Method for over-temperature early warning of excitation system and device thereof

Abstract

The application provides an over-temperature early warning method and device of an excitation system, relates to the technical field of over-temperature alarm of a generator excitation system, and obtains real-time parameters corresponding to excitation equipment and a protection switch cabinet through sensors arranged on the excitation equipment and the protection switch cabinet in the excitation system, wherein the real-time parameters include real-time temperatures of the excitation equipment and the protection switch cabinet; infrared imaging data of the protection switch cabinet is obtained, and a target infrared temperature corresponding to the protection switch cabinet is obtained according to the infrared imaging data; the predicted temperatures of the protection switch cabinet at subsequent multiple time points are obtained based on the real-time parameters; and over-temperature alarm instructions are sent in response to at least one of the real-time temperatures, the target infrared temperature and the predicted temperatures being greater than corresponding temperature thresholds. In the application, the three-level alarm systems are redundant to each other, temperature real-time safety guarantee and over-temperature early warning functions are provided for the excitation system, excitation over-temperature faults are solved in the bud, and the safety and reliability of the excitation system are improved.

Description

Technical Field

[0001] This application relates to the field of over-temperature alarm technology for generator excitation systems, and in particular to an over-temperature early warning method and device for excitation systems. Background Technology

[0002] As a crucial component of synchronous generators, the excitation system plays a vital role in improving the safety and stability of parallel power units in a power system. Numerous safety incidents in the excitation system are caused by overheating, such as excessive carbon brush temperature leading to pressure decay of the constant pressure spring, brush box deformation, and even excessive sparking; and rectifier cabinet fires caused by overheating of the excitation rectifier circuit. A serious overheating fault in the excitation system can lead to unplanned unit shutdowns, causing significant losses to the power plant. Given the current inability to fundamentally solve the excitation overheating problem, increasing overheating inspections and over-temperature early warning systems for the excitation system is particularly important. Summary of the Invention

[0003] This application aims to at least partially address one of the technical problems in the related art.

[0004] Therefore, one objective of this application is to propose an over-temperature early warning method for an excitation system. This method involves acquiring real-time parameters of the excitation equipment and protection switchgear based on sensors installed on these devices, including their real-time temperatures; acquiring infrared imaging data of the protection switchgear and determining its target infrared temperature based on this data; obtaining predicted temperatures of the protection switchgear at multiple subsequent times based on the real-time parameters; and issuing an over-temperature alarm indication in response to at least one of the real-time temperature, target infrared temperature, and predicted temperature exceeding its corresponding temperature threshold.

[0005] This application presents a three-level over-temperature warning system for the excitation system, consisting of a real-time independent temperature alarm, a real-time infrared temperature detection alarm based on the target, and an over-temperature warning function based on real-time parameters. The three-level alarm system is redundant with each other, providing real-time temperature safety protection and over-temperature warning for the excitation system, thus resolving over-temperature faults in their infancy and greatly improving the safety and reliability of the excitation system.

[0006] The second objective of this application is to provide an over-temperature early warning device for an excitation system.

[0007] The third objective of this application is to propose an electronic device.

[0008] The fourth objective of this application is to provide a non-transitory computer-readable storage medium.

[0009] The fifth objective of this application is to provide a computer program product.

[0010] To achieve the above objectives, the first aspect of this application proposes an over-temperature early warning method for an excitation system, comprising: acquiring real-time parameters corresponding to the excitation equipment and the protection switchgear based on sensors installed on the excitation equipment and the protection switchgear in the excitation system, wherein the real-time parameters include the real-time temperature of the excitation equipment and the protection switchgear; acquiring infrared imaging data of the protection switchgear and acquiring the target infrared temperature corresponding to the protection switchgear based on the infrared imaging data; acquiring the predicted temperature of the protection switchgear at multiple subsequent times based on the real-time parameters; and issuing an over-temperature alarm indication in response to at least one of the real-time temperature, the target infrared temperature, and the predicted temperature being greater than its corresponding temperature threshold.

[0011] This application presents a three-level over-temperature warning system for the excitation system, consisting of a real-time independent temperature alarm, a real-time infrared temperature detection alarm based on the target, and an over-temperature warning function based on real-time parameters. The three-level alarm system is redundant with each other, providing real-time temperature safety protection and over-temperature warning for the excitation system, thus resolving over-temperature faults in their infancy and greatly improving the safety and reliability of the excitation system.

[0012] According to one embodiment of this application, obtaining the target infrared temperature of a protective switchgear based on infrared imaging data includes: obtaining the initial infrared temperature of the protective switchgear based on the infrared imaging data; obtaining the target distance between the infrared sensor and the protective switchgear based on a rangefinder; obtaining the compensation coefficient corresponding to the initial infrared temperature at the target distance based on the distance characteristic curve; and correcting the initial infrared temperature based on the target distance and the compensation coefficient to obtain the target infrared temperature of the protective switchgear.

[0013] According to one embodiment of this application, a method for obtaining a distance characteristic curve includes: obtaining the measured temperature of the preset constant temperature device as measured by an infrared sensor at different distances from the preset constant temperature device; obtaining the actual temperature of the preset constant temperature device in the current state; and fitting the distance value, the measured temperature, and the actual temperature based on the least squares method to obtain a distance characteristic curve.

[0014] According to one embodiment of this application, the excitation equipment includes an excitation chamber and a generator shaft, and the protection switch cabinet includes a rectifier cabinet, an excitation voltage regulator cabinet, and an excitation cabinet.

[0015] According to one embodiment of this application, based on real-time parameters, the predicted temperature of the protection switchgear at multiple subsequent moments is obtained, including: based on real-time parameters, obtaining the ambient temperature and humidity of the excitation chamber and the rectifier cabinet airflow and rectifier cabinet body temperature of the rectifier cabinet; fitting the ambient temperature and humidity, rectifier cabinet airflow and rectifier cabinet body temperature, and performing gray prediction processing on the fitted temperature values ​​to obtain the first predicted temperature of the rectifier cabinet, and using the first predicted temperature as the predicted temperature.

[0016] According to one embodiment of this application, based on real-time parameters, the predicted temperature of the protection switchgear at multiple subsequent moments is obtained, including: based on real-time parameters, obtaining the ambient temperature and humidity corresponding to the excitation compartment, the real-time cabinet temperature of each protection switchgear, and the excitation voltage and excitation current corresponding to the excitation cabinet; fitting the ambient temperature and humidity, excitation voltage and excitation current as input values ​​and the real-time cabinet temperature of each protection switchgear as the response value, and performing gray prediction processing on the fitted temperature values ​​to obtain the second predicted temperature of each protection switchgear, and using the second predicted temperature as the predicted temperature.

[0017] According to one embodiment of this application, the over-temperature warning method for the excitation system further includes: in response to the protection switch cabinet being an excitation cabinet, acquiring real-time parameters corresponding to the excitation cabinet, wherein the real-time parameters include excitation voltage and excitation current; in response to the excitation voltage not conforming to a preset voltage range, issuing a voltage fault alarm indication; or, in response to the excitation current not conforming to a preset current range, issuing a current fault alarm indication.

[0018] To achieve the above objectives, a second aspect of this application provides an over-temperature early warning device for an excitation system, comprising: a first acquisition module, configured to acquire real-time parameters corresponding to the excitation equipment and the protection switchgear based on sensors installed on the excitation equipment and the protection switchgear in the excitation system, wherein the real-time parameters include the real-time temperatures of the excitation equipment and the protection switchgear; a second acquisition module, configured to acquire infrared imaging data of the protection switchgear and acquire the target infrared temperature corresponding to the protection switchgear based on the infrared imaging data; a third acquisition module, configured to acquire the predicted temperatures of the protection switchgear at multiple subsequent times based on the real-time parameters; and an alarm module, configured to issue an over-temperature alarm indication in response to at least one of the real-time temperature, the target infrared temperature, and the predicted temperature exceeding its corresponding temperature threshold.

[0019] According to one embodiment of this application, the second acquisition module is further configured to: acquire the initial infrared temperature of the protection switchgear based on infrared imaging data; acquire the target distance between the infrared sensor and the protection switchgear based on a rangefinder; acquire the compensation coefficient corresponding to the initial infrared temperature at the target distance based on the distance characteristic curve; and correct the initial infrared temperature based on the target distance and the compensation coefficient to acquire the target infrared temperature of the protection switchgear.

[0020] According to one embodiment of this application, the second acquisition module is further configured to: acquire the measured temperature of the preset constant temperature device as measured by the infrared sensor at different distances from the preset constant temperature device; acquire the actual temperature of the preset constant temperature device in the current state; and fit the distance value, the measured temperature and the actual temperature based on the least squares method to obtain a distance characteristic curve.

[0021] According to one embodiment of this application, the excitation equipment includes an excitation chamber and a generator shaft, and the protection switch cabinet includes a rectifier cabinet, an excitation voltage regulator cabinet, and an excitation cabinet.

[0022] According to one embodiment of this application, the third acquisition module is further configured to: acquire the ambient temperature and humidity corresponding to the excitation chamber and the rectifier cabinet air volume and rectifier cabinet body temperature corresponding to the rectifier cabinet based on real-time parameters; fit the ambient temperature and humidity, rectifier cabinet air volume and rectifier cabinet body temperature, and perform gray prediction processing on the fitted temperature values ​​to acquire the first predicted temperature corresponding to the rectifier cabinet, and use the first predicted temperature as the predicted temperature.

[0023] According to one embodiment of this application, the third acquisition module is further configured to: acquire, based on real-time parameters, the ambient temperature and humidity corresponding to the excitation chamber, the real-time cabinet temperature of each protection switchgear, and the excitation voltage and excitation current corresponding to the excitation cabinet; fit the ambient temperature and humidity, excitation voltage and excitation current as input values ​​and the real-time cabinet temperature of each protection switchgear as response values, and perform gray prediction processing on the fitted temperature values ​​to obtain the second predicted temperature of each protection switchgear, and use the second predicted temperature as the predicted temperature.

[0024] According to one embodiment of this application, the alarm module is further configured to: in response to the protection switchgear being an excitation cabinet, acquire the real-time parameters corresponding to the excitation cabinet, wherein the real-time parameters include excitation voltage and excitation current; in response to the excitation voltage not conforming to a preset voltage range, issue a voltage fault alarm indication; or, in response to the excitation current not conforming to a preset current range, issue a current fault alarm indication.

[0025] To achieve the above objectives, a third aspect of this application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to implement the over-temperature early warning method for the excitation system as described in the first aspect of this application.

[0026] To achieve the above objectives, a fourth aspect of this application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the over-temperature early warning method for the excitation system as described in the first aspect of this application.

[0027] To achieve the above objectives, a fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the over-temperature early warning method for the excitation system as described in the first aspect of this application. Attached Figure Description

[0028] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0029] Figure 1 This is an exemplary implementation of an over-temperature early warning method for an excitation system, as shown in one embodiment of this application.

[0030] Figure 2 This is a schematic diagram of the structure of an excitation system for implementing over-temperature early warning, as shown in one embodiment of this application.

[0031] Figure 3 This is an exemplary implementation of a first-level host computer processing coupled data method shown in one embodiment of this application.

[0032] Figure 4 This is a logic diagram of a three-level redundant over-temperature early warning method shown in one embodiment of this application.

[0033] Figure 5 This is an exemplary implementation of obtaining the target infrared temperature corresponding to the protective switchgear based on infrared imaging data, as shown in one embodiment of this application.

[0034] Figure 6 This is a flowchart illustrating the solution process of a cabinet temperature prediction model in one embodiment of this application.

[0035] Figure 7 This is a schematic diagram of an over-temperature warning device for an excitation system, as shown in one embodiment of this application.

[0036] Figure 8 This is a schematic diagram of an electronic device according to one embodiment of this application. Detailed Implementation

[0037] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0038] Figure 1 This application illustrates an exemplary implementation of an over-temperature early warning method for an excitation system, such as... Figure 1As shown, the over-temperature early warning method for the excitation system includes the following steps:

[0039] S101, based on the sensors installed on the excitation equipment and protection switchgear in the excitation system, acquire the real-time parameters corresponding to the excitation equipment and protection switchgear, wherein the real-time parameters include the real-time temperature of the excitation equipment and protection switchgear.

[0040] Figure 2 This is a schematic diagram of an excitation system for achieving over-temperature early warning, as shown below. Figure 2 As shown, the excitation system for over-temperature early warning mainly consists of a primary host computer, a secondary host computer, various excitation devices, various protection switch cabinets, and their respective independent detection sensors.

[0041] The excitation equipment includes the excitation compartment and the generator shaft, while the protection switchgear includes the rectifier cabinet, the automatic voltage regulator (AVR) cabinet, and the excitation cabinet. It's easy to understand that the rectifier cabinet, AVR cabinet, and excitation cabinet are located in the excitation compartment.

[0042] This application sets up a three-layer alarm system. The first-level alarm system mainly uses sensors installed on each excitation device and each protection switch cabinet in the excitation system to obtain the real-time parameters of each excitation device and protection switch cabinet. The real-time parameters are independently transmitted to their respective second-level host computers. When a fault occurs, the second-level host computers will independently alarm.

[0043] like Figure 2 As shown, an intelligent inspection sentinel sensor is installed inside the excitation chamber. This sensor features automatic constant-speed cruise, infrared temperature imaging, and ambient temperature and humidity data acquisition. Optionally, the intelligent inspection sentinel sensor is mounted on a track along the wall of the excitation chamber. The sensor completes one revolution every 10 minutes, uploading real-time infrared temperature data from the rectifier cabinet, AVR cabinet, and excitation cabinet within the excitation chamber to the corresponding secondary host computer 1 for image recognition. Upon detecting over-temperature conditions, the secondary host computer 1 independently triggers an alarm. The secondary host computer 1 also uploads the ambient temperature and humidity data and infrared temperature data measured by the intelligent inspection sentinel sensor to the primary host computer. The ambient temperature and humidity data and infrared temperature data are real-time parameters of the excitation chamber. For example, if the ambient temperature and humidity exceed a preset threshold, the secondary host computer 1 independently triggers an alarm.

[0044] like Figure 2As shown, an intelligent monitoring device is installed at the generator main shaft. This device includes a temperature sensor that monitors the carbon brush and slip ring temperatures at the generator main shaft. The carbon brush and slip ring temperatures are uploaded in real-time to a secondary host computer 2 corresponding to the generator main shaft for temperature identification processing. If an over-temperature condition is detected, the secondary host computer 2 will independently trigger an alarm. Optionally, the temperature sensor can be an infrared temperature sensor. The carbon brush and slip ring temperatures are real-time parameters of the generator main shaft. For example, if the carbon brush temperature exceeds a preset carbon brush temperature threshold, the secondary host computer 2 will independently trigger an alarm.

[0045] like Figure 2 As shown, the rectifier cabinet is equipped with an airflow sensor and a temperature sensor. The airflow sensor is used to obtain the real-time airflow of the rectifier cabinet, and the temperature sensor is used to obtain the cabinet temperature. The real-time airflow and cabinet temperature are uploaded to the corresponding secondary host computer 3. Upon detecting an over-temperature condition, the secondary host computer 3 independently triggers an alarm. The secondary host computer 3 also uploads the real-time airflow and cabinet temperature to the primary host computer and controls the ventilation system to adjust the airflow according to the rectifier cabinet temperature, thus providing independent feedback. The real-time airflow and cabinet temperature are real-time parameters of the rectifier cabinet. For example, if the rectifier cabinet temperature exceeds a preset temperature threshold, the secondary host computer 3 independently triggers an alarm.

[0046] like Figure 2 As shown, an embedded temperature sensor is installed on the CPU board of the AVR cabinet to upload the electronic board temperature to the corresponding secondary host computer 4 in real time. In the event of an over-temperature condition, the secondary host computer 4 will independently trigger an alarm. The electronic board temperature is a real-time parameter of the AVR cabinet. For example, if the electronic board temperature exceeds a preset electronic board temperature threshold, the secondary host computer 4 will trigger an independent alarm.

[0047] like Figure 2 As shown, a protection device is installed on the excitation cabinet. This device acquires the excitation voltage and current of the excitation cabinet and uploads them to the corresponding secondary host computer 5. Simultaneously, it uploads the excitation voltage and current to the primary host computer, primarily for coupled data analysis in the primary host computer, thereby achieving over-temperature early warning. Furthermore, although the excitation voltage and current are not temperature values, to improve the safety and reliability of the excitation system, if the excitation voltage does not conform to the preset voltage range, the secondary host computer 5 independently issues a voltage fault alarm indication; or, if the excitation current does not conform to the preset current range, the secondary host computer 5 independently issues a current fault alarm indication.

[0048] S102, acquire infrared imaging data of the protection switchgear, and obtain the target infrared temperature corresponding to the protection switchgear based on the infrared imaging data.

[0049] In this application, the secondary alarm layer mainly uses intelligent inspection sentinel sensors to inspect the excitation compartment. The infrared imaging results are corrected by the least squares method and the ranging method. The cabinet temperature of each protection switch cabinet in the excitation compartment is detected in real time, and abnormal temperature areas are identified to realize the real-time alarm function.

[0050] Figure 3 An exemplary implementation of a method for processing coupled data by a primary host computer, such as... Figure 3 As shown, this application uses an intelligent inspection sentinel sensor to perform real-time infrared temperature measurement on the protection switchgear in the excitation compartment. Infrared temperature measurement is based on the blackbody radiation law: the higher the temperature of an object, the greater the amount of radiation emitted. In infrared imaging monitoring, radiance is directly proportional to temperature and inversely proportional to the square of the distance. However, the intelligent inspection sentinel sensor is in a moving state during temperature measurement, which causes the distance to the measured target to change constantly, affecting the accuracy of temperature feedback. This results in an error between the measured infrared temperature of the protection switchgear and the actual temperature. Therefore, it is necessary to correct and compensate for the temperature results measured by the infrared sensor to reduce the measurement error. Thus, it is necessary to correct the cabinet temperature returned by infrared temperature measurement based on the rangefinder and the distance characteristic curve to ensure the accuracy of the returned temperature data and obtain the target infrared temperature corresponding to each protection switchgear after correction.

[0051] S103, based on real-time parameters, obtains the predicted temperature of the protection switchgear at multiple subsequent moments.

[0052] In this application, the three-level alarm layer mainly involves the first-level host computer acquiring and establishing the correlation between various data and temperature based on the aforementioned real-time parameters, and then using the gray prediction method to predict the temperature and obtain the predicted temperature of the protection switchgear at multiple subsequent times.

[0053] For example, such as Figure 3 As shown, this application employs a BP neural network to fit the rectifier cabinet airflow, ambient temperature and humidity, and rectifier cabinet temperature to establish a correlation. Then, a grey prediction model is used to predict the fitted temperature values ​​to obtain the predicted temperature of the rectifier cabinet at multiple subsequent times. On the other hand, excitation voltage, excitation current, and ambient temperature and humidity are used as input values, and the real-time cabinet temperature of each protection switchgear is used as the response value to establish a fitting relationship. Finally, a grey prediction model is used to predict the temperature values ​​obtained from the aforementioned fitting formula to obtain the predicted temperature of each protection switchgear at multiple subsequent times.

[0054] S104, in response to at least one of the real-time temperature, target infrared temperature and predicted temperature being greater than its corresponding temperature threshold, issues an over-temperature alarm indication.

[0055] Figure 4 This application illustrates a logic diagram of a three-level redundancy over-temperature early warning method, such as... Figure 4As shown, in this application, the three alarm layers are redundant. If at least one of the real-time temperature, target infrared temperature, and predicted temperature exceeds its corresponding temperature threshold, the corresponding alarm layer will issue an over-temperature alarm indication. For example, if the carbon brush temperature at the generator shaft exceeds the set carbon brush temperature threshold, the secondary host computer 2 corresponding to the generator shaft in the first-level alarm layer will independently alarm and send a fault message; for example, if the target infrared temperature of the rectifier cabinet in the second-level alarm layer exceeds the set infrared temperature threshold, the first-level host computer corresponding to the second-level alarm layer will alarm and send a fault message; for example, if the predicted temperature of the excitation cabinet in the third-level alarm layer exceeds the set predicted temperature threshold, the first-level host computer corresponding to the third-level alarm layer will alarm and send a fault message.

[0056] This application discloses an over-temperature early warning method for an excitation system. It acquires real-time parameters of the excitation equipment and protection switchgear based on sensors installed on them, including the real-time temperature of the equipment and switchgear. The method also acquires infrared imaging data of the protection switchgear and determines its target infrared temperature. Based on the real-time parameters, it obtains predicted temperatures for the switchgear at multiple subsequent times. An over-temperature alarm is issued when at least one of the real-time temperature, target infrared temperature, or predicted temperature exceeds its corresponding temperature threshold. This application establishes a three-level over-temperature early warning system for the excitation system, consisting of independent real-time temperature alarm, real-time target infrared temperature detection alarm, and over-temperature early warning based on real-time parameters. These three levels of alarms are redundant, providing real-time temperature safety assurance and over-temperature early warning for the excitation system, preventing over-temperature faults in their early stages and significantly improving the safety and reliability of the excitation system.

[0057] Figure 5 This application illustrates an exemplary implementation of an over-temperature early warning method for an excitation system, such as... Figure 5 As shown, based on the above embodiments, obtaining the target infrared temperature corresponding to the protection switchgear according to infrared imaging data includes the following steps:

[0058] S501, based on infrared imaging data, obtains the initial infrared temperature of the protection switchgear.

[0059] Infrared imaging data of each protection switchgear is acquired, and the initial infrared temperature of the protection switchgear is obtained based on the infrared imaging data. Since the aforementioned intelligent inspection sentinel sensor has infrared temperature measurement and imaging capabilities, in this application, the infrared sensor can be directly adopted from the aforementioned intelligent inspection sentinel sensor; that is, the infrared imaging data of each protection switchgear can be obtained by measuring the infrared data of the aforementioned intelligent inspection sentinel sensor.

[0060] S502 uses a rangefinder to obtain the target distance between the infrared sensor and the protection switchgear.

[0061] The target distance between the infrared sensor and the protection switchgear is obtained based on a rangefinder. Since the aforementioned intelligent inspection sentinel sensor has infrared temperature measurement and imaging capabilities, in this application, the infrared sensor can be directly adopted from the aforementioned intelligent inspection sentinel sensor; that is, the target distance between the intelligent inspection sentinel sensor and each protection switchgear is obtained based on the rangefinder.

[0062] S503, based on the distance characteristic curve, obtains the compensation coefficient corresponding to the initial infrared temperature at the target distance.

[0063] The method for obtaining the distance characteristic curve includes: obtaining the measured temperature of the preset constant temperature device measured by the infrared sensor at different distances from the preset constant temperature device under the ambient temperature of the excitation chamber; obtaining the actual temperature of the preset constant temperature device under the current state; and fitting the distance value, measured temperature and actual temperature based on the least squares method to obtain the distance characteristic curve.

[0064] Among them, the least squares method uses the minimization of the sum of squared errors as the objective function to fit the function expression that best suits the measured data, based on several existing measured data points (x... i ,y i Seek an expression y = f(x) for x and y, and denote the error as equation (1):

[0065] δ i =f(x) i )-y i ,i=1,2,...,k(1)

[0066] In the above formula, x i This indicates the measured temperature of the preset constant temperature device, y i This indicates the actual temperature of the preset thermostat under its current condition.

[0067] Then we need to minimize the sum of squared errors, that is, to make The goal is to minimize the variance (SSE). The goodness of fit is used to judge the quality of the fitted formula. The closer the SSE value is to 0 and the closer the R-square coefficient is to 1, the better the fitted formula is, and the closer it is to the actual pattern of the data. SSE and R-square are calculated as shown in equation (2-3).

[0068]

[0069]

[0070] Taking into account both goodness of fit and formula complexity, this patent uses a sixth-order polynomial to generate the distance characteristic curve of the target distance versus temperature deviation percentage. The compensation coefficient is shown in equation (4).

[0071] K(L) = k6 * L 6 +k5*L 5 +k4*L 4 +k3*L 3 +k2*L 2 +k1*L+k0(4)

[0072] In the above formula, k0, k1, k2, k3, k4, k5, and k6 are constant values ​​obtained through fitting, and L is the target distance between the infrared sensor and the protection switch cabinet. In this application, the infrared sensor can be the aforementioned intelligent inspection sentinel sensor.

[0073] S504 corrects the initial infrared temperature based on the target distance and compensation coefficient to obtain the target infrared temperature of the protection switchgear.

[0074] The initial infrared temperature is corrected based on the target distance and compensation coefficient to obtain the target infrared temperature of the protected switchgear, thereby reducing the temperature measurement error of the protected switchgear under test.

[0075] The actual temperature after correction and compensation is shown in equation (5).

[0076] T 实际 =T 测 / K(L)(5)

[0077] In the above formula, T 实际 For the target infrared temperature, T 测 Where is the initial infrared temperature, and K(L) is the compensation coefficient.

[0078] This application provides real-time infrared temperature detection and alarm for the excitation system, enabling real-time temperature safety protection and over-temperature early warning, thus resolving excitation over-temperature faults in their early stages and greatly improving the safety and reliability of the excitation system.

[0079] Furthermore, when obtaining the predicted temperature of the protection switchgear at multiple subsequent moments based on real-time parameters, since the BP neural network used in this patent fits multiple input quantities and a single output quantity, a single-layer neural network will be constructed, i.e., y = f(x iBackpropagation (BP) neural networks are highly effective fitting tools. A BP neural network model has a three-layer structure: an input layer, hidden layers, and an output layer. The main components introduced are activation functions and weights. The activation function introduces non-linearity to enhance the neural network's expressive power. BP neural network fitting involves forward propagating the signal from the training set to calculate the result, then iteratively backpropagating the error, continuously adjusting the threshold and weights to minimize the sum of squared errors, ultimately finding a suitable fitting function.

[0080] Let x1, x2, ..., x n For multidimensional input values, y is a single output value, and u is a multidimensional input value. i Let f be the neurons in the hidden layer, f be the mapping relationship of the activation function, and v be the neurons in the hidden layer. ij Let θ be the weight between the i-th input value and the j-th neuron. j u The threshold value for the j-th neuron in hidden layer u is also called the bias term. The activation function is chosen based on the actual fit. The forward propagation formulas are shown in equations (6)-(7).

[0081]

[0082]

[0083] Let x be the true value of the input data, and let the corresponding output value be... The value obtained by fitting the data through a BP neural network is y. The goal is to minimize the error between the true value and the calculated value. Therefore, the objective function is shown in equation (8). First, the k-th object is taken as the objective, and then the sum of all objects is taken as the final objective.

[0084]

[0085] This application will use the gradient descent method commonly used in BP neural networks to solve the objective function, that is, to optimize in the gradient descent direction until the optimal value is reached, and finally optimize the weights and threshold parameters. The formula is shown in equation (9), where u is the learning rate, also known as the descent speed, y is the objective, and w is the required optimization parameter. For the network system of this patent, v ij θ j u w j and θ y To optimize the parameters, E is the objective function.

[0086]

[0087] Since the over-temperature warning in this application is qualitatively a short-term prediction, the grey prediction method is used to make short-term predictions on the dataset composed of data collected every minute. In the field of short-term prediction, grey prediction has the advantages of high efficiency and accuracy when modeling datasets with few statistical data and short time series. This patent uses grey prediction with an accumulation generation method to predict the cabinet temperature of each protection switch cabinet in the excitation room. The original collected dataset is accumulated and a differential formula is constructed. The prediction model can be obtained by deriving the formula based on the least squares estimation. The derivation process is shown in equations (10)-(13).

[0088]

[0089]

[0090]

[0091]

[0092] After obtaining the predicted data, the accuracy of the data needs to be further verified to ensure its validity. The accuracy verification method adopts the posterior error test. The corresponding parameter verification formula is shown in equation (14-15).

[0093]

[0094]

[0095] In the formula, e(k) represents the residual value between x0 and the predicted dataset. Let k be the average difference between the actual dataset and the predicted dataset at time k. S1 is the actual average dataset for x0. 2 and S2 2 S1 and S2 are the variances of the original dataset x0 and the residual dataset e(k), respectively. A smaller S2 and a larger S1 result in a smaller C value, indicating higher prediction accuracy. The more times the absolute value of the difference is less than the set value, the larger the P-value, indicating higher prediction accuracy. The gray prediction accuracy is shown in Table 1.

[0096] Table 1. Accuracy Levels of Prediction Models

[0097]

[0098] Figure 6 Flowchart for solving the cabinet temperature prediction model, as follows: Figure 6As shown, the number of predictions can be preset, the cabinet temperature dataset is updated every minute, the original cabinet temperature data is read and accumulated, a model is built to solve the predicted value, the data accuracy is verified and the predicted temperature of the protection switch cabinet at multiple times within the next T minutes is output. After the current prediction is completed, the next prediction continues until the prediction stop command is received, thereby achieving the effect of over-temperature early warning.

[0099] Figure 7 This is a schematic diagram of an over-temperature early warning device for an excitation system shown in this application, such as... Figure 7 As shown, the over-temperature warning device 700 of the excitation system includes a first acquisition module 701, a second acquisition module 702, a third acquisition module 703, and an alarm module 704, wherein:

[0100] The first acquisition module 701 is used to acquire real-time parameters corresponding to the excitation equipment and protection switchgear based on the sensors installed on the excitation equipment and protection switchgear in the excitation system. The real-time parameters include the real-time temperature of the excitation equipment and protection switchgear.

[0101] The second acquisition module 702 is used to acquire infrared imaging data of the protection switchgear and acquire the target infrared temperature corresponding to the protection switchgear based on the infrared imaging data.

[0102] The third acquisition module 703 is used to acquire the predicted temperature of the protection switchgear at multiple subsequent times based on real-time parameters.

[0103] The alarm module 704 is used to issue an over-temperature alarm indication in response to at least one of the real-time temperature, target infrared temperature and predicted temperature being greater than its corresponding temperature threshold.

[0104] The over-temperature early warning device for the excitation system provided in this application consists of a three-level over-temperature early warning system for the excitation system, which is based on real-time independent temperature alarm, real-time target infrared temperature detection alarm, and over-temperature early warning function based on real-time parameters. The three-level alarm system is redundant with each other, which realizes real-time temperature safety protection and over-temperature early warning function for the excitation system, resolves excitation over-temperature faults in their infancy, and greatly improves the safety and reliability of the excitation system.

[0105] Furthermore, the second acquisition module 702 is also used to: acquire the initial infrared temperature of the protection switchgear based on infrared imaging data; acquire the target distance between the infrared sensor and the protection switchgear based on the rangefinder; acquire the compensation coefficient corresponding to the initial infrared temperature at the target distance based on the distance characteristic curve; and correct the initial infrared temperature based on the target distance and the compensation coefficient to acquire the target infrared temperature of the protection switchgear.

[0106] Furthermore, the second acquisition module 702 is also used to: acquire the measured temperature of the preset constant temperature device as measured by the infrared sensor at different distances from the preset constant temperature device; acquire the actual temperature of the preset constant temperature device in the current state; and fit the distance value, measured temperature and actual temperature based on the least squares method to obtain the distance characteristic curve.

[0107] Furthermore, the excitation equipment in the over-temperature early warning device of the excitation system includes the excitation chamber and the generator shaft, and the protection switch cabinet includes the rectifier cabinet, the excitation voltage regulator cabinet and the excitation cabinet.

[0108] Furthermore, the third acquisition module 703 is also used to: acquire the ambient temperature and humidity corresponding to the excitation chamber and the rectifier cabinet air volume and rectifier cabinet body temperature corresponding to the rectifier cabinet based on real-time parameters; fit the ambient temperature and humidity, rectifier cabinet air volume and rectifier cabinet body temperature, and perform gray prediction processing on the fitted temperature values ​​to obtain the first predicted temperature corresponding to the rectifier cabinet, and use the first predicted temperature as the predicted temperature.

[0109] Furthermore, the third acquisition module 703 is also used to: acquire the ambient temperature and humidity corresponding to the excitation chamber, the real-time cabinet temperature of each protection switchgear, and the excitation voltage and excitation current corresponding to the excitation cabinet based on real-time parameters; fit the ambient temperature and humidity, excitation voltage and excitation current as input values ​​and the real-time cabinet temperature of each protection switchgear as response values, and perform gray prediction processing on the fitted temperature values ​​to obtain the second predicted temperature of each protection switchgear, and use the second predicted temperature as the predicted temperature.

[0110] Furthermore, the alarm module 704 is also used to: in response to the protection switchgear being an excitation cabinet, obtain the real-time parameters corresponding to the excitation cabinet, wherein the real-time parameters include excitation voltage and excitation current; in response to the excitation voltage not conforming to the preset voltage range, issue a voltage fault alarm indication; or, in response to the excitation current not conforming to the preset current range, issue a current fault alarm indication.

[0111] To implement the above embodiments, this application also proposes an electronic device 800, such as... Figure 8 As shown, the electronic device 800 includes a processor 801 and a memory 802 communicatively connected to the processor. The memory 802 stores instructions that can be executed by at least one processor. The instructions are executed by at least one processor 801 to implement the over-temperature early warning method of the excitation system as shown in the above embodiment.

[0112] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to implement the over-temperature early warning method for the excitation system as shown in the above embodiments.

[0113] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the over-temperature early warning method for the excitation system as shown in the above embodiments.

[0114] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0115] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0116] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0117] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for over-temperature early warning of an excitation system, characterized in that, include: Based on the sensors installed on the excitation equipment and protection switchgear in the excitation system, real-time parameters corresponding to the excitation equipment and protection switchgear are obtained, wherein the real-time parameters include the real-time temperature of the excitation equipment and protection switchgear; Acquire infrared imaging data of the protection switchgear, and obtain the target infrared temperature corresponding to the protection switchgear based on the infrared imaging data; Based on the real-time parameters, the predicted temperature of the protection switchgear at multiple subsequent moments is obtained; In response to at least one of the real-time temperature, the target infrared temperature and the predicted temperature being greater than its corresponding temperature threshold, an over-temperature alarm indication is issued. The excitation equipment includes an excitation chamber and a generator shaft, and the protection switch cabinet includes a rectifier cabinet, an excitation voltage regulator cabinet, and an excitation cabinet. The step of obtaining the predicted temperature of the protection switchgear at multiple subsequent moments based on the real-time parameters includes: Based on the real-time parameters, the ambient temperature and humidity corresponding to the excitation room, the real-time cabinet temperature of each protection switch cabinet, and the excitation voltage and excitation current corresponding to the excitation cabinet are obtained. The ambient temperature and humidity, the excitation voltage and the excitation current are used as input values, and the real-time cabinet temperature of each protection switch cabinet is used as the response value for fitting. The fitted temperature values ​​are then subjected to gray prediction processing to obtain the second predicted temperature of each protection switch cabinet, and the second predicted temperature is used as the predicted temperature. A three-level over-temperature warning system for the excitation system is composed of real-time independent temperature alarm, target infrared temperature real-time detection alarm, and over-temperature warning function based on real-time parameters. The three-level over-temperature warning system includes: a primary alarm layer, a secondary alarm layer, and a tertiary alarm layer, which are redundant. If at least one of the real-time temperature, target infrared temperature, and predicted temperature exceeds its corresponding temperature threshold, the corresponding alarm layer issues an over-temperature alarm indication. If the carbon brush temperature at the generator shaft exceeds the set carbon brush temperature threshold, the secondary upper computer corresponding to the generator shaft in the primary alarm layer independently alarms and sends a fault message. If the target infrared temperature of the rectifier cabinet in the secondary alarm layer exceeds the set infrared temperature threshold, the primary upper computer corresponding to the secondary alarm layer alarms and sends a fault message. If the predicted temperature of the excitation cabinet in the tertiary alarm layer exceeds the set predicted temperature threshold, the primary upper computer corresponding to the tertiary alarm layer alarms and sends a fault message.

2. The method of claim 1, wherein, The step of obtaining the target infrared temperature corresponding to the protection switchgear based on the infrared imaging data includes: Based on the infrared imaging data, the initial infrared temperature of the protection switchgear is obtained; The target distance between the infrared sensor and the protection switchgear is obtained based on the rangefinder; Based on the distance characteristic curve, obtain the compensation coefficient corresponding to the initial infrared temperature at the target distance; The initial infrared temperature is corrected based on the target distance and the compensation coefficient to obtain the target infrared temperature of the protection switchgear.

3. The method of claim 2, wherein, The method for obtaining the distance characteristic curve includes: The infrared sensor measures the temperature of the preset constant temperature device at different distances from the preset constant temperature device. Obtain the actual temperature of the preset constant temperature device in its current state; The distance characteristic curve is obtained by fitting the distance value, the measured temperature, and the actual temperature using the least squares method.

4. The method of claim 1, wherein, The method further includes: In response to the fact that the protection switchgear is the excitation cabinet, the real-time parameters corresponding to the excitation cabinet are obtained, wherein the real-time parameters include excitation voltage and excitation current; In response to the excitation voltage not conforming to the preset voltage range, a voltage fault alarm indication is issued; or, In response to the excitation current not conforming to the preset current range, a current fault alarm indication is issued.

5. An over-temperature early warning device for an excitation system, characterized in that, include: The first acquisition module is used to acquire real-time parameters corresponding to the excitation equipment and the protection switchgear based on the sensors installed on the excitation equipment and the protection switchgear in the excitation system, wherein the real-time parameters include the real-time temperature of the excitation equipment and the protection switchgear. The second acquisition module is used to acquire infrared imaging data of the protection switchgear and acquire the target infrared temperature corresponding to the protection switchgear based on the infrared imaging data. The third acquisition module is used to acquire the predicted temperature of the protection switchgear at multiple subsequent times based on the real-time parameters. The alarm module is used to issue an over-temperature alarm indication in response to at least one of the real-time temperature, the target infrared temperature and the predicted temperature being greater than its corresponding temperature threshold. The excitation equipment includes an excitation chamber and a generator shaft, and the protection switch cabinet includes a rectifier cabinet, an excitation voltage regulator cabinet, and an excitation cabinet. The step of obtaining the predicted temperature of the protection switchgear at multiple subsequent moments based on the real-time parameters includes: Based on the real-time parameters, the ambient temperature and humidity corresponding to the excitation room, the real-time cabinet temperature of each protection switch cabinet, and the excitation voltage and excitation current corresponding to the excitation cabinet are obtained. Using the ambient temperature and humidity, excitation voltage, and excitation current as input values, and the real-time cabinet temperature of each protection switchgear as the response value, a fitting process is performed. The fitted temperature values ​​are then subjected to gray prediction processing to obtain a second predicted temperature for each protection switchgear, which is then used as the predicted temperature. A three-level over-temperature warning system for the excitation system is constructed based on real-time independent temperature alarm, real-time target infrared temperature detection alarm, and over-temperature warning function based on real-time parameters. This three-level over-temperature warning system includes: a first-level alarm layer, a second-level alarm layer, and a third-level alarm layer. The three alarm layers are redundant. If the real-time temperature, target infrared temperature, and real-time temperature are not directly related to the temperature readings, the system will automatically adjust the alarm level. If at least one of the target infrared temperature and the predicted temperature exceeds its corresponding temperature threshold, the corresponding alarm layer issues an over-temperature alarm indication. If the carbon brush temperature at the generator shaft exceeds the set carbon brush temperature threshold, the secondary host computer corresponding to the generator shaft in the first-level alarm layer independently alarms and sends a fault message. If the target infrared temperature of the rectifier cabinet in the second-level alarm layer exceeds the set infrared temperature threshold, the first-level host computer corresponding to the second-level alarm layer alarms and sends a fault message. If the predicted temperature of the excitation cabinet in the third-level alarm layer exceeds the set predicted temperature threshold, the first-level host computer corresponding to the third-level alarm layer alarms and sends a fault message.

6. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

7. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-4.

Images