Energy storage power station monitoring method and system

Abstract

The present invention discloses a method and system for monitoring an energy storage power station. The method includes receiving power station data sent by an energy storage power station, and performing risk association screening according to historical information screening rules and type screening rules, obtaining a high-risk data set and a high-association data set to perform data risk prediction, obtaining the data risk probability of the energy storage power station, and performing association risk prediction on the high-association data set to obtain the association risk probability corresponding to each power station association set; performing comprehensive risk analysis on the data risk probability and the association risk probability to obtain a high-risk energy storage power station, generating alarm information and performing alarm control according to the high-risk energy storage power station; visualizing the risk of the energy storage power station according to the power station association set and the high-risk energy storage power station, generating a risk visualization picture, and pushing the risk visualization picture to a terminal for display. This embodiment realizes effective monitoring and early warning of the risks of the energy storage power station, and improves the accuracy and convenience of monitoring the energy storage power station.

Description

Technical Field

[0001] The present invention relates to the field of monitoring data processing, and in particular to a method and system for monitoring an energy storage power station. Background Art

[0002] As the demand for electricity in cities continues to rise, the requirements for power generation-related equipment are also getting higher and higher. Among them, energy storage power stations, as core facilities in power generation-related equipment or power generation facilities, have gradually gained attention for their safe operation. Monitoring of energy storage power stations is a core technical element for achieving automated and efficient operation of energy storage power stations. Existing energy storage power stations are equipped with a large number of high-risk energy storage equipment such as converters and batteries. Therefore, it is necessary to combine a variety of information to manage and monitor these energy storage equipment in an orderly manner.

[0003] However, in the prior art, the monitoring system of the energy storage power station is mostly based on the traditional power station model, through the data acquisition of staff and simple controllers, and the energy storage power station is monitored according to preset data analysis rules. This single monitoring method cannot take into account the correlation between the various equipment in the energy storage power station, and does not consider the combination of multiple data of the energy storage power station for effective prediction to comprehensively analyze the dangerous situation of the power station, and cannot accurately monitor the energy storage power station. Summary of the invention

[0004] The present invention provides a method and system for monitoring an energy storage power station, which can effectively monitor and warn of risks in the energy storage power station, intelligently monitor the energy storage power station, and improve the accuracy and convenience of monitoring the energy storage power station.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for monitoring an energy storage power station, comprising:

[0006] Receive power station data sent by several energy storage power stations, and perform risk association screening on the data of each power station according to historical information screening rules and type screening rules to obtain several high-risk data sets and several high-association data sets; wherein the power station data includes power station equipment parameters, equipment operating parameters and sensor data in the power station;

[0007] Perform data risk prediction on each high-risk data set to obtain the data risk probability of the energy storage power station corresponding to each high-risk data set, and perform correlation risk prediction on each high-correlation data set to obtain the correlation risk probability corresponding to each power station correlation set; wherein the power station correlation set includes multiple interrelated energy storage power stations;

[0008] A comprehensive risk analysis is performed on the data risk probabilities of the energy storage power stations corresponding to each high-risk data set and the associated risk probabilities corresponding to each power station associated set to obtain a number of high-risk energy storage power stations. Alarm information is generated based on each high-risk energy storage power station, and alarm control is performed based on the alarm information. Based on each power station associated set and each high-risk energy storage power station, the risk of each energy storage power station is visualized, a risk visualization screen is generated, and the risk visualization screen is pushed to the terminal for display.

[0009] In the implementation of the embodiment of the present invention, power station data sent by several energy storage power stations are received, and risk association screening is performed on the data of each power station according to historical information screening rules and type screening rules to obtain several high-risk data sets and several highly associated data sets; wherein the power station data includes power station equipment parameters, equipment operating parameters and sensor data in the power station; data risk prediction is performed on each high-risk data set to obtain the data risk probability of the energy storage power station corresponding to each high-risk data set, and associated risk prediction is performed on each highly associated data set to obtain the associated risk probability corresponding to each power station associated set; wherein the power station associated set includes a plurality of mutually associated energy storage power stations; comprehensive risk analysis is performed on the data risk probability of the energy storage power station corresponding to each high-risk data set and the associated risk probability corresponding to each power station associated set to obtain several high-risk energy storage power stations, and alarm information is generated according to each high-risk energy storage power station, and alarm control is performed according to the alarm information; risk visualization is performed on each energy storage power station according to each power station associated set and each high-risk energy storage power station, a risk visualization screen is generated, and the risk visualization screen is pushed to a terminal for display. Through risk association screening algorithms and data prediction algorithms, the risks of energy storage power stations can be effectively monitored and warned. At the same time, the intelligence and visualization of energy storage power station monitoring can be improved, greatly improving the accuracy and convenience of monitoring.

[0010] As a preferred solution, according to the historical information screening rules and type screening rules, the data of each power station is screened for risk association to obtain several high-risk data sets and several high-association data sets, specifically:

[0011] Based on the data values ​​of each power station data in the historical time period and the dangerous event information of the power station, and according to the historical information screening rules, each high-risk data set is screened out from the data of each power station;

[0012] Based on the association parameters between the energy storage power stations corresponding to the power station data and according to the type screening rules, each highly associated data set is screened out from the power station data; each highly associated data set includes at least two power station data belonging to a strong correlation relationship.

[0013] As a preferred solution, based on the data values ​​of each power station data in the historical time period and the power station dangerous event information, and according to the historical information screening rules, each high-risk data set is screened out from the power station data, specifically:

[0014] Query the historical data values ​​at multiple historical time points corresponding to the current power station data in the database;

[0015] Query the database to find out whether the energy storage power station corresponding to the current power station data has experienced power station dangerous events at multiple historical time points, and determine the dangerous historical time points at which the energy storage power station corresponding to the current power station data has experienced power station dangerous events; wherein there are at least two dangerous historical time points;

[0016] According to the historical data values ​​and dangerous historical time points of the current power station data, the weighted sum of any two of the numerical similarity, the segment data average value similarity and the adjacent time data change degree similarity is taken to calculate the different types of similarities between the historical data values ​​corresponding to the dangerous historical time points, and obtain the different types of data dangerous similarities corresponding to the current power station data; wherein, the adjacent time data change degree similarity is the similarity of the data change value between the historical data value of the dangerous historical time point and the adjacent historical time point; the segment data average value similarity is the similarity between the average values ​​of the historical data values ​​of all historical time points in the time interval composed of the preset before and after time lengths of any two dangerous historical time points; the weight of the adjacent time data change degree similarity is greater than the weight of the segment data average value similarity, and the weight of the segment data average value similarity is greater than the weight of the numerical similarity;

[0017] According to the data hazard similarity of different types of data of each power station, the data of each power station are sorted from large to small to obtain at least one data sequence;

[0018] The first number of power station data in each data sequence is determined as each high-risk data set.

[0019] As a preferred solution, based on the correlation parameters between the energy storage power stations corresponding to the power station data, and according to the type screening rules, each highly correlated data set is screened out from the power station data, specifically:

[0020] Arbitrarily select multiple power station data from the power station data as the current power station data;

[0021] Obtain the power station location, power supply chain and power station equipment parameters of the energy storage power station corresponding to the current power station data;

[0022] According to the power station locations of the energy storage power stations corresponding to the current power station data, the average distance between the power station locations of the current power station data is calculated;

[0023] According to the power supply chain of the energy storage power station corresponding to the current power station data, the power supply chain similarity between the power supply chains of the power stations in the current power station data is calculated; wherein the power supply chain similarity is the ratio of the number of power station data in the same power supply chain to the total number of power station data;

[0024] According to the power station equipment parameters of the energy storage power station corresponding to the current power station data, the equipment type similarity between the power station equipment parameters of any two power station data is calculated, and the similarity average of all equipment type similarities corresponding to the current power station data is calculated;

[0025] The weighted sum of the distance average value, power supply chain similarity and similarity average value corresponding to the current data of each power station is performed to obtain the weighted sum value of the current data of each power station; wherein the sum of the distance average value, power supply chain similarity and similarity average value is 1, and the weights of the distance average value, power supply chain similarity and similarity average value decrease in sequence;

[0026] Determine whether the weighted sum of the current power station data is greater than a preset parameter threshold, and if so, treat the current power station data as a highly correlated data set;

[0027] If not, then select a plurality of power station data at random from each power station data, re-determine the current power station data, perform correlation similarity calculation based on the current power station data, calculate the weighted sum value of the current power station data, until the weighted sum value of the current power station data is greater than the preset parameter threshold, and obtain each highly correlated data set.

[0028] As a preferred solution, data risk prediction is performed on each high-risk data set to obtain the data risk probability of the energy storage power station corresponding to each high-risk data set, specifically:

[0029] Inputting each power station data in the current high-risk data set into a pre-trained first neural network prediction model to obtain the data risk probability corresponding to each power station data in the current high-risk data set; wherein the first neural network prediction model is trained by a plurality of training power station data and a training data set with data risk annotations corresponding to each training power station data;

[0030] According to the data risk probability corresponding to each power station data in each high-risk data set, the data risk probability of the energy storage power station corresponding to each high-risk data set is obtained.

[0031] As a preferred solution, each highly correlated data set is subjected to correlation risk prediction to obtain the correlation risk probability corresponding to each power station correlation set, specifically:

[0032] Determine all energy storage power stations corresponding to all power station data in each highly correlated data set as each power station correlation set;

[0033] Input all power station data in the current high-correlation data set into a pre-trained second neural network prediction model to obtain the correlation risk probability corresponding to each power station correlation set corresponding to the current high-correlation data set; wherein the second neural network prediction model is trained by a training data set including a plurality of training power station data corresponding to a plurality of training power station correlation sets and data risk annotations corresponding to each training power station correlation set;

[0034] According to the associated risk probabilities corresponding to the respective power station associated sets corresponding to the respective high-associated data sets, the associated risk probabilities corresponding to the respective power station associated sets are obtained.

[0035] As a preferred solution, a comprehensive risk analysis is performed on the data risk probability of the energy storage power station corresponding to each high-risk data set and the associated risk probability corresponding to each power station associated set to obtain several high-risk energy storage power stations, specifically:

[0036] Determine whether the associated risk probability corresponding to the current power station associated set is higher than a preset probability threshold, and if so, determine the current power station associated set as a dangerous power station set;

[0037] Determine each dangerous power station set according to the associated risk probability corresponding to each power station associated set;

[0038] According to the data risk probability of the energy storage power station corresponding to each high-risk data set, the data risk probability corresponding to all energy storage power stations in each dangerous power station set is determined, and the data risk probability corresponding to all energy storage power stations in each dangerous power station set is subjected to risk weight analysis to obtain each high-risk energy storage power station.

[0039] As a preferred solution, the risk probability of the data corresponding to all energy storage power stations in each dangerous power station set is analyzed by risk weight to obtain each high-risk energy storage power station, specifically:

[0040] According to the data risk probability of the current energy storage power station in the current set of dangerous power stations, the average value of the data risk probability corresponding to all power station data corresponding to the current energy storage power station is calculated to obtain the data risk parameter corresponding to the current energy storage power station;

[0041] Calculate the average value of the distance between the current energy storage power station and all other energy storage power stations in the same dangerous power station set, the average value of the weighted sum of the power supply chain similarity and the similarity average value, and obtain the association parameter corresponding to the current energy storage power station;

[0042] Determine the risk weight corresponding to the current energy storage power station according to the associated parameters corresponding to the current energy storage power station and the preset parameter weight rules; wherein the risk weight is proportional to the associated parameters;

[0043] Calculate the product of the data risk parameter and risk weight of the current energy storage power station to obtain the risk value of the current energy storage power station;

[0044] Calculate the danger level of each energy storage power station in each dangerous power station set to obtain the total danger level;

[0045] According to all the danger values, all the energy storage power stations in each dangerous power station set are sorted from large to small to obtain the power station sequence corresponding to each dangerous power station set;

[0046] The first second number of energy storage power stations in the power station sequence corresponding to each dangerous power station set are determined as high-risk energy storage power stations to obtain each high-risk energy storage power station.

[0047] As a preferred solution, the risks of each energy storage power station are visualized according to the associated sets of each power station and each high-risk energy storage power station, and a risk visualization screen is generated, specifically:

[0048] Determine other energy storage power stations in the power station association set to which the current energy storage power station belongs, and obtain multiple associated power stations;

[0049] Determine whether the power station associated set to which the current energy storage power station belongs belongs to a dangerous power station set, and obtain a first determination result corresponding to the current energy storage power station and each associated power station;

[0050] Determine whether the current energy storage power station is a high-risk energy storage power station, and obtain a second determination result corresponding to the current energy storage power station;

[0051] According to each energy storage power station, a first judgment result and a second judgment result corresponding to each energy storage power station are obtained;

[0052] Constructing the objective function of the dynamic programming algorithm model; wherein the objective function is specifically: in the calculated relationship diagram, the distance between each energy storage power station and the corresponding associated power station is minimized and the conspicuity of the display parameters corresponding to each energy storage power station is maximized; the conspicuity is used to characterize the attractiveness of the display parameters; the display parameters include specific dimensional values ​​of the display frame size, display font size and display color;

[0053] The restriction conditions for determining the dynamic programming algorithm model include: in the calculated relationship diagram, the distance between the energy storage power station and the associated power station is less than the distance between the energy storage power station and the non-associated power station; the energy storage power station with a first judgment result of yes is more conspicuous than the energy storage power station with a first judgment result of no; the energy storage power station with a second judgment result of yes is more conspicuous than the energy storage power station with a first judgment result of yes;

[0054] Based on the objective function and constraints, the parameters of all energy storage power stations are input into the dynamic programming algorithm model for iterative calculation to obtain the optimal calculation result that meets the objective function and constraints; the optimal calculation result includes the visual relationship diagram corresponding to all energy storage power stations.

[0055] In order to solve the same technical problem, an embodiment of the present invention further provides an energy storage power station monitoring system, including: the energy storage power station monitoring system is used to implement the energy storage power station monitoring method, including: a data receiving and screening device, a data risk association prediction device and an analysis and monitoring device;

[0056] The data receiving and screening device is used to receive power station data sent by several energy storage power stations, and screen the data of each power station for risk association according to historical information screening rules and type screening rules, and obtain several high-risk data sets and several high-association data sets; wherein the power station data includes power station equipment parameters, equipment working parameters and sensor data in the power station;

[0057] The data risk association prediction device is used to perform data risk prediction on each high-risk data set to obtain the data risk probability of the energy storage power station corresponding to each high-risk data set, and perform association risk prediction on each high-association data set to obtain the association risk probability corresponding to each power station association set; wherein the power station association set includes multiple mutually associated energy storage power stations;

[0058] The analysis and monitoring device is used to conduct a comprehensive risk analysis on the data risk probability of the energy storage power station corresponding to each high-risk data set and the associated risk probability corresponding to each power station associated set, to obtain a number of high-risk energy storage power stations, and generate alarm information according to each high-risk energy storage power station, and perform alarm control according to the alarm information; according to each power station associated set and each high-risk energy storage power station, the risk of each energy storage power station is visualized, a risk visualization screen is generated, and the risk visualization screen is pushed to the terminal for display. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 : A flow chart of an embodiment of a method for monitoring an energy storage power station provided by the present invention;

[0060] Figure 2 : A structural schematic diagram of an embodiment of an energy storage power station monitoring system provided by the present invention;

[0061] Figure 3 : A schematic diagram of a modular structure of an embodiment of an energy storage power station monitoring system provided by the present invention;

[0062] Figure 4: A structural diagram of a data screening module of an embodiment of an energy storage power station monitoring system provided by the present invention;

[0063] Figure 5 : A structural diagram of a risk comprehensive analysis module of an embodiment of an energy storage power station monitoring system provided by the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or ends.

[0066] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] Embodiment 1

[0068] Please refer to Figure 1 , which is a flow chart of a method for monitoring an energy storage power station provided by an embodiment of the present invention. The method for monitoring an energy storage power station of this embodiment is applicable to automatic monitoring of energy storage power stations. This embodiment uses a risk association screening algorithm and a data prediction algorithm to effectively monitor and warn of risks of energy storage power stations, intelligently monitor energy storage power stations, and improve the accuracy and convenience of monitoring energy storage power stations. The method for monitoring an energy storage power station includes steps 11 to 13, and each step is as follows:

[0069] Step 11: Receive power station data sent by several energy storage power stations, and perform risk association screening on the data of each power station according to historical information screening rules and type screening rules to obtain several high-risk data sets and several high-association data sets; wherein the power station data includes power station equipment parameters, equipment operating parameters and sensor data in the power station.

[0070] In this embodiment, multiple power station data of multiple energy storage power stations are received and acquired, and at least one high-risk data set and at least one high-correlation data set are filtered out from the power station data based on historical information filtering rules and type filtering rules, that is, several high-risk data sets and several high-correlation data sets.

[0071] By implementing the embodiments of the present invention, it is possible to screen the power station data to obtain a high-risk data set and a high-correlation data set, thereby further improving the intelligence and visualization of energy storage power station monitoring in the future, greatly improving the accuracy and convenience of monitoring.

[0072] Optionally, step 11 specifically includes step 111 to step 113, and each step is specifically as follows:

[0073] Step 111: receiving power station data sent by a number of energy storage power stations.

[0074] In this embodiment, multiple energy storage power stations are connected to receive multiple power station data sent by each energy storage power station. The power station data may include power station equipment parameters, equipment operating parameters and sensor data in the power station. The power station equipment parameters may include at least one of converter equipment information, battery equipment information, control joystick equipment information, and switch control equipment information. The equipment operating parameters may include converter start and stop parameters, converter reactive power parameters, converter operating state parameters, battery system SOC information, battery system SOH information, battery cell voltage information, battery temperature information, alarm fault information, distribution equipment switch information, and at least one of joystick operating state parameters. The sensor data in the power station may include equipment water flow data, equipment water quality data, station image data, ambient air quality data, ambient temperature data, ambient humidity data, station access control data, station door and window monitoring data, and station staff clock-in data.

[0075] Step 112: Based on the data values ​​of each power plant data in the historical time period and the power plant dangerous event information, and according to the historical information screening rules, each high-risk data set is screened out from each power plant data.

[0076] In this embodiment, at least one high-risk data set is screened out from the power plant data based on the data value of each power plant data in the historical time period and the corresponding information on whether a dangerous event of the power plant has occurred; the high-risk data set includes at least one power plant data belonging to a strong risk-related type.

[0077] Optionally, step 112 specifically includes: querying the database for historical data values ​​corresponding to the current power station data at multiple historical time points;

[0078] Query the database to find out whether the energy storage power station corresponding to the current power station data has experienced power station dangerous events at multiple historical time points, and determine the dangerous historical time points at which the energy storage power station corresponding to the current power station data has experienced power station dangerous events; wherein there are at least two dangerous historical time points;

[0079] According to the historical data values ​​and dangerous historical time points of the current power station data, the weighted sum of any two of the numerical similarity, the segment data average value similarity and the adjacent time data change degree similarity is taken to calculate the different types of similarities between the historical data values ​​corresponding to the dangerous historical time points, and obtain the different types of data dangerous similarities corresponding to the current power station data; wherein, the adjacent time data change degree similarity is the similarity of the data change value between the historical data value of the dangerous historical time point and the adjacent historical time point; the segment data average value similarity is the similarity between the average values ​​of the historical data values ​​of all historical time points in the time interval composed of the preset before and after time lengths of any two dangerous historical time points; the weight of the adjacent time data change degree similarity is greater than the weight of the segment data average value similarity, and the weight of the segment data average value similarity is greater than the weight of the numerical similarity;

[0080] According to the data hazard similarity of different types of data of each power station, the data of each power station are sorted from large to small to obtain at least one data sequence;

[0081] The first number of power station data in each data sequence is determined as each high-risk data set.

[0082] In this embodiment, for each power station data, historical data values ​​corresponding to the power station data at multiple historical time points are queried in the database;

[0083] Query the database to find out whether the energy storage power station corresponding to the power station data has experienced power station dangerous events at multiple historical time points, so as to determine at least two dangerous historical time points at which power station dangerous events occurred in the energy storage power station;

[0084] Calculate different types of similarities between historical data values ​​corresponding to at least two dangerous historical time points to obtain different types of data dangerous similarities corresponding to the power station data; the similarity includes a weighted sum of any two of numerical similarity, segment data average value similarity, and adjacent time data change degree similarity; wherein the weights of adjacent time data change degree similarity, segment data average value similarity, and numerical similarity gradually decrease; adjacent time data change degree similarity is the similarity between data change values ​​between historical data values ​​of two dangerous historical time points and adjacent prior and / or subsequent time points; segment data average value similarity is the similarity between the average values ​​of historical data values ​​of all historical time points in a time interval composed of a preset time length before and after the two dangerous historical time points;

[0085] Sort all power station data from large to small according to the risk similarity of different types of data to obtain at least one data sequence;

[0086] The first first number of power station data in each data sequence is determined as a high-risk data set.

[0087] Through the above steps of screening out each high-risk data set, it is possible to determine the degree of danger of different power station data based on multiple similarities of historical data values ​​at the time points when dangerous times occurred, and screen out data with high risk correlation for subsequent risk prediction, which can effectively improve the accuracy of the prediction.

[0088] Step 113: based on the association parameters between the energy storage power stations corresponding to the power station data and according to the type screening rules, each highly associated data set is screened out from the power station data; each highly associated data set includes at least two power station data belonging to a strong association relationship.

[0089] In this embodiment, at least one highly correlated data set is screened out from the power station data according to the correlation parameters between the energy storage power stations corresponding to at least two power station data; the highly correlated data set includes at least two power station data belonging to a strongly correlated relationship.

[0090] Optionally, step 113 specifically includes: arbitrarily selecting a plurality of power station data from the power station data as the current power station data;

[0091] Obtain the power station location, power supply chain and power station equipment parameters of the energy storage power station corresponding to the current power station data;

[0092] According to the power station locations of the energy storage power stations corresponding to the current power station data, the average distance between the power station locations of the current power station data is calculated;

[0093] According to the power supply chain of the energy storage power station corresponding to the current power station data, the power supply chain similarity between the power supply chains of the power stations in the current power station data is calculated; wherein the power supply chain similarity is the ratio of the number of power station data in the same power supply chain to the total number of power station data;

[0094] According to the power station equipment parameters of the energy storage power station corresponding to the current power station data, the equipment type similarity between the power station equipment parameters of any two power station data is calculated, and the similarity average of all equipment type similarities corresponding to the current power station data is calculated;

[0095] The weighted sum of the distance average value, power supply chain similarity and similarity average value corresponding to the current data of each power station is performed to obtain the weighted sum value of the current data of each power station; wherein the sum of the distance average value, power supply chain similarity and similarity average value is 1, and the weights of the distance average value, power supply chain similarity and similarity average value decrease in sequence;

[0096] Determine whether the weighted sum of the current power station data is greater than a preset parameter threshold, and if so, treat the current power station data as a highly correlated data set;

[0097] If not, then select a plurality of power station data at random from each power station data, re-determine the current power station data, perform correlation similarity calculation based on the current power station data, calculate the weighted sum value of the current power station data, until the weighted sum value of the current power station data is greater than the preset parameter threshold, and obtain each highly correlated data set.

[0098] In this embodiment, for any plurality of power station data, the power station location, the power supply chain where the power station is located, and the power station equipment parameters of the energy storage power station corresponding to the plurality of power station data are determined;

[0099] Calculate the average distance between the power station locations of the plurality of power station data;

[0100] Calculate the power supply chain similarity between the power supply chains of the power stations in which the multiple power station data are located; the power supply chain similarity is the ratio of the number of power station data in the same power supply chain to the total number of power station data;

[0101] Calculate the equipment type similarity between the power plant equipment parameters of any two power plant data, and calculate the similarity average of all equipment type similarities corresponding to the multiple power plant data;

[0102] Calculate the weighted sum of the distance average, power supply chain similarity and similarity average corresponding to the multiple power station data; wherein the sum of the distance average, power supply chain similarity and similarity average is 1; and the weights of the distance average, power supply chain similarity and similarity average decrease in sequence;

[0103] Determine whether the weighted sum value is greater than a preset parameter threshold. If so, the multiple power station data are determined as a highly correlated data set; if not, the multiple power station data are not determined as a highly correlated data set, and multiple power station data can be arbitrarily selected again to perform corresponding calculations to determine whether the multiple power station data belong to a highly correlated data set, thereby obtaining multiple highly correlated data sets.

[0104] Through the above steps of screening out each highly correlated data set, it is possible to determine the degree of correlation between different power stations based on different correlation information of the power stations, such as the distance, the similarity of the power supply chain or the similarity of the equipment type, and screen out the data of power stations with high correlation with each other for subsequent risk prediction, which can effectively improve the accuracy and relevance of the prediction and discover the degree of correlation between dangerous events.

[0105] Step 12: Perform data risk prediction on each high-risk data set to obtain the data risk probability of the energy storage power station corresponding to each high-risk data set, and perform correlation risk prediction on each high-correlation data set to obtain the correlation risk probability corresponding to each power station correlation set; wherein the power station correlation set includes multiple interrelated energy storage power stations.

[0106] In this embodiment, according to any high-risk data set, the data risk probability corresponding to any energy storage power station is predicted, that is, the data risk probability of the energy storage power station corresponding to each high-risk data set. According to any high-correlation data set, the correlation risk probability corresponding to any power station correlation set is predicted; the power station correlation set includes multiple energy storage power stations that are correlated with each other.

[0107] Optionally, step 12 specifically includes step 121 to step 122, and each step is specifically as follows:

[0108] Step 121: inputting each power station data in the current high-risk data set into a pre-trained first neural network prediction model to obtain the data risk probability corresponding to each power station data in the current high-risk data set; wherein the first neural network prediction model is trained by a plurality of training power station data and a training data set with data risk annotations corresponding to each training power station data;

[0109] According to the data risk probability corresponding to each power station data in each high-risk data set, the data risk probability of the energy storage power station corresponding to each high-risk data set is obtained.

[0110] In this embodiment, each power plant data in the high-risk data set is input into a pre-trained first neural network prediction model to obtain the data risk probability corresponding to each power plant data; the first neural network prediction model is trained by a training data set that may include multiple training power plant data and corresponding data risk annotations.

[0111] As an example of this embodiment, the first neural network prediction model can be a combination of at least one or more of a CNN structure network model, an RNN structure network model, an LTSM structure network model, or other random forest algorithm models, and the present invention is not limited thereto.

[0112] By implementing the embodiment of the present invention, the data risk probability corresponding to each power station data is determined by the first neural network prediction model, which can effectively improve the accuracy and relevance of the prediction.

[0113] Step 122: all energy storage power stations corresponding to all power station data in each highly correlated data set are determined as each power station correlation set;

[0114] Input all power station data in the current high-correlation data set into a pre-trained second neural network prediction model to obtain the correlation risk probability corresponding to each power station correlation set corresponding to the current high-correlation data set; wherein the second neural network prediction model is trained by a training data set including a plurality of training power station data corresponding to a plurality of training power station correlation sets and data risk annotations corresponding to each training power station correlation set;

[0115] According to the associated risk probabilities corresponding to the respective power station associated sets corresponding to the respective high-associated data sets, the associated risk probabilities corresponding to the respective power station associated sets are obtained.

[0116] In this embodiment, all energy storage power stations corresponding to all power station data in each highly correlated data set are determined as a power station correlation set;

[0117] All power plant data in each highly correlated data set are input into a pre-trained second neural network prediction model to obtain the associated risk probability corresponding to each power plant associated set; the second neural network prediction model is trained by a training data set including multiple training power plant data corresponding to multiple training power plant associated sets and corresponding data risk annotations.

[0118] As an example of this embodiment, the second neural network prediction model can be a combination of at least one or more of a CNN structure network model, an RNN structure network model, an LTSM structure network model, or other random forest algorithm models, and the present invention is not limited thereto.

[0119] By implementing the embodiment of the present invention, the associated risk probability corresponding to each power station associated set is determined by the second neural network prediction model, which can effectively improve the accuracy and relevance of the prediction. At the same time, the training of the above-mentioned second neural network prediction model is actually also trained using training data related to the first neural network prediction model, and its model parameters also extract parameter features related to the first neural network prediction model, so that when the prediction results of the two models are subsequently used for cross-analysis, the analysis effect has more empirical value and the prediction effect is better.

[0120] Step 13: Perform a comprehensive risk analysis on the data risk probabilities of the energy storage power stations corresponding to each high-risk data set and the associated risk probabilities corresponding to each power station associated set to obtain a number of high-risk energy storage power stations, and generate alarm information based on each high-risk energy storage power station, and perform alarm control based on the alarm information; visualize the risks of each energy storage power station based on each power station associated set and each high-risk energy storage power station, generate a risk visualization screen, and push the risk visualization screen to the terminal for display.

[0121] In this embodiment, at least one high-risk energy storage power station is determined from all energy storage power stations based on the data risk probability and the associated risk probability, and an alarm message is sent to the terminal corresponding to the high-risk energy storage power station for alarm. Based on the data risk probability and the associated risk probability, a risk visualization screen corresponding to a plurality of energy storage power stations is generated and pushed to the terminal for display, thereby realizing risk monitoring and early warning risk display.

[0122] Optionally, a comprehensive risk analysis is performed on the data risk probability of the energy storage power station corresponding to each high-risk data set and the associated risk probability corresponding to each power station associated set to obtain several high-risk energy storage power stations, specifically:

[0123] Determine whether the associated risk probability corresponding to the current power station associated set is higher than a preset probability threshold, and if so, determine the current power station associated set as a dangerous power station set;

[0124] Determine each dangerous power station set according to the associated risk probability corresponding to each power station associated set;

[0125] According to the data risk probability of the energy storage power station corresponding to each high-risk data set, the data risk probability corresponding to all energy storage power stations in each dangerous power station set is determined, and the data risk probability corresponding to all energy storage power stations in each dangerous power station set is subjected to risk weight analysis to obtain each high-risk energy storage power station.

[0126] In this embodiment, for each power station association set, it is determined whether the associated risk probability corresponding to the power station association set is higher than a preset probability threshold. If so, the power station association set is determined as a dangerous power station set.

[0127] Optionally, the risk probability of the data corresponding to all energy storage power stations in each dangerous power station set is analyzed by risk weight to obtain each high-risk energy storage power station, specifically:

[0128] According to the data risk probability of the current energy storage power station in the current set of dangerous power stations, the average value of the data risk probability corresponding to all power station data corresponding to the current energy storage power station is calculated to obtain the data risk parameter corresponding to the current energy storage power station;

[0129] Calculate the average value of the distance between the current energy storage power station and all other energy storage power stations in the same dangerous power station set, the average value of the weighted sum of the power supply chain similarity and the similarity average value, and obtain the association parameter corresponding to the current energy storage power station;

[0130] Determine the risk weight corresponding to the current energy storage power station according to the associated parameters corresponding to the current energy storage power station and the preset parameter weight rules; wherein the risk weight is proportional to the associated parameters;

[0131] Calculate the product of the data risk parameter and risk weight of the current energy storage power station to obtain the risk value of the current energy storage power station;

[0132] Calculate the danger level of each energy storage power station in each dangerous power station set to obtain the total danger level;

[0133] According to all the danger values, all the energy storage power stations in each dangerous power station set are sorted from large to small to obtain the power station sequence corresponding to each dangerous power station set;

[0134] The first second number of energy storage power stations in the power station sequence corresponding to each dangerous power station set are determined as high-risk energy storage power stations to obtain each high-risk energy storage power station.

[0135] In this embodiment, at least one high-risk energy storage power station is determined from the dangerous power station set according to the data risk probabilities corresponding to all energy storage power stations in the dangerous power station set. The process of determining the high-risk energy storage power station is as follows: for any energy storage power station in any dangerous power station set, the average value of the data risk probabilities corresponding to all power station data corresponding to the energy storage power station is calculated to obtain the data risk parameter corresponding to the energy storage power station; the average value of the distance between the energy storage power station and all other energy storage power stations in the same dangerous power station set, the power supply chain similarity and the average value of the weighted sum of the similarity average values ​​are calculated to obtain the associated parameters corresponding to the energy storage power station; according to the associated parameters and the preset parameter-weight rule (the parameter-weight rule can be a preset weight determination formula, and it is defined that the risk weight is proportional to the associated parameters), the risk weight corresponding to the energy storage power station is determined; the risk weight is proportional to the associated parameters; the product of the data risk parameter and the risk weight of the energy storage power station is calculated; according to the product from large to small, all energy storage power stations in each dangerous power station set are sorted to obtain the power station sequence corresponding to each dangerous power station set; the first second number of energy storage power stations in the power station sequence corresponding to each dangerous power station set are determined as high-risk energy storage power stations.

[0136] Optionally, based on the associated sets of each power station and each high-risk energy storage power station, the risk of each energy storage power station is visualized to generate a risk visualization screen, specifically:

[0137] Determine other energy storage power stations in the power station association set to which the current energy storage power station belongs, and obtain multiple associated power stations;

[0138] Determine whether the power station associated set to which the current energy storage power station belongs belongs to a dangerous power station set, and obtain a first determination result corresponding to the current energy storage power station and each associated power station;

[0139] Determine whether the current energy storage power station is a high-risk energy storage power station, and obtain a second determination result corresponding to the current energy storage power station;

[0140] According to each energy storage power station, a first judgment result and a second judgment result corresponding to each energy storage power station are obtained;

[0141] Constructing the objective function of the dynamic programming algorithm model; wherein the objective function is specifically: in the calculated relationship diagram, the distance between each energy storage power station and the corresponding associated power station is minimized and the conspicuity of the display parameters corresponding to each energy storage power station is maximized; the conspicuity is used to characterize the attractiveness of the display parameters; the display parameters include specific dimensional values ​​of the display frame size, display font size and display color;

[0142] The restriction conditions for determining the dynamic programming algorithm model include: in the calculated relationship diagram, the distance between the energy storage power station and the associated power station is less than the distance between the energy storage power station and the non-associated power station; the energy storage power station with a first judgment result of yes is more conspicuous than the energy storage power station with a first judgment result of no; the energy storage power station with a second judgment result of yes is more conspicuous than the energy storage power station with a first judgment result of yes;

[0143] Based on the objective function and constraints, the parameters of all energy storage power stations are input into the dynamic programming algorithm model for iterative calculation to obtain the optimal calculation result that meets the objective function and constraints; the optimal calculation result includes the visual relationship diagram corresponding to all energy storage power stations.

[0144] In this embodiment, for each energy storage power station, other energy storage power stations in the power station associated set to which the energy storage power station belongs are determined to obtain multiple associated power stations; it is determined whether the power station associated set to which the energy storage power station belongs belongs to a dangerous power station set, and a first judgment result corresponding to the energy storage power station and the associated power stations is obtained; it is determined whether the energy storage power station belongs to a high-risk energy storage power station, and a second judgment result corresponding to the energy storage power station is obtained; determining the objective function of the dynamic programming algorithm model may include: in the calculated relationship diagram, the distance between each energy storage power station and the corresponding associated power station is minimized and the conspicuity of the display parameters corresponding to each energy storage power station is maximized; the conspicuity is used to characterize the attractiveness of the display parameters; the display parameters may include the display frame size, the display font size and / or a specific dimension value of the display color; determining the constraint conditions of the dynamic programming algorithm model may include: in the calculated relationship diagram, the distance between the energy storage power station and the associated power station is less than the distance between the energy storage power station and the non-associated power station; the energy storage power station whose first judgment result is yes is more conspicuous than the energy storage power station whose first judgment result is no; the energy storage power station whose second judgment result is yes is more conspicuous than the energy storage power station whose first judgment result is yes; based on the objective function and the constraint conditions, the parameters of all energy storage power stations are input into the dynamic programming algorithm model for iterative calculation to obtain the optimal calculation result that meets the objective function and the constraint conditions; the optimal calculation result may include a visualization relationship diagram corresponding to all energy storage power stations; and the visualization relationship diagram is pushed to the terminal for display.

[0145] As an example of this embodiment, the visualization relationship diagram may include a map of the area where multiple energy storage power stations are located, and the location of each energy storage power station in the map. Then, the display parameters such as the icon size or color of each energy storage power station include the above-mentioned dynamic programming algorithm, such as the particle swarm algorithm. By adjusting the size of the icon, the distance between the energy storage power stations can also be adjusted accordingly. That is, the distance refers to the map distance on the visualization relationship diagram. This distance can be the distance between the closest edge points of two icons. Therefore, the calculation of this distance also includes the calculation of the icon size.

[0146] In other implementation schemes, since the positions between the energy storage power stations may be fixed and calculating the distance cannot produce good results, the visualization relationship diagram may be simply calculated into a drawing that only includes multiple energy storage power stations, in which the distance or display parameters between the energy storage power stations are consistent with the above-mentioned restrictions.

[0147] In the implementation of the embodiment of the present invention, power station data sent by several energy storage power stations are received, and risk association screening is performed on the data of each power station according to historical information screening rules and type screening rules to obtain several high-risk data sets and several highly associated data sets; wherein the power station data includes power station equipment parameters, equipment operating parameters and sensor data in the power station; data risk prediction is performed on each high-risk data set to obtain the data risk probability of the energy storage power station corresponding to each high-risk data set, and associated risk prediction is performed on each highly associated data set to obtain the associated risk probability corresponding to each power station associated set; wherein the power station associated set includes a plurality of mutually associated energy storage power stations; comprehensive risk analysis is performed on the data risk probability of the energy storage power station corresponding to each high-risk data set and the associated risk probability corresponding to each power station associated set to obtain several high-risk energy storage power stations, and alarm information is generated according to each high-risk energy storage power station, and alarm control is performed according to the alarm information; risk visualization is performed on each energy storage power station according to each power station associated set and each high-risk energy storage power station, a risk visualization screen is generated, and the risk visualization screen is pushed to a terminal for display. Through data screening algorithms and data prediction algorithms, it is possible to effectively monitor and warn of risks in energy storage power stations. At the same time, through data visualization processing algorithms, it is also possible to improve the intelligence and visualization of energy storage power station monitoring, greatly improving the accuracy and convenience of monitoring.

[0148] Embodiment 2

[0149] Accordingly, see Figure 2 , Figure 2 Schematic diagram of the structure of the second embodiment of the energy storage power station monitoring system provided by the present invention. Figure 2 As shown, the energy storage power station monitoring system is used to implement the energy storage power station monitoring method, and the energy storage power station monitoring system includes a data receiving and screening device 201, a data risk association prediction device 202 and an analysis and monitoring device 203;

[0150] In this embodiment, the modular structure diagram of the energy storage power station monitoring system is as follows: Figure 3As shown, the energy storage power station monitoring system includes a data receiving module 101, a data screening module 102, a data risk prediction module 103, an associated risk prediction module 104, a risk comprehensive analysis module 105, and a risk visualization module 106. Specifically, the data receiving and screening device 201 includes the data receiving module 101 and the data screening module 102, the data risk associated prediction device 202 includes the data risk prediction module 103, the associated risk prediction module 104, and the analysis and monitoring device 203 includes the risk comprehensive analysis module 105 and the risk visualization module 106.

[0151] Among them, the data receiving and screening device 201 is used to receive power station data sent by several energy storage power stations, and perform risk association screening on the data of each power station according to historical information screening rules and type screening rules to obtain several high-risk data sets and several high-association data sets; among them, the power station data includes power station equipment parameters, equipment operating parameters and sensor data in the power station.

[0152] Optionally, the data receiving and filtering device 201 includes a data receiving module 101 and a data filtering module 102, wherein the data receiving module 101 is used to receive power station data sent by several energy storage power stations, and the data filtering module 102 is used to perform risk association screening on the data of each power station according to historical information filtering rules and type filtering rules to obtain several high-risk data sets and several high-association data sets.

[0153] In this embodiment, if Figure 4 As shown, the data screening module 102 includes: a historical screening unit 1021 and a type screening unit 1022. The historical screening unit 1021 is used to screen out each high-risk data set from each power station data based on the data value of each power station data in the historical time period and the power station dangerous event information, and according to the historical information screening rules. The type screening unit 1022 is used to screen out each highly correlated data set from each power station data based on the association parameters between the energy storage power stations corresponding to each power station data, and according to the type screening rules; each highly correlated data set includes at least two power station data belonging to a strong correlation relationship.

[0154] Optionally, the history screening unit 1021 specifically performs the following steps to screen out the high-risk data set: querying the database for historical data values ​​corresponding to the current power station data at multiple historical time points;

[0155] Query the database to find out whether the energy storage power station corresponding to the current power station data has experienced power station dangerous events at multiple historical time points, and determine the dangerous historical time points at which the energy storage power station corresponding to the current power station data has experienced power station dangerous events; wherein there are at least two dangerous historical time points;

[0156] According to the historical data values ​​and dangerous historical time points of the current power station data, the weighted sum of any two of the numerical similarity, the segment data average value similarity and the adjacent time data change degree similarity is taken to calculate the different types of similarities between the historical data values ​​corresponding to the dangerous historical time points, and obtain the different types of data dangerous similarities corresponding to the current power station data; wherein, the adjacent time data change degree similarity is the similarity of the data change value between the historical data value of the dangerous historical time point and the adjacent historical time point; the segment data average value similarity is the similarity between the average values ​​of the historical data values ​​of all historical time points in the time interval composed of the preset before and after time lengths of any two dangerous historical time points; the weight of the adjacent time data change degree similarity is greater than the weight of the segment data average value similarity, and the weight of the segment data average value similarity is greater than the weight of the numerical similarity;

[0157] According to the data hazard similarity of different types of data of each power station, the data of each power station are sorted from large to small to obtain at least one data sequence;

[0158] The first number of power station data in each data sequence is determined as each high-risk data set.

[0159] Optionally, the type screening unit 1022 determines the highly relevant data set by performing the following steps: arbitrarily selecting a plurality of power station data from each power station data as the current power station data;

[0160] Obtain the power station location, power supply chain and power station equipment parameters of the energy storage power station corresponding to the current power station data;

[0161] According to the power station locations of the energy storage power stations corresponding to the current power station data, the average distance between the power station locations of the current power station data is calculated;

[0162] According to the power supply chain of the energy storage power station corresponding to the current power station data, the power supply chain similarity between the power supply chains of the power stations in the current power station data is calculated; wherein the power supply chain similarity is the ratio of the number of power station data in the same power supply chain to the total number of power station data;

[0163] According to the power station equipment parameters of the energy storage power station corresponding to the current power station data, the equipment type similarity between the power station equipment parameters of any two power station data is calculated, and the similarity average of all equipment type similarities corresponding to the current power station data is calculated;

[0164] The weighted sum of the distance average value, power supply chain similarity and similarity average value corresponding to the current data of each power station is performed to obtain the weighted sum value of the current data of each power station; wherein the sum of the distance average value, power supply chain similarity and similarity average value is 1, and the weights of the distance average value, power supply chain similarity and similarity average value decrease in sequence;

[0165] Determine whether the weighted sum of the current power station data is greater than a preset parameter threshold, and if so, treat the current power station data as a highly correlated data set;

[0166] If not, then select a plurality of power station data at random from each power station data, re-determine the current power station data, perform correlation similarity calculation based on the current power station data, calculate the weighted sum value of the current power station data, until the weighted sum value of the current power station data is greater than the preset parameter threshold, and obtain each highly correlated data set.

[0167] The data risk association prediction device 202 is used to perform data risk prediction on each high-risk data set to obtain the data risk probability of the energy storage power station corresponding to each high-risk data set, and to perform association risk prediction on each high-correlation data set to obtain the association risk probability corresponding to each power station association set; wherein the power station association set includes multiple interrelated energy storage power stations.

[0168] Optionally, the data risk association prediction device 202 includes a data risk prediction module 103 and an association risk prediction module 104. The data risk prediction module 103 is used to perform data risk prediction on each high-risk data set to obtain the data risk probability of the energy storage power station corresponding to each high-risk data set. The association risk prediction module 104 is used to perform association risk prediction on each high-correlation data set to obtain the association risk probability corresponding to each power station association set.

[0169] Optionally, the data risk prediction module 103 is specifically configured to perform the following steps:

[0170] Inputting each power station data in the current high-risk data set into a pre-trained first neural network prediction model to obtain the data risk probability corresponding to each power station data in the current high-risk data set; wherein the first neural network prediction model is trained by a plurality of training power station data and a training data set with data risk annotations corresponding to each training power station data;

[0171] According to the data risk probability corresponding to each power station data in each high-risk data set, the data risk probability of the energy storage power station corresponding to each high-risk data set is obtained.

[0172] Optionally, the associated risk prediction module 104 is specifically configured to perform the following steps:

[0173] Determine all energy storage power stations corresponding to all power station data in each highly correlated data set as each power station correlation set;

[0174] Input all power station data in the current high-correlation data set into a pre-trained second neural network prediction model to obtain the correlation risk probability corresponding to each power station correlation set corresponding to the current high-correlation data set; wherein the second neural network prediction model is trained by a training data set including a plurality of training power station data corresponding to a plurality of training power station correlation sets and data risk annotations corresponding to each training power station correlation set;

[0175] According to the associated risk probabilities corresponding to the respective power station associated sets corresponding to the respective high-associated data sets, the associated risk probabilities corresponding to the respective power station associated sets are obtained.

[0176] The analysis and monitoring device 203 is used to conduct a comprehensive risk analysis on the data risk probability of the energy storage power station corresponding to each high-risk data set and the associated risk probability corresponding to each power station associated set, to obtain a number of high-risk energy storage power stations, and generate alarm information according to each high-risk energy storage power station, and perform alarm control according to the alarm information; according to each power station associated set and each high-risk energy storage power station, the risk of each energy storage power station is visualized, a risk visualization screen is generated, and the risk visualization screen is pushed to the terminal for display.

[0177] Optionally, the analysis and monitoring device 203 includes a comprehensive risk analysis module 105 and a risk visualization module 106. The comprehensive risk analysis module 105 is used to perform a comprehensive risk analysis on the data risk probability of the energy storage power station corresponding to each high-risk data set and the associated risk probability corresponding to each power station associated set, to obtain a number of high-risk energy storage power stations, and generate alarm information based on each high-risk energy storage power station, and perform alarm control based on the alarm information. The risk visualization module 106 is used to visualize the risk of each energy storage power station based on each power station associated set and each high-risk energy storage power station, generate a risk visualization picture, and push the risk visualization picture to the terminal for display.

[0178] In this embodiment, if Figure 5 As shown, the comprehensive risk analysis module 105 includes a first analysis unit 1051 , a second analysis unit 1052 and an alarm unit 1053 .

[0179] The first analysis unit 1051 is used to determine, for each power station association set, whether the associated risk probability corresponding to the power station association set is higher than a preset probability threshold, and if so, determine the power station association set as a dangerous power station set;

[0180] Optionally, the first analyzing unit 1051 is specifically configured to perform the following steps:

[0181] Determine whether the associated risk probability corresponding to the current power station associated set is higher than a preset probability threshold, and if so, determine the current power station associated set as a dangerous power station set;

[0182] Determine each dangerous power station set according to the associated risk probability corresponding to each power station associated set;

[0183] According to the data risk probability of the energy storage power station corresponding to each high-risk data set, the data risk probability corresponding to all energy storage power stations in each dangerous power station set is determined, and the data risk probability corresponding to all energy storage power stations in each dangerous power station set is subjected to risk weight analysis to obtain each high-risk energy storage power station.

[0184] The second analysis unit 1052 is used to perform risk weight analysis on the data risk probabilities corresponding to all energy storage power stations in each dangerous power station set to obtain each high-risk energy storage power station;

[0185] Optionally, the second analysis unit 1052 is specifically configured to perform the following steps:

[0186] According to the data risk probability of the current energy storage power station in the current set of dangerous power stations, the average value of the data risk probability corresponding to all power station data corresponding to the current energy storage power station is calculated to obtain the data risk parameter corresponding to the current energy storage power station;

[0187] Calculate the average value of the distance between the current energy storage power station and all other energy storage power stations in the same dangerous power station set, the average value of the weighted sum of the power supply chain similarity and the similarity average value, and obtain the association parameter corresponding to the current energy storage power station;

[0188] Determine the risk weight corresponding to the current energy storage power station according to the associated parameters corresponding to the current energy storage power station and the preset parameter weight rules; wherein the risk weight is proportional to the associated parameters;

[0189] Calculate the product of the data risk parameter and risk weight of the current energy storage power station to obtain the risk value of the current energy storage power station;

[0190] Calculate the danger level of each energy storage power station in each dangerous power station set to obtain the total danger level;

[0191] According to all the danger values, all the energy storage power stations in each dangerous power station set are sorted from large to small to obtain the power station sequence corresponding to each dangerous power station set;

[0192] The first second number of energy storage power stations in the power station sequence corresponding to each dangerous power station set are determined as high-risk energy storage power stations to obtain each high-risk energy storage power station.

[0193] The alarm unit 1053 is used to generate alarm information according to each high-risk energy storage power station and perform alarm control according to the alarm information.

[0194] In this embodiment, the risk visualization module 106 is specifically configured to perform the following steps:

[0195] Determine other energy storage power stations in the power station association set to which the current energy storage power station belongs, and obtain multiple associated power stations;

[0196] Determine whether the power station associated set to which the current energy storage power station belongs belongs to a dangerous power station set, and obtain a first determination result corresponding to the current energy storage power station and each associated power station;

[0197] Determine whether the current energy storage power station is a high-risk energy storage power station, and obtain a second determination result corresponding to the current energy storage power station;

[0198] According to each energy storage power station, a first judgment result and a second judgment result corresponding to each energy storage power station are obtained;

[0199] Constructing the objective function of the dynamic programming algorithm model; wherein the objective function is specifically: in the calculated relationship diagram, the distance between each energy storage power station and the corresponding associated power station is minimized and the conspicuity of the display parameters corresponding to each energy storage power station is maximized; the conspicuity is used to characterize the attractiveness of the display parameters; the display parameters include specific dimensional values ​​of the display frame size, display font size and display color;

[0200] The restriction conditions for determining the dynamic programming algorithm model include: in the calculated relationship diagram, the distance between the energy storage power station and the associated power station is less than the distance between the energy storage power station and the non-associated power station; the energy storage power station with a first judgment result of yes is more conspicuous than the energy storage power station with a first judgment result of no; the energy storage power station with a second judgment result of yes is more conspicuous than the energy storage power station with a first judgment result of yes;

[0201] Based on the objective function and constraints, the parameters of all energy storage power stations are input into the dynamic programming algorithm model for iterative calculation to obtain the optimal calculation result that meets the objective function and constraints; the optimal calculation result includes the visual relationship diagram corresponding to all energy storage power stations;

[0202] Push the visualization diagram to the terminal for display.

[0203] The present invention can effectively monitor and warn the risks of energy storage power stations through data screening algorithms and data prediction algorithms. At the same time, through data visualization processing algorithms, it can also improve the intelligence and visualization of energy storage power station monitoring, greatly improving the accuracy and convenience of monitoring.

[0204] The above-mentioned energy storage power station monitoring system can implement an energy storage power station monitoring method of the above-mentioned method embodiment. The options in the above-mentioned method embodiment are also applicable to this embodiment and will not be described in detail here. The rest of the contents of the embodiment of this application can refer to the contents of the above-mentioned method embodiment, and will not be repeated in this embodiment.

[0205] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0206] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0207] The apparatus, device, non-volatile computer-readable storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the apparatus, device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding apparatus, device, and non-volatile computer storage medium will not be repeated here.

[0208] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0209] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0210] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0211] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0212] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0213] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0214] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0215] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0216] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0217] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0218] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0219] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0220] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0221] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0222] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for monitoring an energy storage power station, It is characterized in that include: Receive power station data sent by several energy storage power stations, and perform risk association screening on each of the power station data according to historical information screening rules and type screening rules, to obtain several high-risk data sets and several high-association data sets, specifically: based on the data value of each of the power station data in the historical time period and the power station dangerous event information, and according to the historical information screening rules, screen out each of the high-risk data sets from each of the power station data; Based on the association parameters between the energy storage power stations corresponding to the power station data, and according to the type screening rule, each of the highly associated data sets is screened out from the power station data; each of the highly associated data sets includes at least two power station data belonging to a strong correlation relationship; wherein the power station data includes power station equipment parameters, equipment operating parameters and sensor data in the power station; Among them, based on the association parameters between the energy storage power stations corresponding to each of the power station data, and according to the type screening rules, each of the highly associated data sets is screened out from each of the power station data, specifically: arbitrarily select multiple power station data from each of the power station data as the current power station data; obtain the power station location, power supply chain and power station equipment parameters of the energy storage power station corresponding to the current power station data; calculate the average distance between the power station locations of the current power station data according to the power station location of the energy storage power station corresponding to the current power station data; calculate the power supply chain similarity between the power supply chains where the power stations of the current power station data are located according to the power supply chain where the power stations of the energy storage power stations corresponding to the current power station data are located; wherein the power supply chain similarity is the ratio of the number of power station data in the same power supply chain between the current power station data to the total number; calculate the equipment type between the power station equipment parameters of any two power station data according to the power station equipment parameters of the energy storage power station corresponding to the current power station data similarity, and calculate the similarity average of all equipment type similarities corresponding to the current power station data; perform weighted summation on the distance average, the power supply chain similarity and the similarity average corresponding to the current power station data to obtain the weighted summation value of the current power station data; wherein, the sum of the distance average, the power supply chain similarity and the similarity average is 1, and the weights of the distance average, the power supply chain similarity and the similarity average decrease in sequence; determine whether the weighted summation value of the current power station data is greater than the preset parameter threshold, if so, take the current power station data as a highly correlated data set; if not, arbitrarily select multiple power station data from each of the power station data, re-determine the current power station data, perform correlation similarity calculation based on the current power station data, calculate the weighted summation value of the current power station data, until the weighted summation value of the current power station data is greater than the preset parameter threshold, and obtain each of the highly correlated data sets; Performing data risk prediction on each of the high-risk data sets to obtain the data risk probability of the energy storage power station corresponding to each of the high-risk data sets, and performing correlation risk prediction on each of the highly correlated data sets to obtain the correlation risk probability corresponding to each power station correlation set; wherein the power station correlation set includes a plurality of mutually correlated energy storage power stations; A comprehensive risk analysis is performed on the data risk probabilities of the energy storage power stations corresponding to each of the high-risk data sets and the associated risk probabilities corresponding to each of the power station associated sets to obtain a number of high-risk energy storage power stations, and alarm information is generated based on each of the high-risk energy storage power stations, and alarm control is performed based on the alarm information; based on each of the power station associated sets and each of the high-risk energy storage power stations, the risks of each of the energy storage power stations are visualized, a risk visualization screen is generated, and the risk visualization screen is pushed to the terminal for display.

2. The energy storage power station monitoring method according to claim 1, It is characterized in that Based on the data value of each power station data in the historical time period and the power station dangerous event information, and according to the historical information screening rule, each high-risk data set is screened out from each power station data, specifically: Query the historical data values ​​at multiple historical time points corresponding to the current power station data in the database; Query the database to find out whether the energy storage power station corresponding to the current power station data has experienced the power station dangerous event information at the multiple historical time points, and determine the dangerous historical time points at which the energy storage power station corresponding to the current power station data has experienced the power station dangerous event; wherein the dangerous historical time points are at least two; According to the historical data value of the current power station data and the dangerous historical time point, by taking a weighted sum of any two of the numerical similarity, the segment data average value similarity and the adjacent time data change degree similarity, the different types of similarities between the historical data values ​​corresponding to the dangerous historical time point are calculated to obtain different types of data dangerous similarities corresponding to the current power station data; wherein the adjacent time data change degree similarity is the similarity of the data change value between the historical data value of the dangerous historical time point and the adjacent historical time point; the segment data average value similarity is the similarity between the average values ​​of the historical data values ​​of all historical time points in the time interval composed of the preset before and after time lengths of any two of the dangerous historical time points; the weight of the adjacent time data change degree similarity is greater than the weight of the segment data average value similarity, and the weight of the segment data average value similarity is greater than the weight of the numerical similarity; According to different types of data risk similarities of the power station data, the power station data are sorted from large to small to obtain at least one data sequence; The first first quantity of power station data of each of the data sequences is determined as each of the high-risk data sets.

3. The energy storage power station monitoring method according to claim 1, It is characterized in that The data risk prediction is performed on each of the high-risk data sets to obtain the data risk probability of the energy storage power station corresponding to each of the high-risk data sets, specifically: Inputting each power station data in the current high-risk data set into a pre-trained first neural network prediction model to obtain the data risk probability corresponding to each power station data in the current high-risk data set; wherein the first neural network prediction model is trained by a plurality of training power station data and a training data set with data risk annotations corresponding to each of the training power station data; According to the data risk probability corresponding to each power station data in each of the high-risk data sets, the data risk probability of the energy storage power station corresponding to each of the high-risk data sets is obtained.

4. The energy storage power station monitoring method according to claim 1, It is characterized in that The correlation risk prediction is performed on each of the highly correlated data sets to obtain the correlation risk probability corresponding to each power station correlation set, specifically: Determine all the energy storage power stations corresponding to all the power station data in each of the highly correlated data sets as each of the power station correlated sets; Input all power plant data in the current high-correlation data set into a pre-trained second neural network prediction model to obtain the correlation risk probability corresponding to each power plant correlation set corresponding to the current high-correlation data set; wherein the second neural network prediction model is trained by a training data set including a plurality of training power plant data corresponding to a plurality of training power plant correlation sets and data risk annotations corresponding to each of the training power plant correlation sets; The associated risk probabilities corresponding to the power station associated sets corresponding to the highly associated data sets are obtained according to the associated risk probabilities corresponding to the power station associated sets.

5. The energy storage power station monitoring method according to claim 1, It is characterized in that The data risk probability of the energy storage power station corresponding to each of the high-risk data sets and the associated risk probability corresponding to each of the power station associated sets are subjected to a comprehensive risk analysis to obtain a number of high-risk energy storage power stations, specifically: Determine whether the associated risk probability corresponding to the current power station associated set is higher than a preset probability threshold, and if so, determine the current power station associated set as a dangerous power station set; Determining each of the dangerous power plant sets according to the associated risk probabilities corresponding to each of the power plant associated sets; According to the data risk probability of the energy storage power station corresponding to each of the high-risk data sets, the data risk probability corresponding to all the energy storage power stations in each of the dangerous power station sets is determined, and the data risk probability corresponding to all the energy storage power stations in each of the dangerous power station sets is subjected to risk weight analysis to obtain each of the high-risk energy storage power stations.

6. The energy storage power station monitoring method according to claim 5, It is characterized in that The risk weight analysis is performed on the data risk probabilities corresponding to all energy storage power stations in the dangerous power station sets to obtain the high-risk energy storage power stations, specifically: According to the data risk probability of the current energy storage power station in the current set of dangerous power stations, the average value of the data risk probability corresponding to all power station data corresponding to the current energy storage power station is calculated to obtain the data risk parameter corresponding to the current energy storage power station; Calculate the average value of the distance between the current energy storage power station and all other energy storage power stations in the same set of dangerous power stations, the power supply chain similarity and the average value of the weighted sum of the similarity average values, and obtain the association parameter corresponding to the current energy storage power station; Determine the risk weight corresponding to the current energy storage power station according to the associated parameters corresponding to the current energy storage power station and the preset parameter weight rule; wherein the risk weight is proportional to the associated parameters; Calculate the product of the data risk parameter of the current energy storage power station and the risk weight to obtain the risk value of the current energy storage power station; Calculating the danger level value of each energy storage power station in each dangerous power station set to obtain a total danger level value; According to the total risk values, all energy storage power stations in each of the dangerous power station sets are sorted from large to small to obtain a power station sequence corresponding to each of the dangerous power station sets; The first second number of energy storage power stations in the power station sequence corresponding to each of the dangerous power station sets are determined as the high-risk energy storage power stations to obtain each of the high-risk energy storage power stations.

7. The energy storage power station monitoring method according to claim 1, It is characterized in that According to the associated sets of each power station and each high-risk energy storage power station, the risk of each energy storage power station is visualized to generate a risk visualization screen, specifically: Determine other energy storage power stations in the power station association set to which the current energy storage power station belongs, and obtain multiple associated power stations; Determine whether the power station associated set to which the current energy storage power station belongs belongs to a dangerous power station set, and obtain a first determination result corresponding to the current energy storage power station and each of the associated power stations; Determine whether the current energy storage power station belongs to the high-risk energy storage power station, and obtain a second determination result corresponding to the current energy storage power station; According to each of the energy storage power stations, a first judgment result and a second judgment result corresponding to each of the energy storage power stations are obtained; Constructing an objective function of a dynamic programming algorithm model; wherein the objective function is specifically: in the calculated relationship diagram, the distance between each of the energy storage power stations and the corresponding associated power stations is minimized and the conspicuity of the display parameters corresponding to each of the energy storage power stations is maximized; the conspicuity is used to characterize the attractiveness of the display parameters; the display parameters include specific dimensional values ​​of display frame size, display font size and display color; Determining the restriction conditions of the dynamic programming algorithm model includes: in the relationship diagram obtained by calculation, the distance between the energy storage power station and the associated power station is less than the distance between the energy storage power station and the non-associated power station; the conspicuousness of the energy storage power station for which the first judgment result is yes is greater than the energy storage power station for which the first judgment result is no; the conspicuousness of the energy storage power station for which the second judgment result is yes is greater than the energy storage power station for which the first judgment result is yes; Based on the objective function and the constraints, the parameters of all energy storage power stations are input into the dynamic programming algorithm model for iterative calculation to obtain an optimal calculation result that satisfies the objective function and the constraints; the optimal calculation result includes a visualization relationship diagram corresponding to all energy storage power stations.

8. A monitoring system for an energy storage power station, It is characterized in that The energy storage power station monitoring system is used to implement the energy storage power station monitoring method according to any one of claims 1 to 7, comprising: a data receiving and screening device, a data risk association prediction device and an analysis and monitoring device; The data receiving and screening device is used to receive power station data sent by several energy storage power stations, and perform risk association screening on the power station data according to historical information screening rules and type screening rules to obtain several high-risk data sets and several high-association data sets; wherein the power station data includes power station equipment parameters, equipment operating parameters and sensor data in the power station; The data risk association prediction device is used to perform data risk prediction on each of the high-risk data sets to obtain the data risk probability of the energy storage power station corresponding to each of the high-risk data sets, and perform association risk prediction on each of the high-association data sets to obtain the association risk probability corresponding to each power station association set; wherein the power station association set includes a plurality of mutually associated energy storage power stations; The analysis and monitoring device is used to perform a comprehensive risk analysis on the data risk probabilities of the energy storage power stations corresponding to each of the high-risk data sets and the associated risk probabilities corresponding to each of the power station associated sets, to obtain a number of high-risk energy storage power stations, and to generate alarm information based on each of the high-risk energy storage power stations, and to perform alarm control based on the alarm information; based on each of the power station associated sets and each of the high-risk energy storage power stations, to visualize the risks of each of the energy storage power stations, to generate a risk visualization screen, and to push the risk visualization screen to a terminal for display.

Images