Environment-friendly gas-insulated switchgear operation monitoring system

Abstract

The invention discloses an environment-friendly gas-insulated switchgear operation monitoring system, which relates to the technical field of environment-friendly cabinets, and comprises a data acquisition module for acquiring vibration data and temperature data of an environment-friendly gas-insulated switchgear in real time, sending the vibration data and the temperature data to a data processing module through a main control module, and performing data prediction on the vibration data and the temperature data at a fault moment; the corresponding vibration calculation data and temperature calculation data are sent to the comprehensive prediction module through the main control module; historical vibration calculation data and historical temperature calculation data are stored in the database; and the comprehensive prediction module calls historical data in the database, performs similarity comparison on the historical data, the vibration calculation data and the temperature calculation data, and judges that the fault is a corresponding historical fault if the similarity is greater than a preset similarity threshold. According to the invention, the abnormal temperature prediction is carried out on the environment-friendly gas-insulated switchgear which operates in real time, and the abnormal vibration data is combined, so that the early fault identification when the environment-friendly gas-insulated switchgear breaks down is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental protection cabinets, and more particularly to an environmental protection inflatable cabinet operation monitoring system. Background Art

[0002] As an electrical device connecting the power distribution line, the environmental protection cabinet is an important switchgear for ring network power supply and terminal power supply. It is widely used in various places such as power plants, substations, box-type transformers, and integrated rooms. The environmental protection cabinet uses environmentally friendly gas instead of traditional sulfur hexafluoride (SF6) gas, and the gas box uses environmentally friendly gas as the main insulation body to reduce the impact on the environment. All core conductive parts such as circuit breakers, fuses, and load switches in the environmental protection cabinet are installed in a sealed stainless steel gas box. The gas box adopts a micro-positive pressure dry environmental protection gas sealing system, which not only effectively shields the impact of the environment to ensure the normal protection action of the environmental protection cabinet, but also the environmentally friendly gas will not cause damage to the environment.

[0003] In actual application scenarios, as environmental cabinets quickly replace gas cabinets, accidents involving environmental cabinets have also increased significantly. Although environmental cabinets have significant advantages over gas cabinets in terms of environmental protection, they have no advantages in terms of safety and stability. As the existing technology lacks effective diagnosis of the operating status of environmental cabinets, hidden dangers of environmental cabinets cannot be predicted in advance, which can easily affect long-term power safety.

[0004] Therefore, how to predict the failure of the environmental protection cabinet is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0005] In view of this, the present invention provides an environmentally friendly inflatable cabinet operation monitoring system, which realizes early fault identification when a fault occurs in the environmentally friendly inflatable cabinet by predicting the temperature and coordinates of abnormal positions of the environmentally friendly inflatable cabinet running in real time and combining abnormal vibration data.

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

[0007] An environmentally friendly inflatable cabinet operation monitoring system includes: a data acquisition module, a data processing module, a main control module, a comprehensive prediction module, and a database. The data acquisition module collects vibration data and temperature data of the environmentally friendly inflatable cabinet in real time, and sends the data to the data processing module through the main control module. The data processing module predicts the vibration data and temperature data at the time of a fault to obtain corresponding vibration calculation data and temperature calculation data, and sends the vibration calculation data and temperature calculation data to the comprehensive prediction module through the main control module; the database stores historical vibration calculation data and historical temperature calculation data; the comprehensive prediction module retrieves historical data in the database, and compares the similarity with the vibration calculation data and temperature calculation data. If the similarity is greater than a preset similarity threshold, the fault is judged to be a corresponding historical fault.

[0008] Preferably, the data acquisition module is pre-set with sensors, the vibration sensor collects vibration data of the environmentally friendly inflatable cabinet, and a plurality of temperature sensors are provided to collect temperature data of various locations of the environmentally friendly inflatable cabinet.

[0009] Preferably, the data processing module includes: a vibration prediction unit and a temperature prediction module, wherein the vibration prediction unit obtains vibration calculation data at the next moment based on vibration data prediction; the temperature prediction module includes a temperature prediction unit and a coordinate calculation unit, wherein the temperature prediction unit obtains temperature prediction data at the next moment based on temperature data corresponding to the temperature sensor position; the coordinate calculation unit obtains the coordinates of the heat source according to the position of each temperature sensor; and the temperature calculation data includes the coordinates of the heat source and the temperature prediction data.

[0010] Preferably, it also includes a temperature sensor layout module, which arranges temperature sensors for real-time acquisition of regional temperature changes in different areas of the environmental protection inflatable cabinet based on asynchronous spatial layout, regional center layout, and uniform spatial layout, and groups the temperature sensors based on asynchronous spatial layout, regional center layout, and uniform spatial layout; calculates the variance, determination coefficient, covariance and unit score in each group of temperature sensors when a fault occurs, and selects the layout distribution of the temperature sensors according to the variance, determination coefficient, covariance and unit score.

[0011] Preferably, the vibration prediction unit specifically includes: dividing the vibration data of the environmentally friendly inflatable cabinet collected in real time based on preset time periods, adding the preset time periods and the corresponding vibration data to the corresponding historical time series, and calculating the vibration calculation data of the historical time series at the next moment by using an exponential smoothing prediction method.

[0012] Preferably, the temperature prediction unit specifically includes:

[0013] The matrix construction unit obtains the device temperature data of the temperature sensors in multiple time windows according to the layout distribution of the temperature sensors, and obtains the device temperature sequence of the temperature sensors; synchronously collects the ambient temperature of the corresponding temperature sensor positions in multiple time windows to obtain the ambient temperature sequence; constructs a device temperature matrix according to the device temperature sequences of the temperature sensors, and performs device temperature prediction in combination with the ambient temperature sequence to obtain a predicted device temperature matrix;

[0014] A model training module is used to construct a device temperature prediction model and train the device temperature prediction model based on the predicted device temperature matrix;

[0015] The temperature prediction module obtains the temperature prediction data at the next moment according to the temperature data to be predicted and the corresponding temperature sensor position.

[0016] Preferably, the coordinate calculation unit specifically includes: selecting at least two temperature sensors whose temperature prediction data at the next moment exceeds a preset temperature value, converting the collected device temperature data into an azimuth fusion estimate using the far-field positioning principle, locating the heat source within a quadrilateral area according to the azimuth fusion estimate result, and using an analytical geometry method to solve the coordinates of each vertex to obtain the coordinates of the heat source.

[0017] Preferably, the model training module specifically includes: performing matrix transformation according to the temperature monitoring data log of the equipment to obtain sample equipment temperature matrix records, sample environment temperature sequence records and sample prediction equipment temperature matrix records; using the sample equipment temperature matrix records, sample environment temperature sequence records and sample prediction equipment temperature matrix records to train the equipment temperature prediction model.

[0018] Preferably, the comprehensive prediction module calculates the similarity with the historical data based on the temperature prediction data, the heat source coordinates and the vibration calculation data by the Euclidean distance method. When the similarity is greater than the preset similarity threshold, the fault is judged to be a corresponding historical fault.

[0019] It can be seen from the above technical solution that, compared with the prior art, the present invention discloses an environmentally friendly inflatable cabinet operation monitoring system. The system obtains the status data of the switch cabinet in real time through a combination of vibration sensors and temperature sensors, and can detect potential faults in time; the system can calculate the precise coordinates of the heat source according to the readings of the temperature sensor, so as to quickly locate the fault area and reduce the search time; by using historical data and real-time data for comprehensive analysis, the system can more accurately identify and predict the type of fault, thereby supporting decision-making; the system arranges and selects sensors according to different layout strategies (such as asynchronous space layout, regional center layout, uniform space layout) to improve the comprehensiveness and accuracy of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0021] Figure 1 A schematic diagram of the structure provided by the present invention;

[0022] Figure 2 This is a schematic diagram of the data processing module provided by the present invention. DETAILED DESCRIPTION

[0023] 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.

[0024] In an environmental inflatable cabinet, a gas leak usually causes a temperature change that depends on the type of gas used and the operating status of the system. The following is an explanation of the temperature change when a gas leak occurs:

[0025] If SF6 gas is used: SF6 (sulfur hexafluoride) is a gas with excellent insulating properties, commonly used in high-voltage electrical equipment. Leakage usually means a drop in gas concentration.

[0026] Temperature changes: When SF6 gas leaks, the insulating properties of the gas decrease, which may cause arcing or overheating inside the equipment, resulting in a local temperature increase. In addition, the properties of SF6 in the gas state may also cause the temperature to decrease when the pressure decreases, but in actual situations, the trend usually observed is an overall temperature increase due to the increase in heat in electrical equipment.

[0027] Cooling effect caused by gas leakage: If the gas (such as SF6) filled in the gas-filled switchgear leaks, the amount of insulating gas in the system will decrease, which may cause the gas density to decrease, thereby affecting the heat dissipation.

[0028] In this case, there may be a local cooling phenomenon, but in the actual operation process, the heat generated by the equipment may exceed the cooling effect, resulting in an overall temperature rise. The gases used in the environmentally friendly inflatable cabinet of the present invention include but are not limited to SF6 (sulfur hexafluoride), nitrogen (N2), carbon dioxide (CO2), silane (SiH4), etc.

[0029] The embodiment of the present invention discloses an environmental protection inflatable cabinet operation monitoring system, such as Figure 1 As shown, it includes: a data acquisition module, a data processing module, a main control module, a comprehensive prediction module, and a database. The data acquisition module collects the vibration data and temperature data of the environmental protection inflatable cabinet in real time, and sends them to the data processing module through the main control module. The data processing module predicts the vibration data and temperature data at the time of the fault, obtains the corresponding vibration calculation data and temperature calculation data, and sends the vibration calculation data and the temperature calculation data to the comprehensive prediction module through the main control module; the database stores historical vibration calculation data and historical temperature calculation data; the comprehensive prediction module retrieves the historical data in the database, and compares the similarity with the vibration calculation data and the temperature calculation data. If the similarity is greater than the preset similarity threshold, the fault is judged to be a corresponding historical fault.

[0030] In a specific embodiment, the data acquisition module performs sensor settings in advance, the vibration sensor collects vibration data of the environmentally friendly inflatable cabinet, and a number of temperature sensors are provided to collect temperature data at various locations of the environmentally friendly inflatable cabinet.

[0031] In a specific embodiment, Figure 2 As shown, the data processing module includes: a vibration prediction unit and a temperature prediction module, the vibration prediction unit obtains the vibration calculation data of the next moment based on the vibration data prediction; the temperature prediction module includes a temperature prediction unit and a coordinate calculation unit, the temperature prediction unit obtains the temperature prediction data of the next moment based on the temperature data corresponding to the temperature sensor position; the coordinate calculation unit obtains the coordinates of the heat source according to the position of each temperature sensor; the temperature calculation data includes the coordinates of the heat source and the temperature prediction data.

[0032] In a specific embodiment, it also includes a temperature sensor layout module, which arranges temperature sensors for real-time acquisition of regional temperature changes in different areas of the environmental protection inflatable cabinet based on asynchronous spatial layout, regional center layout, and uniform spatial layout, and groups the temperature sensors based on asynchronous spatial layout, regional center layout, and uniform spatial layout; calculates the variance, determination coefficient, covariance and unit score in each group of temperature sensors when a fault occurs, and selects the layout distribution of the temperature sensors based on the variance, determination coefficient, covariance and unit score.

[0033] Unit ratings are: σ 2 is the variance, E(tem) is the mean of the temperature sensor readings, n is the number of temperature sensors, and i is the i-th group of temperature sensors.

[0034] In a specific embodiment, the variance and determination coefficient corresponding to each temperature sensor group are calculated respectively, and the temperature sensor group corresponding to the determination coefficient closest to 1 and the smallest variance is the required sensor layout distribution mode;

[0035] Alternatively, the covariance and unit score corresponding to each temperature sensor group are calculated respectively, and the temperature sensor group corresponding to the minimum covariance and the best score is the required sensor layout distribution mode.

[0036] In a specific embodiment, the vibration prediction unit specifically includes: dividing the vibration data of the environmentally friendly inflatable cabinet collected in real time based on preset time periods, adding the preset time periods and the corresponding vibration data to the corresponding historical time series, and calculating the vibration calculation data of the historical time series at the next moment by using the exponential smoothing prediction method.

[0037] The exponential smoothing forecasting method specifically includes:

[0038] 1) Calculate the exponential smoothing characteristic value of the historical curve

[0039] h (g,1) = z·m g +(1-z)·h (g-1,1)

[0040] h (g,2) = z·h (g,1) +(1-z)·h (g-1,2) ;

[0041] h (g,3) = z·h (g,2 )+(1-z)·h (g-1,3)

[0042] The above three sets of formulas are iterative calculations, where g ranges from 2 to v, h(g,1) is the first smoothing eigenvalue; h(g,2) is the second smoothing eigenvalue; h(g,3) is the third smoothing eigenvalue; v is the number of historical data; z is the prediction coefficient; m g is the g-th historical data; g is the data sequence number;

[0043] 2) Calculate the coefficients of the curve fitting function:

[0044] a=3·h (v,1) -3·h (v,2) +h (v,3)

[0045]

[0046]

[0047] Among them, a is the constant term coefficient of the fitting function; b is the first-order term coefficient of the fitting function; c is the second-order term coefficient of the fitting function;

[0048] 3) Calculate the predicted value for the next T periods

[0049] Q(t)=a+b·t+c·t 2 ;

[0050] Where Q(t) is the predicted value; t is the predicted period; T is the maximum number of predicted periods.

[0051] Asynchronous spatial layout includes a layout method of arranging temperature sensors at different coordinate positions of the overall monitoring area of ​​the equipment and a layout method of arranging sensors at different positions of each unit monitoring area of ​​the equipment; regional center layout includes a layout method of arranging temperature sensors in the central area of ​​each unit monitoring area of ​​the equipment and a layout method of merging different unit monitoring areas into a whole and evenly arranging temperature sensors in this overall area; uniform spatial layout includes a layout method of evenly arranging a number of temperature sensors in each unit monitoring area.

[0052] Since different sensor layouts will have different results, the variance, determination coefficient, covariance and unit score can be used to select the best or most practical distribution. Among them, if you pay more attention to the prediction accuracy of the method, you can use the variance and determination coefficient corresponding to each temperature sensor group to determine it. Specifically, calculate the variance and determination coefficient corresponding to each sensor group respectively, and take the temperature sensor group with the determination coefficient closest to 1 and the smallest variance as the required sensor layout distribution method. If you pay more attention to the overall prediction effect after combining multiple temperature sensors, you can determine it according to the covariance and unit score corresponding to each temperature sensor group. Specifically, calculate the covariance and unit score corresponding to each temperature sensor group respectively, and take the temperature sensor group with the best score when the covariance is relatively small as the required sensor layout distribution method.

[0053] In a specific embodiment, the temperature prediction unit specifically includes:

[0054] The matrix construction unit obtains the device temperature data of several temperature sensors in multiple time windows according to the layout distribution of the temperature sensors, and obtains the device temperature sequence of several temperature sensors; synchronously collects the ambient temperature of the corresponding temperature sensor position in multiple time windows to obtain the ambient temperature sequence; constructs the device temperature matrix according to the device temperature sequence of several temperature sensors, and performs device temperature prediction in combination with the ambient temperature sequence to obtain the predicted device temperature matrix;

[0055] Model training module, building a device temperature prediction model, and training the device temperature prediction model based on the predicted device temperature matrix;

[0056] The temperature prediction module obtains the temperature prediction data at the next moment according to the temperature data to be predicted and the corresponding temperature sensor position.

[0057] In a specific embodiment, the device temperature matrix and the ambient temperature sequence are input into the device temperature prediction model to obtain the predicted device temperature matrix, as shown in the following formula:

[0058]

[0059] Among them, A is the predicted equipment temperature matrix, q jw is the predicted device temperature of the jth temperature sensor in the wth time window.

[0060] The loss function of the equipment temperature prediction model is:

[0061] Where LOSS is the loss, M is the number of data in the sample device temperature matrix record, sample environment temperature sequence record and sample prediction device temperature matrix record, The element y in the predicted device temperature matrix output by the device temperature prediction model during the training of the dth group of training data is jw and the corresponding element x in the sample prediction device temperature matrix jw The closer the predicted temperature output is to the target temperature output, the smaller the absolute value of the difference is, and the smaller the LOSS is.

[0062] The loss function value designed between the prediction matrix and the sample target matrix is ​​calculated based on the constructed loss function, and the gradient of the loss relative to the model parameters is calculated using the back propagation algorithm. Based on the gradient information, the Adam optimization algorithm is used to iteratively update the model parameters, and the model training is repeated for multiple rounds. After each round of training, it is determined whether the loss is lower than the preset loss threshold. When the loss converges to less than the threshold, the training ends and the model parameters are saved. Otherwise, a new round of iterations is continued. The training goal is to minimize the loss function so that the predicted output is as close to the sample target as possible, thereby obtaining a reliable module temperature prediction model.

[0063] In a specific embodiment, the coordinate calculation unit specifically includes: selecting at least two temperature sensors whose temperature prediction data at the next moment exceeds a preset temperature value, converting the collected device temperature data into an azimuth fusion estimate using the far-field positioning principle, locating the heat source within a quadrilateral area according to the azimuth fusion estimate result, and using analytical geometry methods to solve the coordinates of each vertex to obtain the coordinates of the heat source.

[0064] In a specific embodiment, the far-field positioning principle is adopted, and the temperature sensor S and the temperature sensor D respectively convert the collected temperature signals into azimuth fusion estimation and The variances are and Where l is a discrete time marker;

[0065] Determine the coordinates of the vertex boundaries of the device positioning area, fuse the azimuth estimation results of the temperature sensor S and the temperature sensor D, locate the heat source in a quadrilateral area, and use the analytical geometry method to solve the coordinates of each vertex (x r ,y r ), where r = 1, 2, 3, 4;

[0066] Assume the coordinates of the heat source are (x s ,y s ), the effective estimation error radius is R; according to the boundary vertex coordinates (x r ,y r ), establish the dynamic optimization objective function as minR 2 , the constraints are: (x s -x r ) 2 +(y s -y r ) 2 ≤R 2 , where min represents the minimization function;

[0067] In a specific embodiment, the CVX optimization tool is used to directly solve the heat source coordinates. The process of solving the heat source coordinates and the error radius can be described as the following dynamic optimization problem:

[0068]

[0069] Use the CVX toolkit to solve the optimization problem. The optimal solution of the i-th optimization problem is The error radius is:

[0070]

[0071] Therefore, the global optimal error radius is:

[0072]

[0073] Among them, u = 1, 2, 3, 4, so the corresponding heat source coordinates are estimated to be:

[0074]

[0075] In a specific embodiment, the model training module specifically includes: performing matrix transformation according to the temperature monitoring data log of the device to obtain sample device temperature matrix records, sample environment temperature sequence records and sample prediction device temperature matrix records; using sample device temperature matrix records, sample environment temperature sequence records and sample prediction device temperature matrix records to train the device temperature prediction model.

[0076] In a specific embodiment, the comprehensive prediction module calculates the similarity with the historical data based on the temperature prediction data, the heat source coordinates and the vibration calculation data by the Euclidean distance method. When the similarity is greater than a preset similarity threshold, the fault is judged to be a corresponding historical fault.

[0077] When the Euclidean distance method is used in the present invention, the parameters involved in the calculation are the temperature prediction data, the vibration calculation data, and the horizontal and vertical coordinate values ​​of the heat source coordinates.

[0078] In a specific embodiment, it also includes an alarm module, which internally stores fault alarm signals corresponding to historical fault responses in the comprehensive prediction module, and performs signal alarms corresponding to historical faults based on fault information transmitted to the alarm module by the main control module from the comprehensive prediction module.

[0079] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0080] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An environmentally friendly inflatable cabinet operation monitoring system, characterized in that: include: A data acquisition module, a data processing module, a main control module, a comprehensive prediction module, and a database. The data acquisition module collects vibration data and temperature data of the environmental protection inflatable cabinet in real time, and sends the data to the data processing module through the main control module. The data processing module predicts the vibration data and temperature data at the time of failure to obtain corresponding vibration calculation data and temperature calculation data, and sends the vibration calculation data and temperature calculation data to the comprehensive prediction module through the main control module. The database stores historical vibration calculation data and historical temperature calculation data. The comprehensive prediction module retrieves historical data in the database and compares the similarity with the vibration calculation data and temperature calculation data. If the similarity is greater than a preset similarity threshold, the failure is determined to be a corresponding historical failure.

2. The environmental protection inflatable cabinet operation monitoring system according to claim 1 is characterized in that: The data acquisition module is pre-set with sensors, the vibration sensor collects vibration data of the environmental protection inflatable cabinet, and a plurality of temperature sensors are set to collect temperature data of various locations of the environmental protection inflatable cabinet.

3. The environmental protection inflatable cabinet operation monitoring system according to claim 2 is characterized in that: The data processing module includes: a vibration prediction unit and a temperature prediction module, wherein the vibration prediction unit predicts and obtains vibration calculation data at the next moment based on vibration data; the temperature prediction module includes a temperature prediction unit and a coordinate calculation unit, wherein the temperature prediction unit obtains temperature prediction data at the next moment based on temperature data corresponding to the temperature sensor position; the coordinate calculation unit calculates and obtains the coordinates of the heat source according to the position of each temperature sensor; the temperature calculation data includes the coordinates of the heat source and the temperature prediction data.

4. The environmental protection inflatable cabinet operation monitoring system according to claim 2 is characterized in that: It also includes a temperature sensor layout module, which arranges temperature sensors for real-time acquisition of regional temperature changes in different areas of the environmental protection inflatable cabinet based on asynchronous spatial layout, regional center layout, and uniform spatial layout, and groups the temperature sensors based on asynchronous spatial layout, regional center layout, and uniform spatial layout; calculates the variance, determination coefficient, covariance, and unit score in each group of temperature sensors when a fault occurs, and selects the layout distribution of the temperature sensors according to the variance, determination coefficient, covariance, and unit score.

5. The environmental protection inflatable cabinet operation monitoring system according to claim 3 is characterized in that: The vibration prediction unit specifically includes: dividing the vibration data of the environmental protection inflatable cabinet collected in real time based on preset time periods, adding the preset time periods and the corresponding vibration data to the corresponding historical time series, and calculating the vibration calculation data of the historical time series at the next moment by using the exponential smoothing prediction method.

6. The environmental protection inflatable cabinet operation monitoring system according to claim 3 is characterized in that: The temperature prediction unit specifically includes: The matrix construction unit obtains the device temperature data of the temperature sensors in multiple time windows according to the layout distribution of the temperature sensors, and obtains the device temperature sequence of the temperature sensors; synchronously collects the ambient temperature of the corresponding temperature sensor positions in multiple time windows to obtain the ambient temperature sequence; constructs a device temperature matrix according to the device temperature sequences of the temperature sensors, and performs device temperature prediction in combination with the ambient temperature sequence to obtain a predicted device temperature matrix; A model training module is used to construct a device temperature prediction model and train the device temperature prediction model based on the predicted device temperature matrix; The temperature prediction module obtains the temperature prediction data at the next moment according to the temperature data to be predicted and the corresponding temperature sensor position.

7. The environmental protection inflatable cabinet operation monitoring system according to claim 6 is characterized in that: The coordinate calculation unit specifically includes: selecting at least two temperature sensors whose temperature prediction data at the next moment exceeds a preset temperature value, using the far-field positioning principle to convert the collected device temperature data into an azimuth fusion estimate, locating the heat source within a quadrilateral area according to the azimuth fusion estimate result, and using an analytical geometry method to solve the coordinates of each vertex to obtain the coordinates of the heat source.

8. The environmental protection inflatable cabinet operation monitoring system according to claim 6 is characterized in that: The model training module specifically includes: performing matrix transformation according to the temperature monitoring data log of the device to obtain sample device temperature matrix records, sample environment temperature sequence records and sample prediction device temperature matrix records; using the sample device temperature matrix records, sample environment temperature sequence records and sample prediction device temperature matrix records to train the device temperature prediction model.

9. The environmental protection inflatable cabinet operation monitoring system according to claim 3 is characterized in that: The comprehensive prediction module calculates the similarity with the historical data based on the temperature prediction data, the heat source coordinates and the vibration calculation data by the Euclidean distance method. When the similarity is greater than the preset similarity threshold, the fault is determined to be a corresponding historical fault.

Images