A busbar protection method and system for intelligent substation in mine

Abstract

The invention discloses a busbar protection method and system for a mine-used intelligent substation, belonging to the technical field of relay protection of electric power systems. In order to solve the problems of insufficient sensitivity and incomplete busbar protection in the existing busbar protection method for coal mine substations, the invention proposes the following scheme: using a sensor to monitor the busbar parameter data of the coal mine substation in real time; acquiring and processing the busbar parameter data of the coal mine substation and the historical parameter data of the substation bus; performing feature extraction and dimension reduction on the processed historical parameter data of the substation bus to obtain the historical parameter data after dimension reduction; training a fault identification model according to the historical parameter data after dimension reduction, and optimizing it using a loss function to obtain a pre-trained fault identification model; the model is deployed in a coal mine power monitoring system to perform fault identification on real-time data to obtain a fault identification result; and according to the fault identification result, a three-level protection strategy is adopted to realize comprehensive protection of the busbar of the coal mine substation.

Description

Technical Field

[0001] The invention relates to a busbar protection method and system for a mining intelligent substation, belonging to the technical field of relay protection of power systems. Background Art

[0002] With the continuous advancement of power system technology and the continuous improvement of the level of intelligence, substations, as an indispensable part of the power system, have received more and more attention. In the field of coal mining, the stability and safety of the power system are crucial to coal mine production. Due to the particularity of the coal mine environment, for example, the coal mine power system usually contains multi-level substations and distribution points, the power supply network is complex, and there are many series supply levels, which increases the possibility of faults and the difficulty of troubleshooting; the underground environment of coal mines is humid and dusty, which puts higher requirements on the insulation and heat dissipation performance of electrical equipment; long-term operation and harsh environment lead to accelerated equipment aging and increased failure risks, which may affect the power supply and production safety of the entire coal mine. Therefore, protecting the busbar is one of the important measures to ensure that the substation can operate stably and safely.

[0003] However, traditional busbar protection methods often rely on backup protection to remove faults, but the backup protection setting is high and the action time is long, making it difficult to cut off the fault current in time, resulting in serious damage to the equipment. Moreover, in the complex electromagnetic environment of coal mines, traditional protection methods are easily interfered, affecting the accuracy and reliability of protection actions, and cannot effectively respond to various abnormal situations in the power system. Therefore, a more efficient busbar protection method for coal mine substations is needed to cope with the complex and changeable working environment of the power system. Summary of the invention

[0004] In view of the problems of insufficient sensitivity and incomplete busbar protection in the prior art, the present invention provides a busbar protection method and system for a mine-used intelligent substation, which uses a sensor to monitor the busbar parameter data of a coal mine substation in real time, wherein the busbar parameter data of the coal mine substation includes current data, voltage data and temperature data; the busbar parameter data of the coal mine substation and the historical parameter data of the substation bus are acquired and processed to obtain the processed busbar parameter data of the coal mine substation and the processed historical parameter data of the substation bus, wherein the historical parameter data of the substation bus includes historical current data, historical voltage data and historical temperature data; feature extraction and dimension reduction are performed on the processed historical parameter data of the substation bus to obtain the historical parameter data after dimension reduction; a fault identification model is trained according to the historical parameter data after dimension reduction, and optimized using a loss function to obtain a pre-trained fault identification model; the model is deployed in a coal mine power monitoring system to perform fault identification on real-time data and obtain fault identification results; according to the fault identification results, a three-level protection strategy is adopted to achieve comprehensive protection of the busbar of the coal mine substation.

[0005] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions.

[0006] A busbar protection method for a mining intelligent substation comprises the following steps:

[0007] Step S1: using sensors to monitor the bus parameter data of the coal mine substation in real time, wherein the bus parameter data of the coal mine substation includes current data, voltage data and temperature data of the bus and its connected equipment;

[0008] Step S2: acquiring and processing the coal mine substation bus parameter data and the substation bus historical parameter data to obtain processed coal mine substation bus parameter data and processed substation bus historical parameter data, wherein the substation bus historical parameter data includes historical current data, historical voltage data and historical temperature data;

[0009] Step S3: performing feature extraction and dimension reduction on the processed substation bus historical parameter data to obtain dimension-reduced historical parameter data;

[0010] Step S4: training a fault recognition model based on the historical parameter data after dimension reduction, and optimizing it using a loss function to obtain a pre-trained fault recognition model;

[0011] Step S5: deploying the pre-trained fault identification model to the coal mine power monitoring system, performing real-time fault identification on the processed coal mine substation bus parameter data, and obtaining fault identification results;

[0012] Step S6: According to the fault identification result, a three-level protection strategy is adopted to achieve comprehensive protection of the coal mine substation busbar.

[0013] Specifically, the specific steps of step S1 are:

[0014] Step S101: The formula of the busbar current data or voltage data of the coal mine substation output by the sensor is:

[0015]

[0016] Among them, DL t ′ represents the busbar current data or voltage data of the coal mine substation output by the sensor at time t, DL t It represents the current data or voltage data of the busbar data of the coal mine substation passing through the sensor at time t, O1 represents the number of turns of the sensor input coil, O2 represents the number of turns of the sensor output coil, o represents the ratio error, SF t Indicates the scale factor of the sensor;

[0017] Step S102: The formula for the busbar temperature data of the coal mine substation output by the sensor is:

[0018]

[0019] Among them, WD t represents the busbar temperature data of the coal mine substation output by the sensor at time t, r1, r2 and r3 represent the coefficients describing the thermodynamic properties of the substance, R t represents the resistance of the thermistor at time t, R0 represents the nominal resistance of the thermistor, ln(·) represents the natural logarithm, and r0 represents absolute zero.

[0020] Specifically, the specific steps of step S2 are:

[0021] Step S201: determine the interface type of the sensor, select the corresponding type of interface in the PLC according to the interface type of the sensor, connect the sensor and the PLC to receive data sent by the sensor, and obtain bus parameter data of the coal mine substation;

[0022] Step S202: De-noising the bus parameter data of the coal mine substation to obtain the de-noised bus parameter data of the coal mine substation, the formula of which is as follows:

[0023]

[0024] in, represents the de-noised bus parameter data of the coal mine substation at time t, A represents the window size, c b represents the busbar parameter data of the bth coal mine substation, and b represents the number of busbar parameters of the coal mine substation;

[0025] Step S203: transmitting the de-noised coal mine substation bus parameter data to a designated IP address and port number;

[0026] Step S204: setting an interface for receiving the de-noised coal mine substation bus parameter data on the computer, and receiving the de-noised coal mine substation bus parameter data by monitoring the specified IP address and port number through the network;

[0027] Step S205: Obtain the substation bus historical parameter data in the substation cloud server, arrange the substation bus historical parameter data in ascending order, calculate the median of the substation bus historical parameter data, and use the median to fill the missing values ​​of the substation bus historical parameter data to obtain the filled substation bus historical parameter data, wherein the formula for calculating the median of the substation bus historical parameter data is:

[0028]

[0029] Where D represents the median value of the historical parameter data of the substation bus, f represents the number of historical parameter data of the substation bus, Indicates the substation busbar historical parameter data after being arranged in ascending order. data, Indicates the substation busbar historical parameter data after being arranged in ascending order. individual data;

[0030] Step S206: De-noising the filled substation busbar historical parameter data to obtain de-noised substation busbar historical parameter data, the formula is as follows:

[0031]

[0032] Among them, g t represents the denoised historical parameter data of the substation bus at time t, T represents the window size, and d v It represents the vth filled substation bus historical parameter data, and v represents the number of filled substation bus historical parameter data.

[0033] Specifically, the specific steps of step S3 are:

[0034] Step S301: The processed substation busbar historical parameter data is combined into a historical parameter data matrix E. Among them, e N,1 Represents the historical current data of the Nth sample, e N,2 Represents the historical voltage data of the Nth sample, e N,3 Represents the historical temperature data of the Nth sample, where N represents the number of samples;

[0035] Step S302: Process the historical parameter data in the historical parameter data matrix. The formula is as follows:

[0036]

[0037] Among them, e′ m,n represents the nth category historical parameter data of the mth sample after processing, e m,n represents the nth category historical parameter data of the mth sample, e n represents the mean of the nth category of historical parameter data, m represents the number of samples, and n represents the category of historical parameter data;

[0038] Step S303: Calculate the covariance matrix of the processed historical parameter data matrix. The formula is as follows:

[0039]

[0040] Among them, α represents the covariance matrix of the processed historical parameter data matrix, represents the normalization factor, E′ represents the processed historical parameter data matrix, (E′) T represents the transposed matrix of E′;

[0041] Step S304: randomly select a non-zero initial parameter vector in the covariance matrix, and for the kth iteration, calculate the historical parameter eigenvector obtained by the kth iteration, and the formula is as follows:

[0042]

[0043] Among them, e k represents the historical parameter feature vector obtained at the kth iteration, e k-1 represents the historical parameter feature vector obtained at the k-1th iteration, (e k-1 ) T Indicates e k-1 The transpose of , k represents the number of iterations;

[0044] Step S305: Calculate the historical parameter characteristic value, the formula is as follows:

[0045]

[0046] Among them, λ represents the characteristic value of the historical parameter, (E′) T represents the transposed matrix of E′;

[0047] Step S306: Set an iteration end threshold. If If it is less than the iteration end threshold, the iteration is stopped, where ||·|| represents the modulus of the calculated vector;

[0048] Step S307: Set a principal component accumulation threshold. If If it is equal to the principal component accumulation threshold, H historical parameter eigenvectors are retained as principal components to form a principal component matrix, where H represents the number of historical parameter eigenvectors to be retained, q is the total number of historical parameter eigenvalues, and λ h represents the hth historical parameter eigenvalue, and h represents the number of historical parameter eigenvectors to be retained;

[0049] Step S308: Use the principal component matrix to project the parameter data matrix to obtain the historical parameter data after dimensionality reduction.

[0050] Specifically, the specific steps of step S4 are:

[0051] Step S401: Organizing the reduced-dimensional historical parameter data into time-series historical parameter data, and training a fault recognition model based on the time-series historical parameter data;

[0052] Step S402: When training the fault identification model, a loss function is used for optimization, and the formula is as follows:

[0053]

[0054] Where L represents the loss function, S represents the number of historical parameter data of the substation bus, i represents the historical parameter data of the substation bus, P represents the number of fault type categories or fault severity categories, p represents the fault type category or fault severity category, y i ' ,p Indicates that i belongs to the true label of p, y i ″ ,p represents the predicted probability that i belongs to p, and log(·) represents the logarithmic function.

[0055] Specifically, the specific steps of step S5 are:

[0056] Step S501: Calculate the time series characteristics of the bus parameters of the coal mine substation according to the processed bus parameter data of the coal mine substation. The formula is as follows:

[0057]

[0058] Among them, y t represents the time series characteristics of the busbar parameters of the coal mine substation, GRU represents the gated recurrent unit, represents the forward hidden state at time t-1, represents the reverse hidden state at time t-1, G t Indicates the processed busbar parameter data of coal mine substation;

[0059] Step S502: Output according to the time series characteristics of the busbar parameters of the coal mine substation and calculate the fault result of the busbar of the coal mine substation. The formula is as follows:

[0060]

[0061] in, Indicates the result of busbar failure in coal mine substation, e (·) represents the exponential function, W y represents the weight of the fully connected layer, b y represents the bias of the fully connected layer, ReLU(·) represents the activation function, K represents the number of time series features of the busbar parameters of the coal mine substation, express The bias of y i Represents the time series characteristics of bus parameters of the i-th coal mine substation.

[0062] Specifically, the specific steps of step S6 are: the three-level protection strategy includes first-level protection, second-level protection and third-level protection;

[0063] The first-level protection includes: executing early warning measures for minor faults and notifying the operation and maintenance personnel to conduct further inspection and processing. The minor fault refers to a fault that causes abnormal current, voltage or temperature in a local area of ​​the busbar but does not have a serious impact on the entire system;

[0064] The secondary protection includes: isolating the fault section for intermediate faults to ensure that the fault does not spread. The intermediate fault refers to a fault that causes the current or voltage of some parts of the bus to deviate significantly from the normal value, affecting the stability and reliability of the system;

[0065] The three-level protection includes: for serious faults, quickly cutting off the faulty part to prevent further damage to the system. The serious fault refers to a fault that causes some or all parts of the bus to fail to operate normally, seriously affecting the stability and safety of the system.

[0066] A busbar protection system for a mining intelligent substation, comprising:

[0067] A data monitoring module is used to use sensors to monitor the bus parameter data of the coal mine substation in real time, wherein the bus parameter data of the coal mine substation includes current data, voltage data and temperature data;

[0068] The data acquisition and processing module is used to acquire and process the bus parameter data of the coal mine substation and the historical parameter data of the substation bus, and obtain the processed bus parameter data of the coal mine substation and the processed historical parameter data of the substation bus, wherein the historical parameter data of the substation bus includes historical current data, historical voltage data and historical temperature data;

[0069] A feature extraction and dimension reduction module is used to extract features and reduce the dimension of the processed substation busbar historical parameter data to obtain the historical parameter data after dimension reduction;

[0070] The fault identification model training module is used to train the fault identification model according to the historical parameter data after dimension reduction, and optimize it using the loss function to obtain a pre-trained fault identification model;

[0071] The fault identification module is used to perform real-time fault identification on the processed coal mine substation bus parameter data based on the pre-trained fault identification model to obtain the fault identification results;

[0072] The three-level protection module is used to adopt a three-level protection strategy based on the fault identification results to achieve comprehensive protection of the busbar of the coal mine substation.

[0073] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a busbar protection method for a mining intelligent substation when executing the computer program.

[0074] A computer-readable storage medium stores computer instructions, which, when executed, execute the steps of a busbar protection method for a mining intelligent substation.

[0075] Compared with the prior art, the present invention has the following beneficial effects:

[0076] This paper proposes a busbar protection method for a mine-used intelligent substation, which can provide real-time protection for the busbar of a coal mine substation. It has fast response, high accuracy and strong reliability, which can not only effectively protect the equipment of the power system, enhance the safety and stability of the power system, but also provide a strong technical support for the intelligent upgrade of the power system.

[0077] This paper proposes a busbar protection method for intelligent mine substations. Through sensors, various parameters of the busbar of the coal mine substation are monitored in real time, ensuring the timeliness and accuracy of the data, and being able to promptly discover potential operating abnormalities or precursors of faults, reducing the risk of sudden failures; feature extraction and dimensionality reduction processing are performed on the collected parameter data, which not only reduces the complexity of data processing, but also improves the accuracy and efficiency of data analysis, realizes the intelligent identification of busbar faults, and at the same time, reduces manual intervention and reduces operation and maintenance costs; the constructed fault identification model has high recognition accuracy and generalization ability, combined with the three-level protection strategy, it realizes all-round and multi-level protection of busbar faults, ensuring the safety and reliability of the coal mine power system.

[0078] This paper proposes a busbar protection system for a mine-based intelligent substation, which can quickly locate and isolate the fault point, reduce the impact of the fault on the entire system, shorten the system recovery time, reduce the power outage losses caused by the fault, and improve the continuity and stability of coal mine production. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 It is a flow chart of a busbar protection method for a mining intelligent substation disclosed by the present invention;

[0080] Figure 2 This is an architecture diagram of a busbar protection system for a mining intelligent substation disclosed in the present invention;

[0081] Figure 3 This is an electronic equipment diagram of a busbar protection method for a mining intelligent substation disclosed in the present invention. DETAILED DESCRIPTION

[0082] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0083] Example 1

[0084] See also Figure 1 , an embodiment provided by the present invention: a busbar protection method for a mining intelligent substation, comprising the following steps:

[0085] Step S1: Use sensors to monitor the bus parameter data of the coal mine substation in real time, wherein the bus parameter data of the coal mine substation includes current data, voltage data, and temperature data of the bus and its connected equipment.

[0086] Step S2: Acquire and process the coal mine substation bus parameter data and the substation bus historical parameter data to obtain processed coal mine substation bus parameter data and processed substation bus historical parameter data, wherein the substation bus historical parameter data includes historical current data, historical voltage data and historical temperature data.

[0087] Step S3: performing feature extraction and dimension reduction on the processed substation bus historical parameter data to obtain the dimension-reduced historical parameter data.

[0088] Step S4: Train the fault identification model based on the historical parameter data after dimensionality reduction, and use the loss function to optimize it to obtain a pre-trained fault identification model.

[0089] Step S5: deploy the pre-trained fault identification model to the coal mine power monitoring system, perform real-time fault identification on the processed coal mine substation bus parameter data, and obtain fault identification results.

[0090] Step S6: According to the fault identification result, a three-level protection strategy is adopted to achieve comprehensive protection of the coal mine substation busbar.

[0091] The specific steps of step S1 are:

[0092] Step S101: The formula of the busbar current data or voltage data of the coal mine substation output by the sensor is:

[0093]

[0094] Among them, DL t ′ represents the busbar current data or voltage data of the coal mine substation output by the sensor at time t, DL tIt represents the current data or voltage data of the busbar data of the coal mine substation passing through the sensor at time t, O1 represents the number of turns of the sensor input coil, O2 represents the number of turns of the sensor output coil, o represents the ratio error, SF t Indicates the scale factor of the sensor.

[0095] Step S102: The formula for the busbar temperature data of the coal mine substation output by the sensor is:

[0096]

[0097] Among them, WD t represents the busbar temperature data of the coal mine substation output by the sensor at time t, r1, r2 and r3 represent the coefficients describing the thermodynamic properties of the substance, R t represents the resistance of the thermistor at time t, R0 represents the nominal resistance of the thermistor, ln(·) represents the natural logarithm, and r0 represents absolute zero.

[0098] The specific steps of step S2 are:

[0099] Step S201: Determine the interface type of the sensor, select the corresponding type of interface in the PLC according to the interface type of the sensor, connect the sensor and the PLC to receive the data sent by the sensor, and obtain the bus parameter data of the coal mine substation.

[0100] The PLC is a programmable logic controller, which is mainly composed of a central processing unit, input module, output module, storage device and programming software. The sensor will pass the collected data to the PLC through the input module, and then the PLC will perform logical calculations and control according to the preset program. Finally, the output module will send the control signal to the actuator or other related equipment to achieve effective monitoring and management of the entire production process.

[0101] Step S202: De-noising the bus parameter data of the coal mine substation to obtain the de-noised bus parameter data of the coal mine substation, the formula of which is as follows:

[0102]

[0103] in, represents the de-noised bus parameter data of the coal mine substation at time t, A represents the window size, c b represents the busbar parameter data of the bth coal mine substation, and b represents the number of busbar parameters of the coal mine substation;

[0104] Step S203: transmitting the de-noised coal mine substation bus parameter data to a designated IP address and port number.

[0105] Step S204: an interface for receiving the de-noised coal mine substation bus parameter data is set on the computer, and the de-noised coal mine substation bus parameter data is received by monitoring the designated IP address and port number through the network.

[0106] Step S205: Obtain the substation bus historical parameter data in the substation cloud server, arrange the substation bus historical parameter data in ascending order, calculate the median of the substation bus historical parameter data, and use the median to fill the missing values ​​of the substation bus historical parameter data to obtain the filled substation bus historical parameter data, wherein the formula for calculating the median of the substation bus historical parameter data is:

[0107]

[0108] Where D represents the median value of the historical parameter data of the substation bus, f represents the number of historical parameter data of the substation bus, Indicates the substation busbar historical parameter data after being arranged in ascending order. data, Indicates the substation busbar historical parameter data after being arranged in ascending order. data.

[0109] Step S206: De-noising the filled substation busbar historical parameter data to obtain de-noised substation busbar historical parameter data, the formula is as follows:

[0110]

[0111] Among them, g t represents the denoised historical parameter data of the substation bus at time t, T represents the window size, and d v It represents the vth filled substation bus historical parameter data, and v represents the number of filled substation bus historical parameter data.

[0112] The specific steps of step S3 are:

[0113] Step S301: The processed substation busbar historical parameter data is combined into a historical parameter data matrix E. Among them, e N,1 Represents the historical current data of the Nth sample, e N,2 Represents the historical voltage data of the Nth sample, e N,3 Represents the historical temperature data of the Nth sample, where N represents the number of samples.

[0114] Step S302: Process the historical parameter data in the historical parameter data matrix. The formula is as follows:

[0115]

[0116] Among them, e′ m,n represents the nth category historical parameter data of the mth sample after processing, e m,n represents the nth category historical parameter data of the mth sample, represents the mean of the nth category of historical parameter data, m represents the number of samples, and n represents the category of historical parameter data.

[0117] Step S303: Calculate the covariance matrix of the processed historical parameter data matrix. The formula is as follows:

[0118]

[0119] Among them, α represents the covariance matrix of the processed historical parameter data matrix, represents the normalization factor, E′ represents the processed historical parameter data matrix, (E′) T represents the transposed matrix of E′.

[0120] Step S304: randomly select a non-zero initial parameter vector in the covariance matrix, and for the kth iteration, calculate the historical parameter eigenvector obtained by the kth iteration, and the formula is as follows:

[0121]

[0122] Among them, e k represents the historical parameter feature vector obtained at the kth iteration, e k-1 represents the historical parameter feature vector obtained at the k-1th iteration, (e k-1 ) T Indicates e k-1 is the transpose of , and k represents the number of iterations.

[0123] Step S305: Calculate the historical parameter characteristic value, the formula is as follows:

[0124]

[0125] Among them, λ represents the characteristic value of the historical parameter, (E′) T represents the transposed matrix of E′.

[0126] Step S306: Set an iteration end threshold. If If it is less than the iteration end threshold, the iteration is stopped, where ||·|| represents the modulus of the calculated vector.

[0127] Step S307: Set a principal component accumulation threshold. If If it is equal to the principal component accumulation threshold, H historical parameter eigenvectors are retained as principal components to form a principal component matrix, where H represents the number of historical parameter eigenvectors to be retained, q is the total number of historical parameter eigenvalues, and λ h represents the hth historical parameter eigenvalue, and h represents the number of historical parameter eigenvectors to be retained;

[0128] Step S308: multiply the historical parameter matrix by the principal component matrix, project the historical parameter matrix in the new feature space, and obtain the historical parameter data after dimensionality reduction.

[0129] The specific steps of step S4 are:

[0130] Step S401: Organize the reduced-dimensional historical parameter data into time-series historical parameter data, and train a fault recognition model based on the time-series historical parameter data.

[0131] Step S402: When training the fault identification model, a loss function is used for optimization, and the formula is as follows:

[0132]

[0133] Where L represents the loss function, S represents the number of historical parameter data of the substation bus, i represents the historical parameter data of the substation bus, P represents the number of fault type categories or fault severity categories, p represents the fault type category or fault severity category, y i ' ,p Indicates that i belongs to the true label of p, y i ″ ,p represents the predicted probability that i belongs to p, and log(·) represents the logarithmic function.

[0134] The specific steps of step S5 are:

[0135] Step S501: Calculate the time series characteristics of the bus parameters of the coal mine substation according to the processed bus parameter data of the coal mine substation. The formula is as follows:

[0136]

[0137] Among them, y t represents the time series characteristics of the busbar parameters of the coal mine substation, GRU represents the gated recurrent unit, represents the forward hidden state at time t-1, represents the reverse hidden state at time t-1, G t Indicates the processed busbar parameter data of coal mine substation;

[0138] Step S502: Output according to the time series characteristics of the busbar parameters of the coal mine substation and calculate the fault result of the busbar of the coal mine substation. The formula is as follows:

[0139]

[0140] in, Indicates the result of busbar failure in coal mine substation, e (·) represents the exponential function, W y represents the weight of the fully connected layer, b y represents the bias of the fully connected layer, ReLU(·) represents the activation function, K represents the number of time series features of substation bus parameters, express The bias of y i Represents the time series characteristics of bus parameters of the i-th coal mine substation.

[0141] The result of the substation bus fault is a probability distribution vector, in which the elements of the probability distribution vector correspond to the three levels of minor fault, medium fault and severe fault. The sum of these elements is 1, and each element represents the predicted probability of the corresponding level. The predicted probability is used to determine whether the bus of the coal mine substation is in a state of minor fault, medium fault or severe fault.

[0142] The specific steps of step S6 are: the three-level protection strategy includes first-level protection, second-level protection and third-level protection;

[0143] The first-level protection includes: executing early warning measures for minor faults and notifying operation and maintenance personnel to conduct further inspection and processing. The minor faults refer to faults that cause abnormal current, voltage or temperature in a local area of ​​the busbar but will not have a serious impact on the entire system.

[0144] The secondary protection includes: for intermediate faults, isolating the fault section to ensure that the fault does not spread. The intermediate fault refers to a fault that causes the current or voltage of certain parts of the bus to deviate significantly from the normal value, affecting the stability and reliability of the system.

[0145] The three-level protection includes: for serious faults, quickly cutting off the faulty part to prevent further damage to the system. The serious fault refers to a fault that causes some or all parts of the bus to fail to operate normally, seriously affecting the stability and safety of the system.

[0146] Example 2

[0147] See also Figure 2 Based on the same inventive concept as Example 1, this embodiment introduces a busbar protection system for a mining intelligent substation, including:

[0148] A data monitoring module is used to use sensors to monitor the bus parameter data of the coal mine substation in real time, wherein the bus parameter data of the coal mine substation includes current data, voltage data and temperature data;

[0149] The data acquisition and processing module is used to acquire and process the bus parameter data of the coal mine substation and the historical parameter data of the substation bus, and obtain the processed bus parameter data of the coal mine substation and the processed historical parameter data of the substation bus, wherein the historical parameter data of the substation bus includes historical current data, historical voltage data and historical temperature data;

[0150] A feature extraction and dimension reduction module is used to extract features and reduce the dimension of the processed substation busbar historical parameter data to obtain the historical parameter data after dimension reduction;

[0151] The fault identification model training module is used to train the fault identification model according to the historical parameter data after dimension reduction, and optimize it using the loss function to obtain a pre-trained fault identification model;

[0152] The fault identification module is used to perform real-time fault identification based on the processed busbar parameter data of the coal mine substation and the pre-trained fault identification model;

[0153] The three-level protection module is used to adopt a three-level protection strategy based on the fault identification results to achieve comprehensive protection of the busbar of the coal mine substation.

[0154] Example 3

[0155] See also Figure 3 An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the processor implements the steps of a busbar protection method for a mining intelligent substation.

[0156] A computer-readable storage medium stores computer instructions, which, when executed, execute the steps of a busbar protection method for a mining intelligent substation.

[0157] In summary, the present invention can provide real-time protection for the busbar of the substation, implement a three-level protection strategy, and comprehensively cover various faults that the substation busbar may encounter, thereby enhancing the reliability of the substation protection measures.

[0158] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0159] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0160] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0161] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0162] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A busbar protection method for a mining intelligent substation, characterized in that: The following steps are involved: Step S1: using sensors to monitor the bus parameter data of the coal mine substation in real time, wherein the bus parameter data of the coal mine substation includes current data, voltage data and temperature data of the bus and its connected equipment; Step S2: acquiring and processing the coal mine substation bus parameter data and the substation bus historical parameter data to obtain processed coal mine substation bus parameter data and processed substation bus historical parameter data, wherein the substation bus historical parameter data includes historical current data, historical voltage data and historical temperature data; Step S3: performing feature extraction and dimension reduction on the processed historical parameter data of the coal mine substation busbar to obtain the historical parameter data after dimension reduction; Step S4: training a fault recognition model based on the historical parameter data after dimension reduction, and optimizing it using a loss function to obtain a pre-trained fault recognition model; Step S5: deploying the pre-trained fault identification model to the coal mine power monitoring system, performing real-time fault identification on the processed coal mine substation bus parameter data, and obtaining fault identification results; Step S6: According to the fault identification result, a three-level protection strategy is adopted to achieve comprehensive protection of the busbar of the coal mine substation; The specific steps of step S3 are: Step S301: The processed substation busbar historical parameter data is combined into a historical parameter data matrix E. Among them, e N,1 Represents the historical current data of the Nth sample, e N,2 Represents the historical voltage data of the Nth sample, e N,3 Represents the historical temperature data of the Nth sample, where N represents the number of samples; Step S302: Process the historical parameter data in the historical parameter data matrix. The formula is as follows: Among them, e′ m,n represents the nth category historical parameter data of the mth sample after processing, e m,n represents the nth category historical parameter data of the mth sample, represents the mean of the nth category of historical parameter data, m represents the number of samples, and n represents the category of historical parameter data; Step S303: Calculate the covariance matrix of the processed historical parameter data matrix. The formula is as follows: Among them, α represents the covariance matrix of the processed historical parameter data matrix, represents the normalization factor, E′ represents the processed historical parameter data matrix, (E′) T represents the transposed matrix of E′; Step S304: randomly select a non-zero initial parameter vector in the covariance matrix, and for the kth iteration, calculate the historical parameter eigenvector obtained by the kth iteration, and the formula is as follows: Among them, e k represents the historical parameter feature vector obtained at the kth iteration, e k-1 represents the historical parameter feature vector obtained at the k-1th iteration, (ek- 1 ) T Indicates e k-1 The transpose of , k represents the number of iterations; Step S305: Calculate the historical parameter characteristic value, the formula is as follows: Among them, λ represents the characteristic value of the historical parameter, (E′) T represents the transposed matrix of E′; Step S306: Set an iteration end threshold. If If it is less than the iteration end threshold, the iteration is stopped, where ||·|| represents the modulus of the calculated vector; Step S307: Set a principal component accumulation threshold. If If it is equal to the principal component accumulation threshold, H historical parameter eigenvectors are retained as principal components to form a principal component matrix, where H represents the number of historical parameter eigenvectors to be retained, q is the total number of historical parameter eigenvalues, and λ h represents the hth historical parameter eigenvalue, and h represents the number of historical parameter eigenvectors to be retained; Step S308: Project the parameter data matrix using the principal component matrix to obtain the historical parameter data after dimensionality reduction; The specific steps of step S5 are as follows: Step S501: Calculate the time series characteristics of the bus parameters of the coal mine substation according to the processed bus parameter data of the coal mine substation. The formula is as follows: Among them, y t represents the time series characteristics of the busbar parameters of the coal mine substation, GRU represents the gated recurrent unit, represents the forward hidden state at time t-1, represents the reverse hidden state at time t-1, G t Indicates the processed busbar parameter data of coal mine substation; Step S502: Output according to the time series characteristics of the busbar parameters of the coal mine substation and calculate the fault result of the busbar of the coal mine substation. The formula is as follows: in, Indicates the result of busbar failure in coal mine substation, e (·) represents the exponential function, W y represents the weight of the fully connected layer, b y represents the bias of the fully connected layer, ReLU(·) represents the activation function, K represents the number of time series features of the busbar parameters of the coal mine substation, express The bias of y i Represents the time series characteristics of bus parameters of the i-th coal mine substation.

2. A busbar protection method for a mining intelligent substation according to claim 1, characterized in that: The specific steps of step S1 are: Step S101: The formula of the busbar current data or voltage data of the coal mine substation output by the sensor is: Among them, DL t ′ represents the busbar current data or voltage data of the coal mine substation output by the sensor at time t, DL t It represents the current data or voltage data of the busbar data of the coal mine substation passing through the sensor at time t, O1 represents the number of turns of the sensor input coil, O2 represents the number of turns of the sensor output coil, o represents the ratio error, SF t Represents the scale factor of the sensor; Step S102: The formula for the busbar temperature data of the coal mine substation output by the sensor is: Among them, WD t represents the busbar temperature data of the coal mine substation output by the sensor at time t, r1, r2 and r3 represent the coefficients describing the thermodynamic properties of the substance, R t represents the resistance of the thermistor at time t, R0 represents the nominal resistance of the thermistor, ln(·) represents the natural logarithm, and r0 represents absolute zero.

3. A busbar protection method for a mining intelligent substation according to claim 1, characterized in that: The specific steps of step S2 are: Step S201: determine the interface type of the sensor, select the corresponding type of interface in the PLC according to the interface type of the sensor, connect the sensor and the PLC to receive data sent by the sensor, and obtain bus parameter data of the coal mine substation; Step S202: De-noising the bus parameter data of the coal mine substation to obtain the de-noised bus parameter data of the coal mine substation, the formula of which is as follows: in, represents the de-noised bus parameter data of the coal mine substation at time t, A represents the window size, c b represents the busbar parameter data of the bth coal mine substation, and b represents the number of busbar parameters of the coal mine substation; Step S203: transmitting the de-noised coal mine substation bus parameter data to a designated IP address and port number; Step S204: setting an interface for receiving the de-noised coal mine substation bus parameter data on the computer, and receiving the de-noised coal mine substation bus parameter data by monitoring the specified IP address and port number through the network; Step S205: Obtain the substation bus historical parameter data in the substation cloud server, arrange the substation bus historical parameter data in ascending order, calculate the median of the substation bus historical parameter data, and use the median to fill the missing values ​​of the substation bus historical parameter data to obtain the filled substation bus historical parameter data, wherein the formula for calculating the median of the substation bus historical parameter data is: Where D represents the median value of the historical parameter data of the substation bus, f represents the number of historical parameter data of the substation bus, Indicates the substation busbar historical parameter data after being arranged in ascending order. data, Indicates the substation busbar historical parameter data after being arranged in ascending order. individual data; Step S206: De-noising the filled substation busbar historical parameter data to obtain de-noised substation busbar historical parameter data, the formula is as follows: Among them, g t represents the denoised historical parameter data of the substation bus at time t, T represents the window size, and d v It represents the vth filled substation bus historical parameter data, and v represents the number of filled substation bus historical parameter data.

4. A busbar protection method for a mining intelligent substation according to claim 1, characterized in that: The loss function in step S4 is: Where L represents the loss function, S represents the number of historical parameter data of the substation bus, i represents the historical parameter data of the substation bus, P represents the number of fault type categories or fault severity categories, p represents the fault type category or fault severity category, y i ' ,p Indicates that i belongs to the true label of p, y i ″ ,p represents the predicted probability that i belongs to p, and log(·) represents the logarithmic function.

5. A busbar protection method for a mining intelligent substation according to claim 1, characterized in that: The specific steps of step S6 are: the three-level protection strategy includes first-level protection, second-level protection and third-level protection; The first-level protection includes: executing early warning measures for minor faults and notifying the operation and maintenance personnel to conduct further inspection and processing. The minor fault refers to a fault that causes abnormal current, voltage or temperature in a local area of ​​the busbar but does not have a serious impact on the entire system; The secondary protection includes: isolating the fault section for intermediate faults to ensure that the fault does not spread. The intermediate fault refers to a fault that causes the current or voltage of some parts of the bus to deviate significantly from the normal value, affecting the stability and reliability of the system; The three-level protection includes: for serious faults, quickly cutting off the faulty part to prevent further damage to the system. The serious fault refers to a fault that causes some or all parts of the bus to fail to operate normally, seriously affecting the stability and safety of the system.

6. A busbar protection system for a mining intelligent substation, which is implemented based on a busbar protection method for a mining intelligent substation according to any one of claims 1 to 5, characterized in that: include: A data monitoring module is used to use sensors to monitor the bus parameter data of the coal mine substation in real time, wherein the bus parameter data of the coal mine substation includes current data, voltage data and temperature data; The data acquisition and processing module is used to acquire and process the bus parameter data of the coal mine substation and the historical parameter data of the substation bus, and obtain the processed bus parameter data of the coal mine substation and the processed historical parameter data of the substation bus, wherein the historical parameter data of the substation bus includes historical current data, historical voltage data and historical temperature data; A feature extraction and dimension reduction module is used to extract features and reduce the dimension of the processed substation busbar historical parameter data to obtain the historical parameter data after dimension reduction; The fault identification model training module is used to train the fault identification model according to the historical parameter data after dimension reduction, and optimize it using the loss function to obtain a pre-trained fault identification model; The fault identification module is used to perform real-time fault identification on the processed coal mine substation bus parameter data based on the pre-trained fault identification model to obtain the fault identification results; The three-level protection module is used to adopt a three-level protection strategy according to the fault identification results to achieve comprehensive protection of the substation bus.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a busbar protection method for a mining intelligent substation described in any one of claims 1-5 are implemented.

8. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the steps of a busbar protection method for a mining intelligent substation described in any one of claims 1-5 are executed.

Images