Comprehensive online state monitoring device for power distribution station house

Abstract

The invention relates to the technical field of power distribution station monitoring, and particularly discloses a comprehensive online state monitoring device for a power distribution station house, and the device comprises a multivariate data collection module which is used for collecting the charging state information and operation state information of a spare power automatic switching device, and the power utilization parameters of the station house and the power utilization parameters of equipment; a state analysis and prediction module which is connected with the multivariate data acquisition module and is used for receiving the acquired data, carrying out real-time analysis on the state of the spare power automatic switching device, carrying out abnormal prediction and early warning based on the power utilization parameters of the station building and the power utilization parameters of the equipment, and judging whether a potential fault hidden danger exists or not; the remote control module is connected with the state analysis and prediction module and is used for receiving a remote instruction and performing remote starting or stopping control on the spare power automatic switching device according to the remote instruction; and a data transmission and management module. According to the technical scheme, comprehensive detection can be carried out, and data are stored and analyzed to realize early warning in advance.

Description

Technical Field

[0001] The present invention relates to the technical field of substation monitoring, and particularly relates to a comprehensive on-line status monitoring device for substation buildings. Background Art

[0002] In modern power systems, substation buildings, as key nodes for power distribution, the stability and safety of their operation are of crucial importance. With the rapid development of social economy, the power demand continues to grow, posing higher requirements for the monitoring and management of substation buildings.

[0003] At present, although certain progress has been made in the monitoring technology for substation buildings, there are still many deficiencies. Some monitoring systems can only achieve the monitoring of single electrical parameters or environmental parameters, and cannot comprehensively reflect the overall operation status of substation buildings. For example, traditional monitoring means are difficult to simultaneously take into account the comprehensive detection of the backup power automatic switching device, AC power consumption in the substation building, and DC power consumption of equipment, resulting in the inability to timely discover potential fault hazards.

[0004] In terms of the detection of the backup power automatic switching device, the existing technology cannot accurately obtain key information such as its charging status and operation mode, and it is also difficult to achieve real-time monitoring and remote control of the status of the backup power automatic switching device. This makes it possible that the backup power automatic switching device may not act timely and accurately when abnormalities occur in the power system, affecting the reliability of power supply.

[0005] For the detection of substation building power consumption (AC) and equipment power consumption (DC), existing monitoring devices often have a single function, only monitoring parameters such as voltage and current. Although they can timely issue alarms for abnormalities such as overvoltage and undervoltage, they cannot perform predictive early warning based on relevant data and cannot eliminate faults in advance.

[0006] In addition, in terms of data transmission and management, the existing technology cannot make full use of the existing DTU devices in the substation building to efficiently transmit monitoring data to the monitoring room, and there are also problems of incomplete and non-standard data recording and storage, bringing great difficulties to subsequent fault analysis and operation and maintenance management.

[0007] In summary, the existing substation building monitoring technology cannot meet the requirements of comprehensive detection, data preservation and analysis for early warning. Summary of the Invention

[0008] The present invention provides a comprehensive on-line status monitoring device for substation buildings, which can perform comprehensive detection, preserve and analyze data for early warning.

[0009] To solve the above technical problems, the present application provides the following technical solutions:

[0010] A comprehensive on-line status monitoring device for substation buildings, comprising:

[0011] A multi - data acquisition module, which is used to acquire the charging status information and operation status information of the automatic bus transfer device, as well as the power consumption parameters of the substation building and equipment;

[0012] A status analysis and prediction module, connected to the multi - data acquisition module, is used to receive the acquired data, perform real - time analysis on the status of the automatic bus transfer device, and at the same time conduct abnormal prediction and early warning based on the power consumption parameters of the substation building and equipment to determine whether there are potential fault hazards;

[0013] A remote control module, connected to the status analysis and prediction module, is used to receive remote instructions and perform remote enabling or disabling control on the automatic bus transfer device according to the remote instructions;

[0014] A data transmission and management module, connected to the multi - data acquisition module, status analysis and prediction module, and remote control module, is used to use the existing DTU equipment in the substation building to transmit the acquired data and analysis results to the monitoring room, and record and store the data completely and standardly; it is also used to send early warning information to the monitoring room through the data transmission and management module when the status analysis and prediction module determines that there is an abnormality.

[0015] Furthermore, the multi - data acquisition module includes:

[0016] An automatic bus transfer status acquisition sub - module, which is used to acquire the charging status information and operation status information of the automatic bus transfer device; the automatic bus transfer status acquisition sub - module establishes a data connection through the communication interface with the automatic bus transfer device, and reads the charging flag bit and switch position signal data stored inside the automatic bus transfer device according to the preset communication protocol; uses the character "C" to represent the charging status, when the charging is completed, "C" is assigned the value "1", and when not charged, it is assigned the value "0"; uses the character "O" to represent the operation status, when operating normally, "O" is assigned the value "1", and when abnormal, it is assigned the value "0"; then performs CRC check on the acquired data, and if the check fails, re - acquires;

[0017] A sub - module for acquiring the power consumption of the substation building, which is used to acquire the power consumption parameters of the substation building; the sub - module for acquiring the power consumption of the substation building uses high - precision voltage transformers and current transformers to convert the high voltage and large current of the AC power consumption in the substation building into small signals; uses the character "VAC" to represent the AC voltage, with the unit of volts; uses the character "IAC" to represent the AC current, with the unit of amperes; during the acquisition process, samples the signal multiple times and removes noise interference through a digital filtering algorithm; then attaches a timestamp to the acquired data;

[0018] The device power consumption acquisition sub-module is used to acquire device power consumption parameters; the device power consumption acquisition sub-module measures direct current (DC) current using a Hall sensor and acquires DC voltage through a voltage division circuit; the DC voltage is represented by the character "VDC" with the unit of volt; the DC current is represented by the character "IDC" with the unit of ampere; the sensor and the acquisition circuit are electromagnetically shielded in hardware, and then the acquired data is verified and error-corrected; after the data acquisition is completed, the data is normalized and mapped to the interval [0, 1].

[0019] Furthermore, the state analysis and prediction module performs online real-time analysis on the received data based on time series, sets a fixed time interval Δt, and within each time interval, for the data acquired by the multi-source data acquisition module:

[0020] The charging state information and operating state information of the automatic bus transfer device are represented by the characters C and O respectively;

[0021] The power consumption parameters of the substation building, including AC voltage V AC and AC current I AC ;

[0022] The device power consumption parameters, including DC voltage V DC and DC current I DC are integrated and processed.

[0023] Furthermore, for the automatic bus transfer device, if within n consecutive time intervals, the charging state C changes from "0" to "1" and the operating state O is always "1", it is determined that the automatic bus transfer device is in normal charging and ready state; if C remains "0" and O is "0", it is marked that the automatic bus transfer device may have a fault, and the fault time series T fault .

[0024] Furthermore, an anomaly prediction and warning is performed using a long short-term memory network model based on machine learning; various types of acquired data are combined into a feature vector X t =[C t , O t , V AC，t , I AC，t , V DC，t , I DC，t in chronological order, where t represents the time step;

[0025] The core formula of the long short-term memory network model based on machine learning is:

[0026] The forget gate f t =σ(W f ·[h t-1 , X t +b f), which is used to determine which information from the previous moment needs to be retained to the current moment. σ is the Sigmoid function, and W f is the weight matrix of the forget gate, and h t-1 is the hidden state of the previous moment, and b f is the bias vector of the forget gate;

[0027] Input gate i t = σ(W i · [h t-1 , X t + b i ), which is used to determine how the new information at the current moment is added to the cell state. W i , W c are the corresponding weight matrices, and b i , b c are the bias vectors, and tanh is the hyperbolic tangent function;

[0028] Cell state Update the cell state;

[0029] Output gate o t = σ(W o · [h t-1 , X t + b o ), h t = o t * tanh(C t ), calculating the hidden state and output at the current moment.

[0030] Furthermore, in the model training stage, a large amount of historical data is used for training. The historical data includes normal operation data and various types of fault data; in the cross-validation method, the dataset is divided into k non-overlapping subsets. Each time, \(k - 1\) subsets are used for training, and the remaining one subset is used for validation. This is repeated k times, and the average validation result is taken as the model performance evaluation index.

[0031] Furthermore, during the model training process, the hyperparameters of the machine learning-based long short-term memory network model are continuously adjusted to minimize the loss function of the model on the validation set. The loss function uses the mean squared error; the formula is where N is the number of samples, y i is the true value, is the predicted value; when the confidence level of the prediction result is lower than the set threshold α, the abnormal situation is confirmed through manual intervention and further data analysis.

[0032] Further, the status analysis and prediction module is also used to analyze the correlation between data, and introduce a data correlation degree calculation formula to judge the rationality of the data; assuming the data correlation degree is R, for the charging state C of the automatic bus transfer device and the AC voltage V AC The correlation degree calculation formula is as follows:

[0033]

[0034] where n is the sample number of the collected data, C i and V ACi are respectively the charging state of the automatic bus transfer device and the AC voltage data collected for the i-th time, and are respectively the average values of the charging state and the AC voltage data; under normal circumstances, should be within a reasonable range [r min , r max ;

[0035] If the calculated exceeds this range, and the number of times the AC voltage V AC exceeds the normal range reaches a certain threshold m, it is suspected that the AC voltage data may be unreasonable due to sensor errors;

[0036] When it is suspected that a certain data is unreasonable due to sensor errors, compare the data of other relevant sensors; if the other data are all within the normal range and have a large difference from the current abnormal data, it is determined that the currently collected data is unreasonable data, and the abnormal alarm of the automatic bus transfer device state generated by this data is a false alarm, and the alarm signal is not sent, and the abnormal data situation is recorded.

[0037] Further, before transmitting the analysis result to the monitoring room, the data transmission and management module will verify the analysis result; for the analysis result of the automatic bus transfer device state, it will check again whether the current actual state of the automatic bus transfer device matches the analysis result; if the analysis result shows that the automatic bus transfer device should start, but the actual switch position shows that it is in the off and uncharged state, then mark this analysis result as suspicious; the data transmission and management module of this device establishes a data interaction link with the data transmission and management modules of other devices in the station. When receiving relevant data sent by other devices, it will make a comprehensive judgment with the data collected and analyzed by itself. When this device analyzes that there is an abnormality in the equipment power consumption, and at the same time receives similar abnormal data sent by the data transmission and management module of the adjacent device, it will increase the credibility of the abnormal analysis result; if the data of the adjacent device shows normal, this device will check the accuracy of the data collected by itself again and recalculate the analysis result.

[0038] Furthermore, the data transmission and management module is also used to filter the collected data. The sliding average filtering algorithm is adopted, and the time window T is set to perform sliding average calculation on the power consumption parameters of the substation building and equipment within the time window T.

[0039] The principle and beneficial effects of the basic solution are as follows: The multi-source data acquisition module comprehensively acquires the charging status information, operating status information of the backup power supply automatic switching device, as well as the power consumption parameters of the substation building and equipment through specific sensors and communication methods. These data are transmitted to the status analysis and prediction module in real time. This module uses specific algorithms and models to analyze the status of the backup power supply automatic switching device in real time and conduct abnormal prediction and early warning based on the power consumption parameters of the substation building and equipment.

[0040] During the analysis process, unreasonable data caused by sensor errors and other reasons are identified through logics such as data correlation judgment to ensure the accuracy of the analysis results. The remote control module receives external instructions and realizes the remote enabling or disabling control of the backup power supply automatic switching device according to the results of the status analysis and prediction module. The data transmission and management module uses the existing DTU equipment in the substation building to transmit the collected data and analysis results to the monitoring room and conducts complete and standardized recording and storage. During the data transmission process, the analysis results are verified, and comprehensive judgment is made in combination with the data of other equipment to effectively avoid false alarms caused by factors such as power grid fluctuations.

[0041] The multi-source data acquisition module can simultaneously collect various key information of the backup power supply automatic switching device, power consumption of the substation building, and equipment, changing the limitation of traditional monitoring means that can only monitor a single electrical parameter or environmental parameter, realizing the comprehensive detection of the distribution substation building, being able to timely discover potential fault hazards, and improving the comprehensiveness and accuracy of monitoring.

[0042] The data transmission and management module conducts complete and standardized recording and storage of the collected data, providing a rich data basis for subsequent data analysis. The status analysis and prediction module constructs a prediction model based on these data, such as the long short-term memory network (LSTM) model, which can predict abnormal situations in advance. Compared with traditional monitoring devices that can only issue alarms when abnormalities occur, this device realizes early warning, enabling maintenance personnel to have more sufficient time to take measures and reducing the possibility and impact degree of faults.

[0043] Through the real-time monitoring and analysis of the charging status and operating status of the backup power supply automatic switching device, as well as the remote control function, it is ensured that the backup power supply automatic switching device can act timely and accurately when abnormalities occur in the power system. It avoids the problem that the backup power supply automatic switching device cannot respond in time due to the inability to accurately obtain the key information of the backup power supply automatic switching device and the difficulty of remote control, improving the reliability of power supply.

[0044] Precise monitoring and analysis of the electricity consumption parameters of the substation building and equipment can promptly detect abnormal changes in parameters such as voltage and current. Through the prediction and early warning function, measures can be taken in advance to adjust the power distribution, avoiding equipment damage or power system failures caused by abnormal electricity consumption, and enhancing the stability of the operation of the entire substation building system.

[0045] The complete recording and standardized storage of data, as well as the effective transmission of analysis results, provide detailed and accurate data support for operation and maintenance personnel. It is convenient for operation and maintenance personnel to conduct fault analysis and summarize experience, which helps to formulate more reasonable operation and maintenance plans, improve the efficiency and quality of operation and maintenance management, and reduce unnecessary operation and maintenance costs and time waste. By means of reasonable judgment of the relevance of the collected data, verification of the analysis results, and comprehensive judgment in combination with other equipment data, false alarms caused by factors such as sensor errors and power grid fluctuations are effectively avoided. The alarm information received in the monitoring room is more accurate and reliable, reducing the ineffective troubleshooting work of operation and maintenance personnel due to false alarms and improving work efficiency.

[0046] In summary, the present invention achieves the purpose of being able to conduct comprehensive detection, save and analyze data, and achieve early warning. Description of the Drawings

[0047] Figure 1 It is a logic block diagram of an embodiment of a comprehensive on-line status monitoring device for a substation building. Detailed Embodiment

[0048] The following is a further detailed description through specific embodiments:

[0049] The embodiment is basically as Figure 1 shown:

[0050] A comprehensive on-line status monitoring device for a substation building includes:

[0051] A multi-source data acquisition module for acquiring the charging status information and operation status information of the backup power supply automatic switching device, as well as the electricity consumption parameters of the substation building and equipment electricity consumption parameters;

[0052] A status analysis and prediction module, connected to the multi-source data acquisition module, for receiving the acquired data, performing real-time analysis on the status of the backup power supply automatic switching device, and simultaneously performing abnormal prediction and early warning based on the electricity consumption parameters of the substation building and equipment electricity consumption parameters to determine whether there are potential fault hazards;

[0053] A remote control module, connected to the status analysis and prediction module, for receiving remote instructions and performing remote enabling or disabling control on the backup power supply automatic switching device according to the remote instructions;

[0054] The data transmission and management module is connected to the multi-source data acquisition module, the status analysis and prediction module, and the remote control module. It is used to transmit the acquired data and analysis results to the monitoring room by using the existing DTU equipment in the substation building, and record and store the data completely and standardly. It is also used to send a warning message to the monitoring room through the data transmission and management module when the status analysis and prediction module determines that there is an abnormality.

[0055] During specific use: Select appropriate positions in the substation building to install the multi-source data acquisition module, the status analysis and prediction module, the remote control module, and the data transmission and management module. These modules can be integrated into a control cabinet or installed separately according to the actual situation, but it is necessary to ensure stable electrical connections and reliable signal transmissions between the modules.

[0056] The data acquisition of the automatic bus transfer device is connected to the automatic bus transfer device through a dedicated communication interface (such as RS-485, Ethernet, etc.). According to the communication protocol of the automatic bus transfer device, its charging status information (such as charging flag bit, charging progress, etc.) and operating status information (such as switch position, fault alarm signal, etc.) are read regularly.

[0057] Install sensors such as voltage transformers and current transformers at key positions such as the incoming switchgear and outgoing switchgear in the substation building to collect power consumption parameters such as AC voltage, AC current, active power, and reactive power of the substation building. For important equipment (such as transformers, capacitors, etc.) in the substation building, install corresponding sensors to collect power consumption parameters such as DC voltage, DC current, temperature, and humidity of the equipment.

[0058] Use a high-performance industrial computer or server as the hardware platform of the status analysis and prediction module, and install corresponding data analysis software. The remote control module uses devices such as programmable logic controllers (PLCs) or intelligent relays, and is connected to the status analysis and prediction module through a communication interface. At the same time, the remote control module establishes a remote communication connection with the monitoring room through the network to receive remote instructions issued by the monitoring room. The data transmission and management module can use an embedded system or an industrial-grade data acquisition instrument to transmit the acquired data and analysis results to the monitoring room through the existing DTU equipment in the substation building (such as GPRS DTU, Ethernet DTU, etc.). At the same time, this module is equipped with a large-capacity storage device (such as a hard disk, solid-state drive, etc.) for recording and storing the data completely and standardly.

[0059] When the system starts, each module performs initialization operations in sequence. The multi-source data acquisition module checks the connection status of the sensors and communication interfaces and initializes the data acquisition parameters; the status analysis and prediction module loads the data analysis algorithm and the prediction and warning model; the remote control module checks the communication connection with the monitoring room; the data transmission and management module checks the working status of the DTU equipment and the available space of the storage device.

[0060] After normal operation, the multi-source data acquisition module collects data at set time intervals and transmits the data to the status analysis and prediction module. The status analysis and prediction module performs real-time analysis and prediction on the data to determine whether there are potential fault hazards. The operators in the monitoring room can send remote commands to the remote control module through the remote control terminal. After receiving the commands, the remote control module parses and executes the corresponding control operations. The data transmission and management module transmits the collected data and analysis results to the monitoring room through the DTU device and stores the data in the local storage device. At the same time, it processes the warning information in a timely manner to ensure that the monitoring room can timely understand the operation status of the distribution substation building.

[0061] The multi-source data acquisition module includes:

[0062] The backup power supply automatic switching state acquisition sub-module is used to collect the charging state information and operation state information of the backup power supply automatic switching device; the backup power supply automatic switching state acquisition sub-module establishes a data connection through the communication interface with the backup power supply automatic switching device, and reads the charging flag bit and switch position signal data stored inside the backup power supply automatic switching device according to the preset communication protocol; uses the character "C" to represent the charging state, when the charging is completed, "C" is assigned the value "1", and when not charged, it is assigned the value "0"; uses the character "O" to represent the operation state, when operating normally, "O" is assigned the value "1", and when abnormal, it is assigned the value "0"; then performs CRC check on the collected data, and if the check fails, re-collects;

[0063] The sub-module for collecting the electricity consumption of the substation building is used to collect the electricity consumption parameters of the substation building; the sub-module for collecting the electricity consumption of the substation building uses high-precision voltage transformers and current transformers to convert the high voltage and large current of the alternating current power consumption in the substation building into small signals; uses the character "VAC" to represent the alternating current voltage, with the unit of volt; uses the character "IAC" to represent the alternating current, with the unit of ampere; during the collection process, samples the signal multiple times and removes noise interference through digital filtering algorithms; then attaches a timestamp to the collected data;

[0064] The sub-module for collecting the electricity consumption of equipment is used to collect the electricity consumption parameters of equipment; the sub-module for collecting the electricity consumption of equipment uses Hall sensors to measure direct current, and collects direct current voltage through a voltage dividing circuit; uses the character "VDC" to represent the direct current voltage, with the unit of volt; uses the character "IDC" to represent the direct current, with the unit of ampere; conducts electromagnetic shielding on the sensors and collection circuits in hardware, and then performs verification and error correction on the collected data; after the data collection is completed, normalizes the data and maps the data to the [0, 1] interval.

[0065] The status analysis and prediction module performs online real-time analysis on the received data based on time series, sets a fixed time interval Δt, and within each time interval, for the data collected by the multi-source data acquisition module:

[0066] The charging status information and operating status information of the backup power supply automatic switching device are represented by the characters C and O respectively;

[0067] The electrical parameters of the substation building include the AC voltage V AC and the AC current I AC ;

[0068] The electrical parameters of the equipment include the DC voltage V DC and the DC current I DC for integrated processing.

[0069] For the backup power supply automatic switching device, if the charging status C changes from "0" to "1" within n consecutive time intervals and the operating status O is always "1", it is determined that the backup power supply automatic switching device is in normal charging and ready state; if C remains "0" and O is "0", it is marked that the backup power supply automatic switching device may have a fault, and the fault time series T is recorded fault .

[0070] Anomaly prediction and early warning are carried out using a long short-term memory network model based on machine learning; various collected data are composed into a feature vector X in chronological order t =[C t , O t , V AC，t , I AC，t , V DC，t , I DC，t , where t represents the time step;

[0071] The core formula of the long short-term memory network model based on machine learning is:

[0072] The forget gate f t =σ(W f ·[h t-1 , X t +b f ), which is used to determine which information from the previous moment needs to be retained to the current moment, σ is the Sigmoid function, W f is the weight matrix of the forget gate, h t-1 is the hidden state of the previous moment, b f is the bias vector of the forget gate;

[0073] The input gate i t =σ(W i ·[h t-1 , X t +b i ), which is used to determine how the new information at the current moment is added to the cell state, W i , W c are the corresponding weight matrices, b i , b cis the bias vector, and tanh is the hyperbolic tangent function;

[0074] Cell state Update the cell state;

[0075] Output gate o t = σ(W o ·[h t-1 , X t +b o ), h t = o t *tanh(C t ), and calculate the hidden state and output at the current moment.

[0076] In the model training stage, a large amount of historical data is used for training. The historical data includes normal operation data and various fault data; in the cross-validation method, the data set is divided into k non-overlapping subsets. Each time, \(k - 1\) subsets are used for training, and the remaining one subset is used for validation. Repeat k times, and take the average validation result as the model performance evaluation index.

[0077] During the model training process, the hyperparameters of the machine learning-based long short-term memory network model are continuously adjusted to minimize the loss function on the validation set. The loss function uses the mean square error; the formula is where N is the number of samples, yi is the true value, is the predicted value; when the confidence level of the prediction result is lower than the set threshold α, the abnormal situation is confirmed through manual intervention and further data analysis.

[0078] The state analysis and prediction module is also used to analyze the correlation between data, and introduce a data correlation degree calculation formula to judge the rationality of the data; let the data correlation degree be R. For the charging state C of the backup power supply automatic switching device and the AC voltage V AC The correlation degree calculation formula is:

[0079]

[0080] where n is the number of samples of the collected data, C i and V ACi : are the charging state of the backup power supply automatic switching device and the AC voltage data collected for the i-th time respectively, and are the average values of the charging state and the AC voltage data respectively; under normal circumstances, should be within a reasonable range [r min , r max ;

[0081] If the calculated exceeds this range, and the AC voltage V ACIf the number of times exceeding the normal range reaches a certain threshold m, it is suspected that the AC voltage data may be unreasonable due to sensor errors;

[0082] When it is suspected that a certain data is unreasonable due to sensor errors, compare the data of other relevant sensors; if other data are all within the normal range and have a large difference from the current abnormal data, it is determined that the currently collected data is unreasonable data, and the abnormal alarm of the backup power supply automatic switching device status caused by this data is a false alarm, and the alarm signal is not sent, and the abnormal data situation is recorded.

[0083] Before transmitting the analysis result to the monitoring room, the data transmission and management module will verify the analysis result; for the analysis result of the backup power supply automatic switching device status, it will check again whether the current actual status of the backup power supply automatic switching device matches the analysis result; if the analysis result shows that the backup power supply automatic switching device should start, but the actual switch position shows that it is in the off and uncharged state, mark this analysis result as suspicious; the data transmission and management module establishes a data interaction link with the data transmission and management modules of other devices in the station. When receiving relevant data sent by other devices, it will make a comprehensive judgment with the data collected and analyzed by itself. When this device analyzes that there is an abnormal power consumption of the device, and at the same time receives similar abnormal data sent by the data transmission and management module of the adjacent device, it will increase the credibility of the abnormal analysis result; if the data of the adjacent device shows normal, this device will check the accuracy of the data collected by itself again and recalculate the analysis result.

[0084] The data transmission and management module is also used to filter the collected data. The sliding average filtering algorithm is adopted, and the time window T is set to perform sliding average calculation on the power consumption parameters of the station building and the power consumption parameters of the equipment within the time window T.

[0085] When specifically used: Assume that the backup power supply automatic switching device installed in the distribution substation supports the Modbus RTU communication protocol, and the backup power supply status acquisition sub-module is connected to the backup power supply automatic switching device through the RS485 interface. During system initialization, according to the register address specified by the Modbus RTU protocol, read the charging flag bit and switch position signal data stored inside the backup power supply automatic switching device. For example, data is collected every 10 seconds. When the register value corresponding to the charging flag bit meets the charging completion condition, assign the character "C" as "1"; if not, assign it as "0". For the operating status, it is judged according to the switch position signal and the internal fault feedback information of the device. When normal, assign "O" as "1", and when abnormal, assign it as "0". During a collection process, the collected data is [C = 0, O = 1]. After CRC verification, it is found that the verification fails, and the system immediately re-collects until the verification is successful to ensure the accuracy of the data.

[0086] Install high-precision voltage transformers and current transformers at the incoming switchgear of the substation building. For example, the voltage transformer ratio is 10000:100, and the current transformer ratio is 200:5. When the AC power supply voltage of the substation building is 10 kV and the current is 100 A, the voltage transformer outputs a small signal of 100 V, and the current transformer outputs a small signal of 2.5 A. The substation power consumption acquisition sub-module samples these signals at a frequency of 10 times per second, and then uses the median filtering algorithm to remove noise interference. The collected AC voltage data "VAC" and AC current data "IAC" will be attached with a time stamp accurate to milliseconds, such as "2024-12-01 10:00:00.123". At a certain moment, a series of AC voltage data are collected. After filtering, a stable "VAC = 10.1 kV" is obtained and stored with a time stamp.

[0087] For key DC equipment in the distribution substation building, such as the standby charging power supply, use Hall sensors to measure its DC current and collect the DC voltage through a voltage dividing circuit. Both the Hall sensor and the voltage dividing circuit are subjected to electromagnetic shielding treatment to reduce external electromagnetic interference. The collected data, such as "VDC = 225 V" and "IDC = 5 A", are first subjected to verification and error correction processing, and then normalized through the formula "Normalized value = (Original value - Minimum value) / (Maximum value - Minimum value)". Assuming that the minimum value of the DC voltage is 200 V and the maximum value is 250 V, the normalized value of "VDC" is (225 - 200) / (250 - 200) = 0.5.

[0088] Set the time interval Δt = 1 minute, and integrate the collected data within each time interval. For example, within 5 consecutive time intervals, the charging status C of the backup power supply automatic switching device changes from "0" to "1", and the operating status 0 is always "1", then it is determined that the backup power supply automatic switching device is in normal charging and ready state. If within a period of time, C is continuously "0" and 0 is "0", such as for 10 consecutive time intervals, then mark that the backup power supply automatic switching device may have a fault and record the fault time sequence.

[0089] Anomaly prediction and early warning are carried out using a Long Short-Term Memory (LSTM) model. The operation data of the distribution substation room in the past year is collected as historical data, including various data during normal operation and fault data that has occurred, such as AC voltage fluctuations, equipment overload, etc. The data set is divided into 5 non-overlapping subsets (k = 5) for 5-fold cross-validation. During the training process, hyperparameters such as the number of neurons in the hidden layer and the learning rate of the LSTM model are continuously adjusted. Assuming that the initial number of neurons in the hidden layer is 64 and the learning rate is 0.01, after multiple experiments, it is found that when the number of neurons in the hidden layer is adjusted to 128 and the learning rate is adjusted to 0.001, the mean squared error loss function of the model on the validation set is the smallest. In a certain prediction, the confidence level of the prediction result is 0.7, which is lower than the set threshold of 0.8. At this time, the system prompts for manual intervention, and the operation and maintenance personnel conduct further analysis and confirmation by combining more on-site data and experience.

[0090] For data correlation analysis, assume that 100 sample data are collected within a certain period of time, and the correlation between the charging state C of the backup power supply automatic switching device and the AC voltage VAC is calculated. If the calculated exceeds the normal range [0.5, 0.7], and the number of times the AC voltage VAC exceeds the normal range (such as the normal range is 9.5 - 10.5 kV, and V AC has appeared below 9.5 kV many times) reaches the threshold m = 10 times, then it is suspected that there may be a problem with the AC voltage data. At this time, compare the AC voltage data of other monitoring points in the station. If other data are all within the normal range and are quite different from the current abnormal data, such as the voltage at other monitoring points is between 10.2 - 10.3 kV, while the current data is 9.2 kV, it is determined that the currently collected AC voltage data is unreasonable, to avoid false alarms caused by this data, and record this abnormal situation.

[0091] Before transmitting the analysis result to the monitoring room, the analysis result of the backup power supply automatic switching device status is verified. For example, the analysis result shows that the backup power supply automatic switching device should start, but by querying the actual switch position register and charging flag bit of the backup power supply automatic switching device, it is found that the switch is in the off and uncharged state, then mark this analysis result as suspicious.

[0092] The data transmission and management module and the data transmission and management modules of other devices in the station establish a data interaction link through Ethernet. When this device analyzes that the power consumption of a certain device is abnormal, such as "VDC" exceeding the normal range, and at the same time receives similar abnormal data sent by the data transmission and management module of the adjacent device, the credibility of the abnormal analysis result of the system is increased from 0.6 to 0.8. If the data of the adjacent device shows normal, this device will re-check its own acquisition circuit and sensors, re-acquire data and calculate the analysis result.

[0093] For the filtering process of the collected data, a time window T = 5 minutes is set, and the moving average calculation is performed on the power consumption parameters of the station house and the power consumption parameters of the equipment. Taking the alternating current "IAC" as an example, data is collected every 10 seconds within 5 minutes, and a total of 30 data points are collected. The moving average filtering algorithm is used to calculate the average value, and more stable current data is obtained for subsequent analysis and transmission, effectively avoiding data misjudgment caused by instantaneous fluctuations.

[0094] The above are only embodiments of the present invention. The invention is not limited to the fields involved in this embodiment. Common knowledge such as the specific structures and characteristics known in the art is not described in detail here. Those of ordinary skill in the art know all the common technical knowledge in the technical field to which the invention belongs before the application date or the priority date, can know all the existing technologies in this field, and have the ability to apply the conventional experimental means before this date. Those of ordinary skill in the art can, under the inspiration given in this application, combine their own abilities to improve and implement this solution. Some typical known structures or known methods should not become obstacles for those of ordinary skill in the art to implement this application. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, and these should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be based on the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to interpret the content of the claims.

Claims

1. An integrated on-line status monitoring device for a substation building, characterized in that, Including: A multi-source data acquisition module, which is used to acquire the charging status information and operating status information of the automatic bus transfer device, as well as the power consumption parameters of the substation building and the equipment; A status analysis and prediction module, which is connected to the multi-source data acquisition module, is used to receive the acquired data, perform real-time analysis on the status of the automatic bus transfer device, and at the same time perform abnormal prediction and early warning based on the power consumption parameters of the substation building and the equipment, and judge whether there are potential fault hazards; A remote control module, which is connected to the status analysis and prediction module, is used to receive remote instructions and perform remote enabling or disabling control on the automatic bus transfer device according to the remote instructions; A data transmission and management module, which is connected to the multi-source data acquisition module, the status analysis and prediction module, and the remote control module, is used to use the existing DTU equipment in the substation building to transmit the acquired data and analysis results to the monitoring room, and record and save the data completely and standardly; it is also used to send a warning message to the monitoring room through the data transmission and management module when the status analysis and prediction module judges an abnormality.

2. The integrated on-line status monitoring device for a power distribution substation according to claim 1, characterized in that The multi-source data acquisition module includes: An automatic bus transfer status acquisition sub-module, which is used to acquire the charging status information and operating status information of the automatic bus transfer device; the automatic bus transfer status acquisition sub-module establishes a data connection through the communication interface with the automatic bus transfer device, and reads the charging flag bit and switch position signal data stored inside the automatic bus transfer device according to the preset communication protocol; uses the character "C" to represent the charging status, when the charging is completed, "C" is assigned the value of "1", and when not charged, it is assigned the value of "0"; uses the character "O" to represent the operating status, when operating normally, "O" is assigned the value of "1", and when abnormal, it is assigned the value of "0"; then performs CRC check on the acquired data, and if the check fails, re-acquires; A substation building power consumption acquisition sub-module, which is used to acquire the power consumption parameters of the substation building; the substation building power consumption acquisition sub-module uses high-precision voltage transformers and current transformers to convert the high voltage and large current of the AC power consumption in the substation building into small signals; uses the character "VAC" to represent the AC voltage, with the unit of volts; uses the character "IAC" to represent the AC current, with the unit of amperes; during the acquisition process, samples the signal multiple times and removes noise interference through a digital filtering algorithm; then attaches a timestamp to the acquired data; An equipment power consumption acquisition sub-module, which is used to acquire the power consumption parameters of the equipment; the equipment power consumption acquisition sub-module uses a Hall sensor to measure the DC current and acquires the DC voltage through a voltage dividing circuit; uses the character "VDC" to represent the DC voltage, with the unit of volts; uses the character "IDC" to represent the DC current, with the unit of amperes; performs electromagnetic shielding on the sensor and the acquisition circuit in hardware, and then performs verification and error correction on the acquired data; after the data acquisition is completed, performs normalization processing on the data and maps the data to the interval [0, 1].

3. The integrated on-line status monitoring device for a power distribution substation room according to claim 2, wherein, The status analysis and prediction module performs online real-time analysis on the received data based on time series, sets a fixed time interval Δt, and within each time interval, for the data acquired by the multi-source data acquisition module: The charging status information and operating status information of the automatic bus transfer device, represented by the characters C and O respectively; Power consumption parameters of the station building, including AC voltage V AC and AC current I AC ; The electrical parameters of the device, including the DC voltage V DC and the DC current I DC are integrated and processed.

4. The integrated on-line status monitoring device for a power distribution station room according to claim 3, characterized in that For the automatic bus transfer device, if the charging state C changes from "0" to "1" within consecutive n time intervals and the operating state O is always "1", it is determined that the automatic bus transfer device is in a normal charging and ready state; if C remains "0" and O is "0", it is marked that there may be a fault in the automatic bus transfer device, and the fault time series T is recorded fault 。 5. The integrated on-line status monitoring device for a power distribution substation according to claim 4, characterized in that, Anomaly prediction and early warning are carried out using a long short-term memory network model based on machine learning; various types of collected data are organized into a feature vector X in chronological order t =[C t , O t , V AC，t , I AC，t , V DC，t , I DC，t , where t represents the time step; The core formula of the long short-term memory network model based on machine learning is: Forgotten gate f t = σ(W f · [h t-1 , X t + b f ), which is used to determine which information from the previous moment needs to be retained to the current moment. σ is the Sigmoid function, W f is the weight matrix of the forgotten gate, h t-1 is the hidden state of the previous moment, and b f is the bias vector of the forgotten gate; Input gate i t = σ(W i · [h t-1 , X t + b i ), which is used to determine how the new information at the current time step is added to the cell state. W i , W c are the corresponding weight matrices, and b i , b c are the bias vectors. Tanh is the hyperbolic tangent function; Cell state Update the cell state; Output gate o t = σ(W o · [h t-1 , X t + b o ), h t = o t * tanh(C t ), calculate the hidden state and output at the current time.

6. The integrated on-line status monitoring device for a distribution substation building according to claim 5, characterized in that, In the model training stage, a large amount of historical data is used for training. The historical data includes normal operation data and various types of fault data. The cross-validation method is adopted to divide the dataset into k non-overlapping subsets. Each time, \(k - 1\) subsets are used for training, and the remaining one subset is used for validation. This is repeated k times, and the average validation result is taken as the model performance evaluation index.

7. The integrated on-line status monitoring device for a power distribution station room according to claim 6, characterized in that, During the model training process, the hyperparameters of the machine learning-based long short-term memory network model are continuously adjusted to minimize the loss function of the model on the validation set. The loss function uses the mean squared error; the formula is where N is the number of samples, y i is the true value, is the predicted value; when the confidence level of the prediction result is lower than the set threshold α, manual intervention and further data analysis are used to confirm the abnormal situation.

8. The integrated on-line status monitoring device for a power distribution substation room according to claim 7, characterized in that The state analysis and prediction module is also used to analyze the correlation between data, and introduce a calculation formula for data correlation degree to judge the rationality of data; assuming the data correlation degree is R, for the charging state C of the backup power supply automatic switching device and the AC voltage V AC the calculation formula for the correlation degree is as follows: where n is the number of samples of the collected data, C i and V ACi are respectively the charging state and AC voltage data of the backup power supply automatic switching device for the i-th collection, and are respectively the average values of the charging state and AC voltage data; under normal circumstances, should be within a reasonable range [r min , r max ; If the calculated exceeds this range, and the number of times the AC voltage V AC exceeds the normal range reaches a certain threshold m, it is suspected that the AC voltage data may be unreasonable due to sensor errors; When it is suspected that a certain data has an unreasonable situation due to sensor error, the data of other relevant sensors is compared. If the other data are all within the normal range and have a large difference from the current abnormal data, it is determined that the currently collected data is unreasonable data, and the abnormal alarm of the backup power supply automatic switching device status generated by this data is a false alarm, and the alarm signal is not sent, and the abnormal data situation is recorded.

9. The integrated on-line condition monitoring device for substation buildings according to claim 8, characterized in that Before transmitting the analysis result to the monitoring room, the data transmission and management module will verify the analysis result. For the analysis result of the backup power supply automatic switching device status, it will check again whether the current actual status of the backup power supply automatic switching device matches the analysis result. If the analysis result shows that the backup power supply automatic switching device should start, but the actual switch position shows that it is in the off and uncharged state, the analysis result is marked as suspicious. The data transmission and management module establishes a data interaction link with the data transmission and management modules of other devices in the station. When receiving relevant data sent by other devices, it will make a comprehensive judgment with the data collected and analyzed by itself. When this device analyzes that there is an abnormal power consumption of the device and at the same time receives similar abnormal data sent by the data transmission and management module of the adjacent device, the credibility of the abnormal analysis result will be improved. If the data of the adjacent device shows normal, this device will check the accuracy of the data collected by itself again and recalculate the analysis result.

10. The integrated on-line status monitoring device for a power distribution station room according to claim 9, characterized in that The data transmission and management module is also used for filtering the collected data. The moving average filtering algorithm is adopted, and the time window T is set to perform the moving average calculation on the power consumption parameters of the station building and the power consumption parameters of the equipment within the time window T.

Images