A method and system for intelligent detection of synchronization accuracy of fault indicators

Abstract

The present invention discloses a fault indicator synchronization accuracy intelligent detection method and system, which relate to the field of intelligent electric energy management technology, and solve the technical problem in the prior art that when an electric power system consumes electric energy, it is impossible to collect, monitor and analyze data on electric energy consumption, and the accuracy of data collection cannot be guaranteed. Specifically, a data collection, monitoring and analysis unit collects data on electric energy consumption, collects electric energy data from the electric power system monitored in real time, constructs an electric energy data set based on the collected electric energy data, and performs data comparison processing on the electric energy data set, and obtains a modeling analysis set after completion; a data modeling, analysis and prediction unit performs modeling, analysis and prediction on the modeling and analysis set, and generates a predicted normal signal or a predicted fault signal through a modeling and analysis early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent power management, and in particular to a method and system for intelligently detecting synchronization accuracy of a fault indicator. Background Art

[0002] Smart power management is a comprehensive management system that integrates modern information technology, Internet of Things technology, and big data analysis technology. It aims to achieve safe, efficient, environmentally friendly, and economical operation of the power system. The importance of smart power management is becoming increasingly prominent. First of all, it helps to improve the efficiency of power utilization and reduce power waste. By monitoring the use of power in real time, it is possible to promptly identify links with excessive power consumption and take corresponding measures to adjust and improve them.

[0003] However, in the prior art, it is impossible to collect data, monitor and analyze the power consumption when the power system consumes electricity, and the accuracy of data collection cannot be guaranteed. At the same time, it is impossible to model, analyze and predict the modeling analysis set, resulting in low efficiency in real-time power parameter prediction. In addition, it is impossible to monitor and warn of real-time power parameters, which reduces the efficiency of power parameter control.

[0004] In view of the above technical defects, a method and system for intelligent detection of synchronization accuracy of fault indicators are proposed. Summary of the invention

[0005] The purpose of the present invention is to solve the above-mentioned problem and to provide a method and system for intelligent detection of synchronization accuracy of a fault indicator.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A fault indicator synchronization accuracy intelligent detection system, used for electric energy parameter monitoring of power system, comprises a monitoring center cloud platform, wherein the monitoring center cloud platform is communicatively connected with a data acquisition monitoring and analysis unit, a data modeling analysis and prediction unit, a data real-time parameter early warning unit and a power management strategy evaluation unit;

[0008] The data collection, monitoring and analysis unit collects, monitors and analyzes the power consumption data, collects the power data of the power consumption system monitored in real time through the fault indicator, constructs the power data set according to the collected power data and performs data comparison processing on the power data set, and obtains the modeling analysis set after completion;

[0009] The data modeling analysis prediction unit performs modeling analysis and prediction on the modeling analysis set, and generates a predicted normal signal or a predicted fault signal through the modeling analysis warning. When the prediction is normal, the data real-time parameter warning unit performs a real-time parameter warning on the power data of the power consumption system, collects the real-time warning parameters, and substitutes them into the formula to obtain the real-time parameter warning coefficient during the operation of the power consumption system. According to the comparison of the coefficient threshold, a high warning signal or a low warning signal is generated, and sent to the monitoring center cloud platform;

[0010] The power management strategy evaluation unit conducts power management strategy evaluation on the power data of the power consumption system during early warning, collects power dispatch duration data and power control speed data, and infers whether the power management strategy evaluation is qualified based on data comparison.

[0011] As a preferred embodiment of the present invention, the operation process of the data acquisition, monitoring and analysis unit is as follows:

[0012] Electric energy data is collected for the power consumption system under real-time monitoring; the operation time is arbitrarily selected according to the operation time period of the power consumption system and the selected operation time is constructed into an electric energy data collection period according to the time sequence; the electric energy data within the electric energy data collection period is collected, and each electric energy data is sorted into groups according to the same type of data and an electric energy data collection is constructed.

[0013] As a preferred embodiment of the present invention, floating deviation information and floating duration information are obtained, and the floating deviation information and floating duration information are respectively the deviation value of any two electric energy data values ​​in each electric energy data set and the numerical value floating span peak value of the corresponding type of electric energy data at the fault moment, and the non-intersection duration corresponding to the numerical value floating period of the corresponding type of electric energy data at the fault moment and the duration period of the instantaneous floating of the value in the current electric energy data set;

[0014] If the floating deviation information exceeds the numerical deviation threshold, or the floating duration information does not exceed the non-intersection duration threshold, the current value in the electric energy data set is excluded, and the processed electric energy data set is marked as a modeling analysis set and sent to the monitoring center cloud platform;

[0015] If the floating deviation information does not exceed the numerical deviation threshold, and the floating duration information exceeds the non-intersection duration threshold, the current value in the electric energy data set is retained, and the electric energy data set after the retention is marked as a modeling analysis set and sent to the monitoring center cloud platform.

[0016] As a preferred embodiment of the present invention, the modeling analysis and prediction process is as follows:

[0017] A curve is constructed for the electric energy data values ​​in the modeling and analysis set, with the corresponding time intervals of adjacent electric energy data values ​​as the adjacent intervals of the horizontal axis, and the electric energy data values ​​as the vertical axis. The values ​​of each subset in the modeling and analysis set are substituted and connected to construct a real-time curve of electric energy data; at the same time, the historical operation time period of the power system is collected and the historical operation time points are selected, and the adjacent intervals of the collected time points are consistent with the intervals of the corresponding order in the current modeling and analysis set. At the same time, the time period constructed by the historical operation time points collected includes the power system fault period and the time when the power system fault occurs and the end time.

[0018] As a preferred embodiment of the present invention, the electric energy data values ​​at the historical operating time points in the historical operating period are synchronously substituted into the coordinate system and the electric energy data historical curve is constructed. The curve angle is formed according to the peak point of the curve corresponding to the power system fault period in the electric energy data historical curve, and the curve angle is marked as the fault risk angle. At the same time, the average value of the curve slope of each time point in the curve corresponding to the time when the power system fault occurs and ends in the electric energy data historical curve is marked as the fault risk slope.

[0019] As a preferred embodiment of the present invention, if the curve angle formed by the corresponding curve point at any time in the curve constructed in the modeling and analysis set does not exceed the fault risk angle, or the corresponding curve slopes at any adjacent time in the curve constructed in the modeling and analysis set do not exceed the mean value of the curve slope, then it is determined that the current modeling and analysis set data prediction is abnormal;

[0020] If the curve angle formed by the corresponding curve points at any time in the constructed curve in the modeling and analysis set exceeds the fault risk angle, and the corresponding curve slopes at any adjacent times in the constructed curve in the modeling and analysis set exceed the mean value of the curve slopes, then the current modeling and analysis set data prediction is judged to be normal.

[0021] As a preferred embodiment of the present invention, the real-time warning parameters include the excess of the instantaneous growth span of the real-time adjacent moment fluctuations of the same type of electric energy data during the operation of the power system and the average of the growth spans, the synchronous growth time interval span value of the floating duration of different types of electric energy data during the operation of the power system, and the continuous increase rate of the current floating electric energy type data after the floating of any type of electric energy data during the operation of the power system.

[0022] As a preferred implementation mode of the present invention, if the real-time parameter warning coefficient during the operation of the power system exceeds the real-time parameter warning coefficient threshold, it is determined that the real-time parameter warning of the data during the operation of the power system is abnormal; if the real-time parameter warning coefficient during the operation of the power system does not exceed the real-time parameter warning coefficient threshold, it is determined that the real-time parameter warning of the data during the operation of the power system is normal.

[0023] As a preferred implementation manner of the present invention, the power scheduling duration data and the power control speed data are respectively the overlapping duration of the power supply buffer duration corresponding to the power procurement alternative strategy when the power system power data is warned and the power system warning operation duration, and the maximum control speed ratio corresponding to the growth rate of the floating span of the power data after the execution of the power procurement alternative strategy when the power system power data is warned.

[0024] As a preferred implementation mode of the present invention, if the power scheduling duration data exceeds the overlapping duration threshold, or the power control speed data does not exceed the maximum control speed proportion threshold, then the power management strategy evaluation of the power system is determined to be inefficient; if the power scheduling duration data does not exceed the overlapping duration threshold, and the power control speed data exceeds the maximum control speed proportion threshold, then the power management strategy evaluation of the power system is determined to be efficient.

[0025] As a preferred embodiment of the present invention, a fault indicator synchronization accuracy intelligent detection method, the specific management method steps are as follows:

[0026] Step 1: Data collection and monitoring: Collect, monitor and analyze the power consumption data, collect power data from the power consumption system monitored in real time, construct a power data set according to the set sorting, and perform data comparison processing on the power data set. After completion, a modeling analysis set is obtained;

[0027] Step 2: Data modeling, analysis and prediction, modeling, analysis and prediction of the modeling analysis set, and generating predicted normal signals or predicted fault signals through modeling analysis warning;

[0028] Step 3: Real-time parameter warning of data, real-time parameter warning of power consumption system power data, collect real-time warning parameters, and substitute them into the formula to obtain the real-time parameter warning coefficient during the operation of the power consumption system, and generate a high warning signal or a low warning signal according to the coefficient threshold comparison;

[0029] Step 4: Electricity management strategy evaluation: Conduct electricity management strategy evaluation when warning electricity data of the power consumption system is issued. Collect electricity dispatch duration data and electricity control speed data, and infer whether the electricity management strategy evaluation is qualified based on data comparison.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. In the present invention, data collection, monitoring and analysis are performed on the power consumption, real-time power consumption data is collected and processed, anomalies in the power consumption data are eliminated, and the instantaneous value during the operation of the power system affects the accuracy of power consumption detection, while also avoiding the power management deviation caused by accidental deviation data of the power system; modeling, analysis and prediction are performed on the modeling and analysis set, and the current data modeling set is compared and analyzed with the historical time period data curve to infer whether there is an anomaly in the current modeling and analysis set, so as to facilitate the prediction and analysis of the real-time power system power data trend, and timely infer the abnormal probability of the power data of the current power system, which is beneficial to improve the efficiency of intelligent control of power data, ensure the operation qualification of the power system, and reduce the impact of the abnormal power data of the power system on the system operation.

[0032] 2. In the present invention, real-time parameter warning is performed on the power data of the power consumption system, and whether there are parameter anomalies in the power data in the current power consumption system is inferred through real-time parameter analysis. Real-time efficiency monitoring is performed on the operation of the power consumption system to ensure the efficiency of power data management and control, and to ensure that fault prediction can be performed in time during the power data monitoring process to ensure the operating efficiency of the power consumption system; when the power data of the power consumption system is warned, the power management strategy is evaluated to infer whether the power control efficiency of the current power consumption system meets the actual needs, so as to avoid the power consumption system being unable to be rectified in time when the power data is abnormal, thereby reducing the high efficiency of the power consumption system operation, and ensuring that the abnormal power data does not affect the overall operation of the power consumption system. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0034] Figure 1 A flowchart of a fault indicator synchronization accuracy intelligent detection system according to an embodiment of the present invention;

[0035] Figure 2 The present invention is a flowchart of a method for intelligently detecting synchronization accuracy of a fault indicator according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0038] Example 1, please refer to Figure 1 As shown, a fault indicator synchronization accuracy intelligent detection system is used for electric energy parameter monitoring of a power system, including a monitoring center cloud platform, wherein the monitoring center cloud platform is communicatively connected to a data acquisition monitoring and analysis unit, a data modeling analysis and prediction unit, a data real-time parameter early warning unit, and a power management strategy evaluation unit;

[0039] The monitoring center cloud platform generates a data collection, monitoring and analysis signal and sends it to the data collection, monitoring and analysis unit. After receiving the data collection, monitoring and analysis signal, the data collection, monitoring and analysis unit performs data collection, monitoring and analysis on the power consumption through the fault indicator, collects and processes the real-time power consumption data, eliminates abnormal amounts of power consumption data, and affects the accuracy of power consumption detection by the instantaneous value when the power system is running. At the same time, it also avoids deviations in power control caused by accidental deviation data of the power system;

[0040] Collecting electric energy data from the real-time monitored power consumption system, where the electric energy data includes the real-time electric energy consumption parameters of the power consumption system, such as voltage, current, and power consumption; selecting an operation time at random according to the operation time period of the power consumption system and constructing an electric energy data collection period according to the time sequence of the selected operation time, collecting electric energy data within the electric energy data collection period, and sorting each electric energy data into groups according to the same type of data and constructing an electric energy data collection;

[0041] The deviation between the deviation value of any two electric energy data values ​​in each electric energy data set and the numerical deviation of the numerical floating span peak value of the corresponding type of electric energy data at the fault moment is obtained, and at the same time, the non-intersection duration corresponding to the numerical floating period of the corresponding type of electric energy data at the fault moment and the duration period of the instantaneous floating of the value in the current electric energy data set is obtained, and the deviation value of any two electric energy data values ​​in each electric energy data set and the numerical deviation between the numerical floating span peak value of the corresponding type of electric energy data at the fault moment, and the non-intersection duration corresponding to the numerical floating period of the corresponding type of electric energy data at the fault moment and the duration period of the instantaneous floating of the value in the current electric energy data set are marked as floating deviation information and floating duration information, respectively, and compared with the numerical deviation threshold and the non-intersection duration threshold, respectively:

[0042] If the deviation between any two electric energy data values ​​in each electric energy data set and the numerical deviation of the numerical floating span peak value of the corresponding type of electric energy data at the time of the fault exceeds the numerical deviation threshold, or the non-intersection duration corresponding to the numerical floating period of the corresponding type of electric energy data at the time of the fault and the duration of the instantaneous floating of the values ​​in the current electric energy data set does not exceed the non-intersection duration threshold, the current value in the electric energy data set is excluded, and the electric energy data set after processing is marked as a modeling analysis set and sent to the monitoring center cloud platform;

[0043] If the deviation between any two electric energy data values ​​in each electric energy data set and the numerical deviation of the numerical floating span peak value of the corresponding type of electric energy data at the time of the fault does not exceed the numerical deviation threshold, and the non-intersection duration corresponding to the numerical floating period of the corresponding type of electric energy data at the time of the fault and the duration of the instantaneous floating of the value in the current electric energy data set exceeds the non-intersection duration threshold, the current value in the electric energy data set is numerically retained, and the electric energy data set after the retention is completed is marked as a modeling analysis set and sent to the monitoring center cloud platform;

[0044] At the same time, a data modeling analysis prediction signal is generated and sent to the data modeling analysis prediction unit. After receiving the data modeling analysis prediction signal, the data modeling analysis prediction unit performs modeling analysis prediction on the modeling analysis set, compares and analyzes the historical period data curve with the current data modeling set, and infers whether there is an abnormality in the current modeling analysis set, which is convenient for predicting and analyzing the trend of electric energy data of the real-time power consumption system, and timely inferring the abnormal probability of electric energy data of the current power consumption system, which is conducive to improving the efficiency of intelligent control of electric energy data, ensuring the operation qualification of the power consumption system, and reducing the impact of abnormal electric energy data of the power consumption system on system operation;

[0045] Construct a curve of the electric energy data values ​​in the modeling and analysis set, use the time intervals of the corresponding moments of adjacent electric energy data values ​​as the adjacent time intervals of the horizontal axis, and use the electric energy data values ​​as the vertical axis, substitute the values ​​of each subset in the modeling and analysis set and connect them to construct a real-time curve of electric energy data; at the same time, collect the historical operation time period of the power system and select the historical operation time points, and the adjacent time intervals of the collected time points are consistent with the intervals of the corresponding order in the current modeling and analysis set, and the time period constructed by the historical operation time point collection includes the power system fault period and the time when the power system fault occurs and ends;

[0046] The electric energy data values ​​at the historical operation time points in the historical operation period are synchronously substituted into the coordinate system and the electric energy data historical curve is constructed. The curve angle formed by the peak point of the curve corresponding to the power system fault period in the electric energy data historical curve is marked as the fault risk angle. At the same time, the average value of the curve slope of each time point in the curve corresponding to the power system fault occurrence time and end time in the electric energy data historical curve is marked as the fault risk slope.

[0047] If the curve angle formed by the corresponding curve point at any time in the curve constructed in the modeling and analysis set does not exceed the fault risk angle, or the corresponding curve slopes at any adjacent times in the curve constructed in the modeling and analysis set do not exceed the average of the curve slopes, then the current modeling and analysis set data prediction is judged to be abnormal, a predicted fault signal is generated and sent to the monitoring center cloud platform. After receiving the predicted fault signal, the monitoring center cloud platform sets the time point corresponding to the curve part in the modeling and analysis set as the risk time and performs traceability monitoring on the operation process at the risk time, and at the same time, repairs the equipment involved in the power system at the current risk time;

[0048] If the curve angle formed by the corresponding curve point at any time in the constructed curve in the modeling and analysis set exceeds the fault risk angle, and the corresponding curve slopes at any adjacent time in the constructed curve in the modeling and analysis set exceed the average value of the curve slope, then it is determined that the current modeling and analysis set data prediction is normal, and a prediction normal signal is generated and sent to the monitoring center cloud platform;

[0049] At the same time, a data real-time parameter warning signal is generated and sent to a data real-time parameter warning unit. After receiving the data real-time parameter warning signal, the data real-time parameter warning unit performs a real-time parameter warning on the power data of the power consumption system, and infers whether there are parameter anomalies in the power data in the current power consumption system through real-time parameter analysis. The power consumption system operation is monitored in real time to ensure the efficiency of power data management and control, and to ensure that faults can be predicted in time during the power data monitoring process to ensure the operation efficiency of the power consumption system;

[0050] The excess of the instantaneous growth span and the average value of the growth span of the real-time adjacent moment value fluctuation of the same type of electric energy data during the operation of the power system is obtained, and the synchronous growth time interval span value of the floating duration of different types of electric energy data during the operation of the power system is obtained, and the excess of the instantaneous growth span and the average value of the growth span of the real-time adjacent moment value fluctuation of the same type of electric energy data during the operation of the power system and the synchronous growth time interval span value of the floating duration of different types of electric energy data during the operation of the power system are marked as DCL and KDZ respectively;

[0051] Obtain the continuous increase rate of the current floating electric energy type data after any type of electric energy data floats during the operation of the electric power system, and mark the continuous increase rate of the current floating electric energy type data after any type of electric energy data floats during the operation of the electric power system as ZSD;

[0052] The above collected data are uniformly marked as real-time warning parameters, and substituted into the formula to obtain the real-time parameter warning coefficient YJ during the operation of the power system. The formula is: , where mkj1, mkj2, and mkj3 are all preset proportional coefficients, and β is used as an error correction factor with a value of 0.98;

[0053] Compare the real-time parameter warning coefficient YJ with the real-time parameter warning coefficient threshold during the operation of the power system:

[0054] If the real-time parameter warning coefficient YJ exceeds the real-time parameter warning coefficient threshold during the operation of the power consumption system, it is determined that the real-time parameter warning of the data during the operation of the power consumption system is abnormal, and a high warning signal is generated and sent to the monitoring center cloud platform. After receiving the high warning signal, the monitoring center cloud platform performs maintenance control on the power consumption system and continuously monitors the electric energy data;

[0055] If the real-time parameter warning coefficient YJ during the operation of the power system does not exceed the real-time parameter warning coefficient threshold, it is determined that the real-time parameter warning of the data during the operation of the power system is normal, and a low warning signal is generated and sent to the monitoring center cloud platform;

[0056] At the same time, an electric energy management strategy evaluation signal is generated and sent to the electric energy management strategy evaluation unit. After receiving the electric energy management strategy evaluation signal, the electric energy management strategy evaluation unit evaluates the electric energy data of the power consumption system when warning, and infers whether the electric energy control efficiency of the current power consumption system meets the actual demand, so as to avoid the power consumption system being unable to be rectified in time when the electric energy data is abnormal, thereby reducing the high efficiency of the operation of the power consumption system, and ensuring that the abnormal electric energy data does not affect the overall operation of the power consumption system;

[0057] The overlapping time of the power supply buffer time corresponding to the power procurement alternative strategy during the power consumption system power data early warning and the power system early warning operation time is obtained, and at the same time, the proportion of the power data floating span growth rate corresponding to the maximum control speed after the power system power data early warning alternative strategy is executed is obtained, and the overlapping time of the power supply buffer time corresponding to the power procurement alternative strategy during the power consumption system power data early warning and the power system early warning operation time, and the proportion of the power data floating span growth rate corresponding to the maximum control speed after the power system power data early warning alternative strategy is executed are marked as power scheduling time data and power control speed data, and are compared with the overlapping time threshold and the maximum control speed proportion threshold respectively:

[0058] If the overlapping time of the power supply buffer time corresponding to the power procurement alternative strategy during the power consumption system power data warning and the power consumption system warning operation time exceeds the overlapping time threshold, or the proportion of the power data floating span growth rate corresponding to the maximum control speed after the power procurement alternative strategy is executed during the power consumption system power data warning does not exceed the maximum control speed proportion threshold, then it is determined that the power consumption system power management strategy evaluation is inefficient, a management strategy adjustment signal is generated and sent to the monitoring center cloud platform. After receiving the management strategy adjustment signal, the monitoring center cloud platform readjusts the power consumption system power management strategy, specifically, controls the power consumption of the power consumption system power dispatching time, and speeds up the power data control speed.

[0059] If the overlapping duration of the power supply buffer duration corresponding to the alternative power procurement strategy during the power system power data warning and the power system warning operation duration does not exceed the overlapping duration threshold, and the proportion of the maximum control speed corresponding to the floating span growth rate of the power data after the execution of the alternative power procurement strategy during the power system power data warning exceeds the maximum control speed proportion threshold, then the power system power management strategy evaluation is determined to be efficient, and a management strategy efficiency signal is generated and sent to the monitoring center cloud platform.

[0060] Example 2, see Figure 2 , a fault indicator synchronization accuracy intelligent detection method, the specific management method steps are as follows:

[0061] Step 1: Data collection and monitoring, data collection, monitoring and analysis of power consumption, power data collection for real-time monitored power consumption systems, building power data sets based on the collected power data and performing data comparison processing on the power data sets, and obtaining a modeling analysis set after completion;

[0062] Step 2: Data modeling, analysis and prediction, modeling, analysis and prediction of the modeling analysis set, and generating predicted normal signals or predicted fault signals through modeling analysis warning;

[0063] Step 3: Real-time parameter warning of data, real-time parameter warning of power consumption system power data, collect real-time warning parameters, and substitute them into the formula to obtain the real-time parameter warning coefficient during the operation of the power consumption system, and generate a high warning signal or a low warning signal according to the coefficient threshold comparison;

[0064] Step 4: Electricity management strategy evaluation: Conduct electricity management strategy evaluation when warning electricity data of the power consumption system is issued. Collect electricity dispatch duration data and electricity control speed data, and infer whether the electricity management strategy evaluation is qualified based on data comparison.

[0065] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by technicians in this field according to actual conditions;

[0066] When the present invention is in use, the data acquisition, monitoring and analysis unit performs data acquisition, monitoring and analysis on the power consumption, collects power data on the power consumption system monitored in real time, constructs a power data set based on the collected power data, and then performs data comparison processing on the power data set to obtain a modeling analysis set after completion; the data modeling, analysis and prediction unit performs modeling, analysis and prediction on the modeling analysis set, and generates a predicted normal signal or a predicted fault signal through the modeling and analysis early warning, and when the prediction is normal, the data real-time parameter early warning unit performs real-time parameter early warning on the power system power data, collects real-time early warning parameters, and substitutes them into the formula to obtain the real-time parameter early warning coefficient during the operation of the power system, generates a high warning signal or a low warning signal according to the comparison of the coefficient threshold, and sends it to the monitoring center cloud platform; the power management strategy evaluation unit performs power management strategy evaluation on the power system power data during the early warning, collects power scheduling duration data and power control speed data, and infers whether the power management strategy evaluation is qualified according to data comparison.

[0067] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A fault indicator synchronization accuracy intelligent detection system for monitoring electric energy parameters in a power system, characterized in that: It includes a monitoring center cloud platform, wherein the monitoring center cloud platform is connected to a data acquisition monitoring and analysis unit, a data modeling analysis and prediction unit, a data real-time parameter early warning unit, and a power management strategy evaluation unit; The data collection, monitoring and analysis unit collects, monitors and analyzes the power consumption, that is, collects the power data of the power consumption system monitored in real time through the fault indicator, builds the power data set according to the collected power data, and performs data comparison processing on the power data set, and obtains the modeling analysis set after completion; The data modeling analysis prediction unit performs modeling analysis and prediction on the modeling analysis set, and generates a predicted normal signal or a predicted fault signal through the modeling analysis warning. When the prediction is normal, the data real-time parameter warning unit performs a real-time parameter warning on the power data of the power consumption system, collects the real-time warning parameters, and obtains the real-time parameter warning coefficient during the operation of the power consumption system through calculation, generates a high warning signal or a low warning signal according to the comparison of the coefficient threshold, and sends it to the monitoring center cloud platform; The power management strategy evaluation unit evaluates the power management strategy of the power consumption system power data during early warning, collects power dispatch duration data and power control speed data, and infers whether the power management strategy evaluation is qualified based on data comparison; The modeling analysis and prediction process is as follows: Construct a curve of the electric energy data values ​​in the modeling and analysis set, use the time intervals of the corresponding moments of adjacent electric energy data values ​​as the adjacent time intervals of the horizontal axis, and use the electric energy data values ​​as the vertical axis, substitute the values ​​of each subset in the modeling and analysis set and connect them to construct a real-time curve of electric energy data; at the same time, collect the historical operation time period of the power system and select the historical operation time points, and the adjacent time intervals of the collected time points are consistent with the intervals of the corresponding order in the current modeling and analysis set, and the time period constructed by the historical operation time point collection includes the power system fault period and the time when the power system fault occurs and ends; The electric energy data values ​​at the historical operation time points in the historical operation period are synchronously substituted into the coordinate system and the electric energy data historical curve is constructed. The curve angle formed by the peak point of the curve corresponding to the power system fault period in the electric energy data historical curve is marked as the fault risk angle. At the same time, the average value of the curve slope of each time point in the curve corresponding to the power system fault occurrence time and end time in the electric energy data historical curve is marked as the fault risk slope. If the curve angle formed by the corresponding curve point at any time in the constructed curve in the modeling and analysis set does not exceed the fault risk angle, or the corresponding curve slopes at any adjacent time in the constructed curve in the modeling and analysis set do not exceed the mean value of the curve slope, then the current modeling and analysis set data prediction is determined to be abnormal; If the curve angle formed by the corresponding curve points at any time in the constructed curve in the modeling and analysis set exceeds the fault risk angle, and the corresponding curve slopes at any adjacent times in the constructed curve in the modeling and analysis set exceed the mean value of the curve slopes, then the current modeling and analysis set data prediction is judged to be normal.

2. The fault indicator synchronization accuracy intelligent detection system according to claim 1 is characterized in that: The operation process of the data acquisition, monitoring and analysis unit is as follows: Electric energy data is collected for the power consumption system under real-time monitoring; the operation time is arbitrarily selected according to the operation time period of the power consumption system and the selected operation time is constructed into an electric energy data collection period according to the time sequence; the electric energy data within the electric energy data collection period is collected, and each electric energy data is sorted into groups according to the same type of data and an electric energy data collection is constructed.

3. The fault indicator synchronization accuracy intelligent detection system according to claim 2 is characterized in that: The floating deviation information and floating duration information are obtained, and the floating deviation information and floating duration information are respectively the numerical deviation between the deviation value of any two electric energy data values ​​in each electric energy data set and the numerical floating span peak value of the corresponding type of electric energy data at the fault moment, and the non-intersection duration corresponding to the numerical floating period of the corresponding type of electric energy data at the fault moment and the duration period of the instantaneous floating of the values ​​in the current electric energy data set; If the floating deviation information exceeds the numerical deviation threshold, or the floating duration information does not exceed the non-intersection duration threshold, the current value in the electric energy data set is excluded, and the processed electric energy data set is marked as a modeling analysis set and sent to the monitoring center cloud platform; If the floating deviation information does not exceed the numerical deviation threshold, and the floating duration information exceeds the non-intersection duration threshold, the current value in the electric energy data set is retained, and the electric energy data set after the retention is marked as a modeling analysis set and sent to the monitoring center cloud platform.

4. The fault indicator synchronization accuracy intelligent detection system according to claim 1 is characterized in that: The real-time warning parameters include the excess of the instantaneous growth span of the real-time adjacent moments of the same type of electric energy data during the operation of the power system and the average of the growth span, the synchronous growth time interval span value of the floating duration of different types of electric energy data during the operation of the power system, and the continuous increase rate of the current floating electric energy type data after the floating of any type of electric energy data during the operation of the power system.

5. The fault indicator synchronization accuracy intelligent detection system according to claim 4 is characterized in that: If the real-time parameter warning coefficient during the operation of the power system exceeds the real-time parameter warning coefficient threshold, it is determined that the real-time parameter warning of the data during the operation of the power system is abnormal; If the real-time parameter warning coefficient during the operation of the power consumption system does not exceed the real-time parameter warning coefficient threshold, it is determined that the real-time parameter warning of the data during the operation of the power consumption system is normal.

6. The fault indicator synchronization accuracy intelligent detection system according to claim 1, characterized in that: The power dispatch duration data and power control speed data are respectively the overlap duration of the power supply buffer duration corresponding to the power procurement alternative strategy during the power system power data warning and the power system warning operation duration, and the proportion of the maximum control speed corresponding to the growth rate of the power data floating span after the power procurement alternative strategy is executed during the power system power data warning; If the power dispatching duration data exceeds the overlapping duration threshold, or the power control speed data does not exceed the maximum control speed ratio threshold, it is determined that the power management strategy evaluation of the power consumption system is inefficient; If the power dispatching duration data does not exceed the overlapping duration threshold, and the power control speed data exceeds the maximum control speed ratio threshold, it is determined that the power management strategy evaluation of the power consumption system is efficient.

7. A fault indicator synchronization accuracy intelligent detection method, characterized in that: An intelligent detection system for synchronization accuracy of a fault indicator is implemented based on any one of claims 1 to 6.

Images