Station monitoring index threshold value generation method and terminal

Abstract

The invention discloses a station monitoring index threshold generation method and a terminal, and the method comprises the steps: obtaining historical detection index data of a station in a preset time period, and recognizing abnormal points in the historical detection index data and an abnormal interval of each abnormal point according to a time sequence anomaly detection algorithm; obtaining an abnormal interval upper bound sequence and an abnormal interval lower bound sequence corresponding to the historical detection index data according to the interval upper bound and the interval lower bound of the abnormal interval of each abnormal point; and determining an anomaly detection upper bound threshold according to the anomaly interval upper bound sequence, obtaining an anomaly detection lower bound threshold according to the anomaly interval lower bound sequence, and obtaining a safety index threshold interval. The method is corresponding to the judgment standard for detecting whether the current detection index data of the station is abnormal or not, thereby assisting in accurately identifying the abnormal condition of the data of the station monitoring index, and ensuring the safe operation of the station.

Description

Technical Field

[0001] The present invention relates to the field of electronic information technology, and in particular to a method and a terminal for generating a threshold value of a site monitoring indicator. Background Art

[0002] As the popularity of electric vehicles increases, the coverage of photovoltaic storage charging and inspection stations, as one of the basic infrastructures for vehicle charging and inspection, is becoming wider and wider. Ensuring the safe operation of stations is an important task in daily operation and maintenance. To this end, the existing real-time monitoring of many safety monitoring indicators of each station is conducive to the fine management of the station and improves the safety management level of the station.

[0003] However, due to the influence of personalized configuration, the situation of each station is different; and the data distribution of station safety monitoring indicators itself has multiple distribution characteristics such as unimodal distribution and bimodal distribution. The data fluctuation range is large, and it is difficult to timely detect whether there are abnormalities in data changes during the monitoring process; how to accurately identify abnormalities in the data of station monitoring indicators has become the key to ensuring the safe operation of the station. Summary of the invention

[0004] The technical problem to be solved by the present invention is to propose a method and terminal for generating threshold values ​​of monitoring indicators of a station, which can assist in accurately identifying abnormal conditions of data of monitoring indicators of the station and ensure the key to the safe operation of the station.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for generating a threshold value of a site monitoring indicator comprises the following steps: S1. Obtain historical detection index data of the station within a preset time period, and identify abnormal points in the historical detection index data and abnormal intervals of each abnormal point according to a time series anomaly detection algorithm; S2. Obtain an upper bound sequence and a lower bound sequence of abnormal intervals corresponding to the historical detection index data according to the upper bound and the lower bound of the abnormal interval of each abnormal point; S3. Determine an upper threshold value for abnormality detection according to the abnormal interval upper limit value sequence, obtain an abnormality detection lower threshold value according to the abnormal interval lower limit sequence, and obtain a safety indicator threshold interval.

[0006] In order to solve the above technical problems, another technical solution adopted by the present invention is: A terminal for generating a threshold value of a monitoring index of a station includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: S1. Obtain historical detection index data of the station within a preset time period, and identify abnormal points in the historical detection index data and abnormal intervals of each abnormal point according to a time series anomaly detection algorithm; S2. Obtain an upper bound sequence and a lower bound sequence of abnormal intervals corresponding to the historical detection index data according to the upper bound and the lower bound of the abnormal interval of each abnormal point; S3. Determine an upper threshold value for abnormality detection according to the abnormal interval upper limit value sequence, obtain an abnormality detection lower threshold value according to the abnormal interval lower limit sequence, and obtain a safety indicator threshold interval.

[0007] The beneficial effects of the present invention are as follows: a method and a terminal for generating threshold values ​​of monitoring indicators of a station are proposed, a time series algorithm is used to identify abnormal points of historical detection indicator data of the station within a preset time period and abnormal intervals of each abnormal point, and then the upper and lower thresholds of the safety indicator threshold interval are determined by integrating the upper limit sequence of the abnormal interval and the lower limit sequence of the abnormal interval, so as to obtain a judgment standard that can be used as a corresponding detection standard for whether the current detection indicator data of the station is abnormal, thereby assisting in accurately identifying abnormal conditions of the data of the monitoring indicators of the station and ensuring the safe operation of the station. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of the steps of a method for generating a threshold value of a monitoring index of a station according to the present invention; Figure 2 A system block diagram of a terminal for generating a threshold value of a site monitoring index according to the present invention.

[0009] Description of labels: 1. A terminal for generating threshold values ​​of site monitoring indicators; 2. A memory; 3. A processor. DETAILED DESCRIPTION

[0010] In order to explain the technical content, achieved objectives and effects of the present invention in detail, the following is an explanation in conjunction with the implementation modes and the accompanying drawings.

[0011] Please refer to Figure 1 A method for generating a threshold value of a site monitoring indicator comprises the following steps: S1. Obtain historical detection index data of the station within a preset time period, and identify abnormal points in the historical detection index data and abnormal intervals of each abnormal point according to a time series anomaly detection algorithm; S2. Obtain an upper bound sequence and a lower bound sequence of abnormal intervals corresponding to the historical detection index data according to the upper bound and the lower bound of the abnormal interval of each abnormal point; S3. Determine an upper threshold value for abnormality detection according to the abnormal interval upper limit value sequence, obtain an abnormality detection lower threshold value according to the abnormal interval lower limit sequence, and obtain a safety indicator threshold interval.

[0012] From the above description, it can be seen that the beneficial effects of the present invention are: proposing a method for generating threshold values ​​of station monitoring indicators, using a time series algorithm to identify abnormal points of historical detection indicator data of the station within a preset time period and abnormal intervals of each abnormal point, and using multiple change intervals of abnormal points generated as the station operation time increases to grasp the abnormal changes in the monitoring indicator data of the station, and then determining the upper and lower thresholds of the safety indicator threshold interval by integrating the upper limit sequence of the abnormal interval and the lower limit sequence of the abnormal interval, that is, the safety indicator threshold interval represents the range in which the data size is concentrated after different abnormal situations occur, which is used as the judgment standard for detecting whether the current detection indicator data of the station is abnormal, thereby assisting in accurately identifying the abnormal situation of the data of the station monitoring indicators and ensuring the safe operation of the station.

[0013] Furthermore, the step S3 specifically includes: The maximum value in the abnormal interval upper boundary value sequence is selected as the abnormality detection upper boundary threshold, and the minimum value in the abnormal interval lower boundary value sequence is selected as the abnormality detection lower boundary threshold.

[0014] From the above description, it can be seen that when determining the upper and lower bounds, the safety index threshold interval is generated by referring to the extreme values ​​corresponding to the upper bound value sequence of the abnormal interval and the lower bound value sequence of the abnormal interval, so as to improve the coverage of abnormal situations and help to more reliably ensure the safe operation of the station.

[0015] Furthermore, the step S2 specifically includes: S21, eliminating the maximum values ​​in the upper bounds of the abnormal intervals of all the abnormal points, to obtain a sequence of upper bounds of the abnormal intervals; S22: Eliminate the minimum values ​​in the lower bounds of the abnormal intervals of all the abnormal points to obtain a sequence of lower bounds of the abnormal intervals.

[0016] From the above description, it can be seen that by eliminating extreme values, the rationality of selected data can be improved, the final judgment can be avoided from being affected by some very rare special cases, and the accuracy and applicability of the threshold range of safety indicators can be improved.

[0017] Furthermore, it also includes: S4. Obtain the current detection index data of the site, detect whether there is data anomaly in the current detection index data according to the safety index threshold interval, if not, add the current detection index data to the historical detection index data, identify the abnormal points in the historical detection index data and the abnormal interval of each abnormal point according to the time series anomaly detection algorithm, and execute steps S2 and S3.

[0018] From the above description, it can be seen that the generated safety indicator threshold interval is used to detect whether there is an abnormality in the current detection indicator data. If the size does not fall into the safety indicator threshold interval, it means that the current data of the station is normal; at the same time, the current detection indicator data can also be used as the latest historical detection indicator data to update the safety indicator threshold interval to ensure the reliability of subsequent anomaly detection.

[0019] Furthermore, before step S1, the following steps are also included: S0. While acquiring the detection index data of the site within a preset period, the number of acquisitions is accumulated, and the length of the preset time period is adjusted according to the number of acquisitions.

[0020] From the above description, it can be seen that as the detection index data of the site continues to increase, the length of the preset time period is adaptively adjusted, that is, the referenced historical detection index data is increased, so as to obtain a more comprehensive understanding of the changes in the detection index data and maintain the accuracy of the safety index threshold range.

[0021] Please refer to Figure 2 A terminal 1 for generating a threshold value of a monitoring index of a station includes a memory 2, a processor 3, and a computer program stored in the memory 2 and executable on the processor 3. When the processor 3 executes the computer program, the following steps are implemented: S1. Obtain historical detection index data of the station within a preset time period, and identify abnormal points in the historical detection index data and abnormal intervals of each abnormal point according to a time series anomaly detection algorithm; S2. Obtain an upper bound sequence and a lower bound sequence of abnormal intervals corresponding to the historical detection index data according to the upper bound and the lower bound of the abnormal interval of each abnormal point; S3. Determine an upper threshold value for abnormality detection according to the abnormal interval upper limit value sequence, obtain an abnormality detection lower threshold value according to the abnormal interval lower limit sequence, and obtain a safety indicator threshold interval.

[0022] From the above description, it can be seen that the beneficial effects of the present invention are: using a time series algorithm to identify abnormal points in the historical detection index data of the station within a preset time period and the abnormal intervals of each abnormal point, and using multiple change intervals of abnormal points generated as the station operation time increases to grasp the abnormal changes in the monitoring index data of the station, and then by integrating the upper limit sequence of the abnormal interval and the lower limit sequence of the abnormal interval, the upper and lower thresholds of the safety index threshold interval are determined, that is, the safety index threshold interval represents the range in which the data size is concentrated after different abnormal situations occur, which is used as the judgment standard for detecting whether the current detection index data of the station is abnormal, thereby assisting in accurately identifying the abnormal situation of the data of the station monitoring indicators and ensuring the safe operation of the station.

[0023] Furthermore, the step S3 specifically includes: The maximum value in the abnormal interval upper boundary value sequence is selected as the abnormality detection upper boundary threshold, and the minimum value in the abnormal interval lower boundary value sequence is selected as the abnormality detection lower boundary threshold.

[0024] From the above description, it can be seen that when determining the upper and lower bounds, the safety index threshold interval is generated by referring to the extreme values ​​corresponding to the upper bound value sequence of the abnormal interval and the lower bound value sequence of the abnormal interval, so as to improve the coverage of abnormal situations and help to more reliably ensure the safe operation of the station.

[0025] Furthermore, the step S2 specifically includes: S21, eliminating the maximum values ​​in the upper bounds of the abnormal intervals of all the abnormal points, to obtain a sequence of upper bounds of the abnormal intervals; S22: Eliminate the minimum values ​​in the lower bounds of the abnormal intervals of all the abnormal points to obtain a sequence of lower bounds of the abnormal intervals.

[0026] From the above description, it can be seen that by eliminating extreme values, the rationality of selected data can be improved, the final judgment can be avoided from being affected by some very rare special cases, and the accuracy and applicability of the threshold range of safety indicators can be improved.

[0027] Furthermore, it also includes: S4. Obtain the current detection index data of the site, detect whether there is data anomaly in the current detection index data according to the safety index threshold interval, if not, add the current detection index data to the historical detection index data, identify the abnormal points in the historical detection index data and the abnormal interval of each abnormal point according to the time series anomaly detection algorithm, and execute steps S2 and S3.

[0028] From the above description, it can be seen that the generated safety indicator threshold interval is used to detect whether there is an abnormality in the current detection indicator data. If the size does not fall into the safety indicator threshold interval, it means that the current data of the station is normal; at the same time, the current detection indicator data can also be used as the latest historical detection indicator data to update the safety indicator threshold interval to ensure the reliability of subsequent anomaly detection.

[0029] Furthermore, before step S1, the following steps are also included: S0. While acquiring the detection index data of the site within a preset period, the number of acquisitions is accumulated, and the length of the preset time period is adjusted according to the number of acquisitions.

[0030] From the above description, it can be seen that as the detection index data of the site continues to increase, the length of the preset time period is adaptively adjusted, that is, the referenced historical detection index data is increased, so as to obtain a more comprehensive understanding of the changes in the detection index data and maintain the accuracy of the safety index threshold range.

[0031] Please refer to Figure 1 , Embodiment 1 of the present invention is: A method for generating a threshold value of a site monitoring indicator comprises the following steps: S0. While acquiring the detection index data of the station within a preset period, the number of acquisitions is accumulated, and the length of the preset time period is adjusted according to the number of acquisitions; In this embodiment, the length of the preset cycle can be determined based on which of the detection index data of the actual selected site, such as the site PCS insulation value; the working characteristics of the equipment corresponding to the data will affect the length of the cycle. In addition, the method of this implementation is not only applicable to the detection index data of the site, but also applicable to monitoring scenarios such as the main positive and negative insulation values ​​of the battery, the maximum temperature of the battery cell, the battery compartment temperature, the equipment compartment temperature, the battery compartment humidity, the equipment compartment humidity, the hydrogen concentration, the carbon monoxide solubility, etc.

[0032] S1. Obtain historical detection index data of the station within a preset time period, and identify abnormal points and abnormal intervals of each abnormal point in the historical detection index data according to a time series anomaly detection algorithm; In this embodiment, the preset time can be a period from a certain time node in the past to the current time, or it can be a period of time when some data are in different changes as the preset time according to the data change situation. As for the time series anomaly detection algorithm, the SH-ESD algorithm is preferably used. SH-ESD is an anomaly detection method, and its full name is "Seasonal Hybrid Extreme Studentized Deviate". This method is used to detect outliers in time series data, especially for seasonal data sets. Its specific application process can be seen in the journal article named Automatic Anomaly Detection in the Cloud Via Statistical Learning, the author is Jordan Hochenbaum OwenS. Vallis Arun Kejariwal Twitter Inc.

[0033] Based on the SH-ESD algorithm, the process of determining the abnormal points in the historical detection index data and the abnormal interval of each abnormal point is as follows: First, use MAD to define the absolute median deviation MAD in the historical detection indicator data: MAD = median(|X i-median(X)); Among them, Xi is the i-th item of data in the historical detection index data; Then calculate the residual of each data in the historical detection index data and the median difference of the absolute value. If the absolute value of the residual of a certain data is greater than the preset value, it means that the data is abnormal data.

[0034] After the outlier point is determined, the absolute value of the residual of the outlier point can be used as the endpoint of the interval, so as to perform iteration, that is, the outlier interval corresponding to the second outlier point is an interval composed of the absolute value of the residual of the first outlier point and the absolute value of its own residual as upper and lower bounds, and so on; therefore, when determining the safety index threshold interval, in addition to adopting the operation mode of step S2 and step S3, the upper and lower bounds of the outlier interval corresponding to the last outlier point can also be selected as the endpoints of the safety index threshold interval.

[0035] S2. According to the upper and lower bounds of the abnormal interval of each abnormal point, obtain the abnormal interval upper bound sequence and the abnormal interval lower bound sequence of the corresponding historical detection index data; In this embodiment, the maximum value in the abnormal interval upper boundary value sequence is selected as the abnormality detection upper boundary threshold, and the minimum value in the abnormal interval lower boundary value sequence is selected as the abnormality detection lower boundary threshold.

[0036] S3. Determine the upper threshold of anomaly detection according to the upper limit value sequence of the anomaly interval, obtain the lower threshold of anomaly detection according to the lower limit sequence of the anomaly interval, and obtain the threshold interval of the safety index.

[0037] In this embodiment, as a preferred design, the maximum value in the abnormal interval upper boundary value sequence is selected as the abnormality detection upper boundary threshold, and the minimum value in the abnormal interval lower boundary value sequence is selected as the abnormality detection lower boundary threshold.

[0038] S4. Obtain the current detection index data of the station, and detect whether there is data anomaly in the current detection index data according to the safety index threshold interval. If not, add the current detection index data to the historical detection index data, identify the abnormal points in the historical detection index data and the abnormal interval of each abnormal point according to the time series anomaly detection algorithm, and execute steps S2 and S3.

[0039] In this embodiment, the upper and lower limits of the safety index threshold interval are the upper and lower limit thresholds of the station safety monitoring index; if the current detection index data is within the safety index threshold interval, it means that the data is abnormal and an alarm maintenance should be triggered immediately.

[0040] Not only that, in the above steps, the average value and the maximum value in the upper limit value sequence of the abnormal interval can also be combined into an upper limit warning interval, and the average value and the minimum value in the lower limit sequence of the abnormal interval can be combined into a lower limit warning interval; when the size of the current detection index data does not fall into the upper limit warning interval or the lower limit warning interval, although the alarm is not triggered, a reminder will be issued to the operation and maintenance personnel, so that the operation and maintenance personnel can combine other data associated with the data corresponding to the current detection index data to determine whether it is reasonable to fall into the upper limit warning interval or the lower limit warning interval, and then predict possible abnormal conditions.

[0041] Please refer to Figure 2 , Embodiment 2 of the present invention is: A terminal 1 for generating a threshold value of a site monitoring indicator comprises a memory 2, a processor 3 and a computer program stored in the memory 2 and executable on the processor 3. When the processor 3 executes the computer program, a method for generating a threshold value of a site monitoring indicator is implemented in accordance with the first embodiment.

[0042] In summary, the present invention provides a method and terminal for generating a threshold value of a monitoring index of a station, which utilizes a time series algorithm to identify abnormal points of the historical detection index data of the station within a preset time period and abnormal intervals of each abnormal point, and utilizes a plurality of change intervals of abnormal points generated as the operation time of the station increases to grasp the abnormal changes of the monitoring index data of the station, and then determines the upper and lower thresholds of the safety index threshold interval by integrating the upper limit sequence of the abnormal interval and the lower limit sequence of the abnormal interval, that is, the safety index threshold interval represents the range in which the data size is concentrated after different abnormal situations occur, and uses this as the judgment standard for detecting whether the current detection index data of the station is abnormal, thereby assisting in accurately identifying the abnormal situation of the data of the monitoring index of the station and ensuring the safe operation of the station.

[0043] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's specification and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for generating thresholds of site monitoring indicators, characterized in that: The steps include: S1. Obtain historical detection index data of the station within a preset time period, and identify abnormal points in the historical detection index data and abnormal intervals of each abnormal point according to a time series anomaly detection algorithm; S2. Obtain an upper bound sequence and a lower bound sequence of abnormal intervals corresponding to the historical detection index data according to the upper bound and the lower bound of the abnormal interval of each abnormal point; S3. Determine an upper threshold value for abnormality detection according to the abnormal interval upper limit value sequence, obtain a lower threshold value for abnormality detection according to the abnormal interval lower limit sequence, and obtain a safety indicator threshold interval.

2. A method for generating a threshold value of a station monitoring indicator according to claim 1, characterized in that: The step S3 specifically includes: The maximum value in the abnormal interval upper boundary value sequence is selected as the abnormality detection upper boundary threshold, and the minimum value in the abnormal interval lower boundary value sequence is selected as the abnormality detection lower boundary threshold.

3. A method for generating a threshold value of a station monitoring indicator according to claim 1, characterized in that: The step S2 specifically includes: S21, eliminating the maximum values ​​in the upper bounds of the abnormal intervals of all the abnormal points, to obtain a sequence of upper bounds of the abnormal intervals; S22: Eliminate the minimum values ​​in the lower bounds of the abnormal intervals of all the abnormal points to obtain a sequence of lower bounds of the abnormal intervals.

4. A method for generating a threshold value of a site monitoring indicator according to claim 1, characterized in that: Also includes: S4. Obtain the current detection index data of the site, detect whether there is data anomaly in the current detection index data according to the safety index threshold interval, if not, add the current detection index data to the historical detection index data, identify the abnormal points in the historical detection index data and the abnormal interval of each abnormal point according to the time series anomaly detection algorithm, and execute steps S2 and S3.

5. A method for generating a threshold value of a site monitoring indicator according to claim 1, characterized in that: Before step S1, the following steps are also included: S0. While acquiring the detection index data of the site within a preset period, the number of acquisitions is accumulated, and the length of the preset time period is adjusted according to the number of acquisitions.

6. A terminal for generating a threshold value of a site monitoring index, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the following steps are implemented: S1. Obtain historical detection index data of the station within a preset time period, and identify abnormal points in the historical detection index data and abnormal intervals of each abnormal point according to a time series anomaly detection algorithm; S2. Obtain an upper bound sequence and a lower bound sequence of abnormal intervals corresponding to the historical detection index data according to the upper bound and the lower bound of the abnormal interval of each abnormal point; S3. Determine an upper threshold value for abnormality detection according to the abnormal interval upper limit value sequence, obtain a lower threshold value for abnormality detection according to the abnormal interval lower limit sequence, and obtain a safety indicator threshold interval.

7. A terminal for generating a threshold value of a site monitoring index according to claim 6, characterized in that: The step S3 specifically includes: The maximum value in the abnormal interval upper boundary value sequence is selected as the abnormality detection upper boundary threshold, and the minimum value in the abnormal interval lower boundary value sequence is selected as the abnormality detection lower boundary threshold.

8. A terminal for generating a threshold value of a site monitoring index according to claim 6, characterized in that: The step S2 specifically includes: S21, eliminating the maximum values ​​in the upper bounds of the abnormal intervals of all the abnormal points, to obtain a sequence of upper bounds of the abnormal intervals; S22: Eliminate the minimum values ​​in the lower bounds of the abnormal intervals of all the abnormal points to obtain a sequence of lower bounds of the abnormal intervals.

9. A terminal for generating a threshold value of a site monitoring index according to claim 6, characterized in that: Also includes: S4. Obtain the current detection index data of the site, detect whether there is data anomaly in the current detection index data according to the safety index threshold interval, if not, add the current detection index data to the historical detection index data, identify the abnormal points in the historical detection index data and the abnormal interval of each abnormal point according to the time series anomaly detection algorithm, and execute steps S2 and S3.

10. A terminal for generating a threshold value of a site monitoring index according to claim 6, characterized in that: Before step S1, the following steps are also included: S0. While acquiring the detection index data of the site within a preset period, the number of acquisitions is accumulated, and the length of the preset time period is adjusted according to the number of acquisitions.

Images