of equipment, due to the influence of air attenuation coefficient, especially in long distances or complex environments, the temperature data collected by infrared instruments is easily interfered by environmental factors such as temperature, humidity, and air pressure, resulting in measurement errors. Therefore, traditional infrared thermal imaging technology faces the problems of insufficient accuracy and large limitations, and cannot fully meet the requirements of large-scale power equipment monitoring for high precision and high reliability.

[0003] The current power equipment monitoring system generally fails to effectively analyze environmental factors and equipment temperature changes, ignoring the significant impact of environmental temperature, humidity, air pressure and other factors on the surface temperature of the equipment, resulting in deviations in the prediction and fault diagnosis process of equipment temperature. Especially in complex environments, temperature changes are not only determined by the operating status of the equipment itself, but also closely related to external environmental conditions. Most of the existing equipment anomaly detection methods rely on simple threshold settings or static judgments. This method cannot accurately capture the potential trend of equipment temperature fluctuations, and there are large errors in the prediction and early warning of equipment failures, which is prone to omissions or false alarms. Therefore, how to overcome the air attenuation effect in traditional monitoring methods, combine real-time environmental data, use advanced Gaussian process regression models for temperature prediction, and then accurately identify equipment anomalies through temperature fluctuation rate analysis has become a key technical problem that needs to be solved in the current power equipment management. Through these innovative methods, not only can the accuracy of temperature monitoring be effectively improved, but also real-time and accurate fault early warning can be achieved, and the operation safety and maintenance efficiency of power equipment can be improved. Summary of the invention

[0004] The purpose of the present invention is to provide a power engineering site security management system and method based on big data to solve the above-mentioned background problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The power engineering site security management method based on big data includes the following steps:

[0007] S1: Use infrared thermal imaging equipment to monitor the surface temperature of power equipment at the power engineering site in real time, collect temperature data on the surface of power equipment in real time, and record the temperature distribution of each power equipment;

[0008] Wherein, the power equipment includes: generator sets, transformers, power switches and transmission lines;

[0009] S2: Real-time collection of environmental data at the power engineering site, using the Gaussian process regression model to predict the surface temperature data of power equipment by inputting the current environmental data;

[0010] Wherein, the environmental data includes: environmental temperature, humidity and air pressure;

[0011] S3: Since the air attenuation coefficient may cause the temperature data collected by the infrared thermal imaging instrument to be inaccurate, the predicted surface temperature data of the power equipment is compared and analyzed with the real-time surface temperature data of the power equipment to determine the degree of deviation between the surface temperature data of the power equipment and the real-time surface temperature data of the power equipment;

[0012] S4: According to the judgment result, the deviation degree of the temperature data is divided into: high deviation and low deviation. Based on the surface temperature data of the power equipment with high deviation, the air attenuation coefficient is calculated according to the real-time environmental data. According to the air attenuation coefficient, the temperature correction factor is calculated to correct the surface temperature data of the equipment with high deviation.

[0013] S5: Based on the corrected equipment surface temperature data, the temperature fluctuation rate is calculated to identify the power equipment with abnormal temperature, and early warning processing and fault analysis are performed for the power equipment with abnormal temperature.

[0014] As a further solution of the present invention: the real-time collection of environmental data at the power engineering site, using the Gaussian process regression model, by inputting the current environmental data, predicting the surface temperature data of the power equipment, specifically includes:

[0015] Get a set of training data, including environment data X = {x1, x2, ..., x n} and the corresponding power equipment surface temperature data y={y1,y2,…,y n};

[0016] The Gaussian process model represents the similarity between input data points through the covariance function;

[0017] The calculation expression of the similarity between the input data points is:

[0018]

[0019] In the formula, f(x) represents the function value, that is, the surface temperature of the power equipment, m(x) represents the mean function, k(x,x′) represents the covariance function, and x and x′ represent two environmental data input points respectively;

[0020] Wherein, the calculation expression of the covariance function is:

[0021]

[0022] In the formula, represents the amplitude of change of the function value, and l represents the length scale;

[0023] Calculate the covariance matrix of the training data and the covariance of the predicted data;

[0024] The calculation process of the covariance matrix of the training data is as follows:

[0025] For the training data X, the covariance matrix K(X,X) is an n*n matrix, and the element K(x i ,x j ) is calculated by the covariance function, and the calculation expression is:

[0026]

[0027] Due to the existence of noise, a noise term is added to the covariance matrix, and the calculation expression is:

[0028]

[0029] In the formula, represents the noise term, I represents the identity matrix, represents the variance of the noise;

[0030] For new environment data input x * , calculate the new covariance matrix K(X,x * ) and K(x * ,x * );

[0031] K(X,x * ) is the covariance between the training data and the prediction points, indicating the similarity between the training data and the prediction data;

[0032] K(x * ,x * ) represents the covariance between the predicted points;

[0033] Based on the training data and new environmental data, temperature prediction is performed to calculate the predicted surface temperature of the power equipment. The calculation expression is:

[0034]

[0035] In the formula, K(X,x * ) T represents the transpose of the covariance matrix between the training data and the predicted data, y represents the real-time surface temperature of the power equipment corresponding to the training data, μ * (x * ) represents the predicted surface temperature of the power equipment given the current environmental data.

[0036] As a further solution of the present invention: the step of determining the degree of deviation between the surface temperature data of the power equipment and the real-time collected surface temperature data of the power equipment and calculating the temperature deviation value specifically includes:

[0037] Obtain the real-time collected surface temperature data T of the power equipment real (t) and predicted power equipment surface temperature data T pred (t);

[0038] The deviation between the predicted surface temperature data of the power equipment and the real-time collected surface temperature data of the power equipment is calculated by using a mean square error calculation expression, and recorded as a temperature deviation value;

[0039] Wherein, the mean square error calculation expression is:

[0040]

[0041] Where N represents the total number of time points, t represents the time point, and MSE represents the temperature deviation value.

[0042] As a further solution of the present invention: the deviation degree of the temperature data is determined by:

[0043] Determine whether the temperature deviation value is greater than or equal to a preset temperature deviation value threshold. If so, it is recorded as a high deviation; if not, it is recorded as a low deviation.

[0044] As a further solution of the present invention: the calculation of the air attenuation coefficient based on the surface temperature data of the power equipment with high deviation and the real-time environmental data specifically includes:

[0045] Get the distance between the power equipment and the infrared thermal imaging instrument;

[0046] Get real-time environmental data;

[0047] According to the real-time environmental data and the distance between the power equipment and the infrared thermal imaging instrument, the air attenuation coefficient is calculated by the calculation method of the physical model. The calculation expression is:

[0048]

[0049] Where α0 represents the initial value of the air attenuation coefficient, d represents the distance between the power equipment and the thermal imaging instrument, λ represents the wavelength attenuation factor, and T env Indicates the real-time temperature, T ref Indicates the preset standard temperature, H env Indicates real-time humidity, H ref Indicates the preset standard humidity, F env Indicates real-time air pressure, F ref represents the preset standard atmospheric pressure, and e represents the logarithm of the base of a natural number.

[0050] As a further solution of the present invention: the temperature correction factor is calculated according to the air attenuation coefficient to correct the high-deviation equipment surface temperature data, specifically including:

[0051] Calculate the correction factor based on the air attenuation coefficient;

[0052] Wherein, the calculation expression of the correction factor is:

[0053]

[0054] In the formula, K cor represents the correction factor;

[0055] According to the correction factor, the real-time collected equipment surface temperature is corrected to obtain the corrected equipment surface temperature data;

[0056] The calculation expression of the corrected temperature data is:

[0057] T corr =T g *K cor ;

[0058] Where, T corr Indicates the corrected equipment surface temperature data, T g Indicates highly deviated device surface temperature data.

[0059] As a further solution of the present invention: the process of obtaining the temperature fluctuation rate is:

[0060] The corrected equipment surface temperature data and the low-deviation equipment surface temperature data are integrated into a set of time series data, denoted as T(t);

[0061] Perform discrete wavelet transform on the temperature signal;

[0062] Wherein, the calculation expression of the discrete wavelet transform is:

[0063]

[0064] Where N is the total number of time points, t is the time point, j is the scale parameter, k is the translation parameter, W(j,k) is the kth coefficient of the jth layer decomposition, 2 j / 2 ψ(2 j tk) represents the wavelet basis function;

[0065] Wavelet transform decomposes the temperature signal into approximate components and detail components. The calculation expression is:

[0066]

[0067] In the formula, A j (t) represents the approximate component, and D(t) represents the detail component;

[0068] The high-frequency fluctuation information is extracted from the wavelet detail component to calculate the temperature fluctuation rate. The calculation expression is:

[0069]

[0070] In the formula, R j represents the temperature fluctuation rate, D j (k) represents the kth detail component coefficient of the jth layer decomposition, k represents the translation parameter, and B represents the length of the translation parameter.

[0071] As a further solution of the present invention: the power equipment for identifying temperature anomalies specifically includes:

[0072] Determine whether the temperature fluctuation rate of the device surface is greater than or equal to the preset temperature fluctuation threshold. If so, it is recorded as a temperature abnormal device; if not, it is recorded as a temperature normal device.

[0073] The power engineering site security management system based on big data is characterized by including:

[0074] A data acquisition module, which uses an infrared thermal imaging instrument to monitor the surface temperature of power equipment at the power engineering site in real time and collects temperature data on the surface of the power equipment in real time;

[0075] Real-time collection of environmental data at power engineering sites;

[0076] The power equipment surface temperature prediction module collects environmental data of the power engineering site in real time, uses a Gaussian process regression model, and predicts the surface temperature data of the power equipment by inputting the current environmental data;

[0077] A data deviation analysis module, wherein the data deviation analysis module compares and analyzes the predicted surface temperature data of the power equipment with the real-time collected surface temperature data of the power equipment to determine the degree of deviation between the surface temperature data of the power equipment and the real-time collected surface temperature data of the power equipment;

[0078] A temperature data correction module, which divides the degree of deviation of the temperature data into high deviation and low deviation according to the judgment result, calculates the air attenuation coefficient according to the real-time environmental data based on the surface temperature data of the power equipment with high deviation, calculates the temperature correction factor according to the air attenuation coefficient, and corrects the surface temperature data of the equipment with high deviation;

[0079] The abnormal equipment identification module identifies the power equipment with abnormal temperature by calculating the temperature fluctuation rate based on the corrected equipment surface temperature data, and performs early warning processing and fault analysis on the power equipment with abnormal temperature.

[0080] Beneficial effects of the present invention:

[0081] (1) The present invention innovatively combines infrared thermal imaging technology with the Gaussian process regression model to achieve accurate monitoring and prediction of the surface temperature of power equipment, making up for the shortcomings of traditional temperature measurement methods in complex environments. By collecting the surface temperature and surrounding environmental data of power equipment in real time, and analyzing and correcting the deviation between the predicted value and the actual collected value, the air attenuation correction model is introduced to successfully solve the problem of temperature measurement error caused by the dynamic change of the air attenuation coefficient. This method greatly improves the credibility and consistency of temperature data, and provides a more reliable data basis for the evaluation of the operating status of power equipment. In addition, by introducing temperature fluctuation rate analysis technology, high-frequency abnormal information can be quickly extracted from subtle temperature changes, and potential equipment failure hazards can be effectively identified. This systematic solution not only realizes the optimization of the entire chain from data collection to abnormality detection, but also improves the intelligence and precision of on-site security management of power projects.

[0082] (2) The present invention realizes accurate identification and preventive maintenance before equipment failure or abnormality occurs by accurately correcting high-deviation temperature data and conducting real-time early warning analysis of temperature abnormality equipment. This forward-looking monitoring method can effectively capture potential problems in equipment operation and reduce serious consequences caused by hidden faults not being discovered in time. In particular, the analysis method based on temperature fluctuation rate not only improves the detection sensitivity of abnormal equipment, but also provides operation and maintenance personnel with an intuitive basis for quickly locating problem equipment, shortens fault response time, reduces unplanned downtime of equipment and the resulting production losses and operating costs. By combining environmental data to deeply analyze the non-fault causes of equipment temperature abnormality, such as external environmental changes or measurement errors, it reduces the waste of resources caused by false alarms and the expenditure caused by excessive maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The present invention will be further described below in conjunction with the accompanying drawings.

[0084] Figure 1 It is a flowchart of the specific steps of the power engineering site security management method based on big data of the present invention;

[0085] Figure 2 It is a flowchart of the power engineering site security management system based on big data in the present invention. DETAILED DESCRIPTION

[0086] 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.

[0087] See also Figure 1 As shown, the present invention is a power engineering site security management method based on big data, comprising the following steps:

[0088] S1: Use infrared thermal imaging equipment to monitor the surface temperature of power equipment at the power engineering site in real time, collect temperature data on the surface of power equipment in real time, and record the temperature distribution of each power equipment;

[0089] Wherein, the power equipment includes: generator sets, transformers, power switches and transmission lines;

[0090] S2: Real-time collection of environmental data at the power engineering site, using the Gaussian process regression model to predict the surface temperature data of power equipment by inputting the current environmental data;

[0091] Wherein, the environmental data includes: environmental temperature, humidity and air pressure;

[0092] S3: Since the air attenuation coefficient may cause the temperature data collected by the infrared thermal imaging instrument to be inaccurate, the predicted surface temperature data of the power equipment is compared and analyzed with the real-time surface temperature data of the power equipment to determine the degree of deviation between the surface temperature data of the power equipment and the real-time surface temperature data of the power equipment;

[0093] S4: According to the judgment result, the deviation degree of the temperature data is divided into: high deviation and low deviation. Based on the surface temperature data of the power equipment with high deviation, the air attenuation coefficient is calculated according to the real-time environmental data. According to the air attenuation coefficient, the temperature correction factor is calculated to correct the surface temperature data of the equipment with high deviation.

[0094] S5: Based on the corrected equipment surface temperature data, the temperature fluctuation rate is calculated to identify the power equipment with abnormal temperature, and early warning processing and fault analysis are performed for the power equipment with abnormal temperature.

[0095] In S1, the surface temperature of power equipment at the power engineering site is monitored in real time by infrared thermal imaging instruments, the temperature data of the power equipment surface is collected in real time, and the temperature distribution of each power equipment is recorded, including:

[0096] Select infrared thermal imaging instruments according to the power equipment, and ensure that the equipment has sufficient resolution, temperature range and measurement accuracy to meet the needs of temperature monitoring of power equipment;

[0097] At the power engineering site, infrared thermal imaging equipment is installed according to the layout and monitoring requirements of the power equipment;

[0098] After the equipment is installed, calibrate the infrared thermal imaging instrument;

[0099] Start the infrared thermal imaging instrument to start real-time monitoring of the surface temperature of the power equipment;

[0100] Scan the surface of the power equipment in a time series (e.g., every minute) to obtain a set of real-time time series temperature data;

[0101] Infrared thermal imaging equipment will scan the surface of the equipment and record the temperature distribution in real time;

[0102] The collected temperature data is transmitted to the data storage platform in real time;

[0103] The data platform should have real-time data storage and management functions, be able to classify and store data according to equipment, time, location, etc., and generate data backup;

[0104] In S2, the environmental data of the power engineering site is collected in real time, and the Gaussian process regression model is used to predict the surface temperature data of the power equipment by inputting the current environmental data, including:

[0105] Use temperature sensors, humidity sensors, and air pressure sensors to collect on-site environmental data in real time through wireless networks and Internet of Things (IoT) technologies;

[0106] Wherein, the environmental data includes: environmental temperature, humidity and air pressure;

[0107] The data acquisition system should have high frequency, stability and accuracy, and be able to acquire data in real time and transmit it to the cloud platform or local server for processing;

[0108] Environmental data may contain noise or outliers, and data cleaning is required to remove invalid or extreme data points;

[0109] Get a set of training data, including environment data X = {x1, x2, ..., x n} and the corresponding power equipment surface temperature data y={y1,y2,…,y n};

[0110] A Gaussian process is a random process in which the output values ​​of any set of input values ​​follow a joint normal distribution;

[0111] The Gaussian process model uses a covariance function (kernel function) to represent the similarity between input data points;

[0112] The calculation expression of the similarity between the input data points is:

[0113]

[0114] In the formula, f(x) represents the function value (i.e., the surface temperature of the power equipment), m(x) represents the mean function, k(x, x′) represents the covariance function, and x and x′ represent two environmental data input points respectively;

[0115] Wherein, the calculation expression of the covariance function is:

[0116]

[0117] In the formula, Indicates the magnitude of the function value change, l indicates the length scale (determines the similarity between inputs, a smaller l indicates a stronger similarity between inputs, and a larger l indicates a weaker similarity);

[0118] Calculate the covariance matrix of the training data and the covariance of the predicted data;

[0119] The calculation process of the covariance matrix of the training data is as follows:

[0120] For the training data X, the covariance matrix K(X,X) is an n*n matrix, and the element K(x i ,x j ) is calculated by the covariance function, and the calculation expression is:

[0121]

[0122] It should be noted that the covariance matrix K(X,X) reflects the similarity between training data points;

[0123] Considering the existence of noise, the noise term is added to the covariance matrix, and the calculation expression is:

[0124]

[0125] In the formula, represents the noise term, I represents the identity matrix, represents the variance of the noise;

[0126] For new environment data input x * , calculate the new covariance matrix K(X,x * ) and K(x * ,x * );

[0127] K(X,x * ) is the covariance between the training data and the prediction points, indicating the similarity between the training data and the prediction data;

[0128] K(x * ,x * ) represents the covariance between the predicted points;

[0129] Based on the training data and new environmental data, temperature prediction is performed to calculate the predicted surface temperature of the power equipment. The calculation expression is:

[0130]

[0131] In the formula, K(X,x * ) T represents the transpose of the covariance matrix between the training data and the predicted data, y represents the surface temperature of the power equipment corresponding to the training data (temperature data collected in real time), μ * (x * ) represents the predicted surface temperature of the power equipment given the current environmental data.

[0132] In S3, since the air attenuation coefficient may cause the temperature data collected by the infrared thermal imaging instrument to be inaccurate, the predicted surface temperature data of the power equipment is compared and analyzed with the real-time surface temperature data of the power equipment to determine the degree of deviation between the surface temperature data of the power equipment and the real-time surface temperature data of the power equipment, specifically including:

[0133] Obtain the real-time collected surface temperature data T of the power equipment real (t) and predicted power equipment surface temperature data T pred (t);

[0134] The deviation between the predicted surface temperature data of the power equipment and the real-time collected surface temperature data of the power equipment is calculated by using a mean square error calculation expression, and recorded as a temperature deviation value;

[0135] Wherein, the mean square error calculation expression is:

[0136]

[0137] In the formula, N represents the total number of time points, t represents the time point, and MSE represents the temperature deviation value;

[0138] comparing the temperature deviation value with a preset temperature deviation value threshold;

[0139] If the temperature deviation value is greater than or equal to the preset temperature deviation value threshold, it means that the surface temperature data of the corresponding power equipment is not accurately collected and the degree of deviation is high, which is recorded as high deviation;

[0140] If the temperature deviation value is less than the preset temperature deviation value threshold, it means that the surface temperature data of the corresponding power equipment is collected accurately and the degree of deviation is low, which is recorded as low deviation.

[0141] It should be noted that the air attenuation coefficient will cause the temperature data collected by the infrared thermal imaging instrument to be inaccurate. The reason is that the air attenuation effect will be aggravated by the increase in distance and the dynamic changes in environmental conditions (such as temperature, humidity, and air pressure), resulting in deviations in the measurement of the equipment surface temperature data, which may cause the hidden danger of equipment overheating to not be discovered in time or misdiagnose the fault, affecting the efficiency and reliability of security management.

[0142] In S4, based on the surface temperature data of the power equipment with high deviation, the air attenuation coefficient is calculated according to the real-time environmental data, and the temperature correction factor is calculated according to the air attenuation coefficient to correct the surface temperature data of the equipment with high deviation, which specifically includes:

[0143] Get the distance between the power equipment and the infrared thermal imaging instrument;

[0144] Get real-time environmental data;

[0145] According to the real-time environmental data and the distance between the power equipment and the infrared thermal imaging instrument, the air attenuation coefficient is calculated by the calculation method of the physical model. The calculation expression is:

[0146]

[0147] Where α0 represents the initial value of the air attenuation coefficient, d represents the distance between the power equipment and the thermal imaging instrument, λ represents the wavelength attenuation factor, and T env Indicates the real-time temperature, T ref Indicates the preset standard temperature, H env Indicates real-time humidity, H ref Indicates the preset standard humidity, F env Indicates real-time air pressure, F ref represents the preset standard air pressure, and e represents the logarithm of the base of a natural number;

[0148] Calculate the correction factor based on the air attenuation coefficient;

[0149] Wherein, the calculation expression of the correction factor is:

[0150]

[0151] In the formula, K cor represents the correction factor;

[0152] According to the correction factor, the real-time collected equipment surface temperature is corrected to obtain the corrected equipment surface temperature data;

[0153] The calculation expression of the corrected temperature data is:

[0154] T corr =T g *K cor ;

[0155] Where, T corr Indicates the corrected equipment surface temperature data, T g Equipment surface temperature data indicating high deviations;

[0156] It should be noted that due to the existence of air attenuation, the infrared signal strength received by infrared thermal imaging instruments is often lower than the actual signal strength, resulting in low or high measurement errors of the equipment surface temperature data; the risk of equipment overheating cannot be identified in time, and the failure to accurately measure the temperature rise may cause equipment hidden dangers to go undetected, increasing the risk of equipment failure or fire; and the abnormal surface temperature data of the equipment may be mistaken for equipment failure, resulting in unnecessary downtime and maintenance.

[0157] In S5, based on the corrected equipment surface temperature data, the temperature fluctuation rate is calculated to identify the power equipment with abnormal temperature. For the power equipment with abnormal temperature, early warning processing and fault analysis are performed, including:

[0158] The corrected equipment surface temperature data and the low-deviation equipment surface temperature data are integrated into a set of time series data, denoted as T(t);

[0159] Perform discrete wavelet transform on the temperature signal;

[0160] Wherein, the calculation expression of the discrete wavelet transform is:

[0161]

[0162] Where N is the total number of time points, t is the time point, j is the scale parameter, k is the translation parameter, W(j,k) is the kth coefficient of the jth layer decomposition, 2 j / 2 ψ(2 j tk) represents the wavelet basis function;

[0163] Wavelet transform decomposes the temperature signal into approximate components and detail components. The calculation expression is:

[0164]

[0165] In the formula, A j (t) represents the approximate component, and D(t) represents the detail component;

[0166] The high-frequency fluctuation information is extracted from the wavelet detail component to calculate the temperature fluctuation rate. The calculation expression is:

[0167]

[0168] In the formula, R j represents the temperature fluctuation rate, D j (t) represents the k-th detail component coefficient of the j-th layer decomposition, k represents the translation parameter, and B represents the length of the translation parameter;

[0169] comparing the temperature fluctuation rate of the device surface with a preset temperature fluctuation threshold;

[0170] If the temperature fluctuation rate is greater than or equal to the preset temperature fluctuation threshold, it means that the temperature of the corresponding device is abnormal and is recorded as a temperature abnormal device;

[0171] If the temperature fluctuation rate is less than the preset temperature fluctuation threshold, it means that the temperature of the corresponding device is normal and is recorded as a normal temperature device;

[0172] It should be noted that the temperature fluctuation rate reflects whether the temperature of the equipment is normal during operation, and the larger the value of the temperature fluctuation rate, the higher the abnormality of the corresponding equipment.

[0173] Based on the equipment with abnormal temperature, a real-time warning signal is generated. Based on the warning signal, it is analyzed whether the abnormality is caused by environmental data. If not, the load condition, electrical contact status and component aging of the equipment are checked one by one.

[0174] See also Figure 2 As shown in the figure, the power engineering site security management system based on big data includes:

[0175] A data acquisition module, which uses an infrared thermal imaging instrument to monitor the surface temperature of power equipment at the power engineering site in real time and collects temperature data on the surface of the power equipment in real time;

[0176] Real-time collection of environmental data at power engineering sites;

[0177] The power equipment surface temperature prediction module collects environmental data of the power engineering site in real time, uses a Gaussian process regression model, and predicts the surface temperature data of the power equipment by inputting the current environmental data;

[0178] A data deviation analysis module, wherein the data deviation analysis module compares and analyzes the predicted surface temperature data of the power equipment with the real-time collected surface temperature data of the power equipment to determine the degree of deviation between the surface temperature data of the power equipment and the real-time collected surface temperature data of the power equipment;

[0179] A temperature data correction module, which divides the degree of deviation of the temperature data into high deviation and low deviation according to the judgment result, calculates the air attenuation coefficient according to the real-time environmental data based on the surface temperature data of the power equipment with high deviation, calculates the temperature correction factor according to the air attenuation coefficient, and corrects the surface temperature data of the equipment with high deviation;

[0180] The abnormal equipment identification module identifies the power equipment with abnormal temperature by calculating the temperature fluctuation rate based on the corrected equipment surface temperature data, and performs early warning processing and fault analysis on the power equipment with abnormal temperature.

[0181] The working principle of the present invention is to use infrared thermal imaging instruments to monitor the surface temperature of equipment such as generator sets, transformers, power switches and transmission lines in real time, record their temperature distribution, and store and back up in real time through a data transmission platform. Subsequently, by deploying environmental sensors, environmental temperature, humidity and air pressure data are collected in real time, and a Gaussian process regression model is used to predict the surface temperature of power equipment based on environmental data. Considering that the air attenuation coefficient may cause deviations in the temperature data collected by the infrared thermal imaging instrument, the deviation value between the predicted temperature and the actual collected temperature is calculated by the mean square error formula, and air attenuation correction is performed on the data with high deviations. After correction, the temperature fluctuation rate on the surface of the equipment is calculated based on the wavelet transform algorithm, high-frequency features are extracted from the time series data, equipment with abnormal temperature is identified, and an early warning signal is further generated. For the identified abnormal temperature equipment, the source of the abnormality is comprehensively evaluated by analyzing the dynamic changes of the temperature fluctuation rate and environmental data. If the abnormality originates from the equipment itself, the load, electrical contact and component aging of the equipment are carefully analyzed, and a reasonable repair and maintenance plan is formulated.

[0182] 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 in the formula are set by technicians in this field according to actual conditions.

[0183] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0184] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0185] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0186] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A power engineering site security management method based on big data, characterized in that: The following steps are involved: S1: Use infrared thermal imaging equipment to monitor the surface temperature of power equipment at the power engineering site in real time, collect temperature data on the surface of power equipment in real time, and record the temperature distribution of each power equipment; Wherein, the power equipment includes: generator sets, transformers, power switches and transmission lines; S2: Real-time collection of environmental data at the power engineering site, using the Gaussian process regression model to predict the surface temperature data of power equipment by inputting the current environmental data; Wherein, the environmental data includes: ambient temperature, humidity and air pressure; S3: Since the air attenuation coefficient may cause the temperature data collected by the infrared thermal imaging instrument to be inaccurate, the predicted surface temperature data of the power equipment is compared and analyzed with the real-time surface temperature data of the power equipment to determine the degree of deviation between the surface temperature data of the power equipment and the real-time surface temperature data of the power equipment; S4: According to the judgment result, the deviation degree of the temperature data is divided into: high deviation and low deviation. Based on the surface temperature data of the power equipment with high deviation, the air attenuation coefficient is calculated according to the real-time environmental data. According to the air attenuation coefficient, the temperature correction factor is calculated to correct the surface temperature data of the equipment with high deviation. S5: Based on the corrected equipment surface temperature data, the temperature fluctuation rate is calculated to identify the power equipment with abnormal temperature, and early warning processing and fault analysis are performed for the power equipment with abnormal temperature.

2. The method for power engineering site security management based on big data according to claim 1 is characterized in that: The real-time collection of environmental data at the power engineering site and the use of a Gaussian process regression model to predict the surface temperature data of the power equipment by inputting the current environmental data specifically include: Get a set of training data, including environment data X = {x1, x2, ..., x n } and the corresponding power equipment surface temperature data y={y1,y2,…,y n }; The Gaussian process model represents the similarity between input data points through the covariance function; The calculation expression of the similarity between the input data points is: In the formula, f(x) represents the function value, that is, the surface temperature of the power equipment, m(x) represents the mean function, k(x,x′) represents the covariance function, and x and x′ represent two environmental data input points respectively; Wherein, the calculation expression of the covariance function is: In the formula, represents the amplitude of change of the function value, and l represents the length scale; Calculate the covariance matrix of the training data and the covariance of the predicted data; The calculation process of the covariance matrix of the training data is as follows: For the training data X, the covariance matrix K(X,X) is an n*n matrix, and the element K(x i ,x j ) is calculated by the covariance function, and the calculation expression is: Due to the existence of noise, a noise term is added to the covariance matrix, and the calculation expression is: In the formula, represents the noise term, I represents the identity matrix, represents the variance of the noise; For new environment data input x * , calculate the new covariance matrix K(X,x * ) and K(x * ,x * ); K(X,x * ) is the covariance between the training data and the prediction points, indicating the similarity between the training data and the prediction data; K(x * ,x * ) represents the covariance between the predicted points; Based on the training data and new environmental data, temperature prediction is performed to calculate the predicted surface temperature of the power equipment. The calculation expression is: In the formula, K(X,x * ) T represents the transpose of the covariance matrix between the training data and the predicted data, y represents the real-time surface temperature of the power equipment corresponding to the training data, μ * (x * ) represents the predicted surface temperature of the power equipment given the current environmental data.

3. The method for power engineering site security management based on big data according to claim 1 is characterized in that: The step of determining the degree of deviation between the surface temperature data of the power equipment and the temperature data collected in real time on the surface of the power equipment and calculating the temperature deviation value specifically includes: Obtain the real-time collected surface temperature data T of the power equipment real (t) and predicted power equipment surface temperature data T pred (t); The deviation between the predicted surface temperature data of the power equipment and the real-time collected surface temperature data of the power equipment is calculated by using a mean square error calculation expression, and recorded as a temperature deviation value; Wherein, the mean square error calculation expression is: Where N represents the total number of time points, t represents the time point, and MSE represents the temperature deviation value.

4. The method for power engineering site security management based on big data according to claim 3 is characterized in that: The deviation degree of the temperature data is determined by: Determine whether the temperature deviation value is greater than or equal to a preset temperature deviation value threshold. If so, it is recorded as a high deviation; if not, it is recorded as a low deviation.

5. The method for power engineering site security management based on big data according to claim 1, characterized in that: The method of calculating the air attenuation coefficient based on the surface temperature data of the power equipment with high deviation and the real-time environmental data specifically includes: Get the distance between the power equipment and the infrared thermal imaging instrument; Get real-time environmental data; According to the real-time environmental data and the distance between the power equipment and the infrared thermal imaging instrument, the air attenuation coefficient is calculated by the calculation method of the physical model. The calculation expression is: Where α0 represents the initial value of the air attenuation coefficient, d represents the distance between the power equipment and the thermal imaging instrument, λ represents the wavelength attenuation factor, and T env Indicates the real-time temperature, T ref Indicates the preset standard temperature, H env Indicates real-time humidity, H ref Indicates the preset standard humidity, F env Indicates real-time air pressure, F ref represents the preset standard atmospheric pressure, and e represents the logarithm of the base of a natural number.

6. The method for power engineering site security management based on big data according to claim 1, characterized in that: The temperature correction factor is calculated according to the air attenuation coefficient to correct the high-deviation equipment surface temperature data, specifically including: Calculate the correction factor based on the air attenuation coefficient; Wherein, the calculation expression of the correction factor is: In the formula, K cor represents the correction factor; According to the correction factor, the real-time collected equipment surface temperature is corrected to obtain the corrected equipment surface temperature data; The calculation expression of the corrected temperature data is: T corr =T g *K cor ; Where, T corr Indicates the corrected equipment surface temperature data, T g Indicates highly deviated device surface temperature data.

7. The method for power engineering site security management based on big data according to claim 1, characterized in that: The process of obtaining the temperature fluctuation rate is as follows: The corrected equipment surface temperature data and the low-deviation equipment surface temperature data are integrated into a set of time series data, denoted as T(t); Perform discrete wavelet transform on the temperature signal; Wherein, the calculation expression of the discrete wavelet transform is: Where N is the total number of time points, t is the time point, j is the scale parameter, k is the translation parameter, W(j,k) is the kth coefficient of the jth layer decomposition, 2 j / 2 ψ(2 j tk) represents the wavelet basis function; Wavelet transform decomposes the temperature signal into approximate components and detail components. The calculation expression is: In the formula, A j (t) represents the approximate component, and D(t) represents the detail component; The high-frequency fluctuation information is extracted from the wavelet detail component to calculate the temperature fluctuation rate. The calculation expression is: In the formula, R j represents the temperature fluctuation rate, D j (k) represents the kth detail component coefficient of the jth layer decomposition, k represents the translation parameter, and B represents the length of the translation parameter.

8. The method for power engineering site security management based on big data according to claim 1, characterized in that: The electrical equipment for identifying abnormal temperature specifically includes: Determine whether the temperature fluctuation rate of the device surface is greater than or equal to the preset temperature fluctuation threshold. If so, it is recorded as a temperature abnormal device; if not, it is recorded as a temperature normal device.

9. The power engineering site security management system based on big data is characterized by: The method for on-site security management of electric power engineering projects based on big data as claimed in any one of claims 1 to 8 comprises: A data acquisition module, which uses an infrared thermal imaging instrument to monitor the surface temperature of power equipment at the power engineering site in real time and collects temperature data on the surface of the power equipment in real time; Real-time collection of environmental data at power engineering sites; The power equipment surface temperature prediction module collects environmental data of the power engineering site in real time, uses a Gaussian process regression model, and predicts the surface temperature data of the power equipment by inputting the current environmental data; A data deviation analysis module, wherein the data deviation analysis module compares and analyzes the predicted surface temperature data of the power equipment with the real-time collected surface temperature data of the power equipment to determine the degree of deviation between the surface temperature data of the power equipment and the real-time collected surface temperature data of the power equipment; A temperature data correction module, which divides the degree of deviation of the temperature data into high deviation and low deviation according to the judgment result, calculates the air attenuation coefficient according to the real-time environmental data based on the surface temperature data of the power equipment with high deviation, calculates the temperature correction factor according to the air attenuation coefficient, and corrects the surface temperature data of the equipment with high deviation; The abnormal equipment identification module identifies the power equipment with abnormal temperature by calculating the temperature fluctuation rate based on the corrected equipment surface temperature data, and performs early warning processing and fault analysis on the power equipment with abnormal temperature.

Images