Water, electricity and electric energy real-time monitoring device and method

Abstract

The invention relates to the technical field of hydropower station electric energy monitoring, in particular to a hydropower electric energy real-time monitoring device and method. The technical problems that in the prior art, an electric energy monitoring system can only simply process data in a single time period and lacks the correlation analysis capability of continuous multi-time-period data, and due to the limitation of a data processing technology, the recognition precision of an existing system on abnormal data is limited; according to the technical scheme, the real-time monitoring device and method for hydropower and electric energy comprise a data acquisition module, a data transmission module, a data processing module, a data display module and an early warning module; according to the method, deep mining is carried out on continuous multi-period data through correlation analysis and an anomaly detection algorithm, so that the recognition precision of abnormal data is effectively improved, and the rate of missing report and false report is reduced; through intelligent analysis and early warning functions, potential dangerous states can be found and early warned in time, the early warning response speed and processing capacity are improved, and safe and stable operation of the hydropower station is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower station electric energy monitoring, and in particular to a hydropower electric energy real-time monitoring device and method. Background Art

[0002] As an important energy supply base, the stability and safety of hydropower station power parameters are directly related to the operation quality and power safety of the power grid. Traditional hydropower power monitoring methods mostly rely on manual inspections and regular testing, which have problems such as long monitoring cycles, poor real-time performance, and insufficient data accuracy. With the rapid development of information technology, automated and intelligent monitoring technologies have gradually become mainstream, but existing technologies still face challenges such as limited data processing capabilities, low anomaly recognition accuracy, and delayed early warning responses.

[0003] Among them, the existing monitoring system can only perform simple processing on the data of a single period, lacks the ability to analyze the correlation of continuous multi-period data, and is difficult to explore the internal connections and patterns between the data; due to the limitations of data processing technology, the existing system has limited accuracy in identifying abnormal data, and is prone to underreporting or false reporting, which affects the monitoring effect; at the same time, the early warning function of the existing monitoring system is mostly based on threshold settings, lacks intelligent analysis and prediction capabilities, resulting in delayed early warning response and failure to effectively prevent potential dangers in a timely manner;

[0004] Therefore, in view of the problems of low abnormal recognition accuracy and delayed early warning response of the electric energy monitoring system under the existing technology, a real-time monitoring device and method for hydropower electric energy are proposed, aiming to achieve comprehensive, real-time and accurate monitoring of the electric energy parameters of the hydropower station through advanced data acquisition, transmission, processing and analysis technologies. Summary of the invention

[0005] In order to overcome the problems that the monitoring systems under existing technologies can only perform simple processing on data of a single time period, lack the ability to conduct correlation analysis on continuous data of multiple time periods, and find it difficult to explore the intrinsic connections and patterns between data; due to the limitations of data processing technology, the existing systems have limited accuracy in identifying abnormal data, and are prone to underreporting or false reporting, which affects the monitoring effect; at the same time, the early warning functions of existing monitoring systems are mostly based on threshold settings, lack intelligent analysis and prediction capabilities, resulting in delayed early warning responses and an inability to timely and effectively prevent potential dangers.

[0006] The technical solution of the present invention is: a real-time monitoring device for hydropower and electric energy, comprising:

[0007] Data acquisition module, used to collect real-time power data of the hydropower station, including current, voltage, and power factor parameters;

[0008] A data transmission module, used for transmitting the collected data to a data processing center;

[0009] The data processing module is used to process and analyze the collected data, including data cleaning, conversion, correlation analysis, and time series feature mining of abnormal data;

[0010] The data display module is used to display the processed data to the user in a graphical and visual way;

[0011] The early warning module is used to warn of potential dangerous conditions of hydropower and electric energy based on the analysis results of the data processing module.

[0012] Preferably, the electric energy data of the hydropower station, including current, voltage, and power factor parameters, are collected in real time through the data collection module; the collected data are transmitted to the data processing center through the data transmission module; the collected data are processed and analyzed through the data processing module, including data cleaning, conversion, correlation analysis, and time series feature mining of abnormal data; the processed data are displayed to the user in a graphical and visual manner through the data display module; and the potential dangerous state of hydropower electricity is warned through the early warning module according to the analysis results of the data processing module.

[0013] Preferably, the data acquisition module includes a sensor group and a data collector; the sensor group is composed of a variety of sensors, including a current sensor, a voltage sensor and a power factor sensor, which are used to collect the electric energy data of the hydropower station in real time; the data collector is connected to the sensor group, responsible for receiving the data collected by the sensor group, and performing preliminary processing and conversion to ensure the accuracy and real-time nature of the data; when the data acquisition module is working, it includes the following steps:

[0014] S201: Initializing the data acquisition module, including calibration of the sensor group and parameter setting of the data acquisition module;

[0015] S202: The sensor group collects the power data of the hydropower station in real time, including current, voltage, and power factor parameters;

[0016] S203: The data collector receives the data collected by the sensor group and performs preliminary processing and conversion, including data cleaning, denoising, and format conversion operations.

[0017] Preferably, the data transmission module includes a data interface unit, a data transmission unit, a data encryption unit, a data verification unit and a communication management unit; the data interface unit is used to connect to the data acquisition module to receive the electric energy data collected by it; the data transmission unit is used to transmit the received data to the data processing module via wireless transmission; the data encryption unit is used to encrypt the data before data transmission using an encryption algorithm and a key management method; the data verification unit is used to verify the data during the data transmission process by adding a verification code; the communication management unit is used to manage and monitor the communication status during the data transmission process, including the establishment, maintenance and disconnection of the communication link, and the monitoring and optimization of the communication quality.

[0018] Preferably, the data processing module includes a data receiving unit, a data cleaning unit, a data conversion unit, a correlation analysis unit, an anomaly detection unit, a feature extraction unit and a data storage unit; the data receiving unit is used to receive the electric energy data transmitted by the data transmission module; the data cleaning unit is used to clean the received data, remove invalid data, fill in missing data, and correct erroneous data; the data conversion unit is used to convert the format of the cleaned data into time series data and structured data; the correlation analysis unit is used to use the correlation analysis algorithm to perform correlation analysis on the results of multiple consecutive time periods, explore the internal connections and laws between the data, and provide strong support for anomaly detection and early warning; the anomaly detection unit is used to use the anomaly detection algorithm to deeply mine the time series features and identify abnormal data and potential dangerous conditions; the feature extraction unit is used to further analyze the abnormal data and extract relevant feature information, including the type, occurrence time and duration of the abnormal data; the data storage unit is used to store the processed data.

[0019] Preferably, the data processing module uses the Apriori algorithm when performing association analysis, including the following steps:

[0020] S501: Divide the time series data according to the time window to form a data set of multiple time periods; the data set of each time period includes the current, voltage, and power factor parameters within the time period;

[0021] S502: Starting from a data set of a single period, scanning the data set to find all frequent item sets, that is, item sets with an occurrence frequency higher than a preset threshold;

[0022] S503: According to the property of the Apriori algorithm, that is, any infrequent (k-1) item set cannot be a superset of the frequent k item set, the candidate item set is pruned to remove the impossible candidate item sets;

[0023] S504: Calculate the support of the remaining candidate item sets in the data set, that is, the frequency of the remaining candidate item sets appearing in the data set;

[0024] S505: retaining candidate item sets with support higher than a preset threshold as frequent item sets;

[0025] S506: Generate association rules based on frequent item sets; the rules describe the association relationship between data items in different time periods;

[0026] The data processing module uses the isolation forest algorithm when performing anomaly detection, including the following steps:

[0027] S601: converting the time series data into a format suitable for processing by the isolation forest algorithm, taking the data of each period as a sample, and the sample features are current, voltage, and power factor parameters;

[0028] S602: randomly selecting multiple features and a random split point to split the data space until each subspace contains only one data point or reaches a preset tree depth, and repeating this process to construct multiple isolated trees;

[0029] S603: For each data point, calculate its path length in the isolation forest, that is, the number of edges from the root node to the leaf node. The shorter the path length, the more abnormal the data point.

[0030] S604: according to the path length distribution of normal data points in the isolation forest, a threshold is set to distinguish normal data from abnormal data;

[0031] S605: Input the data point to be detected into the isolation forest, calculate its anomaly score, and compare it with the threshold to determine whether it is abnormal data.

[0032] Preferably, the data processing module uses a time series-based feature extraction method when performing feature extraction, including the following steps:

[0033] S701: Divide the time period where the abnormal data is located into multiple sub-time periods;

[0034] S702: Calculate the statistical characteristics of each sub-time period, including mean, variance, kurtosis, and skewness, to describe the distribution characteristics of the data;

[0035] S703: Describe the dynamic characteristics of the data according to the changing trend of the abnormal data over time, including linear trend and periodic trend;

[0036] S704: Perform spectrum analysis on the abnormal data to extract spectrum features, including frequency components and spectrum energy, to describe the frequency characteristics of the data.

[0037] Preferably, the data display module includes a graphical display unit, a visualization interaction unit and a user interface unit; the graphical display unit is used to display the processed data in a graphical manner, including but not limited to line graphs, bar graphs, pie charts; the visualization interaction unit is used to provide users with interactive functions with the graphical display, including zooming, panning, and selection; the user interface unit is used to provide a user operation interface so that users can easily view and analyze data.

[0038] Preferably, the data display module comprises the following steps when operating:

[0039] S801: The data display module first receives processed data from the data processing module; the data includes real-time values ​​of current, voltage, power factor parameters, historical data, and abnormal detection results;

[0040] S802: After receiving the data, the data display module performs filtering, sorting, and aggregation operations on the data to convert it into a graphical display format;

[0041] S803: The data processed in step S802 is transmitted to a graphical display unit, which selects appropriate graphics for display according to the type of data and user needs; for time series data, a line graph is selected to display the data change trend; for categorical data, a pie chart is selected to display the proportion of each category;

[0042] S804: The user interacts with the graphical display through the visualization interaction unit;

[0043] S805: When the user interacts or the data changes, the data display module will update the graphical display to reflect the latest data and user needs.

[0044] Preferably, the early warning module includes an early warning analysis unit, an early warning rule base, an early warning signal generation unit and an early warning notification unit; the early warning analysis unit is used to determine whether the hydropower and electric energy are in a potentially dangerous state based on the analysis results of the data processing module in combination with the rules in the early warning rule base; the early warning rule base stores early warning rules related to the dangerous state of hydropower and electric energy; the early warning signal generation unit is used to generate an early warning signal when it is determined that the hydropower and electric energy is in a potentially dangerous state; the early warning notification unit is used to notify the user of the early warning signal in a variety of ways, including but not limited to sound, light, text message, and email.

[0045] A method for real-time monitoring of hydropower energy comprises the following steps:

[0046] S1: Initialize the data acquisition module, including the calibration of the sensor group and the parameter setting of the data collector;

[0047] S2: The sensor group collects the power data of the hydropower station in real time, including current, voltage, and power factor parameters;

[0048] S3: The data collector receives the data collected by the sensor group and performs preliminary processing and conversion, including data cleaning, denoising, and format conversion operations;

[0049] S4: The data interface unit is connected to the data acquisition module to receive the collected electric energy data;

[0050] S5: The data transmission unit transmits the received data to the data processing module via wireless transmission;

[0051] S6: The data encryption unit uses an encryption algorithm and a key management method to encrypt the data before transmission;

[0052] S7: The data checking unit verifies the data during the data transmission by adding a check code;

[0053] S8: The data receiving unit receives the electric energy data transmitted by the data transmission module;

[0054] S9: The data cleaning unit cleans the received data to remove invalid data, fill in missing data, and correct erroneous data;

[0055] S10: The data conversion unit converts the format of the cleaned data into time series data and structured data;

[0056] S11: Divide the time series data into time windows to form data sets for multiple time periods;

[0057] S12: Scan the data set to find all frequent itemsets, i.e., itemsets whose occurrence frequency is higher than a preset threshold;

[0058] S13: Prune the candidate item sets and remove impossible candidate item sets;

[0059] S14: Calculate the support of the remaining candidate item sets in the data set;

[0060] S15: retain candidate item sets with support higher than the preset threshold as frequent item sets;

[0061] S16: Generate association rules based on frequent item sets to describe the association relationship between data items in different time periods;

[0062] S17: Convert the time series data into a format suitable for processing by the Isolation Forest algorithm;

[0063] S18: Build multiple isolated trees to split the data space by randomly selecting multiple features and a random split point;

[0064] S19: Calculate the path length of each data point in the isolation forest and determine the abnormality of the data point based on the path length;

[0065] S20: Setting a threshold to distinguish normal data from abnormal data;

[0066] S21: Input the data point to be detected into the isolation forest, calculate its anomaly score, and compare it with the threshold to determine whether it is abnormal data;

[0067] S22: The feature extraction unit extracts relevant feature information from the abnormal data, including the type, occurrence time, and duration of the abnormal data;

[0068] S23: The early warning analysis unit determines whether the hydropower energy is in a potentially dangerous state based on the analysis results of the data processing module and the rules in the early warning rule library;

[0069] S24: If it is determined that the hydropower energy is in a potentially dangerous state, the warning signal generating unit generates a warning signal;

[0070] S25: The warning notification unit notifies the user of the warning signal in a variety of ways, including but not limited to sound, light, text message, and email.

[0071] Beneficial effects of the present invention:

[0072] 1. Aiming at the problem that the abnormality recognition accuracy of the electric energy monitoring system under the existing technology is not high, the present invention uses correlation analysis and anomaly detection algorithm to deeply mine the data of multiple consecutive periods, effectively improving the recognition accuracy of abnormal data and reducing the omission and false alarm rates;

[0073] 2. In view of the problem of delayed early warning response of the electric energy monitoring system under the prior art, the present invention can timely discover and warn of potential dangerous conditions through intelligent analysis and early warning functions, improve the early warning response speed and processing capabilities, and help ensure the safe and stable operation of the hydropower station. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 Shown is a schematic diagram of the working process of the hydropower and electric energy real-time monitoring device of the present invention;

[0075] Figure 2 Shown is a schematic flow chart of the steps of the real-time monitoring method for hydropower and electric energy of the present invention. DETAILED DESCRIPTION

[0076] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0077] See also Figure 1-2The present invention provides an embodiment: a real-time monitoring device for hydropower and electric energy, comprising:

[0078] Data acquisition module, used to collect real-time power data of the hydropower station, including current, voltage, and power factor parameters;

[0079] A data transmission module, used for transmitting the collected data to a data processing center;

[0080] The data processing module is used to process and analyze the collected data, including data cleaning, conversion, correlation analysis, and time series feature mining of abnormal data;

[0081] The data display module is used to display the processed data to the user in a graphical and visual way;

[0082] The early warning module is used to warn of potential dangerous conditions of hydropower and electric energy based on the analysis results of the data processing module.

[0083] Preferably, the electric energy data of the hydropower station, including current, voltage, and power factor parameters, are collected in real time through the data collection module; the collected data are transmitted to the data processing center through the data transmission module; the collected data are processed and analyzed through the data processing module, including data cleaning, conversion, correlation analysis, and time series feature mining of abnormal data; the processed data are displayed to the user in a graphical and visual manner through the data display module; and the potential dangerous state of hydropower electricity is warned through the early warning module according to the analysis results of the data processing module.

[0084] Preferably, the data acquisition module includes a sensor group and a data collector; the sensor group is composed of a variety of sensors, including a current sensor, a voltage sensor and a power factor sensor, which are used to collect the electric energy data of the hydropower station in real time; the data collector is connected to the sensor group, responsible for receiving the data collected by the sensor group, and performing preliminary processing and conversion to ensure the accuracy and real-time nature of the data; when the data acquisition module is working, it includes the following steps:

[0085] S201: Initializing the data acquisition module, including calibration of the sensor group and parameter setting of the data acquisition module;

[0086] S202: The sensor group collects the power data of the hydropower station in real time, including current, voltage, and power factor parameters;

[0087] S203: The data collector receives the data collected by the sensor group and performs preliminary processing and conversion, including data cleaning, denoising, and format conversion operations.

[0088] Preferably, the data transmission module includes a data interface unit, a data transmission unit, a data encryption unit, a data verification unit and a communication management unit; the data interface unit is used to connect to the data acquisition module to receive the electric energy data collected by it; the data transmission unit is used to transmit the received data to the data processing module via wireless transmission; the data encryption unit is used to encrypt the data before data transmission using an encryption algorithm and a key management method; the data verification unit is used to verify the data during the data transmission process by adding a verification code; the communication management unit is used to manage and monitor the communication status during the data transmission process, including the establishment, maintenance and disconnection of the communication link, and the monitoring and optimization of the communication quality.

[0089] Preferably, the data processing module includes a data receiving unit, a data cleaning unit, a data conversion unit, a correlation analysis unit, an anomaly detection unit, a feature extraction unit and a data storage unit; the data receiving unit is used to receive the electric energy data transmitted by the data transmission module; the data cleaning unit is used to clean the received data, remove invalid data, fill in missing data, and correct erroneous data; the data conversion unit is used to convert the format of the cleaned data into time series data and structured data; the correlation analysis unit is used to use the correlation analysis algorithm to perform correlation analysis on the results of multiple consecutive time periods, explore the internal connections and laws between the data, and provide strong support for anomaly detection and early warning; the anomaly detection unit is used to use the anomaly detection algorithm to deeply mine the time series features and identify abnormal data and potential dangerous conditions; the feature extraction unit is used to further analyze the abnormal data and extract relevant feature information, including the type, occurrence time and duration of the abnormal data; the data storage unit is used to store the processed data.

[0090] Preferably, the data processing module uses the Apriori algorithm when performing association analysis, including the following steps:

[0091] S501: Divide the time series data according to the time window to form a data set of multiple time periods; the data set of each time period includes the current, voltage, and power factor parameters within the time period;

[0092] S502: Starting from a data set of a single period, scanning the data set to find all frequent item sets, that is, item sets with an occurrence frequency higher than a preset threshold;

[0093] S503: According to the property of the Apriori algorithm, that is, any infrequent (k-1) item set cannot be a superset of the frequent k item set, the candidate item set is pruned to remove the impossible candidate item sets;

[0094] S504: Calculate the support of the remaining candidate item sets in the data set, that is, the frequency of the remaining candidate item sets appearing in the data set;

[0095] S505: retaining candidate item sets with support higher than a preset threshold as frequent item sets;

[0096] S506: Generate association rules based on frequent item sets; the rules describe the association relationship between data items in different time periods;

[0097] The data processing module uses the isolation forest algorithm when performing anomaly detection, including the following steps:

[0098] S601: converting the time series data into a format suitable for processing by the isolation forest algorithm, taking the data of each period as a sample, and the sample features are current, voltage, and power factor parameters;

[0099] S602: randomly selecting multiple features and a random split point to split the data space until each subspace contains only one data point or reaches a preset tree depth, and repeating this process to construct multiple isolated trees;

[0100] S603: For each data point, calculate its path length in the isolation forest, that is, the number of edges from the root node to the leaf node. The shorter the path length, the more abnormal the data point.

[0101] S604: according to the path length distribution of normal data points in the isolation forest, a threshold is set to distinguish normal data from abnormal data;

[0102] S605: Input the data point to be detected into the isolation forest, calculate its anomaly score, and compare it with the threshold to determine whether it is abnormal data.

[0103] Preferably, the data processing module uses a time series-based feature extraction method when performing feature extraction, including the following steps:

[0104] S701: Divide the time period where the abnormal data is located into multiple sub-time periods;

[0105] S702: Calculate the statistical characteristics of each sub-time period, including mean, variance, kurtosis, and skewness, to describe the distribution characteristics of the data;

[0106] S703: Describe the dynamic characteristics of the data according to the changing trend of the abnormal data over time, including linear trend and periodic trend;

[0107] S704: Perform spectrum analysis on the abnormal data to extract spectrum features, including frequency components and spectrum energy, to describe the frequency characteristics of the data.

[0108] Preferably, the data display module includes a graphical display unit, a visualization interaction unit and a user interface unit; the graphical display unit is used to display the processed data in a graphical manner, including but not limited to line graphs, bar graphs, pie charts; the visualization interaction unit is used to provide users with interactive functions with the graphical display, including zooming, panning, and selection; the user interface unit is used to provide a user operation interface so that users can easily view and analyze data.

[0109] Preferably, the data display module comprises the following steps when operating:

[0110] S801: The data display module first receives processed data from the data processing module; the data includes real-time values ​​of current, voltage, power factor parameters, historical data, and abnormal detection results;

[0111] S802: After receiving the data, the data display module performs filtering, sorting, and aggregation operations on the data to convert it into a graphical display format;

[0112] S803: The data processed in step S802 is transmitted to a graphical display unit, which selects appropriate graphics for display according to the type of data and user needs; for time series data, a line graph is selected to display the data change trend; for categorical data, a pie chart is selected to display the proportion of each category;

[0113] S804: The user interacts with the graphical display through the visualization interaction unit;

[0114] S805: When the user interacts or the data changes, the data display module will update the graphical display to reflect the latest data and user needs.

[0115] Preferably, the early warning module includes an early warning analysis unit, an early warning rule base, an early warning signal generation unit and an early warning notification unit; the early warning analysis unit is used to determine whether the hydropower and electric energy are in a potentially dangerous state based on the analysis results of the data processing module in combination with the rules in the early warning rule base; the early warning rule base stores early warning rules related to the dangerous state of hydropower and electric energy; the early warning signal generation unit is used to generate an early warning signal when it is determined that the hydropower and electric energy is in a potentially dangerous state; the early warning notification unit is used to notify the user of the early warning signal in a variety of ways, including but not limited to sound, light, text message, and email.

[0116] A method for real-time monitoring of hydropower energy comprises the following steps:

[0117] S1: Initialize the data acquisition module, including the calibration of the sensor group and the parameter setting of the data collector;

[0118] S2: The sensor group collects the power data of the hydropower station in real time, including current, voltage, and power factor parameters;

[0119] S3: The data collector receives the data collected by the sensor group and performs preliminary processing and conversion, including data cleaning, denoising, and format conversion operations;

[0120] S4: The data interface unit is connected to the data acquisition module to receive the collected electric energy data;

[0121] S5: The data transmission unit transmits the received data to the data processing module via wireless transmission;

[0122] S6: The data encryption unit uses an encryption algorithm and a key management method to encrypt the data before transmission;

[0123] S7: The data checking unit verifies the data during the data transmission by adding a check code;

[0124] S8: The data receiving unit receives the electric energy data transmitted by the data transmission module;

[0125] S9: The data cleaning unit cleans the received data to remove invalid data, fill in missing data, and correct erroneous data;

[0126] S10: The data conversion unit converts the format of the cleaned data into time series data and structured data;

[0127] S11: Divide the time series data into time windows to form data sets for multiple time periods;

[0128] S12: Scan the data set to find all frequent itemsets, i.e., itemsets whose occurrence frequency is higher than a preset threshold;

[0129] S13: Prune the candidate item sets and remove impossible candidate item sets;

[0130] S14: Calculate the support of the remaining candidate item sets in the data set;

[0131] S15: retain candidate item sets with support higher than the preset threshold as frequent item sets;

[0132] S16: Generate association rules based on frequent item sets to describe the association relationship between data items in different time periods;

[0133] S17: Convert the time series data into a format suitable for processing by the Isolation Forest algorithm;

[0134] S18: Build multiple isolated trees to split the data space by randomly selecting multiple features and a random split point;

[0135] S19: Calculate the path length of each data point in the isolation forest and determine the abnormality of the data point based on the path length;

[0136] S20: Setting a threshold to distinguish normal data from abnormal data;

[0137] S21: Input the data point to be detected into the isolation forest, calculate its anomaly score, and compare it with the threshold to determine whether it is abnormal data;

[0138] S22: The feature extraction unit extracts relevant feature information from the abnormal data, including the type, occurrence time, and duration of the abnormal data;

[0139] S23: The early warning analysis unit determines whether the hydropower energy is in a potentially dangerous state based on the analysis results of the data processing module and the rules in the early warning rule library;

[0140] S24: If it is determined that the hydropower energy is in a potentially dangerous state, the warning signal generating unit generates a warning signal;

[0141] S25: The warning notification unit notifies the user of the warning signal in a variety of ways, including but not limited to sound, light, text message, and email.

[0142] Example

[0143] Optionally, a large hydropower station has an installed capacity of 2 million kilowatts and 8 generator sets. In order to improve the safety and stability of its operation, the hydropower station decides to introduce the real-time monitoring device for hydropower and electric energy of the present invention. The device needs to monitor the key parameters of the generator set such as current, voltage, power factor, etc. in real time, and ensure the accuracy, real-time and safety of the data.

[0144] When the data acquisition module is working:

[0145] Sensor group: including current sensor, voltage sensor and power factor sensor, which are installed on each generator set respectively;

[0146] Data collector: connected to the sensor group, receiving and processing data in real time; for example, during a data collection process, the data collector successfully received the following data: the current of generator 1 is 1200A, the voltage is 13.8kV, and the power factor is 0.85; the current of generator 2 is 1150A, the voltage is 13.9kV, and the power factor is 0.87; and so on;

[0147] When the data transmission module is working:

[0148] The data is transmitted to the data processing center in real time via wireless. During the transmission process, the data encryption unit uses the AES encryption algorithm to encrypt the data to ensure data security. The data verification unit verifies the data by adding CRC checksum to prevent data loss or error.

[0149] Data receiving and cleaning steps:

[0150] The data receiving unit successfully receives the data from the data transmission module; the data cleaning unit cleans the data. For example, during a data cleaning process, it is found that the current data of the generator 3 has abnormal fluctuations. The data cleaning algorithm is used to smooth the data to ensure the accuracy of the data.

[0151] Data conversion and association analysis steps:

[0152] The data conversion unit converts the cleaned data into time series data and structured data; the association analysis unit uses the Apriori algorithm to perform association analysis on the data of continuous multiple time periods; for example, through analysis, it is found that between 1:00 and 3:00 in the morning every day, the current of the generator set is generally low, about 1000A to 1100A, while the voltage is relatively stable at around 13.8kV; between 3:00 and 5:00 in the afternoon, both the current and voltage increase, the current reaches 1250A to 1350A, the voltage is stable at around 14kV, and the power factor is also correspondingly increased to around 0.90; these association analysis results provide strong support for the operation and management of the hydropower station;

[0153] Anomaly detection and feature extraction steps:

[0154] The anomaly detection unit uses the isolation forest algorithm to deeply mine the time series features; during a certain anomaly detection process, it was found that the voltage data of generator 4 dropped sharply in a short period of time, from 13.8kV to 12.5kV, and then quickly returned to normal; the anomaly detection unit successfully identified this abnormal event and triggered the early warning mechanism; the feature extraction unit further analyzed the abnormal event and extracted the type of abnormal data (voltage abnormality), occurrence time (14:30 on xx / xx / xx), duration (15 seconds) and other feature information;

[0155] When the data display module is working:

[0156] The graphical display unit displays the processed data to the user in the form of line graphs, bar graphs, pie charts, etc. For example, in a certain data display, the user can clearly see the current changes of the generator set in one day through the line graph; understand the power factor distribution of different generator sets through the bar graph; and grasp the overall power distribution of the hydropower station through the pie chart;

[0157] The visualization interaction unit provides interactive functions such as zooming, panning, and selection. Users can use these functions to view data for a specific period of time or perform data analysis. For example, users can use the zoom function to view detailed current data of a generator set in a specific period of time; use the pan function to view data comparisons on different dates; and use the selection function to conduct in-depth analysis of voltage data of a specific generator set.

[0158] The user interface unit provides a friendly operation interface, through which users can easily view and analyze data; the interface is equipped with clear navigation menus and shortcut buttons, so users can quickly find the data and analysis tools they need to view;

[0159] When the early warning module is working:

[0160] The early warning analysis unit makes a judgment based on the analysis results of the data processing module and the rules in the early warning rule library; in a certain early warning analysis, the early warning analysis unit finds that the current data of the generator 5 exceeds the preset threshold value of 1400A, and the duration exceeds the specified time range of 5 minutes; based on these judgment results, the early warning analysis unit determines that the hydropower energy is in a potentially dangerous state;

[0161] Once it is determined that the hydropower and electricity are in a potentially dangerous state, the warning signal generation unit immediately generates a warning signal; the warning notification unit notifies the user of the warning signal in various ways such as sound, light, text message, and email; for example, in a certain warning event, the warning notification unit reminds the user to check the warning information through sound and light; at the same time, a text message warning notification is sent to the user's mobile phone; and a detailed warning report and data analysis results are sent to the user's email;

[0162] In practical applications, the hydropower real-time monitoring device of the present invention has achieved remarkable results; specifically, it includes:

[0163] Improved accuracy of abnormal identification: Through correlation analysis and abnormal detection algorithms, the device successfully identified multiple potential abnormal equipment operation events; for example, in a certain abnormal identification, the device successfully identified the abnormal current fluctuation event of generator 6 and issued a warning signal in time; after on-site inspection and confirmation, it was found that the abnormal current fluctuation was caused by a short-circuit fault in the winding of generator 6; due to the timely discovery and handling of this fault, downtime accidents and safety hazards caused by equipment failure were avoided; similarly, the device also successfully identified multiple voltage instability, power factor abnormality and other events, effectively improving the recognition accuracy and accuracy of abnormal data;

[0164] The early warning response speed is accelerated: the device can send out an early warning signal at the early stage of an abnormal event, providing users with sufficient response time; compared with the traditional early warning method based on threshold setting, the early warning response speed of the present invention is faster and more accurate; for example, in a certain early warning response, the device immediately sent out an early warning signal after discovering that the voltage data of the generator 7 was abnormal; after receiving the early warning signal, the user quickly organized relevant personnel to inspect and repair the generator 7; due to the timely early warning response, the user successfully avoided equipment damage and shutdown accidents caused by voltage abnormalities;

[0165] Improved operational safety and stability: Through real-time monitoring and early warning, the hydropower station can promptly discover and deal with potential problems, avoiding downtime accidents and safety hazards caused by equipment failures; at the same time, the data support provided by the device also provides a strong basis for the daily operation and maintenance and decision-making of the hydropower station; for example, during a certain equipment maintenance, the user carried out preventive replacement of the winding of the generator 8 based on the data analysis results provided by the device; due to timely and targeted maintenance, the operational stability and safety of the generator 8 have been significantly improved; similarly, the device also helped users discover a number of potential equipment hazards and problems, and took effective treatment measures in a timely manner, thereby ensuring the safe and stable operation of the hydropower station;

[0166] In summary, the real-time monitoring device and method for hydropower energy of the present invention have achieved remarkable results in practical applications, effectively improving the safety and stability of hydropower station operation; through real-time monitoring, data analysis, early warning notification and other functions, the device successfully identified and handled multiple potential abnormal equipment operation events, providing users with sufficient data support and decision-making basis.

[0167] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. A real-time monitoring device for hydropower and electric energy; characterized in that: Included are: Data acquisition module, used to collect real-time power data of the hydropower station, including current, voltage, and power factor parameters; A data transmission module, used for transmitting the collected data to a data processing center; The data processing module is used to process and analyze the collected data, including data cleaning, conversion, correlation analysis, and time series feature mining of abnormal data; The data display module is used to display the processed data to the user in a graphical and visual way; The early warning module is used to warn of potential dangerous conditions of hydropower and electric energy based on the analysis results of the data processing module.

2. The real-time monitoring device for hydropower energy according to claim 1 is characterized by: The data acquisition module includes a sensor group and a data collector; The sensor group consists of a variety of sensors, including current sensors, voltage sensors, and power factor sensors, which are used to collect power data from the hydropower station in real time; The data collector is connected to the sensor group and is responsible for receiving the data collected by the sensor group and performing preliminary processing and conversion to ensure the accuracy and real-time nature of the data. When the data collection module is working, it includes the following steps: S201: Initializing the data acquisition module, including calibration of the sensor group and parameter setting of the data acquisition module; S202: The sensor group collects the power data of the hydropower station in real time, including current, voltage, and power factor parameters; S203: The data collector receives the data collected by the sensor group and performs preliminary processing and conversion, including data cleaning, denoising, and format conversion operations.

3. A real-time monitoring device for hydropower energy according to claim 2, characterized in that: The data transmission module includes a data interface unit, a data transmission unit, a data encryption unit, a data verification unit and a communication management unit; the data interface unit is used to connect with the data acquisition module to receive the electric energy data collected by it; The data transmission unit is used to transmit the received data to the data processing module via wireless transmission; The data encryption unit is used to encrypt data before transmission by using encryption algorithm and key management method; the data verification unit is used to verify the data during the data transmission process by adding verification code; The communication management unit is used to manage and monitor the communication status during data transmission, including the establishment, maintenance and disconnection of communication links, as well as the monitoring and optimization of communication quality.

4. A real-time monitoring device for hydropower energy according to claim 3, characterized in that: The data processing module includes a data receiving unit, a data cleaning unit, a data conversion unit, a correlation analysis unit, an anomaly detection unit, a feature extraction unit and a data storage unit; the data receiving unit is used to receive the electric energy data transmitted by the data transmission module; the data cleaning unit is used to clean the received data, remove invalid data, fill missing data, and correct erroneous data; the data conversion unit is used to convert the format of the cleaned data into time series data and structured data; the correlation analysis unit is used to use the correlation analysis algorithm to perform correlation analysis on the results of multiple consecutive time periods, and to mine the inherent connections and laws between the data, so as to provide strong support for anomaly detection and early warning; the anomaly detection unit is used to use the anomaly detection algorithm to perform in-depth mining of time series features, and identify abnormal data and potential dangerous states; the feature extraction unit is used to further analyze the abnormal data and extract relevant feature information, including the type, occurrence time and duration of the abnormal data; The data storage unit is used to store the processed data.

5. A hydropower real-time monitoring device according to claim 4, characterized in that: The data processing module uses the Apriori algorithm when performing association analysis, including the following steps: S501: Divide the time series data according to the time window to form a data set of multiple time periods; the data set of each time period includes the current, voltage, and power factor parameters within the time period; S502: Starting from a data set of a single period, scanning the data set to find all frequent item sets, that is, item sets with an occurrence frequency higher than a preset threshold; S503: According to the property of the Apriori algorithm, that is, any infrequent (k-1) item set cannot be a superset of the frequent k item set, the candidate item set is pruned to remove the impossible candidate item sets; S504: Calculate the support of the remaining candidate item sets in the data set, that is, the frequency of the remaining candidate item sets appearing in the data set; S505: retaining candidate item sets with support higher than a preset threshold as frequent item sets; S506: Generate association rules based on frequent item sets; the rules describe the association relationship between data items in different time periods; The data processing module uses the isolation forest algorithm when performing anomaly detection, including the following steps: S601: converting the time series data into a format suitable for processing by the isolation forest algorithm, taking the data of each period as a sample, and the sample features are current, voltage, and power factor parameters; S602: randomly selecting multiple features and a random split point to split the data space until each subspace contains only one data point or reaches a preset tree depth, and repeating this process to construct multiple isolated trees; S603: For each data point, calculate its path length in the isolation forest, that is, the number of edges from the root node to the leaf node. The shorter the path length, the more abnormal the data point. S604: according to the path length distribution of normal data points in the isolation forest, a threshold is set to distinguish normal data from abnormal data; S605: Input the data point to be detected into the isolation forest, calculate its anomaly score, and compare it with the threshold to determine whether it is abnormal data.

6. A hydropower real-time monitoring device according to claim 5, characterized in that: The data processing module uses a time series-based feature extraction method when performing feature extraction, including the following steps: S701: Divide the time period where the abnormal data is located into multiple sub-time periods; S702: Calculate the statistical characteristics of each sub-time period, including mean, variance, kurtosis, and skewness, to describe the distribution characteristics of the data; S703: Describe the dynamic characteristics of the data according to the changing trend of the abnormal data over time, including linear trend and periodic trend; S704: Perform spectrum analysis on the abnormal data to extract spectrum features, including frequency components and spectrum energy, to describe the frequency characteristics of the data.

7. A hydropower real-time monitoring device according to claim 6, characterized in that: The data display module includes a graphical display unit, a visualization interaction unit and a user interface unit; the graphical display unit is used to display the processed data in a graphical manner, including but not limited to line graphs, bar graphs, and pie charts; the visualization interaction unit is used to provide users with interactive functions with the graphical display, including zooming, panning, and selection; the user interface unit is used to provide a user operation interface so that users can easily view and analyze data.

8. A hydropower real-time monitoring device and method according to claim 7, characterized in that: When the data display module is working, the following steps are included: S801: The data display module first receives processed data from the data processing module; the data includes real-time values ​​of current, voltage, power factor parameters, historical data, and abnormal detection results; S802: After receiving the data, the data display module performs filtering, sorting, and aggregation operations on the data to convert it into a graphical display format; S803: The data processed in step S802 is transmitted to a graphical display unit, which selects appropriate graphics for display according to the type of data and user needs; for time series data, a line graph is selected to display the data change trend; for categorical data, a pie chart is selected to display the proportion of each category; S804: The user interacts with the graphical display through the visualization interaction unit; S805: When the user interacts or the data changes, the data display module will update the graphical display to reflect the latest data and user needs.

9. A hydropower real-time monitoring device according to claim 8, characterized in that: The early warning module includes an early warning analysis unit, an early warning rule base, an early warning signal generation unit and an early warning notification unit; the early warning analysis unit is used to judge whether the hydropower and electric energy are in a potentially dangerous state according to the analysis results of the data processing module and the rules in the early warning rule base; the early warning rule base stores early warning rules related to the dangerous state of hydropower and electric energy; The warning signal generating unit is used to generate a warning signal when it is determined that the hydropower electric energy is in a potentially dangerous state; The warning notification unit is used to notify the user of the warning signal in a variety of ways, including but not limited to sound, light, text message, and email.

10. A method for real-time monitoring of hydropower energy, characterized in that: The following steps are included: S1: Initialize the data acquisition module, including the calibration of the sensor group and the parameter setting of the data collector; S2: The sensor group collects the power data of the hydropower station in real time, including current, voltage, and power factor parameters; S3: The data collector receives the data collected by the sensor group and performs preliminary processing and conversion, including data cleaning, denoising, and format conversion operations; S4: The data interface unit is connected to the data acquisition module to receive the collected electric energy data; S5: The data transmission unit transmits the received data to the data processing module via wireless transmission; S6: The data encryption unit uses an encryption algorithm and a key management method to encrypt the data before transmission; S7: The data checking unit verifies the data during the data transmission by adding a check code; S8: The data receiving unit receives the electric energy data transmitted by the data transmission module; S9: The data cleaning unit cleans the received data to remove invalid data, fill in missing data, and correct erroneous data; S10: The data conversion unit converts the format of the cleaned data into time series data and structured data; S11: Divide the time series data into time windows to form data sets for multiple time periods; S12: Scan the data set to find all frequent itemsets, i.e., itemsets whose occurrence frequency is higher than a preset threshold; S13: Prune the candidate item sets and remove impossible candidate item sets; S14: Calculate the support of the remaining candidate item sets in the data set; S15: retain candidate item sets with support higher than the preset threshold as frequent item sets; S16: Generate association rules based on frequent item sets to describe the association relationship between data items in different time periods; S17: Convert the time series data into a format suitable for processing by the Isolation Forest algorithm; S18: Build multiple isolated trees to split the data space by randomly selecting multiple features and a random split point; S19: Calculate the path length of each data point in the isolation forest and determine the abnormality of the data point based on the path length; S20: Setting a threshold to distinguish normal data from abnormal data; S21: Input the data point to be detected into the isolation forest, calculate its anomaly score, and compare it with the threshold to determine whether it is abnormal data; S22: The feature extraction unit extracts relevant feature information from the abnormal data, including the type, occurrence time, and duration of the abnormal data; S23: The early warning analysis unit determines whether the hydropower energy is in a potentially dangerous state based on the analysis results of the data processing module and the rules in the early warning rule library; S24: If it is determined that the hydropower energy is in a potentially dangerous state, the warning signal generating unit generates a warning signal; S25: The warning notification unit notifies the user of the warning signal in a variety of ways, including but not limited to sound, light, text message, and email.

Images