A power plant visualization information management system based on digital twin technology

Abstract

The present invention belongs to the technical field of power plant management. The present invention provides a power plant visualization information management system based on digital twin technology, including: based on processing and analyzing operation data, obtaining an operation deviation performance value, judging whether there is a fault trend, based on the operation data, processing and analyzing to obtain an operation change value, judging the change type of the operation data, selecting and matching prediction models, continuing to monitor the operation voltage in real time during the prediction period, comparing and analyzing the predicted voltage to obtain a change approach value, judging whether the operation voltage change is close to the predicted operation voltage, obtaining a non-approaching similarity value, judging whether the degree to which the operation voltage of the power plant equipment at different time points is not close to the predicted operation voltage, which is conducive to the stable operation management of the power plant.

Description

Technical Field

[0001] The present invention belongs to the technical field of power plant management, and specifically is a power plant visualization information management system based on digital twin technology. Background Art

[0002] The visual information management of power plants based on digital twin technology can realize real-time monitoring, early warning and protection of the operating status of power plants. The system can promptly discover and solve potential problems and improve the safety and stability of power plants. Therefore, the visual information management of power plants based on digital twin technology is of great significance.

[0003] A Chinese patent application with publication number CN117610226A discloses a method for building a digital center visualization system based on digital twins, including: collection of basic data of the data center; establishment of a digital twin model of the data center based on a game engine; collection and transmission of data center operation data; monitoring of the operation and maintenance status of the data center; and release of a data center visualization system.

[0004] In the prior art, during the operation of a power plant, the operating data is usually compared with the operating data threshold to detect abnormalities in the operation of the power plant, resulting in untimely and inefficient monitoring of the operation of the power plant, and failure to ensure the stable operation of the power plant. In addition, in the predictive analysis of the operation of the power plant, there is a lack of selection of appropriate predictive models and methods based on the type of data changes, resulting in low prediction accuracy. Secondly, there is a lack of comparison and analysis of the predictive analysis results with the real-time data of the power plant operation, and the accuracy of the prediction results cannot be verified, which is not conducive to the stable operation management of the power plant.

[0005] To this end, the present invention provides a power plant visualization information management system based on digital twin technology. Summary of the invention

[0006] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0007] The technical solution adopted by the present invention to solve the technical problem is: a power plant visualization information management system based on digital twin technology, comprising:

[0008] Trend analysis module: During the monitoring period, the operation data of the power plant equipment is obtained in real time, and the operation deviation performance value is obtained based on the processing and analysis of the operation data. According to the operation deviation performance value, it is determined whether the power plant equipment has a fault trend. If so, an analysis signal is generated;

[0009] Among them, the operating data includes the equipment operating voltage;

[0010] Change determination module: based on the analysis signal and the operation data of the power plant equipment, the operation change value is obtained through processing and analysis, and the change type of the operation data of the power plant equipment is determined based on the operation change value, wherein the change type includes regular change and irregular change;

[0011] Prediction analysis module: Based on the change type of the operating data of the power plant equipment, a prediction model matching the change type of the operating data is selected, and the remaining time for the operating voltage of the power plant equipment to reach the equipment voltage threshold is obtained through prediction analysis of the prediction model. Based on the remaining time, the prediction period is obtained, and the predicted voltage at different time nodes within the prediction period is obtained through the prediction model;

[0012] Approach analysis module: During the forecast period, the operating voltage of the power plant equipment is continuously monitored in real time, and the operating data of the power plant equipment monitored in real time is compared and analyzed with the forecast voltage at different time nodes to obtain the change approach value. According to the change approach value, it is judged whether the operating voltage change of the power plant equipment at different time points is close to the forecasted operating voltage. If so, an approach signal is generated and a countdown warning display is performed. If not, a non-approach signal is generated.

[0013] Control and analysis module: Based on the non-approach signal, obtain the non-approach similarity value, and judge whether the degree to which the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage is similar according to the non-approach similarity value. If so, generate an adjustment signal, and display a countdown warning based on the adjustment signal.

[0014] As a further technical solution of the present invention, the operation deviation performance value is obtained by:

[0015] Obtain the operating voltage of the device in real time and compare it with the normal voltage of the device and the voltage threshold of the device;

[0016] If the operating voltage of the device is greater than the normal voltage of the device and less than the voltage threshold of the device, an out-of-bounds signal is generated;

[0017] Based on the processing and analysis of the out-of-bounds signal, the out-of-bounds duration ratio SC and the out-of-bounds degree value CD are obtained;

[0018] By formula: The running deviation performance value PL is obtained, wherein a1 and a2 are both preset proportional coefficients.

[0019] As a further technical solution of the present invention, the method for obtaining the over-limit duration ratio SC and the over-limit degree value CD is as follows:

[0020] The time period when the out-of-bounds signal appears is marked as the out-of-bounds period, and the duration corresponding to the out-of-bounds period is processed by ratio with the duration corresponding to the monitoring period to obtain the out-of-bounds duration ratio, which is marked as SC;

[0021] The operating voltages within the out-of-bounds period are summed and averaged to obtain the mean operating voltage within the out-of-bounds period. The mean operating voltage within the out-of-bounds period is processed by difference with the normal voltage of the equipment to obtain the mean operating voltage difference. The mean operating voltage difference is processed by ratio with the normal voltage of the equipment to obtain the out-of-bounds degree value, which is marked as CD.

[0022] As a further technical solution of the present invention, the operation change value is obtained by:

[0023] Obtain the operating voltage of the power plant equipment during the out-of-bounds period, construct an operating voltage change curve, and obtain a change overlap value CH and a change deviation value BL based on processing and analysis of the operating voltage change curve;

[0024] By formula: The running change value BH is obtained, wherein z1 and z2 are both preset proportional coefficients.

[0025] As a further technical solution of the present invention, the change overlap value CH and the change deviation value BL are obtained in the following manner:

[0026] Connect the two end points of the operating voltage change curve with a straight line to obtain a voltage change reference line, measure the overlap length between the operating voltage change curve and the voltage change reference line, and perform ratio processing with the length of the voltage change reference line to obtain the change overlap value, which is marked as CH;

[0027] The part of the operating voltage change curve that does not overlap with the voltage change reference line is marked as a non-overlapping curve. The shortest distance between different points on the non-overlapping curve and the voltage change reference line is obtained, and the sum is averaged to obtain the average distance between the non-overlapping curve and the voltage change reference line. The average distance is then ratioed with the length of the voltage change reference line to obtain the change deviation value, which is marked as BL.

[0028] As a further technical solution of the present invention, the predicted voltage at different time nodes is obtained by:

[0029] All operating voltages of power plant equipment within the out-of-bounds period are integrated into a data set as a training data set. If the change type of the operating data of the power plant equipment is a regular change, a linear regression model is selected as the prediction model. If the change type of the operating data of the power plant equipment is an irregular change, a random forest network model is selected as the prediction model. The prediction model is trained using the training data set to obtain a trained prediction model.

[0030] The device voltage threshold is input into the prediction model to obtain the time point when the operating voltage of the power plant equipment reaches the device voltage threshold, and is marked as the arrival time point. The arrival time point is processed with the current time point to obtain the remaining time for the operating voltage of the power plant equipment to reach the device voltage threshold, and the time period corresponding to the remaining time is marked as the prediction period;

[0031] The different time nodes within the prediction period are input into the prediction model to obtain the predicted voltages at the different time nodes within the prediction period.

[0032] As a further technical solution of the present invention, the method for obtaining the change approach value is:

[0033] During the forecast period, a monitoring period is preset, and the operating voltage of the power plant equipment monitored in real time at different time nodes during the preset monitoring period is obtained and processed and analyzed to obtain the change deviation quantity ratio BT and the change deviation degree value BJ;

[0034] By formula: The change approach value QJ is obtained, wherein s1 and s2 are both preset proportional coefficients.

[0035] As a further technical solution of the present invention, the change deviation quantity ratio BT and the change deviation degree value BJ are obtained in the following manner:

[0036] Obtain the operating voltage of the power plant equipment monitored in real time at different time nodes within the preset monitoring period, and compare it with the predicted voltage at different time nodes. Specifically:

[0037] Based on any time point;

[0038] If the operating voltage at a time node is not equal to the predicted voltage, the time node is marked as a different time node;

[0039] If the operating voltage at a time node is equal to the predicted voltage, the time node is marked as the same time node;

[0040] Count the total number of time nodes and the number of different time nodes in the preset monitoring period, and perform ratio processing on the number of different time nodes and the total number of time nodes in the preset monitoring period to obtain the change deviation number ratio, which is marked as BT;

[0041] Obtain the operating voltage at different time nodes, and perform difference processing with the predicted voltage at different time nodes to obtain the operating voltage difference at different time nodes, and take the absolute value to obtain the absolute difference of the operating voltage at different time nodes, perform ratio processing on the absolute difference of the operating voltage at different time nodes and the predicted voltage at different time nodes to obtain the absolute difference ratio of the operating voltage at different time nodes, sum and average the absolute difference ratios of the operating voltage at all different time nodes to obtain the degree of change deviation value, and mark it as BJ.

[0042] As a further technical solution of the present invention, the non-approaching similarity value is obtained by:

[0043] Obtain the operating voltage difference at different time nodes, process and analyze to obtain the target quantity ratio MB and the variance value FC of the voltage difference data group;

[0044] By formula: The non-approaching similarity value XS is obtained, where k1, k2 and k3 are preset proportional coefficients, and BT represents the ratio of the number of change deviations;

[0045] The target quantity ratio MB and the variance value FC of the voltage difference data group are obtained as follows:

[0046] Obtain the operating voltage difference of different time nodes. If the operating voltage difference is negative, mark the different time nodes as delayed nodes. If the operating voltage difference is positive, mark the different time nodes as advanced nodes.

[0047] Compare the number of delayed nodes and the number of advanced nodes. If the number of delayed nodes is greater than the number of advanced nodes, the delayed nodes are used as target nodes. If the number of delayed nodes is less than the number of advanced nodes, the advanced nodes are used as target nodes.

[0048] Count the number of target nodes and compare it with the total number of nodes at different times to get the target number ratio, which is marked as MB.

[0049] The operating voltage differences of all target nodes are integrated into a voltage difference data group, and the variance value of the voltage difference data group is obtained and marked as FC.

[0050] As a further technical solution of the present invention, the process of performing countdown warning display based on the adjustment signal is as follows:

[0051] Obtain the operating voltage differences of all target nodes and sum and average them to obtain the target voltage difference mean. If the target voltage difference mean is positive, perform difference processing on the device voltage threshold and the target voltage difference mean to obtain the adjusted device voltage threshold, and re-enter the value prediction model to obtain the remaining time again. If the target voltage difference mean is negative, sum the device voltage threshold and the absolute value of the target voltage difference mean to obtain the adjusted device voltage threshold, and re-enter the value prediction model to obtain the remaining time again.

[0052] The remaining time obtained is sent to the digital twin platform, and a countdown warning is displayed through the display system in the digital twin platform.

[0053] The beneficial effects of the present invention are as follows:

[0054] 1. During the monitoring period, the operating data of the power plant equipment is acquired in real time, and the operating deviation performance value is obtained based on the processing and analysis of the operating data. It is judged whether the power plant equipment has a fault trend according to the operating deviation performance value. If so, an analysis signal is generated. The present invention analyzes whether the power plant equipment has a fault trend by analyzing the real-time operating data of the power plant equipment during the monitoring period, which is beneficial to the early analysis and early warning of the power plant equipment monitoring and to ensure the stable operation of the power plant equipment.

[0055] 2. Based on the analysis signal and the operating data of the power plant equipment, the operation change value is obtained through processing and analysis. The change type of the operating data of the power plant equipment is determined based on the operation change value, wherein the change type includes regular change and irregular change. Based on the change type of the operating data of the power plant equipment, a prediction model matching the change type of the operating data is selected. The remaining time for the operating voltage of the power plant equipment to reach the equipment voltage threshold is obtained through prediction analysis by the prediction model. Based on the remaining time, a prediction period is obtained, and the predicted voltages at different time nodes within the prediction period are obtained through the prediction model. Within the prediction period, the operating voltage of the power plant equipment is continuously tested. The present invention monitors the operating data of the power plant equipment monitored in real time and compares and analyzes the predicted voltages at different time nodes to obtain a change approach value, and judges whether the operating voltage changes of the power plant equipment at different time points are close to the predicted operating voltage according to the change approach value. If so, an approach signal is generated. The present invention analyzes the trend type of the operating voltage change of the power plant equipment, selects a matching prediction model to predict the operating voltage, and compares and analyzes the operating voltage monitored in real time with the predicted operating voltage to determine the accuracy of the prediction result, so as to more accurately predict and judge the operation of the power plant equipment, which is beneficial to the stable operation management of the power plant equipment.

[0056] 3. Based on the non-convergence signal, a non-convergence similarity value is obtained, and whether the degree to which the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage is similar according to the non-convergence similarity value. If so, an adjustment signal is generated. When the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage, the present invention analyzes whether the operating voltage of the power plant equipment at different time points is not approaching the predicted operating voltage as a whole and whether the degree of overall non-convergence is similar. If so, the equipment voltage threshold is adjusted according to the degree of overall non-convergence and input into the model to accurately predict the remaining time for the operating voltage of the power plant equipment to reach the equipment voltage threshold. When the actual operating voltage is not close to the predicted voltage, the remaining time for the operating voltage of the power plant equipment to reach the equipment voltage threshold is accurately predicted by changing the input of the equipment voltage threshold, which is beneficial to the stable operation management of the power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The present invention will be further described below in conjunction with the accompanying drawings.

[0058] Figure 1 It is a module diagram of a power plant visual information management system based on digital twin technology according to an embodiment of the present invention;

[0059] Figure 2 It is a flowchart of the steps for countdown warning display in a power plant visual information management system based on digital twin technology described in an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0061] Example 1

[0062] like Figure 1 , Figure 2 As shown, a power plant visualization information management system based on digital twin technology according to an embodiment of the present invention includes:

[0063] Trend analysis module: During the monitoring period, the operation data of the power plant equipment is obtained in real time, and the operation deviation performance value is obtained based on the processing and analysis of the operation data. According to the operation deviation performance value, it is determined whether the power plant equipment has a fault trend. If so, an analysis signal is generated;

[0064] Among them, the operating data includes the equipment operating voltage;

[0065] It should be noted that the operating data of power plant equipment is obtained through real-time monitoring of sensors in the digital twin platform;

[0066] In some embodiments, the operating voltage of the device is obtained in real time and compared with the normal voltage of the device and the voltage threshold of the device;

[0067] If the operating voltage of the device is greater than the normal voltage of the device and less than the voltage threshold of the device, an out-of-bounds signal is generated;

[0068] If the operating voltage of the device is less than or equal to the normal voltage of the device, no processing is performed and real-time monitoring continues;

[0069] It should be noted that the normal voltage of the equipment is obtained in the following manner: the maximum voltage reached by the power plant equipment during normal operation in each historical monitoring cycle in multiple historical monitoring cycles is obtained, and the maximum normal voltage is marked as the maximum normal voltage, and the maximum normal voltage of the power plant equipment in each historical monitoring cycle is summed and averaged to obtain the normal voltage of the equipment, wherein the normal voltage of the equipment is less than the voltage threshold of the equipment;

[0070] The time period when the out-of-bounds signal appears is marked as the out-of-bounds period, and the duration corresponding to the out-of-bounds period is processed by ratio with the duration corresponding to the monitoring period to obtain the out-of-bounds duration ratio, which is marked as SC;

[0071] The operating voltages in the out-of-bounds period are summed and averaged to obtain the mean operating voltage in the out-of-bounds period. The mean operating voltage in the out-of-bounds period is processed by difference with the normal voltage of the equipment to obtain the mean operating voltage difference. The mean operating voltage difference is processed by ratio with the normal voltage of the equipment to obtain the out-of-bounds degree value, which is marked as CD.

[0072] The obtained over-limit duration ratio SC and over-limit degree value CD are processed by data, and the formula is: The running deviation performance value PL is obtained, wherein a1 and a2 are both preset proportional coefficients;

[0073] It should be noted that the purpose of obtaining the operation deviation performance value PL is that the operation deviation performance value PL reflects the time and degree of the power plant equipment operation data exceeding the normal level, and the purpose is to reflect the abnormal degree of the power plant equipment operation compared with the normal level;

[0074] In some embodiments, the operating deviation performance value is compared to an operating deviation performance threshold;

[0075] If the operation deviation performance value is greater than the operation deviation performance threshold, it indicates that the power plant equipment has a failure trend;

[0076] If the operation deviation performance value is less than or equal to the operation deviation performance threshold, it means that there is no failure trend in the power plant equipment;

[0077] The technical solution of the embodiment of the present invention is: within the monitoring period, the operating data of the power plant equipment is obtained in real time, based on the processing and analysis of the operating data, the operating deviation performance value is obtained, and it is judged whether the power plant equipment has a fault trend according to the operating deviation performance value. If so, an analysis signal is generated. The present invention analyzes whether the power plant equipment has a fault trend by analyzing the real-time operating data of the power plant equipment within the monitoring period, which is beneficial to the early analysis and early warning of the power plant equipment monitoring and to ensure the stable operation of the power plant equipment.

[0078] Example 2

[0079] like Figure 1 , Figure 2 As shown, based on Example 1, a power plant visualization information management system based on digital twin technology described in an embodiment of the present invention includes:

[0080] Change determination module: based on the analysis signal and the operation data of the power plant equipment, the operation change value is obtained through processing and analysis, and the change type of the operation data of the power plant equipment is determined based on the operation change value, wherein the change type includes regular change and irregular change;

[0081] Specifically, the operating voltage of the power plant equipment in the out-of-bounds period is obtained, and an XY two-dimensional coordinate system is constructed with time as the X-axis and the operating voltage as the Y-axis. The operating voltage of the power plant equipment in the out-of-bounds period is marked and connected in the XY coordinate system to obtain an operating voltage change curve;

[0082] Connect the two end points of the operating voltage change curve with a straight line to obtain a voltage change reference line, measure the overlap length between the operating voltage change curve and the voltage change reference line, and perform ratio processing with the length of the voltage change reference line to obtain the change overlap value, which is marked as CH;

[0083] The part of the operating voltage change curve that does not overlap with the voltage change reference line is marked as a non-overlapping curve, and the shortest distances between different points on the non-overlapping curve and the voltage change reference line are obtained, and the sum is averaged to obtain the average distance between the non-overlapping curve and the voltage change reference line, and the ratio is processed with the length of the voltage change reference line to obtain the change deviation value, which is marked as BL;

[0084] The obtained change overlap value CH and change deviation value BL are processed by the formula: The running change value BH is obtained, wherein z1 and z2 are both preset proportional coefficients;

[0085] It should be noted that the meaning of the operation change performance value is: the operation change performance value is obtained by processing the change coincidence value CH and the change deviation value BL, wherein the change coincidence value CH reflects the degree to which the data change presents a linear regular change, and the change deviation value BL reflects the degree to which the data change does not present a linear regular change, wherein the larger the change coincidence value CH and the smaller the change deviation value BL, the stronger the degree to which the data change presents a regular change;

[0086] In some embodiments, the operating change value BH is compared to an operating change threshold value;

[0087] If the operation change value BH is greater than the operation change threshold, it means that the change type of the operation data of the power plant equipment is a regular change;

[0088] If the operation change value BH is less than or equal to the operation change threshold, it means that the operation data change type of the power plant equipment is irregular change;

[0089] Prediction analysis module: Based on the change type of the operating data of the power plant equipment, a prediction model matching the change type of the operating data is selected, and the remaining time for the operating voltage of the power plant equipment to reach the equipment voltage threshold is obtained through prediction analysis of the prediction model. Based on the remaining time, the prediction period is obtained, and the predicted voltage at different time nodes within the prediction period is obtained through the prediction model;

[0090] Specifically, all operating voltages of power plant equipment within the out-of-bounds period are integrated into a data set as a training data set. If the change type of the operating data of the power plant equipment is a regular change, a linear regression model is selected as a prediction model. If the change type of the operating data of the power plant equipment is an irregular change, a random forest network model is selected as a prediction model. The prediction model is trained using the training data set to obtain a trained prediction model.

[0091] The device voltage threshold is input into the prediction model to obtain the time point when the operating voltage of the power plant equipment reaches the device voltage threshold, and is marked as the arrival time point. The arrival time point is processed with the current time point to obtain the remaining time for the operating voltage of the power plant equipment to reach the device voltage threshold, and the time period corresponding to the remaining time is marked as the prediction period;

[0092] Input different time nodes within the prediction period into the prediction model to obtain the predicted voltages at different time nodes within the prediction period;

[0093] Approach analysis module: During the forecast period, the operating voltage of the power plant equipment is continuously monitored in real time, and the operating data of the power plant equipment monitored in real time is compared and analyzed with the forecast voltage at different time nodes to obtain the change approach value. According to the change approach value, it is judged whether the operating voltage change of the power plant equipment at different time points is close to the forecasted operating voltage. If so, an approach signal is generated and a countdown warning display is performed. If not, a non-approach signal is generated.

[0094] Specifically, within the prediction period, a monitoring period is preset, wherein the time length corresponding to the preset monitoring period is less than the time length corresponding to the prediction period;

[0095] It should be noted that the purpose of presetting the monitoring period within the prediction period is to analyze the accuracy of the prediction by real-time monitoring whether the operating voltage within the preset monitoring period is close to the predicted operating voltage, so as to more accurately judge whether the operating voltage of the power plant equipment will reach the threshold state during operation, which is conducive to the stable operation management of the power plant equipment;

[0096] Obtain the operating voltage of the power plant equipment monitored in real time at different time nodes within the preset monitoring period, and compare it with the predicted voltage at different time nodes. Specifically:

[0097] Based on any time point;

[0098] If the operating voltage at a time node is not equal to the predicted voltage, the time node is marked as a different time node;

[0099] If the operating voltage at a time node is equal to the predicted voltage, the time node is marked as the same time node;

[0100] Count the total number of time nodes and the number of different time nodes in the preset monitoring period, and perform ratio processing on the number of different time nodes and the total number of time nodes in the preset monitoring period to obtain the change deviation number ratio, which is marked as BT;

[0101] Obtain the operating voltage at different time nodes, and perform difference processing with the predicted voltage at different time nodes to obtain the operating voltage difference at different time nodes, and take the absolute value to obtain the absolute difference of the operating voltage at different time nodes, perform ratio processing on the absolute difference of the operating voltage at different time nodes and the predicted voltage at different time nodes to obtain the absolute difference ratio of the operating voltage at different time nodes, sum and average the absolute difference ratios of the operating voltage at all different time nodes to obtain the value of the degree of change deviation, and mark it as BJ;

[0102] The change deviation quantity ratio BT and the change deviation degree value BJ are processed by the formula: The change approach value QJ is obtained, where s1 and s2 are both preset proportional coefficients;

[0103] In some embodiments, the change approach value is compared to a change approach threshold;

[0104] If the change approach value is greater than the change approach threshold, it means that the operating voltage change of the power plant equipment at different time points is approaching the predicted operating voltage, and an approach signal is generated;

[0105] If the change approach value is less than or equal to the change approach threshold, it means that the operating voltage change of the power plant equipment at different time points does not approach the predicted operating voltage, and a non-approach signal is generated;

[0106] Based on the approach signal, the remaining time is sent to the digital twin platform, and the countdown warning is displayed through the display system in the digital twin platform;

[0107] The technical solution of the embodiment of the present invention is: based on the analysis signal, based on the operating data of the power plant equipment, the operation change value is obtained by processing and analysis, and the change type of the operating data of the power plant equipment is judged based on the operation change value, wherein the change type includes regular change and irregular change, and based on the change type of the operating data of the power plant equipment, a prediction model matching the change type of the operating data is selected, and the remaining time for the operating voltage of the power plant equipment to reach the equipment voltage threshold is obtained through the prediction analysis of the prediction model, and the prediction period is obtained based on the remaining time, and the predicted voltages at different time nodes within the prediction period are obtained through the prediction model, and the operation of the power plant equipment is continued to be predicted within the prediction period. The voltage is monitored in real time, and the operating data of the power plant equipment monitored in real time is compared and analyzed with the predicted voltage at different time nodes to obtain a change approach value. According to the change approach value, it is judged whether the operating voltage change of the power plant equipment at different time points is close to the predicted operating voltage. If so, an approach signal is generated. The present invention analyzes the trend type of the operating voltage change of the power plant equipment, selects a matching prediction model to predict the operating voltage, and compares and analyzes the operating voltage monitored in real time with the predicted operating voltage to determine the accuracy of the prediction result, so as to more accurately predict and judge the operation of the power plant equipment, which is beneficial to the stable operation management of the power plant equipment.

[0108] Example 3

[0109] like Figure 1 , Figure 2 As shown, based on Example 1 and Example 2, a power plant visualization information management system based on digital twin technology described in an embodiment of the present invention includes:

[0110] Control and analysis module: Based on the non-approaching signal, obtain the non-approaching similarity value, and judge whether the degree to which the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage is similar according to the non-approaching similarity value. If so, generate an adjustment signal, and based on the adjustment signal, perform a countdown warning display;

[0111] Specifically, the operating voltage difference of different time nodes is obtained. If the operating voltage difference is negative, the different time nodes are marked as delayed nodes. If the operating voltage difference is positive, the different time nodes are marked as early nodes.

[0112] Compare the number of delayed nodes and the number of advanced nodes. If the number of delayed nodes is greater than the number of advanced nodes, the delayed nodes are used as target nodes. If the number of delayed nodes is less than the number of advanced nodes, the advanced nodes are used as target nodes.

[0113] It should be noted that if the number of delayed nodes is equal to the number of advanced nodes, the analysis is stopped, indicating that the operating voltage of the power plant equipment at half of the different time points is higher than the predicted voltage, and the operating voltage at half of the different time points is lower than the predicted voltage, and the degree to which the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage is not similar;

[0114] Count the number of target nodes and compare it with the total number of nodes at different times to get the target number ratio, which is marked as MB.

[0115] Integrate the operating voltage differences of all target nodes into a voltage difference data group, obtain the variance value of the voltage difference data group, and mark it as FC;

[0116] The obtained target quantity ratio MB, the variance value FC of the voltage difference data group and the variation deviation quantity ratio BT are processed by the formula: A non-approaching similarity value XS is obtained, wherein k1, k2 and k3 are all preset proportional coefficients;

[0117] In some embodiments, the non-converging similarity value XS is compared to a non-converging similarity threshold;

[0118] If the non-converging similarity value XS is greater than the non-converging similarity threshold, it means that the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage to a similar degree, and an adjustment signal is generated;

[0119] If the non-converging similarity value XS is less than or equal to the non-converging similarity threshold, it means that the operating voltage of the power plant equipment at different time points is not close to the predicted operating voltage, and no operation is performed;

[0120] Based on the adjustment signal, the operating voltage differences of all target nodes are obtained and summed to obtain the target voltage difference mean. If the target voltage difference mean is positive, the device voltage threshold and the target voltage difference mean are differenced to obtain the adjusted device voltage threshold, and the value prediction model is re-entered to obtain the remaining time. If the target voltage difference mean is negative, the device voltage threshold and the absolute value of the target voltage difference mean are summed to obtain the adjusted device voltage threshold, and the value prediction model is re-entered to obtain the remaining time.

[0121] The remaining time obtained is sent to the digital twin platform, and a countdown warning is displayed through the display system in the digital twin platform;

[0122] The technical solution of the embodiment of the present invention is: based on the non-approach signal, a non-approach similarity value is obtained, and whether the degree to which the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage is similar according to the non-approach similarity value. If so, an adjustment signal is generated. When the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage, the present invention analyzes whether the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage as a whole and whether the degree of overall non-approach is similar. If so, the equipment voltage threshold is adjusted according to the degree of overall non-approach and input into the model to accurately predict the remaining time for the operating voltage of the power plant equipment to reach the equipment voltage threshold. When the actual operating voltage is not close to the predicted voltage, the input of the equipment voltage threshold is changed to accurately realize the prediction of the remaining time for the operating voltage of the power plant equipment to reach the equipment voltage threshold, which is beneficial to the stable operation management of the power plant.

[0123] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A power plant visual information management system based on digital twin technology, characterized by: include: Trend analysis module: During the monitoring period, the operation data of the power plant equipment is obtained in real time, and the operation deviation performance value is obtained based on the processing and analysis of the operation data. According to the operation deviation performance value, it is determined whether the power plant equipment has a fault trend. If so, an analysis signal is generated; Among them, the operating data includes the equipment operating voltage; Change determination module: based on the analysis signal and the operation data of the power plant equipment, the operation change value is obtained through processing and analysis, and the change type of the operation data of the power plant equipment is determined based on the operation change value, wherein the change type includes regular change and irregular change; Prediction analysis module: Based on the change type of the operating data of the power plant equipment, a prediction model matching the change type of the operating data is selected, and the remaining time for the operating voltage of the power plant equipment to reach the equipment voltage threshold is obtained through prediction analysis of the prediction model. Based on the remaining time, the prediction period is obtained, and the predicted voltage at different time nodes within the prediction period is obtained through the prediction model; Approach analysis module: During the forecast period, the operating voltage of the power plant equipment is continuously monitored in real time, and the operating data of the power plant equipment monitored in real time is compared and analyzed with the forecast voltage at different time nodes to obtain the change approach value. According to the change approach value, it is judged whether the operating voltage change of the power plant equipment at different time points is close to the forecasted operating voltage. If so, an approach signal is generated and a countdown warning display is performed. If not, a non-approach signal is generated. Control and analysis module: Based on the non-approaching signal, obtain the non-approaching similarity value, and judge whether the degree to which the operating voltage of the power plant equipment at different time points does not approach the predicted operating voltage is similar according to the non-approaching similarity value. If so, generate an adjustment signal, and perform a countdown warning display based on the adjustment signal; The process of displaying the countdown warning based on the adjustment signal is as follows: Obtain the operating voltage differences of all target nodes and sum and average them to obtain the target voltage difference mean. If the target voltage difference mean is positive, perform difference processing on the device voltage threshold and the target voltage difference mean to obtain the adjusted device voltage threshold, and re-enter the value prediction model to obtain the remaining time again. If the target voltage difference mean is negative, sum the device voltage threshold and the absolute value of the target voltage difference mean to obtain the adjusted device voltage threshold, and re-enter the value prediction model to obtain the remaining time again. The remaining time obtained is sent to the digital twin platform, and a countdown warning is displayed through the display system in the digital twin platform.

2. According to claim 1, a power plant visualization information management system based on digital twin technology is characterized by: The operation deviation performance value is obtained in the following manner: Obtain the operating voltage of the device in real time and compare it with the normal voltage of the device and the voltage threshold of the device; If the operating voltage of the device is greater than the normal voltage of the device and less than the voltage threshold of the device, an out-of-bounds signal is generated; Based on the processing and analysis of the out-of-bounds signal, the out-of-bounds duration ratio SC and the out-of-bounds degree value CD are obtained; By formula: The running deviation performance value PL is obtained, wherein a1 and a2 are both preset proportional coefficients.

3. According to claim 2, a power plant visualization information management system based on digital twin technology is characterized by: The method for obtaining the over-limit duration ratio SC and the over-limit degree value CD is as follows: The time period when the out-of-bounds signal appears is marked as the out-of-bounds period, and the duration corresponding to the out-of-bounds period is processed by ratio with the duration corresponding to the monitoring period to obtain the out-of-bounds duration ratio, which is marked as SC; The operating voltages within the out-of-bounds period are summed and averaged to obtain the mean operating voltage within the out-of-bounds period. The mean operating voltage within the out-of-bounds period is processed by difference with the normal voltage of the equipment to obtain the mean operating voltage difference. The mean operating voltage difference is processed by ratio with the normal voltage of the equipment to obtain the out-of-bounds degree value, which is marked as CD.

4. According to claim 3, a power plant visual information management system based on digital twin technology is characterized in that: The operation change value is obtained in the following manner: Obtain the operating voltage of the power plant equipment during the out-of-bounds period, construct an operating voltage change curve, and obtain a change overlap value CH and a change deviation value BL based on processing and analysis of the operating voltage change curve; By formula: The running change value BH is obtained, wherein z1 and z2 are both preset proportional coefficients.

5. According to claim 4, a power plant visualization information management system based on digital twin technology is characterized in that: The change overlap value CH and the change deviation value BL are obtained as follows: Connect the two end points of the operating voltage change curve with a straight line to obtain a voltage change reference line, measure the overlap length between the operating voltage change curve and the voltage change reference line, and perform ratio processing with the length of the voltage change reference line to obtain the change overlap value, which is marked as CH; The part of the operating voltage change curve that does not overlap with the voltage change reference line is marked as a non-overlapping curve. The shortest distance between different points on the non-overlapping curve and the voltage change reference line is obtained, and the sum is averaged to obtain the average distance between the non-overlapping curve and the voltage change reference line. The average distance is then ratioed with the length of the voltage change reference line to obtain the change deviation value, which is marked as BL.

6. According to claim 5, a power plant visual information management system based on digital twin technology is characterized in that: The predicted voltage at different time nodes is obtained as follows: All operating voltages of power plant equipment within the out-of-bounds period are integrated into a data set as a training data set. If the change type of the operating data of the power plant equipment is a regular change, a linear regression model is selected as the prediction model. If the change type of the operating data of the power plant equipment is an irregular change, a random forest network model is selected as the prediction model. The prediction model is trained using the training data set to obtain a trained prediction model. The device voltage threshold is input into the prediction model to obtain the time point when the operating voltage of the power plant equipment reaches the device voltage threshold, and is marked as the arrival time point. The arrival time point is processed with the current time point to obtain the remaining time for the operating voltage of the power plant equipment to reach the device voltage threshold, and the time period corresponding to the remaining time is marked as the prediction period; The different time nodes within the prediction period are input into the prediction model to obtain the predicted voltages at the different time nodes within the prediction period.

7. A power plant visual information management system based on digital twin technology according to claim 6, characterized in that: The method for obtaining the change approach value is: During the forecast period, a monitoring period is preset, and the operating voltage of the power plant equipment monitored in real time at different time nodes during the preset monitoring period is obtained and processed and analyzed to obtain the change deviation quantity ratio BT and the change deviation degree value BJ; By formula: The change approach value QJ is obtained, wherein s1 and s2 are both preset proportional coefficients.

8. A power plant visual information management system based on digital twin technology according to claim 7, characterized in that: The change deviation quantity ratio BT and the change deviation degree value BJ are obtained as follows: Obtain the operating voltage of the power plant equipment monitored in real time at different time nodes within the preset monitoring period, and compare it with the predicted voltage at different time nodes. Specifically: Based on any time point; If the operating voltage at a time node is not equal to the predicted voltage, the time node is marked as a different time node; If the operating voltage at a time node is equal to the predicted voltage, the time node is marked as the same time node; Count the total number of time nodes and the number of different time nodes in the preset monitoring period, and perform ratio processing on the number of different time nodes and the total number of time nodes in the preset monitoring period to obtain the change deviation number ratio, which is marked as BT; Obtain the operating voltage at different time nodes, and perform difference processing with the predicted voltage at different time nodes to obtain the operating voltage difference at different time nodes, and take the absolute value to obtain the absolute difference of the operating voltage at different time nodes, perform ratio processing on the absolute difference of the operating voltage at different time nodes and the predicted voltage at different time nodes to obtain the absolute difference ratio of the operating voltage at different time nodes, sum and average the absolute difference ratios of the operating voltage at all different time nodes to obtain the degree of change deviation value, and mark it as BJ.

9. A power plant visual information management system based on digital twin technology according to claim 8, characterized in that: The non-approaching similarity value is obtained in the following manner: Obtain the operating voltage difference at different time nodes, process and analyze to obtain the target quantity ratio MB and the variance value FC of the voltage difference data group; By formula: The non-approaching similarity value XS is obtained, where k1, k2 and k3 are preset proportional coefficients, and BT represents the ratio of the number of change deviations; The target quantity ratio MB and the variance value FC of the voltage difference data group are obtained as follows: Obtain the operating voltage difference of different time nodes. If the operating voltage difference is negative, mark the different time nodes as delayed nodes. If the operating voltage difference is positive, mark the different time nodes as advanced nodes. Compare the number of delayed nodes and the number of advanced nodes. If the number of delayed nodes is greater than the number of advanced nodes, the delayed nodes are used as target nodes. If the number of delayed nodes is less than the number of advanced nodes, the advanced nodes are used as target nodes. Count the number of target nodes and compare it with the total number of nodes at different times to get the target number ratio, which is marked as MB. The operating voltage differences of all target nodes are integrated into a voltage difference data group, and the variance value of the voltage difference data group is obtained and marked as FC.

Images