Power cable fault monitoring method and system, medium, product and computer equipment
Patent Information
- Application Number
- CN202511454515.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-13
- Publication Date
- 2025-11-11
Smart Images
Figure CN120928097A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing technology, and in particular to a method, system, medium, product and computer equipment for monitoring power cable faults. Background Technology
[0002] Cables are generally used in power transmission and distribution networks to meet the needs of long-distance, high-capacity energy transmission. As the length of the cable increases, the possibility of cable damage increases, but the difficulty of monitoring cable faults also increases.
[0003] In related technologies, a large number of sensors are typically used to collect cable-related data for cable fault monitoring and analysis. However, because the data collected by the sensors usually contains significant noise, it can easily lead to a decrease in the accuracy of cable fault monitoring. Summary of the Invention
[0004] To address the aforementioned technical problems, this application proposes a method, system, medium, product, and computer equipment for monitoring power cable faults, which can improve the accuracy of cable fault monitoring.
[0005] In a first aspect, embodiments of this application provide a method for monitoring power cable faults, including: Acquire sensor data corresponding to the power cable; Based on the sensor data, a preset Kalman filter algorithm is used to determine the estimation result and the first error information corresponding to the estimation result, wherein the first error information includes a first estimation error and a measurement error; Based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm, the neural network is invoked to determine the second error information; Based on the second error information, the estimation result is corrected to obtain the fault monitoring result corresponding to the power cable according to the corrected estimation result.
[0006] Optionally, the step of determining the estimation result and the first error information corresponding to the estimation result using a preset Kalman filter algorithm based on the sensor data includes: Based on the sensor data, the state prediction equation in the time update stage of the preset Kalman filter algorithm is used to determine the expected predicted state information. Based on the sensor data and the expected predicted state information, the state estimation update equation in the measurement update stage of the preset Kalman filter algorithm is used to determine the predicted state information. The first estimation error is determined based on the difference between the predicted state information and the expected predicted state information.
[0007] Optionally, the estimation result is the predicted state information.
[0008] Optionally, the second error information includes a second estimation error, and the step of correcting the estimation result based on the second error information includes: The second estimation error is superimposed on the predicted state information to obtain the corrected estimation result.
[0009] Optionally, the step of determining the estimation result and the first error information corresponding to the estimation result using a preset Kalman filter algorithm based on the sensor data includes: Based on the sensor data, the state prediction equation in the time update stage of the preset Kalman filter algorithm is used to determine the expected predicted state information. Based on the expected predicted state information and the observation matrix corresponding to the preset Kalman filter algorithm, the expected observation value is determined. Based on the sensor data, the actual observed value is determined using the observation equation in the preset Kalman filter algorithm; The measurement error is determined based on the difference between the actual observed value and the expected observed value.
[0010] Optionally, the step of determining the second error information by invoking a neural network based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm includes: The first error information and the Kalman filter gain are input into the neural network to obtain the second error information output by the neural network.
[0011] Secondly, embodiments of this application provide a power cable fault monitoring system, comprising: The data acquisition module is used to acquire sensor data corresponding to the power cable; The first error module is used to determine the estimation result and the first error information corresponding to the estimation result based on the sensor data using a preset Kalman filter algorithm, wherein the first error information includes a first estimation error and a measurement error; The second error module is used to call a neural network to determine the second error information based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm. The correction and monitoring module is used to correct the estimation result based on the second error information, so as to obtain the fault monitoring result corresponding to the power cable according to the corrected estimation result.
[0012] Thirdly, embodiments of this application provide a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in any of the above-mentioned embodiments.
[0013] Fourthly, embodiments of this application provide a computer program product, including computer instructions that, when executed by a processor, implement the steps of the method described in any of the above-described embodiments.
[0014] Fifthly, embodiments of this application provide a computer device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the steps of the method described in any of the preceding claims.
[0015] In summary, the embodiments of this application have at least the following beneficial effects: In this embodiment, sensor data corresponding to the power cable is acquired; based on the sensor data, a preset Kalman filter algorithm is used to determine the estimation result and the first error information corresponding to the estimation result, wherein the first error information includes a first estimation error and a measurement error; based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm, a neural network is invoked to determine the second error information; based on the second error information, the estimation result is corrected to obtain the fault monitoring result corresponding to the power cable. This allows for the first use of the Kalman filter algorithm to filter the sensor data to eliminate redundant data and obtain the corresponding estimation result and the first error information. Then, the neural network is used to optimize the Kalman filter based on the first error information and the Kalman filter gain, resulting in more accurate second error information, which facilitates more precise correction of the estimation result and improves the accuracy of cable fault monitoring. Attached Figure Description
[0016] Figure 1 This is a flowchart illustrating the power cable fault monitoring method provided in the embodiments of this application; Figure 2 This is a schematic diagram of sensor data processing provided in an embodiment of this application; Figure 3 This is a schematic diagram of the neural network input and output provided in an embodiment of this application; Figure 4 This is a schematic diagram of an experimental comparison provided in an embodiment of this application; Figure 5 This is another schematic diagram illustrating the experimental comparison provided in the embodiments of this application; Figure 6 This is yet another schematic diagram illustrating the experimental comparison provided in the embodiments of this application; Figure 7 This is a schematic diagram of the power cable fault monitoring system provided in the embodiments of this application; Figure 8 This is a schematic diagram of the computer device provided in the embodiments of this application. Detailed Implementation
[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments / examples are only a part of the embodiments / examples of this application, and not all of the embodiments / examples. Based on the embodiments / examples in this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.
[0018] In the description of this application, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "multiple" means two or more. In the description of this application, the term "comprising" and its variations are open-ended, meaning "including but not limited to." The term "based on" means "at least partially based on." The term "according to" means "at least partially according to." The term "one embodiment / example" means "at least one embodiment / example"; the term "another embodiment / example" means "at least one additional embodiment / example"; the term "some embodiments / examples" means "at least some embodiments / examples."
[0019] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0020] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this application is for the purpose of describing specific embodiments only and is not intended to limit the application. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.
[0021] The following explains some terms and concepts used in the embodiments of this application: The Kalman filter algorithm has the ability to separate useful signals from signals affected by various random noise interferences (that is, it can be used to separate useful signals from sensor data to further output estimation results). Its basic principle includes: for random signals, based on the statistical characteristics of system noise and observation noise, the system observations are used as the input to a filter constructed based on a preset Kalman filter algorithm, and the desired estimated value is used as the output of the filter. Furthermore, the input and output of the filter are correlated through the time update algorithm and observation update algorithm included in the preset Kalman filter algorithm, so as to obtain the desired estimated signal (estimation result) according to the system equation and observation equation. The mathematical principles of the Kalman filter algorithm are introduced below.
[0022] When the Kalman filter algorithm is expressed as a mathematical model, the corresponding state equation is as follows (1).
[0023] (1) In the formula, for time 3D state vector; for time 3D state vector; for Time's up Moment 3D state transition matrix; for The state noise of the system at any given moment; for The coefficient matrix of the system state noise at any given time.
[0024] The corresponding observation equation is as follows (2).
[0025] (2) In the formula, for time 3D observation vector; for time 3D observation matrix; for Continuously monitor noise.
[0026] Assuming state noise and observation noise It is uncorrelated and normally distributed white noise, i.e. , .
[0027] The state prediction equation for the time update stage, which ignores state noise, can be obtained as shown in equation (3).
[0028] (3) In the formula, Indicates based on State estimation based on time-time information is used to predict the state at time k (prior state estimation). express State estimation based on time information.
[0029] The corresponding state estimation update equation at this time is as follows (4).
[0030] (4) In the formula, This represents the updated state estimate, that is, using Correcting the prior state estimate at time k The posterior state estimate at time k is obtained.
[0031] In the formula, for The filter gain matrix at time t, and satisfies the following equation (5).
[0032] (5) In the formula, T represents the transpose, and R represents the uncertainty of the observation. for Time's up The predicted covariance at time t is given by equation (6).
[0033] (6) In the formula, State noise The covariance matrix.
[0034] The covariance matrix of the state estimate at time k. It is the following formula (7).
[0035] (7) In the formula, I is the identity matrix.
[0036] In summary, this constitutes part of the mathematical principles involved in the Kalman filtering algorithm provided in the embodiments of this application.
[0037] In some cases, the main causes of damage to power cables during power transmission can typically include at least one of the following: First, damage caused by external violent excavation, directly leading to internal cable breakage and power outages; second, manufacturing defects in the cable's internal processes causing insulation damage at the cable head, resulting in insulation breakdown, discharge, and fire; third, damage to the load-bearing capacity of cable manhole covers, posing safety hazards to passing vehicles and pedestrians. Among various cable fault causes, many are due to sheath system failures, such as water ingress into cable joints, corrosion of the cable sheath, damage by third parties, and insulation damage at joints, all of which can lead to excessive sheath current. Therefore, researching online monitoring and real-time location methods for power cable faults to achieve real-time monitoring, intelligent early warning, and location locking to improve power transmission efficiency is urgently needed.
[0038] In related technologies, with the gradual expansion of IoT and intelligent technologies into new fields, sensor networks have become a key means of acquiring important environmental information and sensing the operating status of operating systems. Multi-sensor information fusion technology is crucial for the identification, characterization, and condition monitoring of cable insulation. Related technologies, through multi-sensor information fusion, can identify and locate defects or faults, including the acquisition and processing of information on partial discharge, insulation resistance, and dielectric loss. However, information fusion from multiple sensors typically involves a large amount of data, which is generally affected by complex noise, incompleteness, and inaccuracy, thus exacerbating the uncertainty of the information fusion results and affecting the accuracy of power cable fault monitoring. Therefore, how to suppress complex noise interference and obtain complete and accurate information to improve the credibility and reliability of information acquired by multiple sensors has become a current focus. Related technologies may use Kalman filtering algorithms to eliminate noise in sensor data.
[0039] The conditions for implementing the Kalman filter algorithm generally require that both the system noise and measurement noise are known, corresponding to Gaussian white noise with a mean of 0. Additionally, the system model corresponding to the Kalman filter algorithm must be accurate, and the corresponding system error model and observation error model must be known. However, in complex and ever-changing working environments, these requirements of the Kalman filter algorithm are often difficult to meet, potentially leading to filter divergence, low accuracy, or unsatisfactory filtering results.
[0040] Firstly, see [the following] Figure 1 The diagram shows a flowchart of a power cable fault monitoring method provided in an embodiment of this application. The method includes steps S101-S104, as detailed below.
[0041] S101, acquire sensor data corresponding to the power cable.
[0042] In some examples, the sensor described above may include at least one of the following: a first sensor, a second sensor, and a third sensor. Further explanation of each type of sensor follows.
[0043] The first sensor used to capture discharge signals may include a high-frequency current transformer (HFCT), an ultra-high frequency sensor (UHF), and / or a distributed acoustic sensing (DAS) sensor. This first sensor may be designed to address insulation damage issues such as cable insulation degradation and partial discharge.
[0044] The second sensor used for concentration monitoring may include an electrochemical gas sensor, an infrared gas sensor, and / or a semiconductor gas sensor. This second sensor may be used to detect harmful gases (such as...) within conduits (e.g., cable tunnels, pipe racks). , It was designed to address the problem of CO accumulation.
[0045] The third sensor may include a distributed fiber optic temperature sensor (DTS), a distributed fiber optic acoustic sensor (DAS), and / or a distributed fiber optic vibration sensor (DVS). The distributed fiber optic temperature sensor can be used to detect abnormal temperature rise points, and the distributed fiber optic acoustic sensor and / or the distributed fiber optic vibration sensor can be used to capture abnormal vibration signals from excavation, chiseling, etc. This third sensor may be designed to address the problem of unclear location and morphological information of pipeline holes (such as external damage or joint defects).
[0046] S102, based on the sensor data, a preset Kalman filter algorithm is used to determine the estimation result and the first error information corresponding to the estimation result, wherein the first error information includes a first estimation error and a measurement error.
[0047] In some examples, the aforementioned preset Kalman filter algorithm can be used to filter the sensor data in order to eliminate redundant data in the sensor data, thereby obtaining the estimation result output by the preset Kalman filter algorithm and the first error information corresponding to the estimation result.
[0048] In some examples, the aforementioned preset Kalman filter algorithm may include a general Kalman filter algorithm, an improved Kalman filter algorithm, etc., and is not specifically limited here.
[0049] S103, based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm, the neural network is invoked to determine the second error information.
[0050] In some examples, a pre-trained neural network can be used to determine the second error information based on the first error information and the Kalman filter gain. This neural network can be a trained model capable of predicting using the first error information and the Kalman filter gain as model input and the second error information as model output. During training, sample error information and its corresponding sample Kalman filter gain can be used as sample data (this sample data also carries the expected corresponding error label, which represents the corresponding expected error information). A general training algorithm (e.g., gradient descent) is then used to train the neural network, enabling it to possess the aforementioned capabilities. It is easy to understand that the sample data in this embodiment can be experimental data obtained in advance through multiple corresponding experiments (e.g., experiments identical to those used in the experimental verification provided later in this application).
[0051] In some examples, the Kalman filter gain can be achieved through the above... To express.
[0052] S104, Based on the second error information, the estimation result is corrected to obtain the fault monitoring result corresponding to the power cable according to the corrected estimation result.
[0053] In some examples, general fault monitoring algorithms can be used to obtain fault monitoring results based on the corrected estimation results. For example, general fault detection, diagnosis, or classification algorithms can be used, such as some pre-trained fault monitoring models based on machine learning. These fault monitoring models can determine the fault monitoring results based on the corrected estimation results. The fault monitoring model can be a trained model capable of predicting with the corrected estimation results as input and the fault monitoring results as output. During training, sample estimation results can be used as sample data (which also carries the expected corresponding fault label, representing the corresponding expected fault monitoring result), and a general training algorithm (such as gradient descent) can be used to train the model, so that the trained model possesses the aforementioned capabilities.
[0054] In one optional implementation, the step of determining the estimation result and the first error information corresponding to the estimation result using a preset Kalman filter algorithm based on the sensor data includes: Based on the sensor data, the state prediction equation in the time update stage of the preset Kalman filter algorithm is used to determine the expected predicted state information; for example, the state prediction equation can be the above equation (3).
[0055] Based on the sensor data and the expected predicted state information, the state estimation update equation in the measurement update stage of the preset Kalman filter algorithm is used to determine the predicted state information; for example, the state estimation update equation can be the above equation (4).
[0056] The first estimation error is determined based on the difference between the predicted state information and the expected predicted state information.
[0057] It is understood that the mathematical principle of this embodiment is obtained by transforming the above equation (4), that is, the following equation (8).
[0058] From equation (8), it can be seen that the predicted state information With expected predicted state information The difference between them can be expressed as That is, the first estimation error can be expressed as .
[0059] In one optional implementation, the estimation result is the predicted state information.
[0060] See in some examples Figure 2 The aforementioned sensors may include a first sensor 11, a second sensor 12, ..., an nth sensor 1n, etc. The aforementioned preset Kalman filter algorithm can be implemented based on multiple Kalman filters, which may include a first Kalman filter 21, a second Kalman filter 22, ..., an mth Kalman filter 2m. The sensor data collected by each sensor can be input into the corresponding Kalman filter for filtering. It can be understood that a one-to-one correspondence can be set between sensors and Kalman filters, or multiple sensors can be assigned to the same Kalman filter. Then, the output of each Kalman filter is fed into a neural network for optimization to obtain a correction amount (i.e., second error information), which is used to correct the estimation result, that is, to correct the predicted state information obtained from the state estimation update equation. In other words, the effect of updating the state estimation update equation is achieved.
[0061] In one optional implementation, the second error information includes a second estimation error, and the step of correcting the estimation result based on the second error information includes: The second estimation error is superimposed on the predicted state information to obtain the corrected estimation result.
[0062] In this embodiment, considering that the Kalman filtering algorithm requires the system model and error model to be known and that these models cannot be changed throughout the filtering process, this embodiment obtains a second estimation error between the output true value and the estimation result by using the first estimation error, measurement error and Kalman gain as inputs to the neural network. The second estimation error is then added to the estimation result to obtain an estimated value that is very close to the true value as the superposition result. A more accurate fault monitoring result is then determined based on the superposition result.
[0063] In one optional implementation, the step of determining the estimation result and the first error information corresponding to the estimation result using a preset Kalman filter algorithm based on the sensor data includes: Based on the sensor data, the state prediction equation in the time update stage of the preset Kalman filter algorithm is used to determine the expected predicted state information. Based on the expected predicted state information and the observation matrix corresponding to the preset Kalman filter algorithm, the expected observation value is determined. Based on the sensor data, the actual observed value is determined using the observation equation in the preset Kalman filter algorithm; The measurement error is determined based on the difference between the actual observed value and the expected observed value.
[0064] In some examples, the state prediction equation for this time update phase can be expressed as equation (3) above, thus the desired predicted state information can be represented as The observation matrix can be represented as described above. The expected observation can be expressed as the matrix product of the expected predicted state information and the corresponding matrices of the observation matrix, that is, expressed as... The observation equation can be expressed as equation (2) above, and thus the actual observed value can be obtained through the above equation. To represent it. Thus, in this embodiment, the measurement error can be expressed as... .
[0065] In one optional implementation, the step of determining the second error information by invoking a neural network based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm includes: The first error information and the Kalman filter gain are input into the neural network to obtain the second error information output by the neural network.
[0066] As can be seen from the above-mentioned related embodiments, see Figure 3At this point, the first estimation error can be... Kalman filter gain Measurement error The inputs are respectively fed into the neural network to obtain the second error information output by the neural network. Furthermore, the predicted state information will be used. As an estimation result, it is used in conjunction with the second error information. By superimposing these values, the final corrected estimate can be represented as T.
[0067] To better illustrate the beneficial effects of the relevant embodiments of this application, some experimental analyses are provided below for demonstration.
[0068] Experimental conditions: Inside a laboratory in a building, four positioning base stations were installed with dimensions of 10m x 40m. The base station transmission power and reception loss coefficient were both set to 10dBm. Four identical power cables were then connected to each of the four positioning base stations. The initial coordinates of the four positioning base stations were set as follows: (Here, the positioning base stations are installed in the same area, so they can be considered to be at the same coordinates within the error range.) The corresponding initial speed is set as the speed measured by the positioning base stations. Thus, the four positioning base stations can be regarded as positioning sensors for the four power cables. The data collected from the four positioning base stations are used as the positioning-related sensor data for the four power cables. (Here, since the process of damage to general power cables is difficult to simulate and poses a significant safety hazard, for the convenience of experimental design, data collection and verification, this experiment verifies the processing effect of the sensor data in this application embodiment through the accuracy of positioning analysis, which can also be applied to the accuracy analysis of general power cable fault monitoring.)
[0069] The selection of input values for the input layer in the neural network structure used in the experiment Kalman gain and It should be noted that here It is a 4-dimensional variable, i.e., coordinates. The difference between position and velocity in the direction, Kalman gain for The matrix, after transformation, becomes matrix, The input to the neural network is a 2D matrix, meaning there are 10 variables. Through a series of experiments, it was found that when the number of neurons in the output layer of the neural network is 1, the training effect is better, and the results do not diverge. It should be noted that the formula used in this embodiment for the number of hidden layers in the neural network structure is expressed as follows (9).
[0070] (9) In the formula, the parameter This represents the number of neurons in the hidden layer of a neural network, and the parameters are... This represents the number of neurons in the input layer of the neural network, and the parameters are... Indicates the number of neurons in the output layer of the neural network, parameters The value range is set to Positive integers within the range. Based on the analysis of experimental results, the number of neurons in the hidden layer of the neural network was set to 8, the number of iterations was set to 5000, and the expected error was 0.01m.
[0071] The following section describes the real-time positioning design and experimental verification using the neural network-optimized Kalman filter algorithm provided in this embodiment, along with a general Kalman filter algorithm. Simultaneously, Python programming software is used to process the collected experimental data, and the resulting real-time positioning results for each positioning base station are shown below. Figures 4-6 As shown.
[0072] exist Figure 4 In this process, a standard Kalman filter algorithm is used to process the raw data (i.e., the raw sensor data). Figure 4 The dashed line represents the original data, and the solid line represents the data after processing with a general Kalman filter algorithm. It can be seen that the original data without processing has a relatively jittery positioning trajectory, while the data processed by the Kalman filter algorithm has a smoother trajectory, although some positions still have jitter.
[0073] exist Figure 5 The images shown are sensor data processed using the neural network-optimized Kalman filter algorithm provided in the embodiments of this application and a general Kalman filter algorithm, respectively. Figure 5 The dashed line represents the data processed by the general Kalman filter algorithm, while the solid line represents the data processed by the neural network-optimized Kalman filter algorithm provided in this embodiment. It is evident that the trajectory of the data processed by the neural network-optimized Kalman filter algorithm is smoother and exhibits no significant jitter than the data processed by the general Kalman filter algorithm. Therefore, the neural network-optimized Kalman filter algorithm provided in this embodiment demonstrates better filtering performance and stronger robustness against system and observation noise.
[0074] exist Figure 6The diagram illustrates the errors between the predicted and actual positions obtained using the neural network-optimized Kalman filter algorithm provided in this application (solid lines) and the errors between the predicted and actual positions obtained using a general Kalman filter algorithm (dashed lines). It is evident that the neural network-optimized Kalman filter algorithm significantly reduces positioning errors compared to the general Kalman filter algorithm. Furthermore, in the early stages of positioning, the neural network-optimized Kalman filter algorithm effectively eliminates filtering errors and can even eliminate redundant data caused by base station failures, making the trajectory corresponding to the predicted position almost identical to the trajectory corresponding to the actual position. Therefore, the neural network-optimized Kalman filter algorithm offers higher accuracy for real-time positioning, demonstrating the superior error elimination effect of the sensor data in this application, and ultimately leading to more accurate fault monitoring results for power cables.
[0075] Secondly, correspondingly, the embodiments of this application also provide a power cable fault monitoring system, which can implement all the processes of the power cable fault monitoring method provided in the above embodiments.
[0076] See Figure 7 The diagram shows a schematic representation of a power cable fault monitoring system provided in an embodiment of this application. The power cable fault monitoring system includes: Data acquisition module 701 is used to acquire sensor data corresponding to the power cable; The first error module 702 is used to determine the estimation result and the first error information corresponding to the estimation result based on the sensor data using a preset Kalman filter algorithm, wherein the first error information includes a first estimation error and a measurement error; The second error module 703 is used to call a neural network to determine the second error information based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm. The correction and monitoring module 704 is used to correct the estimation result based on the second error information, so as to obtain the fault monitoring result corresponding to the power cable according to the corrected estimation result.
[0077] In one optional implementation, the step of determining the estimation result and the first error information corresponding to the estimation result using a preset Kalman filter algorithm based on the sensor data includes: Based on the sensor data, the state prediction equation in the time update stage of the preset Kalman filter algorithm is used to determine the expected predicted state information. Based on the sensor data and the expected predicted state information, the state estimation update equation in the measurement update stage of the preset Kalman filter algorithm is used to determine the predicted state information. The first estimation error is determined based on the difference between the predicted state information and the expected predicted state information.
[0078] In one optional implementation, the estimation result is the predicted state information.
[0079] In one optional implementation, the second error information includes a second estimation error, and the step of correcting the estimation result based on the second error information includes: The second estimation error is superimposed on the predicted state information to obtain the corrected estimation result.
[0080] In one optional implementation, the step of determining the estimation result and the first error information corresponding to the estimation result using a preset Kalman filter algorithm based on the sensor data includes: Based on the sensor data, the state prediction equation in the time update stage of the preset Kalman filter algorithm is used to determine the expected predicted state information. Based on the expected predicted state information and the observation matrix corresponding to the preset Kalman filter algorithm, the expected observation value is determined. Based on the sensor data, the actual observed value is determined using the observation equation in the preset Kalman filter algorithm; The measurement error is determined based on the difference between the actual observed value and the expected observed value.
[0081] In one optional implementation, the step of determining the second error information by invoking a neural network based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm includes: The first error information and the Kalman filter gain are input into the neural network to obtain the second error information output by the neural network.
[0082] Thirdly, embodiments of this application provide a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in any of the above-mentioned embodiments.
[0083] Fourthly, embodiments of this application provide a computer program product, including computer instructions that, when executed by a processor, implement the steps of the method described in any of the above-described embodiments.
[0084] Fifthly, embodiments of this application provide a computer device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the steps of the method described in any of the preceding claims.
[0085] See Figure 8 The computer device in this embodiment includes a processor 801, a memory 802, and a computer program stored in the memory 802 and executable on the processor 801, such as a power cable fault monitoring program. When the processor 801 executes the computer program, it implements the steps in the various power cable fault monitoring method embodiments described above, for example... Figure 1 The steps S101-S104 are shown.
[0086] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 802 and executed by the processor 801 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the computer device.
[0087] The computer device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device may include, but is not limited to, a processor 801 and a memory 802. Those skilled in the art will understand that the schematic diagram is merely an example of a computer device and does not constitute a limitation on the computer device. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the computer device may also include input / output devices, network access devices, buses, etc.
[0088] The processor 801 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or processor 801 can be any conventional processor. The processor 801 is the control center of the computer device, connecting various parts of the entire computer device through various interfaces and lines.
[0089] The memory 802 can be used to store the computer programs and / or modules. The processor 801 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 802 and calling the data stored in the memory 802. The memory 802 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 802 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0090] Wherein, if the modules / units integrated into the computer device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a non-transitory computer-readable storage medium. When the computer program is executed by the processor 801, it can implement the steps of the various method embodiments described above. Wherein, the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.
[0091] In summary, the embodiments of this application have at least the following beneficial effects: In this embodiment, sensor data corresponding to the power cable is acquired; based on the sensor data, a preset Kalman filter algorithm is used to determine the estimation result and the first error information corresponding to the estimation result, wherein the first error information includes a first estimation error and a measurement error; based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm, a neural network is invoked to determine the second error information; based on the second error information, the estimation result is corrected to obtain the fault monitoring result corresponding to the power cable. This allows for the first use of the Kalman filter algorithm to filter the sensor data to eliminate redundant data and obtain the corresponding estimation result and the first error information. Then, the neural network is used to optimize the Kalman filter based on the first error information and the Kalman filter gain, resulting in more accurate second error information, which facilitates more precise correction of the estimation result and improves the accuracy of cable fault monitoring.
[0092] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary hardware platforms, or it can be implemented entirely by hardware. Based on this understanding, all or part of the technical solutions of this application that contribute to the background technology can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.
[0093] The above description is the preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications are also considered to be within the scope of protection of this application.
Claims
1. A method for monitoring power cable faults, characterized in that, include: Acquire sensor data corresponding to the power cable; Based on the sensor data, a preset Kalman filter algorithm is used to determine the estimation result and the first error information corresponding to the estimation result, wherein the first error information includes a first estimation error and a measurement error; Based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm, the neural network is invoked to determine the second error information; Based on the second error information, the estimation result is corrected to obtain the fault monitoring result corresponding to the power cable according to the corrected estimation result.
2. The method according to claim 1, characterized in that, The step of determining the estimation result and the corresponding first error information based on the sensor data using a preset Kalman filter algorithm includes: Based on the sensor data, the state prediction equation in the time update stage of the preset Kalman filter algorithm is used to determine the expected predicted state information. Based on the sensor data and the expected predicted state information, the state estimation update equation in the measurement update stage of the preset Kalman filter algorithm is used to determine the predicted state information. The first estimation error is determined based on the difference between the predicted state information and the expected predicted state information.
3. The method according to claim 2, characterized in that, The estimation result is the predicted state information.
4. The method according to claim 3, characterized in that, The second error information includes a second estimation error, and the step of correcting the estimation result based on the second error information includes: The second estimation error is superimposed on the predicted state information to obtain the corrected estimation result.
5. The method according to claim 1, characterized in that, The step of determining the estimation result and the corresponding first error information based on the sensor data using a preset Kalman filter algorithm includes: Based on the sensor data, the state prediction equation in the time update stage of the preset Kalman filter algorithm is used to determine the expected predicted state information. Based on the expected predicted state information and the observation matrix corresponding to the preset Kalman filter algorithm, the expected observation value is determined. Based on the sensor data, the actual observed value is determined using the observation equation in the preset Kalman filter algorithm; The measurement error is determined based on the difference between the actual observed value and the expected observed value.
6. The method according to claim 1, characterized in that, The step of determining the second error information by calling a neural network based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm includes: The first error information and the Kalman filter gain are input into the neural network to obtain the second error information output by the neural network.
7. A power cable fault monitoring system, characterized in that, include: The data acquisition module is used to acquire sensor data corresponding to the power cable; The first error module is used to determine the estimation result and the first error information corresponding to the estimation result based on the sensor data using a preset Kalman filter algorithm, wherein the first error information includes a first estimation error and a measurement error; The second error module is used to call a neural network to determine the second error information based on the first error information and the Kalman filter gain corresponding to the preset Kalman filter algorithm. The correction and monitoring module is used to correct the estimation result based on the second error information, so as to obtain the fault monitoring result corresponding to the power cable according to the corrected estimation result.
8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-6.
9. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the method described in any one of claims 1-6.
10. A computer device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the method of any one of claims 1-6.