Capacitor temperature online supervision system based on SAM monitoring

Abstract

The invention discloses a capacitor temperature on-line supervision system based on SAM monitoring, which comprises a capacitor temperature on-line supervision module, the capacitor temperature on-line supervision module is connected with a monitoring point, system software, a cloud platform and a data center, the cloud platform is connected with the data center, the data center is connected with an expert system, and the expert system is connected with the monitoring point. The cloud platform is connected with PC terminal software and a mobile terminal APP, the monitoring points are arranged in multiple groups, and each group of monitoring points comprises a temperature sensor, two groups of temperature acquisition antennas and two groups of radio frequency lines. According to the capacitor temperature on-line monitoring system based on SAM monitoring, the installation positions and number of the temperature sensors are determined, the temperature sensors are installed in a limited space, real-time monitoring of the temperature of the capacitors on a rail locomotive is achieved, real-time early warning of an abnormal state is achieved, and real-time monitoring of the temperature of the capacitors on the rail locomotive is achieved through the capacitor real-time monitoring system. The rail traffic operation and maintenance management efficiency and effectiveness are improved; and the operation and maintenance quality is improved while the operation cost is saved.

Description

Technical Field

[0001] The invention relates to the field of online temperature supervision of a three-phase AC filter capacitor of a rail transit locomotive auxiliary inverter, and in particular to an online temperature supervision system of a capacitor based on SAM monitoring. Background Art

[0002] The capacitor temperature online monitoring system is a supporting device for online monitoring of the temperature of the three-phase AC filter capacitor of the auxiliary inverter of the rail transit locomotive. At present, the field of real-time monitoring of the capacitor temperature during the operation of the rail locomotive is still in a lacking stage. The subway is the main artery of urban transportation, carrying a large number of people in the city every day. The capacitor is an important part of the subway locomotive. With the continuous development of science and technology, people have higher and higher requirements for the manufacturing process of the capacitor temperature online monitoring system.

[0003] The existing capacitor temperature online monitoring system has certain drawbacks when in use. The capacitor has a large workload and is in a confined space, making it difficult to dissipate heat. Therefore, the capacitor is prone to overheating, which can cause fire in severe cases and lead to major accidents. Once a capacitor in a running locomotive catches fire, the consequences will be disastrous. Therefore, the temperature of the capacitor on the rail locomotive is monitored and managed in real time. This is of great significance to preventing safety accidents and improving the operation and maintenance capabilities of rail locomotives. To this end, we propose a capacitor temperature online monitoring system based on SAM monitoring. Summary of the invention

[0004] Technical problem to be solved: In view of the shortcomings of the prior art, the present invention provides an online capacitor temperature monitoring system based on SAM monitoring, which determines the installation position and number of temperature sensors and implements installation in a limited space, realizes real-time monitoring of the capacitor temperature on the rail locomotive, and realizes real-time early warning of abnormal conditions. Through the real-time monitoring system of capacitors, the efficiency and effectiveness of rail transit operation and maintenance management are improved; while saving operating costs, the quality of operation and maintenance is improved, which can effectively solve the problems in the background technology.

[0005] Technical solution: To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a capacitor temperature online supervision system based on SAM monitoring, including a capacitor temperature online supervision module, the capacitor temperature online supervision module connects the monitoring point, system software, cloud platform and data center, the cloud platform is connected to the data center, the data center is connected to the expert system, the cloud platform is connected to the PC terminal software and the mobile terminal APP, the monitoring points are arranged in multiple groups, and each group of monitoring points includes a temperature sensor, two groups of temperature acquisition antennas, two groups of radio frequency lines, a group of monitoring hosts, a group of IoT smart gateways, a group of 4G antennas and a 24V to 5V power adapter.

[0006] As a preferred technical solution of the present application, the PC terminal software and the mobile terminal APP are connected to the cloud service, the cloud service connects the IoT smart gateway, the data center and the temperature collector, the temperature collector is connected to the first collector antenna and the second collector antenna, and the temperature collector has a built-in large-capacity data storage card that can copy local data, and the first collector antenna and the second collector antenna are both connected to the capacitor pole temperature sensor, the capacitor surface temperature sensor and the box environment temperature sensor.

[0007] As a preferred technical solution of the present application, the cloud service includes a data acquisition module, a built-in storage unit, a data terminal DTU, a cloud service module and a user remote monitoring module. The data acquisition module is connected to the built-in storage unit and the data terminal DTU, the data terminal DTU is connected to the cloud service module, and the cloud service module is connected to the user remote monitoring module.

[0008] As a preferred technical solution of the present application, the capacitor temperature online monitoring module is bidirectionally connected to the monitoring point, system software, cloud platform and data center, the cloud platform is bidirectionally connected to the data center, the data center is bidirectionally connected to the expert system, and the cloud platform is bidirectionally connected to the PC terminal software and the mobile terminal APP.

[0009] As a preferred technical solution of the present application, the output ends of the capacitor pole temperature sensor, the capacitor surface temperature sensor and the box ambient temperature sensor are electrically connected to the input ends of the first collector antenna and the second collector antenna, the output ends of the first collector antenna and the second collector antenna are electrically connected to the input end of the temperature collector, and the temperature collector is bidirectionally connected to the IoT smart gateway.

[0010] As a preferred technical solution of the present application, an RS485 module is arranged between the data acquisition module and the data terminal DTU, and the data acquisition module and the data terminal DTU are connected via the RS485 module, and a 5G module is arranged between the data terminal DTU and the cloud service module, and the data terminal DTU and the cloud service module are connected via the 5G module.

[0011] As a preferred technical solution of the present application, the capacitor pole temperature sensor, capacitor surface temperature sensor and box ambient temperature sensor all adopt SAM passive wireless temperature sensors to obtain the temperature data of the monitoring points in real time and accurately. The collector antenna and radio frequency line upload the temperature data collected by the temperature sensor to the temperature collector.

[0012] As a preferred technical solution of the present application, the temperature collector performs data preprocessing and data storage, wherein the memory adopts a power-off preservation design, which can ensure that the monitoring data is not lost when the collection host loses power unexpectedly. At the same time, the temperature collector has its own clock system, and the uploaded monitoring results include temperature information, time information and monitoring point information.

[0013] As a preferred technical solution of the present application, the IoT smart gateway uploads the data collected by the temperature collector to the cloud platform in real time, and the cloud platform saves all temperature data, analyzes and displays the data, and issues warnings for abnormal data.

[0014] As a preferred technical solution of the present application, the data center includes client PC software, which can view monitoring results, abnormal alarms, alarm processing progress, alarm point processing status and process records and operation and maintenance management in real time.

[0015] Beneficial effects: Compared with the prior art, the present invention provides an online monitoring system for capacitor temperature based on SAM monitoring, which has the following beneficial effects: This online monitoring system for capacitor temperature based on SAM monitoring determines the installation position and number of temperature sensors and implements installation in a limited space, realizes real-time monitoring of capacitor temperature on rail locomotives, realizes real-time warning of abnormal conditions, and improves rail transit operation and maintenance management efficiency and effectiveness through the capacitor real-time monitoring system; while saving operating costs, it improves the quality of operation and maintenance. The system can alarm in real time, add, modify and delete basic user information, and can define, add, delete and modify various parameters and monitoring points by itself, and can dynamically configure monitoring indicators. For the specified terminal, various parameter default values ​​and alarm upper and lower limits can be set. The communication-related parameter inspection cycle, re-collection times, database access parameter information, monitoring frequency, data refresh time, etc. can be defined by the user. The user can define the terminal interface and communication protocol: the terminal data collection cycle and storage cycle can be set; the system can autonomously learn according to the collected data, calibrate the standard comparison value, and the alarm threshold to achieve safer and more effective protection; the system can automatically generate operation and maintenance work orders, remotely dispatch operation and maintenance tasks, and automatically generate operation and maintenance record sheets; improve the safe operation of rail transit; the system reduces operation and maintenance costs; improves operation and maintenance efficiency, the entire capacitor temperature online supervision system has a simple structure, is easy to operate, and has better results than traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The figure is an overall framework diagram of an online capacitor temperature monitoring system based on SAM monitoring according to the present invention.

[0017] Figure 2 The present invention is a schematic diagram of an online temperature monitoring system for a self-healing filter capacitor of a rail transit train in an online temperature monitoring system for capacitors based on SAM monitoring.

[0018] Figure 3 The present invention is a schematic diagram of data transmission and processing in a capacitor temperature online monitoring system based on SAM monitoring. DETAILED DESCRIPTION

[0019] The technical scheme of the present invention will be clearly and completely described below in conjunction with the accompanying drawings and specific embodiments, but it will be understood by those skilled in the art that the following described embodiments are part of embodiments of the present invention, rather than all embodiments, and are only used to illustrate the present invention, and should not be considered as limiting the scope of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of the present invention. If specific conditions are not specified in the embodiments, they are carried out according to normal conditions or conditions recommended by the manufacturer. If the manufacturer is not specified in the reagents or instruments used, they are all conventional products that can be purchased commercially.

[0020] like Figure 1-3 As shown, a capacitor temperature online supervision system based on SAM monitoring includes a capacitor temperature online supervision module, the capacitor temperature online supervision module connects the monitoring point, the system software, the cloud platform and the data center, the cloud platform and the data center are connected, the data center is connected to the expert system, the cloud platform is connected to the PC terminal software and the mobile terminal APP, there are multiple groups of monitoring points, and each group of monitoring points includes a temperature sensor, two groups of temperature acquisition antennas, two groups of radio frequency lines, a group of monitoring hosts, a group of IoT smart gateways, a group of 4G antennas and a 24V to 5V power adapter, the installation position and number of temperature sensors are determined and installed in a limited space, so as to realize real-time monitoring of the capacitor temperature on the rail locomotive, realize real-time warning of abnormal conditions, and improve the efficiency and effectiveness of rail transit operation and maintenance management through the capacitor real-time monitoring system; while saving operating costs, the quality of operation and maintenance is improved.

[0021] Furthermore, the PC terminal software and the mobile terminal APP are connected to the cloud service, the cloud service connects the IoT smart gateway, the data center and the temperature collector, the temperature collector is connected to the first collector antenna and the second collector antenna, and the temperature collector has a built-in large-capacity data storage card that can copy local data, and the first collector antenna and the second collector antenna are both connected to the capacitor pole temperature sensor, the capacitor surface temperature sensor and the box environment temperature sensor.

[0022] Furthermore, the cloud service includes a data acquisition module, a built-in storage unit, a data terminal DTU, a cloud service module and a user remote monitoring module. The data acquisition module is connected to the built-in storage unit and the data terminal DTU, the data terminal DTU is connected to the cloud service module, and the cloud service module is connected to the user remote monitoring module.

[0023] Furthermore, there are bidirectional connections between the capacitor temperature online monitoring module and the monitoring points, system software, cloud platform and data center, bidirectional connections between the cloud platform and the data center, bidirectional connections between the data center and the expert system, and bidirectional connections between the cloud platform and PC terminal software and mobile terminal APP.

[0024] Furthermore, the output ends of the capacitor pole temperature sensor, the capacitor surface temperature sensor and the box ambient temperature sensor are electrically connected to the input ends of the first collector antenna and the second collector antenna, the output ends of the first collector antenna and the second collector antenna are electrically connected to the input end of the temperature collector, and the temperature collector is bidirectionally connected to the IoT smart gateway.

[0025] Furthermore, an RS485 module is set between the data acquisition module and the data terminal DTU, and the data acquisition module and the data terminal DTU are connected through the RS485 module. A 5G module is set between the data terminal DTU and the cloud service module, and the data terminal DTU and the cloud service module are connected through the 5G module.

[0026] Furthermore, the capacitor pole temperature sensor, capacitor surface temperature sensor and box ambient temperature sensor all use SAM passive wireless temperature sensors to accurately obtain the temperature data of the monitoring points in real time. The collector antenna and RF line upload the temperature data collected by the temperature sensor to the temperature collector.

[0027] Furthermore, the temperature collector performs data preprocessing and data storage, and the memory adopts a power-off preservation design, which can ensure that the monitoring data is not lost when the collection host loses power unexpectedly. At the same time, the temperature collector has its own clock system, and the uploaded monitoring results include temperature information, time information and monitoring point information.

[0028] Furthermore, the IoT smart gateway uploads the data collected by the temperature collector to the cloud platform in real time, and the cloud platform saves all temperature data, analyzes and displays the data, and issues warnings for abnormal data.

[0029] Furthermore, the data center includes client PC software that can view monitoring results, abnormal alarms, alarm processing progress, alarm point processing status and process records and operation and maintenance management in real time.

[0030] like Figure 1 As shown in the figure, the online temperature monitoring system for the self-healing filter capacitor of the rail transit train includes the online temperature monitoring system for the capacitor, the cloud platform, the terminal software and the data center. The online temperature monitoring system for the capacitor includes the software system and several monitoring points set in the train. The terminal software includes the PC terminal software and the mobile terminal APP.

[0031] Each monitoring point in the rail transit train self-healing filter capacitor temperature online management system includes: several temperature sensors, 2 temperature collection antennas, 2 radio frequency lines, 1 monitoring host, 1 IoT smart gateway, 1 4G antenna, and 24V to 5V power adapter.

[0032] The whole system consists of:

[0033] 1. Temperature sensor: Use SAM passive wireless temperature sensor to obtain real-time and accurate temperature data of monitoring points.

[0034] 2. Collector antenna, RF line: upload the temperature data collected by the temperature sensor to the temperature collector.

[0035] 3. Temperature collector: data preprocessing and data storage (1min / time, can be stored locally for 1 month), the memory adopts power-off saving design, when the acquisition host is accidentally powered off, it can also ensure that the monitoring data is not lost; at the same time, the temperature collector has its own clock system, and the uploaded monitoring results include temperature information, time information, and monitoring point information.

[0036] 4. Intelligent gateway: upload the data collected by the temperature collector to the cloud platform in real time.

[0037] 5. Cloud platform: save all temperature data, analyze and display the data, and issue warnings for abnormal data.

[0038] 6. Data Center: Contains client PC software, which can view monitoring results, abnormal alarms, alarm processing progress, alarm point processing status and process records in real time. And operation and maintenance management;

[0039] It includes an expert system that collects and analyzes monitoring data and records abnormal processing data. It optimizes normal and abnormal data judgment and warning thresholds through self-learning, and provides more accurate accident prediction and operation and maintenance suggestions.

[0040] Includes computer host, monitor and other supporting hardware equipment (can share users' existing ones).

[0041] 7. Mobile terminal APP: Mobile terminal (mobile phone, tablet), can view authorized monitoring data and accept data center operation and maintenance management (work order issuance, personnel management...), upload operation and maintenance implementation information to the cloud platform.

[0042] Device ID:

[0043] Device ID: Each sensor has a unique ID code. The specific coding rules can be customized by the customer but must follow the following principles:

[0044] Each capacitor under test has a unique ID

[0045] 1. The circuit loops containing the capacitors to be tested are classified by function. Circuit loops with the same functions are grouped into one category, which needs to be reflected in the coding;

[0046] 2. The capacitors under test are classified according to their functions in the circuit loop. Capacitors with the same function are classified into one large category, which needs to be reflected in the coding.

[0047] 3. The capacitors with the same function in parallel or series in the same circuit loop need to be coded;

[0048] The same capacitor under test needs to be reflected when different position sensor codes are used;

[0049] The capacitor pole temperature sensor, capacitor surface temperature sensor, and box ambient temperature sensor must be reflected in the coding;

[0050] The sensor ID code must contain the corresponding ID information of the capacitor being measured. The sensor ID code must be as simple and easy to understand as possible, and can be easily matched to the position of the capacitor being measured during use.

[0051] Data transmission and processing

[0052] Data transmission: All temperature data collected by the sensor is first saved locally in the temperature collector, and then uploaded to the cloud platform through the 4G or 5G gateway. Users can view and download monitoring results in real time through the client software;

[0053] The acquisition host collects the temperature data of the temperature sensor in the capacitor box at a frequency of 1min / time (settable) and saves it. The maximum storage capacity is 1 month.

[0054] The client software will automatically query all temperature data time information at intervals (about 5 to 10 minutes / time during the rail transit operation period, and 1 to 2 hours / time during the rail transit fee operation period, which can be customized by the customer according to the actual situation). If data loss is found, it will automatically send a data reissue instruction to the corresponding temperature collector, and the temperature collector will re-upload the missing time period data to the cloud platform to ensure data integrity. This is to solve the problem that there may be no 4G / 5G signal in some sections during the operation of the train, resulting in failure to upload temperature data during this period.

[0055] Early warning strategy: 1). Over-temperature warning.

[0056] When the temperature exceeds a certain limit, an over-temperature warning is issued. Since the actual working temperature of the capacitor under test is missing in the initial stage, the upper temperature limit is set based on the average normal working temperature of the same type of capacitor under test, plus a suitable margin.

[0057] set up:

[0058] T: Alarm temperature

[0059] Tw: Measured capacitor pole temperature

[0060] Th: Measured temperature inside the equipment cabinet

[0061] Tb: Measured capacitor surface temperature

[0062] Te: Measured ambient temperature

[0063] Tc: Capacitor temperature after compensation

[0064] In order to make the obtained temperature data more accurately reflect the actual internal temperature of the capacitor, appropriate temperature compensation is performed considering the impact of environmental factors such as the heat of surrounding equipment on temperature measurement.

[0065] When Tc≥T, alarm

[0066] T=(T1c+T2c+.....Tnc) / n+TO

[0067] T1C...Tnc: The average value of capacitors with the same function at different positions in the same functional circuit loop and the same measured position within a unit time (30 to 60 minutes, defined according to actual working conditions) is obtained by the expert system through data analysis and is regularly updated and calibrated.

[0068] example:

[0069] T1c=T1c1+T1c2....+T1cn / n

[0070] T0: The temperature margin is calculated by dividing the maximum operating temperature Tw allowed by the capacitor design by a constant, where the constant is customized based on the actual model and function of the capacitor being tested.

[0071] 2). Temperature rise too fast warning

[0072] When the temperature rise rate of a capacitor exceeds a certain range of the average temperature rise rate, an excessive temperature rise warning is issued;

[0073] set up:

[0074] A: Alarm value

[0075] Tv: collected temperature difference data

[0076] When Tv≥A, alarm

[0077] Tv=(Tc2-Tc1+Tc3-Tc2+Tcn-Tcn-1 / N-1) where Tc1~Tcn are the measured temperatures of the capacitor collected in sequence within a unit time. N is the number of times the temperature is collected within a unit time.

[0078] The initial value of A is defined according to the actual working conditions, and the expert system is corrected according to the accumulation of temperature big data during the actual operation process in the later stage; the unit time is defined according to the actual working conditions, and the expert system is corrected according to the accumulation of temperature big data during the actual operation process in the later stage.

[0079] 3). Environmental out-of-tolerance warning (the temperature difference between the ambient temperature and the capacitor electrode temperature exceeds the reasonable range)

[0080] set up:

[0081] B: Alarm value

[0082] When the absolute value of Tw-Te ≥ B, alarm

[0083] The initial value of B value is defined according to the actual working conditions, and the expert system is corrected according to the temperature big data accumulated during the actual operation.

[0084] 4). Warning of excessive temperature difference in the same cabinet (warning when the temperature difference between the capacitor poles in the same capacitor box exceeds the reasonable range)

[0085] C: Alarm value

[0086] When the absolute value of Tw(1)-Tw(2)≥C, an alarm is triggered

[0087] Operation and maintenance data: 1. General maintenance data records (including time, location, personnel, maintenance items, and maintenance process)

[0088] 2. Abnormal operation and maintenance progress, time data record

[0089] 3. Records of abnormal operation and maintenance accident judgment and maintenance person in charge

[0090] 4. Record of abnormal operation and maintenance processing (processing method)

[0091] Expert system: All data are uploaded to the expert system for cross-comparison processing, automatically correcting the corresponding temperature warning data in the warning strategy, and making accident predictions based on the accumulated analysis of maintenance data.

[0092] Data analysis

[0093] 1. Temperature analysis of the same capacitor;

[0094] 2. Temperature comparison and analysis of capacitors with the same function in the same circuit function loop;

[0095] 3. Comparative analysis of the temperature of capacitors with the same function in different circuit function loops;

[0096] 4. Comparative analysis of different capacitor temperatures in different circuit function loops;

[0097] 5. Analysis of the impact of environment on capacitor temperature;

[0098] 6. Comparative analysis of temperature of capacitors of the same specifications and models from different manufacturers.

[0099] 7. Comparative analysis of capacitors at different service life and temperature

[0100] Implementation steps

[0101] 1. Data Collection

[0102] Record the capacitor contact temperature, capacitor surface temperature, cabinet temperature and ambient temperature in different environments and motion states.

[0103] 2. Data comparison and analysis

[0104] Compare and analyze the collected temperature data to obtain the relationship between different temperatures, change trends and abnormal conditions.

[0105] Descriptive statistical analysis

[0106] Perform statistical analysis on each temperature variable (such as contact temperature Tw, equipment cabinet temperature Th, capacitor surface temperature Tb, ambient temperature Te), and calculate the mean, standard deviation, maximum, minimum, median, etc. of each temperature data set. Understand the distribution of each temperature variable.

[0107] Mean μ:

[0108]

[0109] Where T i is the ith temperature value and n is the total number of data points.

[0110] Variance σ 2 :

[0111]

[0112] Standard deviation σ:

[0113]

[0114] Minimum value T min , maximum value T max :

[0115] T min =min(T1, T2, ..., T n ), T max =max(T1, T2, ..., T n )

[0116] MedianT median : The middle value after sorting.

[0117] (2) Comparison of temperature change trends over time

[0118] Use a line graph to compare the temperature changes over time and observe the trend of different temperatures over time. To determine the relationship between the temperatures, such as whether the capacitor surface temperature Tb rises synchronously with the contact temperature Tw or the temperature inside the equipment cabinet Th. There is no complicated formula involved here, just associate the temperature Ti with the time ti.

[0119] (3) To analyze the temperature change rate, the temperature rise rate can be used:

[0120]

[0121] Among them, T(t i+1 ) is the temperature value at the next time point, T(t i ) is the temperature value at the current time point, t i+1 -t i is the time interval. (4). Correlation analysis between temperatures

[0122] Through the correlation matrix, we can find out which temperature variables are closely related.

[0123] By calculating the correlation coefficients between different temperature variables, the linear relationship between them is obtained.

[0124] For example, if the correlation between the contact temperature Tw and the capacitor surface temperature Tb is high, then Tb may be greatly affected by Tw.

[0125] The linear correlation data between the two temperature variables is obtained by calculating the Pearson correlation coefficient. The formula is as follows:

[0126]

[0127] Where X and Y are two temperature variables (such as T w and T b ), μ X and μ Y are their means, n is the number of data points. The result ranges between -1 and 1.

[0128] 1 means a perfect positive correlation, -1 means a perfect negative correlation, and 0 means no correlation.

[0129] (5) Temperature difference analysis

[0130] The temperature difference is calculated by the difference between two sets of temperature data:

[0131] ΔT(t)=T w (t)-T b (t)

[0132] Among them, T w (t) is the contact temperature, T b (t) is the capacitor surface temperature, and t is the time point.

[0133] The calculated temperature difference database is then subjected to linear regression analysis to obtain the temperature relationship equation

[0134] (6) Outlier detection and analysis

[0135] In the collected temperature data, there may be outliers or points with sudden changes. Boxplot is used to detect outliers.

[0136] Quartiles are used to define the normal range of data. They are defined as follows:

[0137] The first quartile Q1 is the first 25% of the data points in the sorted data;

[0138] The third quartile Q3 is the first 75% of the data points in the sorted data;

[0139] Interquartile Range (IQR):

[0140] IQR=Q3-Q1

[0141] Outliers: If a data point T i Meet T i <Q1-1.5×IQR or T i >Q3+1.5×IQR, it is considered an outlier.

[0142] After recording the abnormal value, compare the working conditions of the capacitor at the abnormal value node and analyze the cause of the abnormal value of the capacitor.

[0143] (7). Time series analysis (moving average)

[0144] (8) Use time series analysis to capture trends and cycles in temperature changes.

[0145] Moving average is used to smooth time series data. The formula is:

[0146]

[0147] Where k is the sliding window size, T(t i ) is the time point t i The temperature value.

[0148] If the temperature change of the equipment has a nonlinear cumulative effect as the working time continues, an exponential model is introduced to assume that the temperature growth accelerates with the working time. The exponential model is used:

[0149]

[0150] where λ controls the rate of temperature increase.

[0151] Through timing analysis, we can understand the working rhythm of capacitors in rail transit circuits, and use the service expert system to predict the normal working temperature of capacitors.

[0152] (8) Regression analysis based on machine learning

[0153] Regression analysis is used to predict the relationship between temperature variables. For example, using contact temperature Tw, equipment cabinet temperature Th, ambient temperature Te, etc. as independent variables, predict capacitor surface temperature Tb. The formula is:

[0154] T b =β0+β1T w +β2T h +β3T e +∈

[0155] in:

[0156] ·T b is the target variable (capacitor surface temperature);

[0157] ·T w , T h , T e They are the independent variables (contact temperature, temperature inside the equipment cabinet, and ambient temperature);

[0158] β0 is the intercept, β1, β2, β3 are regression coefficients, and ∈ is the error term.

[0159] The regression coefficient is estimated by the least squares method, and the formula is as follows:

[0160] β=(X T X) -1 X T y

[0161] in:

[0162] X is the matrix containing the independent variables;

[0163] y is the target variable vector;

[0164] β is the regression coefficient vector.

[0165] (9) Use the multivariate linear regression model formula to estimate and analyze the actual operating temperature Tc of the sensor for alarm value (data analysis when the capacitor is in working state)

[0166] Set the model to

[0167] Tc =β0+β1T w +β2T h +β3T b +β4T e +∈

[0168] in:

[0169] ·T c is the operating temperature of the capacitor (target variable)

[0170] ·T w is the sensor contact temperature

[0171] ·T h is the temperature inside the equipment cabinet

[0172] ·T b is the capacitor surface temperature

[0173] ·T e is the ambient temperature

[0174] β0, β1, β2, β3, β4 are the parameters to be estimated for the model

[0175] ∈ is the error term

[0176] Data preprocessing (the system automatically organizes data based on sensor ID and the categories that need data analysis)

[0177] Collect and organize T w , T h , T b , T e and T c The above model is fitted with these historical data to estimate the parameters β0, β1, β2, β3, and β4.

[0178] To facilitate calculation, we use matrix representation

[0179] Y=Xβ+∈

[0180] in:

[0181] ·Y=[T c1 , T c2 , ..., T cn ] T It is T c Vector

[0182] · is the independent variable matrix

[0183] ·β=[β0, β1, β2, β3, β4] T is the vector of parameters to be estimated

[0184] Use the least squares method to estimate the parameters

[0185]

[0186] calculate

[0187] Step 1: Form a data set to collect temperature data, including T w , T h , T b , T e and the target variable T c .

[0188] Step 2: Calculate X T X and X T Y

[0189] Calculate X T X, which is the transpose of the X matrix multiplied by X.

[0190] Calculate X T Y, which is the transpose of the X matrix multiplied by the Y vector.

[0191] Step 3: Calculate β Solve the parameter β using the following formula:

[0192]

[0193] Step 4: Predict capacitor operating temperature using estimated parameters The new input data T w , T h , T b , T e Make predictions:

[0194]

[0195] In summary:

[0196] Through descriptive statistics: Understand the basic characteristics of temperature data.

[0197] Through trend comparison analysis: showing the change of temperature over time, helping to observe the synchronization between different temperature variables.

[0198] Through correlation analysis: Understand the linear relationship between different temperature variables.

[0199] Through difference analysis: understand the differences between temperatures and find the characteristics of temperature rise and heat dissipation.

[0200] Through outlier detection: find abnormal data points in the temperature collection process.

[0201] Through regression analysis: a relationship model between different temperatures can be established to make predictions or explanations.

[0202] 3. Data application:

[0203] Automatically correct the corresponding temperature warning data in the warning strategy, and make accident predictions based on the accumulated analysis of maintenance data.

[0204] Improving rail transit operation safety

[0205] Improve operation and maintenance efficiency to achieve accurate and effective operation and maintenance

[0206] Reduce costs and increase efficiency

[0207] Hardware main features and function introduction

[0208] 1) High-precision SAW temperature sensor

[0209] SAW temperature sensor is a measurement technology based on surface acoustic wave technology (SAW, Surface Acoustic Wave). Surface acoustic wave is an elastic wave that propagates along the surface of an object. The characteristic parameters of surface acoustic wave materials (piezoelectric materials) will change regularly under different temperature conditions. By measuring specific parameters, the temperature of the material can be calculated.

[0210] In the industrial field, especially in places with complex electromagnetic environments, SAW technology has very unique advantages.

[0211] 1. True passive: SAW sensors are essentially special patterns etched on piezoelectric materials, not semiconductor materials, and do not require any form of power supply. They are highly reliable, and the life of the sensor itself can exceed 30 years;

[0212] 2. Tolerance and operation in complex environments: Piezoelectric materials have extremely high environmental tolerance, so SAW sensors can also withstand harsh working environments. They can work in harsh environments such as 750kV voltage (high voltage), 200,000A current (high current, strong magnetic field), 400℃ (high temperature), high-speed operation or rotation of objects (high speed). They can be used directly on metals and dangerous goods;

[0213] 3. High safety: Since the sensor itself does not contain any semiconductor / electronic components, it does not require power supply and has no potential safety hazards. It is particularly suitable for working under high voltage and high current conditions;

[0214] 4. Controllable reading distance: The signal reading distance is controllable and adjustable. In electrical equipment (such as capacitor cabinets), the reading distance can be 1-3 meters. Outdoors, with a high-power antenna, the reading distance can reach 10+ meters.

[0215] Determine the installation location and number of temperature sensors and install them in a limited space to achieve real-time monitoring of the capacitor temperature on the rail locomotive, realize real-time warning of abnormal conditions, and improve the efficiency and effectiveness of rail transit operation and maintenance management through the capacitor real-time monitoring system; improve the quality of operation and maintenance while saving operating costs, through real-time monitoring of capacitor temperature, uploading monitoring data, and using the expert system to collect and cross-compare the temperatures of various capacitors in the same capacitor box / same train / different trains under various conditions and climate environments, automatically improve the capacitor temperature expert library data and algorithms, so as to achieve intelligent prediction of capacitor status, thereby improving rail transit operation safety and reducing operation and maintenance pressure.

[0216] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A capacitor temperature online monitoring system based on SAM monitoring, including a capacitor temperature online monitoring module, characterized in that: The capacitor temperature online monitoring module is connected to the monitoring point, system software, cloud platform and data center, the cloud platform is connected to the data center, the data center is connected to the expert system, the cloud platform is connected to the PC terminal software and the mobile terminal APP, and the monitoring points are arranged in multiple groups, and each group of monitoring points includes a temperature sensor, two groups of temperature acquisition antennas, two groups of radio frequency lines, a group of monitoring hosts, a group of IoT smart gateways, a group of 4G antennas and a 24V to 5V power adapter.

2. According to claim 1, a capacitor temperature online monitoring system based on SAM monitoring is characterized in that: The PC terminal software and the mobile terminal APP are connected to the cloud service, the cloud service connects the IoT smart gateway, the data center and the temperature collector, the temperature collector is connected to the first collector antenna and the second collector antenna, and the temperature collector has a built-in large-capacity data storage card that can copy local data, and the first collector antenna and the second collector antenna are both connected to the capacitor pole temperature sensor, the capacitor surface temperature sensor and the box environment temperature sensor.

3. The capacitor temperature online monitoring system based on SAM monitoring according to claim 2 is characterized in that: The cloud service includes a data acquisition module, a built-in storage unit, a data terminal DTU, a cloud service module and a user remote monitoring module. The data acquisition module is connected to the built-in storage unit and the data terminal DTU, the data terminal DTU is connected to the cloud service module, and the cloud service module is connected to the user remote monitoring module.

4. The capacitor temperature online monitoring system based on SAM monitoring according to claim 1 is characterized in that: The capacitor temperature online monitoring module is bidirectionally connected to the monitoring point, system software, cloud platform and data center, the cloud platform is bidirectionally connected to the data center, the data center is bidirectionally connected to the expert system, and the cloud platform is bidirectionally connected to the PC terminal software and the mobile terminal APP.

5. The capacitor temperature online monitoring system based on SAM monitoring according to claim 2 is characterized in that: The output ends of the capacitor pole temperature sensor, the capacitor surface temperature sensor and the box ambient temperature sensor are electrically connected to the input ends of the first collector antenna and the second collector antenna, the output ends of the first collector antenna and the second collector antenna are electrically connected to the input end of the temperature collector, and the temperature collector is bidirectionally connected to the IoT smart gateway.

6. The capacitor temperature online monitoring system based on SAM monitoring according to claim 3 is characterized in that: An RS485 module is set between the data acquisition module and the data terminal DTU, and the data acquisition module and the data terminal DTU are connected through the RS485 module. A 5G module is set between the data terminal DTU and the cloud service module, and the data terminal DTU and the cloud service module are connected through the 5G module.

7. The capacitor temperature online monitoring system based on SAM monitoring according to claim 2 is characterized in that: The capacitor pole temperature sensor, capacitor surface temperature sensor and box environment temperature sensor all use SAM passive wireless temperature sensors to accurately obtain temperature data of monitoring points in real time. The collector antenna and radio frequency line upload the temperature data collected by the temperature sensor to the temperature collector.

8. The capacitor temperature online monitoring system based on SAM monitoring according to claim 2 is characterized in that: The temperature collector performs data preprocessing and data storage, wherein the memory adopts a power-off preservation design, which can ensure that the monitoring data is not lost when the acquisition host loses power unexpectedly. At the same time, the temperature collector has its own clock system, and the uploaded monitoring results include temperature information, time information and monitoring point information.

9. The capacitor temperature online monitoring system based on SAM monitoring according to claim 2 is characterized in that: The IoT smart gateway uploads the data collected by the temperature collector to the cloud platform in real time, and the cloud platform saves all temperature data, analyzes and displays the data, and issues warnings for abnormal data.

10. The capacitor temperature online monitoring system based on SAM monitoring according to claim 1 is characterized in that: The data center includes client PC software that can view monitoring results, abnormal alarms, alarm processing progress, alarm point processing status and process records and operation and maintenance management in real time.

Images