CN119695900B - Intelligent fault diagnosis and recovery method and system for coal mine power supply network - Google Patents
Intelligent fault diagnosis and recovery method and system for coal mine power supply network Download PDFInfo
- Publication number
- CN119695900B CN119695900B CN202510201632.2A CN202510201632A CN119695900B CN 119695900 B CN119695900 B CN 119695900B CN 202510201632 A CN202510201632 A CN 202510201632A CN 119695900 B CN119695900 B CN 119695900B
- Authority
- CN
- China
- Prior art keywords
- fault
- voltage
- power supply
- supply network
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the field of power supply network fault recovery, in particular to an intelligent fault diagnosis and recovery method and system for a coal mine power supply network. The method comprises the steps of obtaining fault nodes of a power supply network system, determining a priority order among the fault nodes based on the characteristics of the fault nodes, wherein the characteristics of the fault nodes comprise equipment load capacity of the fault nodes, power supply network stability contribution degree of the fault nodes and load recovery adjustment quantity of the fault nodes, and adjusting voltage of the fault nodes according to the priority order until the voltage of the power supply network system is recovered to normal voltage. According to the invention, the fault node with high recovery priority is used for driving the voltage of the peripheral area to tend to be stable, and the integral voltage deviation is reduced, so that the voltage recovery efficiency of the power supply network system is improved.
Description
Technical Field
The invention relates to the field of power supply network fault recovery, in particular to an intelligent fault diagnosis and recovery method and system for a coal mine power supply network.
Background
The power supply network is used as one of the critical infrastructures in the industrial production process, and the stability of the power supply network is directly related to the safe production and economic benefits of the industrial production. The traditional power supply network is generally composed of a transformer substation, a power transmission line, power distribution equipment and the like and is used for conveying electric energy to production links such as mining, transportation and processing. With the continuous expansion of industrial production scale, power supply networks are faced with increasingly complex operating environments and increasing load pressures. Therefore, timely diagnosis and effective recovery of power supply network faults become key for guaranteeing industrial production safety. The intelligent fault diagnosis and recovery technology relies on advanced artificial intelligence, automatic control and data analysis technologies, and by monitoring and analyzing various parameters in the power system, faults are discovered and responded in real time, so that the influence of the faults on production is reduced.
In the conventional power supply network fault diagnosis and recovery process, manual inspection, equipment monitoring and a simplified fault positioning method are generally relied on. The conventional fault diagnosis method is often based on experience rules and preset thresholds, and whether a system is faulty or not is judged through monitoring signals (such as current, voltage and the like) of equipment. Although these methods can provide a preliminary warning in some simple fault conditions, the conventional methods have problems of low diagnosis accuracy and long response time due to the variety of fault types and complexity of the power network. In addition, the traditional fault recovery mainly depends on manual operation and a preset recovery flow, and has low recovery speed and is easily influenced by manual judgment errors. Therefore, limitations of the conventional technology often lead to untimely recovery of the system when facing to a complex power grid fault, and influence continuity and safety of industrial production.
Disclosure of Invention
The invention aims to provide an intelligent fault diagnosis and recovery method and system for a coal mine power supply network, which are used for solving the problem that a power supply network fault cannot be recovered timely and efficiently in the prior art.
The embodiment of the invention provides an intelligent fault diagnosis and recovery method of a coal mine power supply network, which is applied to a power supply network system and comprises the following steps of obtaining a fault node of the power supply network system; the method comprises the steps of determining a priority order among fault nodes based on the characteristics of the fault nodes, wherein the characteristics of the fault nodes comprise equipment load capacity of the fault nodes, power supply network stability contribution degree of the fault nodes and load recovery adjustment quantity of the fault nodes, and adjusting voltage of the fault nodes according to the priority order until the voltage of a power supply network system is recovered to normal voltage.
Optionally, determining the priority order among the fault nodes based on the characteristics of the fault nodes includes obtaining a first weight coefficient corresponding to the equipment load capacity and a second weight coefficient corresponding to the power supply network stability contribution degree, calculating a first product of the first weight coefficient and the equipment load capacity, calculating a second product of the second weight coefficient and the power supply network stability contribution degree, calculating a sum of the first product and the second product to obtain a priority evaluation value, and determining the priority order among the fault nodes according to the magnitude order among the priority evaluation values.
Optionally, the determining the priority order among the fault nodes based on the characteristics of the fault nodes further comprises obtaining load recovery adjustment amounts corresponding to the fault nodes if the priority evaluation values of the fault nodes are the same, and determining the priority order among the fault nodes according to the magnitude order among the load recovery adjustment amounts.
Optionally, the obtaining the load recovery adjustment quantity corresponding to the fault node comprises obtaining the fault voltage and the normal voltage of the fault node and the maximum load recovery adjustment quantity of the fault node, calculating the difference between the fault voltage and the normal voltage according to the fault voltage and the normal voltage of the fault node, and calculating the load recovery adjustment quantity of the fault node according to the difference, the maximum load recovery adjustment quantity of the fault node and the normal voltage of the fault node;
the load recovery adjustment quantity calculation formula of the fault node is as follows:
,
Wherein, Indicating number ofIs a load restoration adjustment amount of the failed node,Indicating number ofThe maximum load recovery adjustment amount of the failed node,Indicating number ofThe difference between the fault voltage and the normal voltage of the fault node of (c),Indicating number ofIs provided, the normal voltage of the failed node of (a).
The method comprises the steps of obtaining the load recovery adjustment quantity of the fault node, adjusting the voltage of the fault node according to the priority sequence and the load recovery adjustment quantity of the fault node, obtaining the load recovery adjustment quantity of each node of the power supply network system after the voltage adjustment of the fault node, and adjusting the voltage of each node of the power supply network system according to the load recovery adjustment quantity of each node of the power supply network system so as to enable the voltage of the power supply network system to be recovered to the normal voltage.
Optionally, the method further comprises limiting the total cut load to be less than a preset cut load threshold during the recovery of the voltage of the power supply network system to the normal voltage.
Optionally, the method further comprises limiting the load shedding speed of each node of the power supply network system to be greater than a preset load shedding speed lower limit threshold value in the process of recovering the voltage of the power supply network system to the normal voltage, and limiting the load shedding speed of each node of the power supply network system to be less than a preset load shedding speed upper limit threshold value.
Optionally, the method further comprises limiting voltage fluctuation of each node of the power supply network system to be smaller than a preset fluctuation voltage threshold in the process of recovering the voltage of the power supply network system to the normal voltage.
Optionally, the acquiring the fault node of the power supply network system comprises building a fault monitoring model of each node of the power supply network system based on a convolutional neural network architecture, and monitoring each node of the power supply network system in real time by utilizing the fault detection model to obtain the fault node of the power supply network system.
Compared with the prior art, the intelligent fault diagnosis and recovery method for the coal mine power supply network has the beneficial effects that:
the intelligent fault diagnosis and recovery method for the coal mine power supply network comprises the steps of obtaining fault nodes of a power supply network system, determining priority orders among the fault nodes based on the characteristics of the fault nodes, wherein the characteristics of the fault nodes comprise equipment load capacity of the fault nodes, power supply network stability contribution degree of the fault nodes and load recovery adjustment quantity of the fault nodes, and adjusting voltage of the fault nodes according to the priority orders until the voltage of the power supply network system is recovered to normal voltage. The fault node with high priority is recovered first to drive the voltage of the peripheral area to be stable, and the integral voltage deviation is reduced, so that the voltage recovery efficiency of the power supply network system is improved.
The embodiment of the invention provides an intelligent fault diagnosis and recovery system of a coal mine power supply network, which comprises an acquisition module, a determination module and a recovery module, wherein the acquisition module is used for acquiring fault nodes of the power supply network system, the determination module is used for determining priority orders among the fault nodes based on characteristics of the fault nodes, the characteristics of the fault nodes comprise equipment load capacity of the fault nodes, power supply network stability contribution degree of the fault nodes and load recovery adjustment quantity of the fault nodes, and the recovery module is used for adjusting voltage of the fault nodes according to the priority orders until the voltage of the power supply network system is recovered to normal voltage.
The intelligent fault diagnosis and recovery system for the coal mine power supply network has the advantages that the same technical effects as those of the intelligent fault diagnosis and recovery method for the coal mine power supply network can be achieved, and repetition is avoided, so that repeated description is omitted.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent fault diagnosis and recovery method for a coal mine power supply network provided by an embodiment of the invention;
FIG. 2 is a schematic flow chart of an intelligent fault diagnosis and recovery method for a specific coal mine power supply network in an embodiment of the invention;
FIG. 3 is a schematic flow chart of a power supply network system fault intelligent diagnosis method in an embodiment of the invention;
FIG. 4 is a schematic flow chart of data acquisition and preprocessing in an embodiment of the invention;
FIG. 5 is a schematic flow chart of a method for constructing a solution platform in an embodiment of the invention;
fig. 6 is a schematic structural diagram of an intelligent fault diagnosis and recovery system for a coal mine power supply network in an embodiment of the invention.
Detailed Description
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
The embodiment of the invention provides an intelligent fault diagnosis and recovery method for a coal mine power supply network, which is applied to a power supply network system. Referring to a schematic flow chart of an intelligent fault diagnosis and recovery method for a coal mine power supply network shown in fig. 1, the method comprises the following steps:
s110, obtaining a fault node of the power supply network system.
Optionally, the step S110 includes building a fault monitoring model of each node of the power supply network system based on the convolutional neural network architecture, and monitoring each node of the power supply network system in real time by using the fault monitoring model to obtain a fault node of the power supply network system.
S120, determining the priority order among the fault nodes based on the characteristics of the fault nodes.
The characteristics of the fault node comprise equipment load capacity of the fault node, power supply network stability contribution degree of the fault node and load recovery adjustment quantity of the fault node.
Optionally, the step S120 includes obtaining a first weight coefficient corresponding to the equipment load amount and a second weight coefficient corresponding to the stability contribution degree of the power supply network, calculating a first product of the first weight coefficient and the equipment load amount, calculating a second product of the second weight coefficient and the stability contribution degree of the power supply network, calculating a sum of the first product and the second product to obtain a priority evaluation value, and determining a priority order between the fault nodes according to a magnitude order between the priority evaluation values.
Optionally, the step S120 further includes obtaining load recovery adjustment amounts of the corresponding fault nodes if the priority evaluation values of the part of the fault nodes are the same, and determining a priority order between the corresponding fault nodes according to the order of magnitude between the load recovery adjustment amounts.
It should be noted that the power supply network includes more than one path, the paths are formed by connecting nodes, one path includes a plurality of nodes, and more than one device may be connected to a node, and they together form a basic element of the power supply network, and are related and affect each other. The embodiment of the invention is described by taking the example of determining the priority among the nodes, and can be used for determining the priority among the paths/devices so as to realize the effect of further improving the recovery efficiency of the power supply network.
Optionally, the step of obtaining the load recovery adjustment amount of the corresponding fault node includes obtaining a fault voltage and a normal voltage of the fault node and a maximum load recovery adjustment amount of the fault node, calculating a difference between the fault voltage and the normal voltage according to the fault voltage and the normal voltage of the fault node, and calculating the load recovery adjustment amount of the fault node according to the difference, the maximum load recovery adjustment amount of the fault node and the normal voltage of the fault node.
The load recovery adjustment amount calculation formula of the fault node is as follows:
,
Wherein, Indicating number ofIs used for the load recovery adjustment of the fault node,Indicating number ofThe maximum load recovery adjustment amount of the failed node of (c),Indicating number ofThe difference between the fault voltage and the normal voltage of the fault node of (c),Indicating number ofNormal voltage of the failed node of (c).
The maximum load recovery adjustment amount of each faulty node is affected by the load amount of each faulty node, and may be acquired in advance. The load recovery adjustment amount calculation formula of the fault node is used for calculating the load amount to be removed in the recovery process through the voltage change amount, so that the recovered voltage level can be ensured to be recovered to a safe range.
And S130, regulating the voltage of the fault node according to the priority order until the voltage of the power supply network system is recovered to the normal voltage.
The higher the priority, the higher the voltage adjustment is performed by the failure node.
Optionally, the step S130 includes obtaining a load recovery adjustment amount of the fault node, adjusting a voltage of the fault node according to the priority order and the load recovery adjustment amount of the fault node, obtaining a load recovery adjustment amount of each node of the power supply network system after the voltage adjustment of the fault node, and adjusting a voltage of each node of the power supply network system according to the load recovery adjustment amount of each node of the power supply network system so as to restore the voltage of the power supply network system to a normal voltage. Therefore, the fault nodes with high recovery priority are recovered first, the voltage of the peripheral area is driven to be stable, serious voltage fluctuation caused by the fault nodes with high recovery priority is avoided when other nodes in the peripheral area regulate the voltage, the problem of repeated regulation of other nodes in the peripheral area is avoided, the supply and demand relation of a power grid can be balanced faster through the reasonable load shedding operation, the voltage is stabilized, the voltage difference value is developed towards the direction of reducing, and the voltage of a power supply network system is recovered to the normal voltage as soon as possible.
Optionally, the method further comprises limiting the total cut load to be smaller than a preset cut load threshold value in the process of recovering the voltage of the power supply network system to the normal voltage.
The load shedding total amount is the load amount actually shed in the process of recovering the voltage of the power supply network system, the load recovery adjustment amount of the fault node is the load amount which is calculated by the load recovery adjustment amount calculation formula of the fault node and is preset to be shed, and the load recovery adjustment amount of each fault node can be used as a reference of the load amount actually shed by each fault node.
Optionally, the method further comprises the step of limiting the load shedding speed of each node of the power supply network system to be larger than a preset load shedding speed lower limit threshold value in the process of recovering the voltage of the power supply network system to the normal voltage, and limiting the load shedding speed of each node of the power supply network system to be smaller than a preset load shedding speed upper limit threshold value.
Optionally, the method further comprises limiting voltage fluctuation of each node of the power supply network system to be smaller than a preset fluctuation voltage threshold in the process of recovering the voltage of the power supply network system to the normal voltage.
The intelligent fault diagnosis and recovery method for the coal mine power supply network comprises the steps of obtaining fault nodes of a power supply network system, determining priority orders among the fault nodes based on characteristics of the fault nodes, and adjusting voltages of the fault nodes according to the priority orders until the voltages of the power supply network system are recovered to normal voltages. The fault nodes with high recovery priority are recovered first to drive the voltage of the peripheral area to be stable, and the overall voltage deviation is reduced.
The embodiment of the invention also provides an intelligent fault diagnosis and recovery method for the specific coal mine power supply network. Referring to a schematic flow chart of a method for intelligent fault diagnosis and recovery of a specific coal mine power supply network shown in fig. 2, the method comprises the following steps:
S202, collecting system voltage and current data and preprocessing.
The preprocessing comprises data acquisition, A/D conversion, filtering and normalization.
S204, constructing input data features of the convolutional neural network model.
S206, constructing a convolutional neural network model.
S208, model training stage.
The convolutional neural network-based network model is trained to have the ability to recognize input features according to steps S202-S206.
S210, model testing stage.
And (3) testing the convolutional neural network model constructed in the steps S202-S208, taking a test set as input, and comparing the output result of the network model with the fault marked by the expert.
S212, applying the model with accurate testing to actual engineering.
And (3) applying the accurate test model constructed in the step S210 to actual engineering.
S214, constructing a fault recovery scheme based on voltage reconstruction.
S216, constructing a solving platform of an optimization objective function of a model solving fault recovery scheme.
S218, calculating the solving platform.
Calculating a solution platform constructed in the step S216;
S210, screening and comparing the calculation results, and selecting an optimal recovery path to implement a fault recovery scheme.
The intelligent fault diagnosis and recovery method for the specific coal mine power supply network realizes intelligent diagnosis and efficient recovery of the coal mine power supply network fault by introducing advanced convolutional neural network (Convolutional Neural Networks, CNN) and voltage reconstruction technology. Compared with the traditional fault diagnosis method relying on manual and experience rules, the scheme can rapidly and accurately identify and locate various types of faults, particularly complex multiple fault conditions, and effectively improves the accuracy and response speed of fault detection. Meanwhile, the fault recovery model based on voltage reconstruction not only optimizes the selection of recovery paths, but also dynamically adjusts the recovery strategy through an intelligent algorithm, thereby ensuring the safety and the high efficiency of the fault recovery process. The technical scheme provided by the embodiment of the invention greatly shortens the fault processing time, avoids delay or improper recovery caused by manual operation errors, ensures the continuity and stability of the coal mine power supply system, and provides powerful guarantee for safe operation of coal mine production. Meanwhile, the intelligent technical means enables the fault recovery of the system to be automatically completed, greatly reduces the dependence on manual intervention, and improves the whole automation level and intelligent management capacity of the coal mine power supply network.
The embodiment of the invention also provides an intelligent diagnosis method for the faults of the power supply network system. Referring to fig. 3, a schematic flow chart of a fault intelligent diagnosis method for a power supply network system is shown. The intelligent fault diagnosis method for the power supply network system comprises the following steps:
And step S302, collecting voltage and current data of a power supply network system and preprocessing the voltage and current data.
It should be noted that the preprocessing includes data acquisition and a/D conversion, filtering, and normalization.
In the data acquisition stage, the intelligent electric energy meter is used for real-time data acquisition, and the sampling frequency is set to be 500Hz, so that accurate capture of voltage and current data of high-frequency change can be ensured. See a schematic flow chart of data acquisition and preprocessing shown in fig. 4. The acquired data is first a/D converted from an analog signal to a digital signal. The data is then frequency domain analyzed using a fourier transform. The fourier transform can transform the time domain signal into a frequency domain signal, so that the frequency component is explicitly expressed, and further filtering and feature extraction are facilitated. The fourier transform formula is as follows:
,
Wherein, Representing the frequency domain signal after the fourier transform,Is a signal in the time domain and,Is the frequency. The result after fourier transformation can be used to analyze the frequency content of the signal, filtering out high frequency noise or extraneous signals, thereby enhancing the reliability of the data. After filtering, a normalization process is performed to scale all data to a uniform range (typically 0 to 1). The normalized data generates data samples, which provide standardized inputs for subsequent model training.
And step S304, based on the voltage and current data, constructing the input data characteristics of the convolutional neural network model.
Illustratively, in constructing the input data features of the convolutional neural network, expert judgment is first performed on the normalized data. And the expert judges that the fault and non-fault characteristics are marked by analyzing the change trend, the frequency distribution and the like of the data. The data is then partitioned into a plurality of small segments, ensuring that each segment of data contains sufficient information for subsequent learning. And marking data for each piece of data to indicate whether a fault occurs or not or the type of the fault. Then, a database is established, and the marked data are stored according to the category.
After the marking and the segmentation of the data are completed, a sample dividing stage is entered. The data samples are divided into training data sets, test data sets and validation data sets according to a certain ratio (e.g., 6:2:2). The training data set is used for model training, the test data set is used for model evaluation, and the verification data set is used for tuning and preventing overfitting during training. In addition, to ensure that convolutional neural networks can learn the features in the data better, training, testing and validation rules need to be formulated, including selection of loss functions, setting of optimization algorithms (e.g., adam or SGD), and evaluation metrics (e.g., accuracy, F1 values, etc.).
And step S306, constructing a convolutional neural network model.
Illustratively, in building a convolutional neural network model, a convolutional layer structure needs to be built first. In the node number setting of the input layer and the output layer of the convolutional neural network, the node numbers of the input layer and the output layer need to be reasonably set according to the dimension and the category number of the actual data. The number of nodes of the input layer is determined by the characteristic dimension of the data, and if each data sample contains a plurality of voltage and current data channels (e.g. current, sampling points of the voltage), the number of nodes of the input layer is the total dimension number of the data. The number of nodes of the output layer is determined by the number of fault classifications, and if the fault types are classified into two types of fault and non-fault, the number of nodes of the output layer is 2.
The setting of the convolution layers requires the number and size of convolution kernels to be calculated according to an empirical formula. Assuming that the number of convolution kernels is defined by the number of input layer nodesNumber of output layer nodesInput range of activation functionAnd output rangeThe relationship between them. The formula is as follows:
, (1)
Wherein, For the number of convolution kernels,Is a constant between 0 and 9, usually adjusted experimentally,Is the number of nodes in the input layer,Is the number of nodes in the output layer,Is the input range of the activation function,Is the output range of the activation function. The formula can reasonably estimate the number and the size of the convolution kernels according to the actual data scale, so that the design of a convolution layer is optimized.
The convolution layer extracts local features in the data by a convolution operation. The convolution operation can be expressed by the following formula:
,
Wherein, The input data is represented by a representation of the input data,Is a convolution kernel which is a convolution kernel,Is the convolved output. The convolution layer is used for extracting local features in input data through the sliding convolution kernel and outputting a feature map.
A pooling layer structure is then built, typically employing maximum pooling or average pooling, aimed at reducing dimensions and computational complexity, while preserving important features in the data. The pooling layer simplifies the data by selecting the maximum or average value within the region.
It should be noted that the above-mentioned pooling layer structure is explained as that the pooling layer is used to reduce the dimension of the output feature map of the convolution layer, while retaining the important features. The calculation of the step size and feature map size of the pooling is critical to the design of the pooling layer. The pooling step size is generally determined by the number of samples in the training set and the validation set, and a larger step size may accelerate the training process, but may lose some detail information. The size of each dimension feature map after pooling is calculated using the following formula:
,
Wherein, Is the characteristic diagram size after pooling,Is the feature map size before pooling,Is the size of the pooling window and,Is the step size. The pooling operation reduces the computational complexity by reducing the dimension of each feature map, and simultaneously enables the convolutional neural network to have better fault tolerance and to be capable of generating stronger robustness for small amplitude changes of input data.
In designing the pooling layer, it is also necessary to calculate the reduction in the number of feature maps after pooling, and the reduced number of features is usually determined by calculating the pooling result of each dimension, so as to ensure that too many valuable features are not lost in the process of dimension reduction.
By the method, the convolutional neural network not only can effectively diagnose faults in the coal mine power supply network, but also can provide accurate data support for subsequent fault recovery.
A Dropout layer structure is then built for preventing the neural network from overfitting. In the training process, the Dropout layer can randomly discard neurons, so that the network structure of each training is different, and the generalization capability of the model is enhanced.
And then, establishing a full-connection layer structure for integrating the extracted features, and finally generating final output through a prediction layer, wherein the output is the fault type or the prediction probability of the fault. Each layer is activated by a nonlinear activation function (e.g., reLU or Sigmoid) so that the network has sufficient expressive power.
In the final construction of the model, the layers are connected in sequence to form a complete convolutional neural network structure, so that fault characteristics can be effectively learned from input data, and accurate fault diagnosis can be made.
For example, it is assumed that in a coal mine power supply network, the collected current data fluctuates significantly when a fault occurs. In the data acquisition stage, the captured data is converted into a frequency domain signal through Fourier transformation by using the sampling frequency of 500Hz, and noise with higher frequency is filtered out. After normalization processing, the generated data samples are used for constructing the input features of the convolutional neural network model. It is assumed that certain characteristics of the piece of data (such as abrupt current value, specific frequency components in the frequency domain) are found to be highly correlated with the fault by expert judgment. In the model training stage, by learning a large number of data samples, the convolutional neural network can automatically extract the characteristics, train according to the labeling result and finally generate a network model capable of accurately diagnosing whether current fluctuation is caused by faults. Through testing and verification, the model can accurately identify faults and classify the faults, so that decision support is provided for a subsequent fault recovery scheme.
And step 308, training based on a network model of the convolutional neural network.
Illustratively, a convolutional neural network-based network model is trained to have the ability to recognize input features. The convolutional neural network training stage is the core of convolutional neural network model optimization, and proper training period and maximum iteration times are set to be critical to training effect. In the embodiment of the invention, the training period is set to 4000 times, the maximum iteration number of the training set is 2000 times, the maximum iteration number of the verification set is set to 4000 times, and the network learning rate is set to 0.001. The learning rate controls the step length of each parameter update, a smaller learning rate is helpful for fine adjustment of model parameters, but training time is increased, and a larger learning rate accelerates convergence, but may result in missing the optimal solution. Therefore, selecting an appropriate learning rate has an important influence on the convergence speed and the final effect of the model.
In the training process, a mode of randomly initializing model parameters is adopted to avoid sinking into a local optimal solution. The samples in the training set will be used repeatedly to train the convolutional neural network until a set maximum number of iterations is reached. And at the end of each iteration period, calculating performance indexes (such as accuracy, loss value and the like) of the model through the verification set, adjusting model parameters according to the result of the verification set, preventing over-fitting, and ensuring the generalization capability of the model on new data.
And step S310, testing and optimizing the constructed convolutional neural network model.
Illustratively, the network model output is compared to the expert-labeled fault with the test set as input, and the network model is optimized until the network model output is consistent with the expert-labeled fault.
And step S312, the constructed accurate test model is applied to actual engineering.
Illustratively, it is assumed that in fault diagnosis of a coal mine power supply network, input data includes a plurality of voltage and current channels, each channel collects 1000 sampling points, and the data dimension is 1000. Therefore, the number of nodes of the input layer is 1000. In the case where the failure type is two types, the number of nodes of the output layer is 2. By applying the above empirical formula, the number of convolution kernels of the convolution layer can be calculated. For example, assume that the constants in the above formula (1)The number of nodes of the input layer is 1000, the number of nodes of the output layer is 2, the input range of the activation function is-1 to 1, the output range is 0 to 1, and the number of convolution kernels is calculated by substituting the formula.
Meanwhile, when dimension reduction is carried out on the feature images through the pooling layer, the size of a pooling window is set to be 2, the step length is set to be 2, and if the size of the feature images before pooling is set to be 28 multiplied by 28, the size of the feature images in each dimension after pooling is set to be 14 multiplied by 14, and the number of the feature images is correspondingly reduced, so that calculation is accelerated and memory occupation is reduced.
In addition, the constructed accurate test model is applied to actual engineering in such a way that a sample set related to faults is generated in the steps of data acquisition and preprocessing according to the actual power supply network system state, so that basic data is provided for subsequent fault diagnosis and recovery. In the process, the generation of the fault sample set is based on the dynamic change of voltage and current data, and the power grid state is trained through a convolutional neural network to obtain key features capable of reflecting the system state. Next, the trained convolutional neural network model is used to input the network node set S1, and the abnormal probability and the fault category of the node are output to obtain the node set S2. The calculation of the network node set S2 lays a foundation for subsequent node classification. Specifically, the convolutional neural network model can output an anomaly probability for each node by processing the input features, and typically, a node having a probability exceeding 70% is selected as an anomaly node. And traversing the nodes according to a depth-first search (DEPTH FIRST SEARCH, DFS) algorithm for the nodes predicted to be abnormal to obtain a node set adjacent to the abnormal nodes, and further classifying the adjacent nodes according to the category predicted by the convolutional neural network to obtain a normal node set S3 and an abnormal node set S4. The key of the step is that the influence range of the abnormal nodes is effectively expanded by combining the network topological relation and the adjacent relation among the nodes, and the area influenced by the faults is comprehensively estimated.
Alternatively, the convolutional neural network prediction category is assumed to be two categories, namely a current overload fault and a voltage sag fault. After performing DFS traversal on the node a predicted to be abnormal to obtain the adjacent node B, C, D, if the voltage and current data of the node B are analyzed to be highly similar to the characteristic data of the current overload fault (for example, the current value is continuously higher than a normal threshold by a certain proportion and the fluctuation is severe), and are matched with the sample data pattern of the current overload fault during convolutional neural network training, the node B is classified into an abnormal node set S4, if the voltage and current data of the node C are relatively stable and within a normal range and accord with the characteristic of normal operation, the node C is classified into a normal node set S3, and if the voltage data of the node D is temporarily and slightly dropped but quickly recovered and the overall trend is close to normal, and is not consistent with the severity standard of the voltage drop fault, the node D is also classified into the normal node set S3.
The embodiment of the invention also provides a method for constructing a solving platform, referring to a schematic flow chart of the method for constructing the solving platform shown in fig. 5, the method for constructing the solving platform comprises the following steps:
step S502, a voltage reconstruction objective function is established, and a voltage reconstruction recovery model is established.
The goal of the voltage reconstruction is to restore the power supply network to a voltage state close to that before the fault as soon as possible after the fault has occurred. Assume that the voltage of the power supply network after failure isAnd the voltage when no fault occurs isThe goal of the voltage reconstruction is to minimize the voltage deviation, i.e. to allow each device to revert to its normal voltage state. The objective function may be expressed as:
,
Wherein, Is the voltage after the failure has occurred,Is the voltage before the occurrence of the fault,Is the total number of devices. The objective function is to perform voltage reconstruction by minimizing voltage deviation to ensure that the voltage level of the power supply network is restored to a normal state.
And step S504, setting constraint conditions corresponding to the voltage reconstruction recovery model, and finishing building a solution platform.
The device recovery priority, the safe operation constraint, the cut load total constraint and the cut load speed constraint are all closely related to the voltage difference.
Illustratively, device recovery priority calculation formula isWhereinIs the amount of load of the device,Is the degree of contribution of the device to the stability of the system,AndIs a weight factor. In practical application, the load capacity and the system stability contribution degree of different devices are monitored and evaluated, and weight factors are reasonably set according to the type, importance and fault influence degree of the devicesAndObtaining a priority evaluation valueThereby determining a restoration priority for each device. In the fault recovery process, preference is given toThe recovery of the equipment with high value can influence the selection and recovery sequence of the recovery path, so that the efficiency and the system stability of the whole recovery process are influenced, and parameters in the relation functions such as voltage reconstruction and the like are indirectly optimized.
The determination of the device recovery priority can influence the sequence of device recovery, and further influence the recovery speed and path of the voltage. Devices with higher recovery priorities recover earlier, and their voltages approach the normal voltages faster, thereby reducing overall voltage bias. For example, the key equipment is firstly restored to operate due to the high priority, and can drive the voltage of the peripheral area to be stable, so that the voltage difference of the whole network is developed towards the direction of reduction.
Illustratively, the safe operation constraint is, for example, a voltageWhereinIs the voltage during the recovery process and,Is the normal operating voltage of the device,Is a preset ripple voltage threshold. During the fault recovery process, the voltage is monitored to ensure that the constraint condition is always met. If the voltage approaches or exceeds the constraint range, the system adjusts the recovery strategy, such as adjusting the cut load or recovery path, to ensure that the voltage stabilizes within a safe range. The method directly limits the variation range of the voltage, ensures that the voltage deviation calculation in the voltage reconstruction objective function is more reasonable, avoids the unstable system caused by excessive voltage fluctuation, optimizes the parameter selection of the whole recovery process, ensures that the recovery process is carried out towards a stable and safe direction, avoids the equipment damage or new faults caused by the voltage fluctuation, ensures the safe and stable operation of the power grid, indirectly influences the variation of other parameters related to the voltage in a reasonable range, and promotes the integral recovery of the system.
During the fault recovery process, the voltage is monitored to ensure that the constraint condition is always met. If the voltage is close to or exceeds the constraint range, the system can adjust the recovery strategy, for example, adjust the cut load or the recovery path to ensure that the voltage is stable within the safety range, avoid causing new faults or equipment damage due to overlarge voltage fluctuation, and further ensure the safety of the voltage reconstruction process.
Illustratively, the cut load total constraint is expressed asWhereinIs an apparatusThe amount of load that needs to be cut down,In order to cut the total amount of load,Is a preset cut load total threshold. In the fault recovery process, the cut load quantity is calculated according to the real-time state of the power grid, the voltage reconstruction and other requirementsAnd ensure that the sum does not exceed. When the load is needed to be cut, the system comprehensively considers the conditions of all the devices and the overall load reduction requirement, and reasonably distributes the cut load. This constraint limits the total amount of load shedding, avoids excessive instability of the system due to excessive load shedding, and also affects the voltage and current distribution. By controlling the total load shedding amount, the power grid can maintain certain load balance in the recovery process, so that the voltage is stabilized, parameters in a voltage reconstruction objective function and other related functions are optimized, the effectiveness and stability of the recovery process are ensured, and the system is gradually recovered to normal operation under a stable load condition.
Cut load speed constraint, cut load speed constraint is set asWhereinIs the firstThe load shedding speed of the strip bus bar,AndThe minimum and maximum allowable cut load speeds, respectively. In the fault recovery process, the cut load speed is monitored and controlled in real time, so that the cut load speed meets the constraint condition. The excessive load shedding speed can cause severe fluctuation of system voltage and frequency to cause unstable system, and the excessive load shedding speed can not timely relieve the power grid pressure to influence the recovery effect. The system can be stably transited by reasonably controlling the load shedding speed, and adverse effects on the stability of the power grid caused by too fast or too slow load adjustment are avoided, so that parameters in the recovery process are optimized, the parameters such as voltage and tide are ensured to be in a reasonable dynamic change range, efficient and stable fault recovery is facilitated, safe operation of the power grid is ensured, a stable operation environment is provided for the processes such as voltage reconstruction and the like, and optimization of related function parameters is facilitated.
During fault recovery, the system can reasonably distribute load shedding amount according to the real-time state of the power grid, and the system is prevented from being excessively unstable due to excessive load shedding. The reasonable load shedding operation can balance the supply and demand relation of the power grid, stabilize the voltage and enable the voltage difference to develop towards the direction of reduction. The load shedding speed is controlled to enable the system to be in stable transition, adverse effects on the stability of the power grid due to too fast or too slow load adjustment are avoided, voltage stabilization is facilitated, voltage difference is reduced, optimization of a voltage reconstruction objective function is achieved, the power grid is enabled to be restored to a voltage state close to that before a fault as soon as possible, and stable operation of the coal mine power supply network is guaranteed.
Illustratively, flow constraints, are critical to controlling voltage and load flow direction in the grid. The load flow constraint comprises voltage constraint, line load flow constraint, generator load flow constraint and load flow constraint.
Taking the line load flow constraint as an example here, the generator load flow constraint and the load flow constraint are similar to each other. The line flow constraint reflects that the admittance matrix of the line changes after the fault occurs. Let the line admittance matrix before failure beAnd the line admittance matrix after failure isThe difference in line flow can be expressed as:
,
Here the number of the elements is the number, Representing the line admittance matrix before the fault,Representing the line admittance matrix after the fault,The difference between the two is indicative of a change in line admittance due to the fault. By adjusting the line flow constraint, the overload or unstable condition of the line can be effectively avoided.
After the solving platform is solved, the nodes which need to be processed preferentially in the recovery process can be determined, so that the influence of faults on the power grid is reduced. The recovery amount of each node is based on a voltage constraint, and the maximum value of the recovery amount can be calculated by the following formula:
,
Wherein, Represents the total load recovery adjustment amount of the power supply network system,In order to cut the total number of nodes for load recovery,Representing the load recovery adjustment amount for each node. The key point in the screening process is to select the node with the strongest recovery capacity and maximize the recovery efficiency of the power grid on the basis of the node.
Reconstructing an objective function at a voltageIn the process, Is a device after failureIs used for the voltage of the (c) transformer,Is the equipment before the fault occursIs aimed at minimizing this voltage deviation. The device recovery priority, the safe operation constraint, the cut load total constraint and the cut load speed constraint are all closely related to the voltage difference. The determination of the device recovery priority can influence the sequence of device recovery, and further influence the recovery speed and path of the voltage. Devices with higher recovery priorities recover earlier, and their voltages approach the normal voltages faster, thereby reducing overall voltage bias. The safety operation constraint directly limits the allowable range of the voltage difference value, ensures that the voltage cannot deviate from the normal range excessively in the recovery process, avoids new faults or equipment damage caused by overlarge voltage fluctuation, and ensures the safety of the voltage reconstruction process. The cut-load total amount constraint and the cut-load speed constraint indirectly affect the voltage difference by adjusting the load. The reasonable load shedding operation can balance the supply and demand relation of the power grid, stabilize the voltage, enable the voltage difference to develop towards a direction of reduction, be beneficial to realizing the optimization of the voltage reconstruction objective function, enable the power grid to recover to a voltage state close to the state before the fault as soon as possible, and ensure the stable operation of the coal mine power supply network.
The intelligent fault diagnosis and recovery method for the specific coal mine power supply network provided by the embodiment of the invention realizes the efficient diagnosis, accurate recovery and safety guarantee of the coal mine power supply network when faults occur by relying on an advanced convolutional neural network technology and a voltage reconstruction fault recovery scheme. The method provided by the embodiment of the invention not only improves the precision of fault identification and recovery, but also obviously improves the stability and reliability of the power grid through a plurality of innovative steps and optimization algorithms. The beneficial effects are mainly shown in the following aspects:
efficient fault diagnosis and classification
The method provided by the embodiment of the invention adopts the convolutional neural network to carry out fault diagnosis, and can rapidly and accurately identify the fault node in the coal mine power supply network through the accurate processing of the voltage and current data. Compared with the traditional fault detection method, the convolutional neural network can automatically learn key features in the network, so that interference of human factors is reduced, and accuracy and instantaneity of fault diagnosis are improved. Particularly, when facing complex and dynamically-changing power grid states, the convolutional neural network model can flexibly adapt to different types of faults, and high-quality data support is provided for subsequent recovery decisions.
Innovative application of voltage reconstruction fault recovery scheme
The method provided by the embodiment of the invention enables the embodiment of the invention to dynamically adjust the recovery strategy according to the current state of the power grid and the specific situation of the fault node by constructing the fault recovery model based on the voltage reconstruction. The voltage reconstruction objective function not only considers the accuracy of the recovery voltage, but also introduces a plurality of factors such as equipment recovery priority, safe operation constraint and the like, and ensures the safety and stability in the recovery process. In particular, by setting the total load shedding amount and the load shedding speed constraint, the secondary faults caused by overload or too fast recovery are avoided in the recovery process, and the normal operation of power grid equipment and a power supply system is effectively protected.
Adaptive restoration path optimization
The method provided by the embodiment of the invention introduces a solving platform based on an optimization objective function in the fault recovery process, and utilizes multiple constraint conditions to perform optimization calculation of the recovery path. By comprehensively considering factors such as voltage, load flow constraint, load shedding speed and the like, the embodiment of the invention can select the optimal recovery path in the complex power grid. The optimization strategy not only reduces the recovery time, but also avoids the instability and load fluctuation of the system to the greatest extent, and improves the efficiency and accuracy of power grid recovery.
Intelligent decision-making in fault recovery process
According to the method provided by the embodiment of the invention, the depth-first search algorithm is introduced in the recovery process, so that the embodiment of the invention can automatically judge the relative positions of the abnormal nodes and the normal nodes and the voltage average value thereof according to the topological relation among the nodes when the fault occurs, and preferentially recover the nodes with the voltage lower than the safety voltage. The scientificity and the high efficiency of the system recovery are ensured by combining the voltage average value calculation and the load shedding speed optimization, so that the accurate control and the intelligent decision in the system recovery process are realized.
Enhanced system stability and reliability
Because the embodiment of the invention adopts a comprehensive fault diagnosis and recovery method and carries out quantitative analysis and optimization on each link in the recovery process, the embodiment of the invention can ensure that the coal mine power supply network can quickly and accurately recover normal operation after faults occur. The method reduces the influence of faults on the coal mine power supply system, reduces the power failure time, avoids the chain reaction caused by fault spreading, and enhances the overall stability and reliability of the power grid.
Saving manual intervention and improving automation level
The method provided by the embodiment of the invention realizes the high intellectualization of fault diagnosis and recovery process through the automatic integration of the data acquisition, the convolutional neural network model, the optimization algorithm and the fault recovery model. Compared with the traditional manual intervention mode, the embodiment of the invention reduces the manual operation intervention, improves the working efficiency, enables the coal mine power supply network to recover itself under the condition of no manual intervention, greatly improves the automation level and reduces the risk of human errors.
The adaptability is strong, and the complex power grid environment can be dealt with
The method provided by the embodiment of the invention has strong adaptability and can cope with coal mine power supply networks with different scales and complexity. Through the deep learning capability of the convolutional neural network, the embodiment of the invention can automatically adjust the fault diagnosis model and the recovery strategy according to the actual condition of the power grid, thereby adapting to challenges of different equipment and different fault types in the coal mine power supply network. Whether the voltage fluctuation, equipment fault, line short circuit and other fault conditions exist, the device can be quickly and accurately identified and recovered.
Improving the safety production guarantee capability of coal mine
The method provided by the embodiment of the invention can greatly reduce the safety risk caused by the fault of the coal mine power supply network and improve the safety production and guarantee capacity of the coal mine through rapid and accurate fault diagnosis and recovery. When faults occur, the power system can be restored to a normal running state as soon as possible, continuous and stable power support is provided for the production process of the coal mine, and the method is beneficial to improving the production efficiency of the coal mine and guaranteeing the safety of the working environment of miners.
In summary, by adopting the innovative intelligent fault diagnosis and recovery method, the fault response speed and recovery efficiency of the coal mine power supply network are remarkably improved, the stable operation of the power network is effectively ensured, and powerful technical support is provided for the safe production of the coal mine.
The embodiment of the invention provides an intelligent fault diagnosis and recovery system for a coal mine power supply network. Referring to fig. 6, a schematic structural diagram of an intelligent fault diagnosis and recovery system for a coal mine power supply network, the system includes:
An obtaining module 602, configured to obtain a fault node of the power supply network system.
A determining module 604, configured to determine a priority order between the failed nodes based on the characteristics of the failed nodes.
The characteristics of the fault node comprise equipment load capacity of the fault node, power supply network stability contribution degree of the fault node and load recovery adjustment quantity of the fault node.
And the recovery module 606 is configured to adjust the voltage of the fault node according to the priority order until the voltage of the power supply network system recovers to the normal voltage.
The intelligent fault diagnosis and recovery system for the coal mine power supply network has the advantages that the same technical effects as those of the intelligent fault diagnosis and recovery method for the coal mine power supply network can be achieved, and repetition is avoided, so that repeated description is omitted.
Of course, it will be appreciated by those skilled in the art that implementing all or part of the above-described methods in the embodiments may be implemented by a computer level to instruct a control device, where the program may be stored in a computer readable storage medium, and the program may include the above-described methods in the embodiments when executed, where the storage medium may be a memory, a magnetic disk, an optical disk, or the like.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention, and the scope of the invention should be assessed accordingly to that of the appended claims.
Claims (8)
1. An intelligent fault diagnosis and recovery method for a coal mine power supply network is characterized by being applied to a power supply network system, and comprises the following steps:
Acquiring a fault node of the power supply network system;
Determining a priority order among the fault nodes based on the characteristics of the fault nodes, wherein the characteristics of the fault nodes comprise equipment load capacity of the fault nodes, power supply network stability contribution degree of the fault nodes and load recovery adjustment quantity of the fault nodes;
Adjusting the voltage of the fault node according to the priority order until the voltage of the power supply network system is recovered to the normal voltage;
the determining the priority order between the fault nodes based on the characteristics of the fault nodes comprises the following steps:
Acquiring a first weight coefficient corresponding to the equipment load capacity and a second weight coefficient corresponding to the stability contribution degree of the power supply network;
Calculating a first product of the first weight coefficient and the equipment load capacity, calculating a second product of the second weight coefficient and the stability contribution degree of the power supply network, and calculating the sum of the first product and the second product to obtain a priority evaluation value;
determining the priority order among the fault nodes according to the order of magnitude among the priority evaluation values;
the determining the priority order between the fault nodes based on the characteristics of the fault nodes further comprises:
if the priority evaluation values of the part of the fault nodes are the same, acquiring a load recovery adjustment quantity corresponding to the fault nodes;
And determining the priority order among the corresponding fault nodes according to the magnitude order among the load recovery adjustment amounts.
2. The method of claim 1, wherein the obtaining the load recovery adjustment amount corresponding to the failed node comprises:
Acquiring fault voltage and normal voltage of the fault node and maximum load recovery adjustment quantity of the fault node;
Calculating a difference value between the fault voltage and the normal voltage according to the fault voltage and the normal voltage of the fault node;
Calculating the load recovery adjustment quantity of the fault node according to the difference value, the maximum load recovery adjustment quantity of the fault node and the normal voltage of the fault node;
the load recovery adjustment quantity calculation formula of the fault node is as follows:
,
Wherein, Indicating number ofIs a load restoration adjustment amount of the failed node,Indicating number ofThe maximum load recovery adjustment amount of the failed node,Indicating number ofThe difference between the fault voltage and the normal voltage of the fault node of (c),Indicating number ofIs provided, the normal voltage of the failed node of (a).
3. The method of claim 1, wherein said adjusting the voltage of the failed node in the order of priority until the voltage of the power supply network system returns to a normal voltage comprises:
Acquiring the load recovery adjustment quantity of the fault node;
according to the priority order and the load recovery adjustment quantity of the fault node, adjusting the voltage of the fault node;
acquiring the load recovery adjustment quantity of each node of the power supply network system after the voltage adjustment of the fault node;
and adjusting the voltage of each node of the power supply network system according to the load recovery adjustment quantity of each node of the power supply network system so as to enable the voltage of the power supply network system to recover to the normal voltage.
4. A method according to claim 3, characterized in that the method further comprises:
And limiting the total cut load amount to be smaller than a preset cut load amount threshold value in the process that the voltage of the power supply network system is recovered to the normal voltage.
5. A method according to claim 3, characterized in that the method further comprises:
and limiting the load shedding speed of each node of the power supply network system to be larger than a preset load shedding speed lower limit threshold value in the process of recovering the voltage of the power supply network system to the normal voltage, and limiting the load shedding speed of each node of the power supply network system to be smaller than a preset load shedding speed upper limit threshold value.
6. A method according to claim 3, characterized in that the method further comprises:
And limiting the voltage fluctuation of each node of the power supply network system to be smaller than a preset fluctuation voltage threshold in the process of recovering the voltage of the power supply network system to the normal voltage.
7. The method of claim 1, wherein the acquiring the failed node of the power supply network system comprises:
Based on a convolutional neural network architecture, establishing a fault monitoring model of each node of the power supply network system;
And monitoring all nodes of the power supply network system in real time by using the fault detection model to obtain fault nodes of the power supply network system.
8. An intelligent fault diagnosis and recovery system for a coal mine power supply network, the system comprising:
the acquisition module is used for acquiring a fault node of the power supply network system;
The system comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining the priority order among the fault nodes based on the characteristics of the fault nodes, wherein the characteristics of the fault nodes comprise equipment load capacity of the fault nodes, power supply network stability contribution degree of the fault nodes and load recovery adjustment quantity of the fault nodes;
The recovery module is used for adjusting the voltage of the fault node according to the priority order until the voltage of the power supply network system is recovered to the normal voltage;
the determining the priority order between the fault nodes based on the characteristics of the fault nodes comprises the following steps:
Acquiring a first weight coefficient corresponding to the equipment load capacity and a second weight coefficient corresponding to the stability contribution degree of the power supply network;
Calculating a first product of the first weight coefficient and the equipment load capacity, calculating a second product of the second weight coefficient and the stability contribution degree of the power supply network, and calculating the sum of the first product and the second product to obtain a priority evaluation value;
determining the priority order among the fault nodes according to the order of magnitude among the priority evaluation values;
the determining the priority order between the fault nodes based on the characteristics of the fault nodes further comprises:
if the priority evaluation values of the part of the fault nodes are the same, acquiring a load recovery adjustment quantity corresponding to the fault nodes;
And determining the priority order among the corresponding fault nodes according to the magnitude order among the load recovery adjustment amounts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510201632.2A CN119695900B (en) | 2025-02-24 | 2025-02-24 | Intelligent fault diagnosis and recovery method and system for coal mine power supply network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510201632.2A CN119695900B (en) | 2025-02-24 | 2025-02-24 | Intelligent fault diagnosis and recovery method and system for coal mine power supply network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119695900A CN119695900A (en) | 2025-03-25 |
| CN119695900B true CN119695900B (en) | 2025-05-06 |
Family
ID=95033514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510201632.2A Active CN119695900B (en) | 2025-02-24 | 2025-02-24 | Intelligent fault diagnosis and recovery method and system for coal mine power supply network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119695900B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120810600B (en) * | 2025-09-08 | 2025-11-14 | 华能庆阳煤电有限责任公司核桃峪煤矿 | A Method and System for Optimizing the Operation of Power Grids in Coal Mining Based on Intelligent Analysis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117674115A (en) * | 2023-12-05 | 2024-03-08 | 国网四川省电力公司 | Method and system for power supply load recovery after distributed power distribution network failure |
| CN119448128A (en) * | 2024-11-11 | 2025-02-14 | 国网福建省电力有限公司浦城县供电公司 | Intelligent control method and system for distribution network fault location and rapid reliability recovery |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112003277B (en) * | 2020-08-21 | 2021-11-30 | 山东大学 | Transmission and distribution cooperative load recovery optimization control method and system |
| CN119362404B (en) * | 2024-09-25 | 2025-09-23 | 国网湖南省电力有限公司 | A fault recovery path evaluation method for flexible interconnected distribution networks in low-voltage distribution substations |
-
2025
- 2025-02-24 CN CN202510201632.2A patent/CN119695900B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117674115A (en) * | 2023-12-05 | 2024-03-08 | 国网四川省电力公司 | Method and system for power supply load recovery after distributed power distribution network failure |
| CN119448128A (en) * | 2024-11-11 | 2025-02-14 | 国网福建省电力有限公司浦城县供电公司 | Intelligent control method and system for distribution network fault location and rapid reliability recovery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119695900A (en) | 2025-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117408162B (en) | Power grid fault control method based on digital twin | |
| CN118779831A (en) | Main transformer fault prediction method based on multivariable data fusion | |
| KR20210017651A (en) | Method for Fault Detection and Fault Diagnosis in Semiconductor Manufacturing Process | |
| CN119695900B (en) | Intelligent fault diagnosis and recovery method and system for coal mine power supply network | |
| CN119419727B (en) | Power load prediction and optimization method based on artificial intelligence | |
| CN120106354B (en) | A method, system, equipment and medium for early warning of faults in wind farm collector lines. | |
| CN118367682B (en) | A method and system for intelligent state identification and control of electrical equipment | |
| CN119004115B (en) | Power equipment fault prediction method and system based on 5G communication | |
| CN118014373A (en) | A risk identification model based on data quality monitoring and its construction method | |
| CN118396132A (en) | Intelligent fault diagnosis device and method for hydropower station based on multi-source information fusion | |
| CN112734141A (en) | Diversified load interval prediction method and device | |
| CN119537969B (en) | Train fault diagnosis method and system based on deep learning | |
| CN115526258A (en) | Power System Temporary Stability Evaluation Method Based on Spearman Correlation Coefficient Feature Extraction | |
| CN118230532B (en) | Real-time monitoring and early warning system of power battery assembly line | |
| CN119475016A (en) | A test result analysis system for flexible DC control and protection system | |
| CN118964851A (en) | Power grid dispatching business verification method based on artificial intelligence | |
| CN118036335A (en) | A method for optimizing a large power visual model in power distribution scenarios | |
| CN120819980B (en) | A method and system for temperature control in drying carbide slag based on multi-agent collaboration | |
| CN119442094B (en) | Power line online production monitoring method and system | |
| CN119944951B (en) | New energy power transmission status monitoring method and system based on artificial intelligence algorithm | |
| CN120123852B (en) | Method, system, device and medium for analyzing operating status of electric power equipment | |
| CN120315916B (en) | Intelligent Processing System and Method for Power Business Data Based on AI and Cloud Technologies | |
| CN120493004A (en) | Power transformer sensor network monitoring and fault diagnosis method and device | |
| CN121111838A (en) | Intelligent optimization control method for stable operation of hydraulic system in complex environment | |
| Nansamba et al. | Developing a Neural Network Based Fault Prediction Tool for a Solar Power Plant in Uganda |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20250325 Assignee: Shaanxi xungongyi Mining Co.,Ltd. Assignor: Huaneng Coal Technology Research Co.,Ltd. Contract record no.: X2025980023782 Denomination of invention: An intelligent fault diagnosis and recovery method and system for a coal mine power supply network Granted publication date: 20250506 License type: Common License Record date: 20250922 |