Hydraulic power plant information processing method and system based on industrial internet of things

Abstract

The invention provides a hydraulic power plant information processing method and system based on an industrial Internet of Things, and belongs to the technical field of big data processing, and the method comprises the steps: collecting industrial Internet of Things sensor data during the normal working period of a hydraulic power plant; weaving the data into time sequence data; carrying out data clustering; dividing each piece of sensor data into N grades; mapping the real-time data into grades divided by corresponding sensors; displaying a first coordinate axis on the first interface; decorating the average grade of nearly M periods on the first coordinate axis; connecting the grade points of all the sensors in the clustering result; the clustering level lines are translated, so that all the clustering level lines are not interwoven with one another; displaying a first bubble on the peak; and displaying the detailed data of the corresponding sensor on the second interface. According to the scheme, hydraulic power plant industrial Internet of Things data with a large data volume can be simply and conveniently analyzed.

Description

Technical Field

[0001] The present invention relates to the field of big data processing, and in particular to a hydropower plant information processing method and system based on industrial Internet of Things. Background Art

[0002] The Industrial Internet of Things (IIoT) refers to the technology and concept of connecting physical devices such as sensors, equipment, and instruments via the internet to collect, transmit, analyze, and apply data, thereby optimizing industrial production and operations. By connecting various physical devices to the internet, the IIoT enables data sharing and collaboration between them, improving production efficiency.

[0003] Various data in the production environment are collected in real time through sensors and other equipment. Sensors are installed at key equipment and locations in hydropower plants to collect data related to hydropower production in real time, such as water level, water quality, temperature, humidity, flow, water pressure, etc. By analyzing large amounts of production data, useful information can be mined from it to detect possible failures in the hydropower plant in advance.

[0004] However, with the development of the industry, more and more sensors are connected to data centers through the Industrial Internet of Things (IIoT). In some hydropower projects, there are tens of thousands of sensors. Furthermore, the complex environment of hydropower plants means that the data collected by the same type of sensor may vary significantly. For example, a water pressure gauge may collect different data at different locations in a body of water and at different water levels. Data security standards may also vary at different locations. For example, the normal water pressure range at point A is 10-20 kPa, while the normal water pressure range at point B is 20-40 kPa. Existing technology typically requires setting separate alarm thresholds for points A and B. When there are many monitoring points and a variety of data types, setting alarm thresholds for each point is a very large workload. Furthermore, sorting out abnormal information from tens of thousands of monitoring data points is also very challenging. Summary of the Invention

[0005] In order to solve the problems in the prior art, the present invention provides a hydropower plant information processing method and system based on industrial Internet of Things.

[0006] In one aspect of the present invention, a method for processing information of a hydropower plant based on the Industrial Internet of Things is provided: collecting Industrial Internet of Things sensor data during normal operation of the hydropower plant; organizing the sensor data into time series data at the same time interval; clustering data with similar trends in the time series data to obtain multiple clustering results; for each sensor data, dividing each sensor data into N levels based on historical records, where N is a positive integer not less than 3; collecting Industrial Internet of Things sensor data in real time, mapping the real-time data into the levels divided by the corresponding sensor; for each sensor data, taking its average level over the past M periods, where M is a positive integer not less than 2 A positive integer; a first coordinate axis is displayed on the first interface, where the vertical axis of the first coordinate axis represents the level and the horizontal axis represents different sensors; for each sensor, the average level of the nearly M cycles is represented on the first coordinate axis to obtain a level point; for the same clustering result, the level points of all sensors in the clustering result are connected to obtain a cluster level line; the cluster level line is translated on the vertical axis of the first coordinate axis so that all cluster level lines do not intertwine with each other; for each cluster level line, when there is a peak on the cluster level line that is higher than the first threshold, a first bubble is displayed on the peak; click the first bubble to display detailed data of the corresponding sensor on the second interface.

[0007] Furthermore, the method of dividing each sensor data into N levels based on historical records includes: calculating the average value and standard deviation of the historical data, determining that the data is at level 0 when it deviates from the average value by plus or minus one standard deviation, at level 1 when it deviates from the average value by between plus one standard deviation and plus two standard deviations, at level -1 when it deviates from the average value by between minus one standard deviation and minus two standard deviations, at level 2 when it deviates from the average value by more than plus two standard deviations, and at level -2 when it deviates from the average value by less than minus two standard deviations.

[0008] Furthermore, there are no less than 2 clustering level lines, and all of the clustering level lines are displayed on the first interface.

[0009] Furthermore, the method for determining whether there is a peak on the cluster level line that is higher than the first threshold is as follows: calculate the current level average of each cluster, calculate the distance from the average value for each point in the same cluster, and determine whether it exceeds the first threshold. If it exceeds the first threshold, it means that the peak is too high.

[0010] Furthermore, the second interface further displays data information links of other sensors in the same cluster as the abnormal sensor, and when the user clicks the link, corresponding sensor data details are displayed.

[0011] Another aspect of the present invention provides an information processing system for a hydropower plant based on the industrial Internet of Things, the system comprising: a data collection module for collecting industrial Internet of Things sensor data during normal operation of the hydropower plant; a data processing module for organizing the sensor data into time series data at the same time interval; clustering data with similar trends in the time series data to obtain multiple clustering results; for each sensor data, dividing each sensor data into N levels according to historical records, where N is a positive integer not less than 3; a real-time acquisition module for real-time acquisition of industrial Internet of Things sensor data, mapping the real-time data into the levels divided by the corresponding sensor; an analysis module for taking nearly M of the data of each sensor The average level of the period, M is a positive integer not less than 2; a display module is used to display a first coordinate axis on the first interface, the vertical axis of the first coordinate axis represents the level, and the horizontal axis represents different sensors; for each sensor, the average level of its nearly M periods is represented on the first coordinate axis to obtain a level point; for the same clustering result, the level points of all sensors in the clustering result are connected to obtain a cluster level line; the cluster level line is translated on the vertical axis of the first coordinate axis so that all cluster level lines do not intertwine with each other; for each cluster level line, when there is a peak on the cluster level line that is higher than the first threshold, a first bubble is displayed on the peak; click on the first bubble to display detailed data of the corresponding sensor on the second interface.

[0012] Furthermore, the method of dividing each sensor data into N levels based on historical records includes: calculating the average value and standard deviation of the historical data, determining that the data is at level 0 when it deviates from the average value by plus or minus one standard deviation, at level 1 when it deviates from the average value by between plus one standard deviation and plus two standard deviations, at level -1 when it deviates from the average value by between minus one standard deviation and minus two standard deviations, at level 2 when it deviates from the average value by more than plus two standard deviations, and at level -2 when it deviates from the average value by less than minus two standard deviations.

[0013] Furthermore, there are no less than 2 clustering level lines, and all of the clustering level lines are displayed on the first interface.

[0014] Furthermore, the method for determining whether there is a peak on the cluster level line that is higher than the first threshold is as follows: calculate the current level average of each cluster, calculate the distance from the average value for each point in the same cluster, and determine whether it exceeds the first threshold. If it exceeds the first threshold, it means that the peak is too high.

[0015] Furthermore, the second interface further displays data information links of other sensors in the same cluster as the abnormal sensor, and when the user clicks the link, corresponding sensor data details are displayed.

[0016] The present invention can produce the following beneficial effects through the above technical solution: Clustering sensor data according to types with the same trend and indicating abnormalities for outlier data can avoid users setting alarm thresholds for each sensor. When users are faced with tens of thousands of sensors, the setup work can be greatly reduced.

[0017] Furthermore, the data is graded and displayed in a straight line on the coordinate axis. The overall situation of tens of thousands of sensors can be displayed in the form of images on the same interface, making it easier for maintenance personnel to observe the overall situation of the hydropower plant. At the same time, abnormalities are displayed as bubbles, which improves the convenience of operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 is an example of a grade point; Figure 2 is an example of a cluster rank line; Figure 3 is an example of a balanced cluster rank line; Figure 4 This is an example of an exception prompt. DETAILED DESCRIPTION

[0020] Below, the invention is preferably described with reference to the accompanying drawings and specific embodiments.

[0021] This embodiment solves the above problem through the following steps: In one embodiment, the present invention provides a hydropower plant information processing method based on the industrial Internet of Things, specifically comprising: Collecting Industrial IoT sensor data during normal operation of a hydropower plant.

[0022] During normal operation of a hydropower plant, various systems and equipment work together to maintain efficient power generation. Since the data during normal operation is of specific reference value, this embodiment uses the data during normal operation as a standard to determine whether the data in subsequent operation processes is normal.

[0023] Industrial IoT sensor data at hydropower plants typically includes various parameters to monitor and manage the power generation process, including water level sensors, flow sensors, temperature sensors, humidity sensors, pressure sensors, vibration sensors, current sensors, voltage sensors, water quality sensors, and speed sensors. Data from these sensors can be collected in real time through the Industrial IoT platform and stored in the cloud or local database for subsequent analysis, monitoring, and control of hydropower plant operations.

[0024] The sensor data are organized into time series data at the same time intervals.

[0025] Different sensors may collect data at different intervals. To synchronize data processing, the sensor data is organized into time series data streams, sampled and recorded at consistent intervals (e.g., every minute, every hour). During the serialization process, each sensor data point is assigned a timestamp indicating the time of data acquisition. This ensures that all sensor data is aligned on the same timeline. This is achieved by sampling at each timestamp, ensuring that each sensor records data at the same point in time.

[0026] Determine the sampling interval, that is, the time interval between data points. This can be seconds, minutes, hours, etc., depending on the needs of data analysis or monitoring, and is not specifically limited in this embodiment. It is also necessary to ensure that there are corresponding data points for each time interval. If data for a time point is missing, interpolation, default value filling, or other processing methods can be used.

[0027] Organize the data into a time series data structure, such as a data frame or database table. Each row represents a time point, and each column represents a sensor measurement parameter. This can be implemented using existing technologies such as the resample method in Pandas.

[0028] For example, the format of time series data can be as follows: | Timestamp | Temperature (Celsius) | |------------------------|----------- | | 2024-01-05 00:00:00 | 20.5 | | 2024-01-05 00:01:00 | 21.0 | | 2024-01-05 00:02:00 | 20.8 | Clustering data with similar trends in the time series data to obtain multiple clustering results.

[0029] Many sensor data at hydropower plants are strongly correlated with water level, flow rate, and flow velocity. Although the absolute data from each sensor varies, the relative trends of the data remain the same when the external environment changes. For example, when the water level at the dam rises, the data from the water pressure sensor at point A rises from 10kPa to 20kPa, and the data from the water pressure sensor at point B rises from 20kPa to 40kPa. There is a lot of similar data from multiple sensors. Clustering data with similar trends can identify data with similar changes. If all data trends are similar, the data at all locations is normal. If there are outliers, there may be equipment anomalies or leakage at that location, requiring further investigation. Based on this principle, this implementation further clusters data with similar trends in time series data, resulting in multiple clustering results.

[0030] When performing clustering, a clustering algorithm can be used to group time series with similar trends. First, determine a method for measuring the similarity between time series, such as Euclidean distance, Manhattan distance, or Dynamic Time Warping (DTW). Select an appropriate clustering algorithm, such as K-means clustering, hierarchical clustering, or DBSCAN. Use the selected clustering algorithm to divide the time series data into different clusters. The goal of clustering is to ensure that the trends of time series within the same cluster are similar. The specific clustering method can be any existing technique and is not specifically limited in this embodiment. Preferably, the tslearn library in Python is used for DTW clustering.

[0031] For each sensor data, each sensor data is divided into N levels according to historical records.

[0032] Since normal sensor data is within a dynamic range, it is difficult to express dynamic characteristics if the raw data is used directly. Therefore, the sensor data is divided into levels. In the subsequent processing process, most of the data are in the same level, the overall data performance is more linear, and abnormal data is easier to observe.

[0033] Collect historical data from sensors before performing rank classification to ensure that there is enough data for calculating quantiles.

[0034] Each sensor data point is divided into N levels, using quantiles or percentiles, commonly used in existing technologies. The levels are defined as 1, 2, 3, or more subdivided levels. Each sensor data point is mapped to the corresponding level. This can be achieved by comparing the data with the quantiles.

[0035] N is a positive integer not less than 3. The specific selection of the level is not specifically limited in this embodiment. A reasonable level can be selected based on experiments conducted according to field data.

[0036] Furthermore, in order to make the levels more representative of the data level, this embodiment preferably uses the following method to perform level division: For each sensor data, the mean and standard deviation of the historical data are calculated. When the data deviates from the mean by plus or minus one standard deviation, it is determined to be level 0; when the data deviates from the mean by between plus one standard deviation and plus two standard deviations, it is determined to be level 1; when the data deviates from the mean by between minus one standard deviation and minus two standard deviations, it is determined to be level -1; when the data deviates from the mean by more than plus two standard deviations, it is determined to be level 2; when the data deviates from the mean by less than minus two standard deviations, it is determined to be level -2.

[0037] Collect industrial IoT sensor data in real time and map the real-time data into levels classified by the corresponding sensors.

[0038] When collecting real-time IIoT sensor data and mapping it to appropriate levels, a similar approach as described in the previous step can be used. For each sensor's real-time data, the same level definition method is used to calculate the level to which the real-time data belongs. The real-time data is then mapped to the appropriate level. For example, when a piece of data is received, the level classification method described in the previous step is used to determine whether the data is level 0, level 1, or another level.

[0039] For each sensor data, take its average level over the past M cycles.

[0040] The period is determined based on the data collection frequency. The level of each sensor data within each period is calculated using the aforementioned method. The level data for each sensor over the last M periods is averaged. Because data may experience short-term fluctuations, using the average level over M periods can further smooth the data and reduce false positives. Where M is a positive integer not less than 2, a larger value of M improves smoothing performance but also slows down the response to anomalies. When implementing this embodiment, experimental selection can be made based on the specific data conditions and is not specifically limited in this embodiment.

[0041] The first coordinate axis is displayed on the first interface. The vertical axis of the first coordinate axis represents the level, and the horizontal axis represents different sensors. For each sensor, the average level of the nearly M cycles is represented on the first coordinate axis to obtain the level point.

[0042] like Figure 1 As shown, the first interface displays the first coordinate axis, and the level data of a sensor is marked on the coordinate axis at every preset distance. Each point represents a sensor, and the value of each point is the average level of the sensor in the past M cycles. Figure 1 The example shows 8 different sensors, all of which have a level of 1 for the past 5 cycles.

[0043] For the same clustering result, the level points of all sensors in the clustering result are connected to obtain a clustering level line.

[0044] For the same clustering result, since the changing trends of all points are similar, if the level points of all sensors in the same clustering result are connected, it will normally be a straight line. Figure 2 As shown, one or two non-clustered level lines are shown, and the two cluster level lines are 1 and 0 at the current level respectively.

[0045] The clustering level lines are translated on the vertical axis of the first coordinate axis so that all clustering level lines do not intertwine with each other.

[0046] Since the number of levels is limited, and the number of clusters may be very large, in order to distinguish different level lines, it is necessary to further disperse different clusters. Figure 2 , if the level of the other two clusters is 0, then only Figure 2 By translating the clustering level lines on the vertical axis of the first coordinate axis, all clustering level lines are not intertwined. Figure 3 As shown, after translating the interwoven grade lines on the vertical axis, four non-interwoven lines are obtained, each representing a cluster. In this embodiment, subsequent steps only focus on whether the lines are straight, not the specific data. Therefore, the specific result after translation (the position of the lines) does not need to be specified; as long as the different grade lines can be distinguished, it is sufficient.

[0047] For each cluster level line, when there is a peak on the cluster level line that is higher than a first threshold, a first bubble is displayed on the peak.

[0048] In this embodiment, because the values ​​within the same cluster tend to change in the same trend, even though the absolute data may differ, the rankings are similar after ranking. This is reflected in the graph as a straight line for each cluster ranking line. If a prominent peak appears on a line, it indicates that the data at that point deviates from the group and may be problematic. Therefore, for each cluster ranking line, if a peak exceeds a first threshold, a first bubble is displayed on the peak to alert the user of the data.

[0049] like Figure 4 As shown, there is a prominent peak on the third level line, which is different from the overall trend (that is, it is not on a straight line). Therefore, the data is likely to be abnormal. A bubble chart is used on this peak to indicate the abnormality.

[0050] The overall situation of the sensors can be intuitively seen through the level lines. There can be multiple level lines, and each point at a certain interval represents a sensor. Therefore, through this embodiment, the overall situation of tens of thousands of sensors can be intuitively monitored on the same screen. Maintenance personnel can judge the situation of the hydropower plant based on the number and distribution of spikes, which is helpful for overall monitoring.

[0051] When making a spike judgment, for the same cluster, the data is generally a straight line, so the average value of the cluster can be calculated, and the distance from the average value to each point in the same cluster is calculated to determine whether it exceeds the first threshold. If it exceeds the first threshold, it means that the spike is too high, and an abnormal prompt will be given.

[0052] Click the first bubble to display the detailed data of the corresponding sensor on the second interface.

[0053] Furthermore, to facilitate maintenance personnel's access to specific abnormal data, when a maintenance personnel clicks on the first bubble on the interface, detailed sensor data, such as sensor location and recent sensor data, is displayed on a second interface separate from the first interface for their reference. Furthermore, the second interface also displays links to data from other sensors in the same cluster as the abnormal sensor. When the user clicks on a link, the corresponding sensor data details are displayed.

[0054] Through the above method, sensor data can be clustered according to types with the same trend, and abnormalities can be prompted for outlier data. This can avoid users setting alarm thresholds for each sensor. When users are faced with tens of thousands of sensors, the setup work can be greatly reduced.

[0055] Furthermore, the data is graded and displayed in a straight line on the coordinate axis. The overall situation of tens of thousands of sensors can be displayed in the form of images on the same interface, making it easier for maintenance personnel to observe the overall situation of the hydropower plant. At the same time, abnormalities are displayed as bubbles, which improves the convenience of operation.

[0056] On the other hand, the present invention also provides a hydropower plant information processing system based on the industrial Internet of Things, the system comprising the following modules: A data collection module, used to collect industrial IoT sensor data during normal operation of the hydropower plant; a data processing module for organizing the sensor data into time series data at the same time interval; clustering data with similar trends in the time series data to obtain multiple clustering results; and for each sensor data, classifying each sensor data into N levels based on historical records, where N is a positive integer not less than 3; Real-time acquisition module, used to collect industrial IoT sensor data in real time and map the real-time data into the levels divided by the corresponding sensors; An analysis module is used to calculate the average level of the data of each sensor over the past M cycles, where M is a positive integer not less than 2; A display module is configured to display a first coordinate axis on a first interface, wherein the vertical axis of the first coordinate axis represents the level and the horizontal axis represents different sensors; for each sensor, the average level of the sensor over nearly M cycles is represented on the first coordinate axis to obtain a level point; for the same clustering result, the level points of all sensors in the clustering result are connected to obtain a cluster level line; and the cluster level line is translated on the vertical axis of the first coordinate axis so that all cluster level lines do not intersect with each other; For each cluster level line, when there is a peak on the cluster level line that is higher than a first threshold, a first bubble is displayed on the peak; when the first bubble is clicked, detailed data of the corresponding sensor is displayed on the second interface.

[0057] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

[0058] For any module structure not specifically defined in this invention, the prior art shall prevail. The prior art mentioned in the aforementioned background and specific embodiments of this invention may be considered as part of this invention and used to understand the meaning of certain technical features or parameters. The scope of protection of this invention shall be based on the actual content of the claims.

Claims

1. A hydropower plant information processing method based on the industrial Internet of Things, characterized by: Collecting IIoT sensor data during normal operation of the hydropower plant; Organizing the sensor data into time series data at the same time intervals; Clustering data with similar trends in the time series data to obtain multiple clustering results; For each sensor data, each sensor data is divided into N levels according to the historical records, where N is a positive integer not less than 3; Collect industrial IoT sensor data in real time and map the real-time data into the levels divided by the corresponding sensors; For each sensor data, take its average level over the past M cycles, where M is a positive integer not less than 2; Displaying a first coordinate axis on the first interface, wherein the vertical axis of the first coordinate axis represents the level and the horizontal axis represents different sensors; For each sensor, the average level of the sensor in the past M cycles is expressed on the first coordinate axis to obtain the level point; For the same clustering result, the level points of all sensors in the clustering result are connected to obtain a clustering level line; translating the clustering level lines on the vertical axis of the first coordinate axis so that all clustering level lines do not intertwine with each other; For each clustering level line, when there is a peak on the clustering level line that is higher than a first threshold, display a first bubble on the peak; Click the first bubble to display the detailed data of the corresponding sensor on the second interface.

2. The hydropower plant information processing method based on industrial Internet of Things according to claim 1 is characterized in that The method of dividing each sensor data into N levels based on historical records includes: calculating the average value and standard deviation of the historical data, determining that the data is level 0 when it deviates from the average value by plus or minus one standard deviation, level 1 when the data deviates from the average value by between plus one standard deviation and plus two standard deviations, level -1 when the data deviates from the average value by between minus one standard deviation and minus two standard deviations, level 2 when the data deviates from the average value by more than plus two standard deviations, and level -2 when the data deviates from the average value by less than minus two standard deviations.

3. The hydropower plant information processing method based on the industrial Internet of Things according to claim 1 is characterized in that: There are no less than 2 clustering level lines, and all of the clustering level lines are displayed on the first interface.

4. The hydropower plant information processing method based on industrial Internet of Things according to claim 1 is characterized in that The method for determining whether there is a peak on the cluster level line that is higher than the first threshold is as follows: calculate the current level average of each cluster, calculate the distance from the average value for each point in the same cluster, and determine whether it exceeds the first threshold. If it exceeds the first threshold, it means that the peak is too high.

5. The hydropower plant information processing method based on the industrial Internet of Things according to claim 1 is characterized in that: The second interface further displays data information links of other sensors in the same cluster as the abnormal sensor. When the user clicks the link, the corresponding sensor data details are displayed.

6. A hydropower plant information processing system based on industrial Internet of Things, characterized by The system comprises: A data collection module, used to collect industrial IoT sensor data during normal operation of the hydropower plant; a data processing module for organizing the sensor data into time series data at the same time interval; clustering data with similar trends in the time series data to obtain multiple clustering results; and for each sensor data, classifying each sensor data into N levels based on historical records, where N is a positive integer not less than 3; Real-time acquisition module, used to collect industrial IoT sensor data in real time and map the real-time data into the levels divided by the corresponding sensors; An analysis module is used to calculate the average level of the data of each sensor over the past M cycles, where M is a positive integer not less than 2; A display module is configured to display a first coordinate axis on a first interface, wherein the vertical axis of the first coordinate axis represents the level and the horizontal axis represents different sensors; for each sensor, the average level of the sensor over nearly M cycles is represented on the first coordinate axis to obtain a level point; for the same clustering result, the level points of all sensors in the clustering result are connected to obtain a cluster level line; and the cluster level line is translated on the vertical axis of the first coordinate axis so that all cluster level lines do not intersect with each other; For each cluster level line, when there is a peak on the cluster level line that is higher than a first threshold, a first bubble is displayed on the peak; when the first bubble is clicked, detailed data of the corresponding sensor is displayed on the second interface.

7. The hydropower plant information processing system based on industrial Internet of Things according to claim 6 is characterized in that The method of dividing each sensor data into N levels based on historical records includes: calculating the average value and standard deviation of the historical data, determining that the data is level 0 when it deviates from the average value by plus or minus one standard deviation, level 1 when the data deviates from the average value by between plus one standard deviation and plus two standard deviations, level -1 when the data deviates from the average value by between minus one standard deviation and minus two standard deviations, level 2 when the data deviates from the average value by more than plus two standard deviations, and level -2 when the data deviates from the average value by less than minus two standard deviations.

8. The hydropower plant information processing system based on industrial Internet of Things according to claim 6 is characterized by: There are no less than 2 clustering level lines, and all of the clustering level lines are displayed on the first interface.

9. The hydropower plant information processing system based on industrial Internet of Things according to claim 6 is characterized in that The method for determining whether there is a peak on the cluster level line that is higher than the first threshold is as follows: calculate the current level average of each cluster, calculate the distance from the average value for each point in the same cluster, and determine whether it exceeds the first threshold. If it exceeds the first threshold, it means that the peak is too high.

10. The hydropower plant information processing system based on industrial Internet of Things according to claim 6 is characterized in that: The second interface further displays data information links of other sensors in the same cluster as the abnormal sensor. When the user clicks the link, the corresponding sensor data details are displayed.

Images