Dynamic processing system for alarm information of energy storage power station

Abstract

The invention provides an energy storage power station alarm information dynamic processing system, and belongs to the technical field of information processing, and the system comprises a first obtaining module which is used for installing a sensor near a key device to monitor the operation state of the key device, and obtaining operation data; the classification module is used for preprocessing the operation data, acquiring alarm information according to a set threshold value and a rule, and classifying and identifying the alarm information; the combination module is used for acquiring an accident of the energy storage power station according to the classified alarm information and combining related information into accident information according to a time window; the second acquisition module is used for training a machine learning model, carrying out accident classification on the accident information according to the trained model, and acquiring corresponding accident information classification attributes; and the grid ascending and descending module is used for ascending and descending the classification attributes of the accident information and realizing the dynamic processing of the alarm information of the energy storage power station. The problems that alarm information cannot be intelligently processed, meanwhile, huge information processing work needs to be carried out, and the efficiency of accident processing operation work is reduced are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and in particular to a dynamic processing system for alarm information of an energy storage power station. Background Art

[0002] With the widespread application of renewable energy, energy storage power stations have become an important way of energy storage. The safety and reliability of energy storage power stations are crucial to the normal operation of the energy system.

[0003] Traditional information processing cannot intelligently process complex and large amounts of alarm information, which reduces the information processing capabilities of the monitoring system. At the same time, operating personnel need to perform a lot of manual information processing work, which greatly reduces the efficiency and level of equipment monitoring, accident handling and other operational operations.

[0004] Therefore, the present invention proposes a dynamic processing system for alarm information of an energy storage power station. Summary of the invention

[0005] The present invention provides a dynamic processing system for alarm information of an energy storage power station, which is used to solve the problem that traditional information processing in the prior art cannot intelligently process alarm information of complex types and large quantities, which reduces the information processing capacity of the monitoring system. At the same time, operating personnel need to perform voluminous manual information processing operations, which greatly reduces the efficiency and level of operating operations such as equipment monitoring and accident handling.

[0006] On the one hand, the present invention provides a system for dynamically processing alarm information of an energy storage power station, characterized in that it includes:

[0007] The first acquisition module: install sensors near the key equipment of the energy storage power station to monitor the operating status of the key equipment in real time and obtain corresponding operating data based on the operating status;

[0008] Classification module: pre-process the operation data, obtain alarm information according to the set thresholds and rules, and classify and identify the alarm information;

[0009] Combination module: Obtain the accident of the energy storage power station according to the classified alarm information, and combine the relevant alarm information and notification information into accident information according to the time window, taking the time interval before and after the accident as the constraint condition;

[0010] The second acquisition module: trains the machine learning model through historical accident events, classifies the accident information into different levels according to the trained model, and obtains the corresponding accident information classification attributes;

[0011] Upgrade and downgrade module: Upgrade or downgrade the classification attributes of the accident information to achieve dynamic processing of the alarm information of the energy storage power station.

[0012] According to a system for dynamically processing alarm information of an energy storage power station provided by the present invention, a first acquisition module includes:

[0013] The first acquisition unit: acquires the working characteristics and working environment of key equipment in the energy storage power station, and acquires corresponding sensors according to the working characteristics and working environment;

[0014] The first determination unit: determines the number and location of sensors according to the working area of ​​key equipment;

[0015] Setting unit: connecting the sensor to the state acquisition system, and setting the state acquisition interval and threshold;

[0016] Operation status acquisition unit: acquires real-time feedback information of sensors according to the status acquisition interval and threshold, and acquires the operation status of key equipment in real time based on the real-time feedback information;

[0017] Operation data acquisition unit: acquires corresponding operation data according to the operation status.

[0018] According to the present invention, a dynamic processing system for alarm information of an energy storage power station, a classification module, includes:

[0019] Conversion unit: converting the operation data into a format suitable for storage and analysis;

[0020] Identification unit: Identify the converted data according to the set thresholds and rules to obtain problematic data points;

[0021] A second acquisition unit: acquiring alarm information based on the trigger condition according to the problematic data point;

[0022] The first classification unit is used to classify the alarm information according to type and severity, and to assign a unique identifier to each alarm information.

[0023] According to the present invention, a dynamic processing system for alarm information of an energy storage power station is provided, and the combined module includes:

[0024] A first extraction unit: extracting key information from the classified alarm information, and determining different accidents occurring in the energy storage power station according to the key information;

[0025] The first collection unit: collects the timestamp and other relevant information of the accident based on system logs and monitoring indicators;

[0026] The third acquisition unit: taking a time interval before and after the accident as a constraint condition, acquires multiple corresponding time windows;

[0027] The fourth acquisition unit: filters the timestamps of different accidents and other related information based on the corresponding time window to obtain relevant warning information and notification information;

[0028] Combination unit: combines the relevant alarm information and notification information filtered out in each time window into accident information, and merges them into a total accident information list.

[0029] According to a system for dynamically processing alarm information of an energy storage power station provided by the present invention, the second acquisition module includes:

[0030] The second collection unit: collects relevant information of historical accident events from historical data, and performs cleaning and conversion;

[0031] The second extraction unit: extracts the level features of historical accident events from the cleaned and converted information;

[0032] Model training unit: training the machine learning model based on the supervised learning algorithm according to the collected historical accident event data and the extracted historical accident event level features;

[0033] The fifth acquisition unit is used to classify the accident information into different levels according to the trained model, and to obtain the accident information classification attribute corresponding to each accident event according to the classification result output by the model.

[0034] According to the present invention, a dynamic processing system for alarm information of an energy storage power station and a lifting and lowering module are provided, comprising:

[0035] A second classification unit: classifying the accident type according to the classification attribute of the accident information;

[0036] Comparison unit: obtains the corresponding number of accident occurrences according to the classification results, and compares them with the preset number;

[0037] Upgrading unit: obtains comparison results, and when a low-level information appears multiple times and meets certain judgment conditions, the information is upgraded;

[0038] Degradation unit: When a high-level message appears repeatedly and is confirmed several times, it will be automatically downgraded to a low-level message when it appears again within a set time, realizing dynamic processing of the alarm information of the energy storage power station.

[0039] According to a system for dynamically processing alarm information of an energy storage power station provided by the present invention, before installing sensors near key equipment of the energy storage power station, the system further includes:

[0040] The first determination module: obtains the configuration resources of the storage power station, and determines the online data information and offline data information of the energy storage power station according to the configuration resources;

[0041] The first generation module: obtains the information type of online data information and offline data information, configures information fusion rules, and generates an information quantity list table according to the information fusion rules;

[0042] The second generation module: determines the scheduling information parameters according to the information quantity list table, and generates the information parameter requirement table according to the scheduling information parameters;

[0043] The third acquisition module: determines the matching measurement point based on the information parameter requirement table, and obtains the equipment components at the corresponding positions of the matching measurement points in the energy storage power station;

[0044] The second determination module: obtains key operating characteristic information of the equipment component, and determines a finite state data set of the equipment component according to the key operating characteristic information;

[0045] Fourth acquisition module: acquiring the safety monitoring rule configuration file and the safety monitoring strategy configuration file of the energy storage power station;

[0046] The third determination module: determines the monitoring safety factors for the energy storage power station according to the safety monitoring rule configuration file and the safety monitoring strategy configuration file;

[0047] The fourth determination module is to determine the linkage decision parameters between the device components and the monitoring safety factors, and determine the key devices for data collection according to the linkage decision parameters.

[0048] According to a system for dynamically processing alarm information of an energy storage power station provided by the present invention, the second extraction unit comprises:

[0049] Extraction subunit: extracting event components of accident events from pre-processed information, and extracting safety risk factors from event components;

[0050] The first determination subunit: determining the disaster description parameters of the safety risk factors, and determining the emergency risk coefficient of the safety risk factors according to the disaster description parameters;

[0051] Sorting subunit: sort the risk level of each accident event according to the emergency risk coefficient and obtain the sorting result;

[0052] The second determination subunit determines the current risk level of the accident event and the accident description features of the accident event at the current risk level based on the sorting result.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] By acquiring the operating data of the energy storage power station equipment, obtaining the alarm information according to the set thresholds and rules, and dynamically processing the alarm information, it is possible to intelligently process a large number of complex alarm information, thereby improving the information processing capabilities of the monitoring system. At the same time, the operating personnel do not need to perform voluminous manual information processing operations, which greatly improves the efficiency and level of equipment monitoring, accident handling and other operating operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 It is a structural schematic diagram of a system for dynamically processing alarm information of an energy storage power station provided by an embodiment of the present invention;

[0057] Figure 2 It is a structural diagram of a first acquisition module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0059] Embodiment 1:

[0060] An embodiment of the present invention provides a system for dynamically processing alarm information of an energy storage power station, such as Figure 1 As shown, the system mainly includes the following modules:

[0061] The first acquisition module: install sensors near the key equipment of the energy storage power station to monitor the operating status of the key equipment in real time and obtain corresponding operating data based on the operating status;

[0062] Classification module: pre-process the operation data, obtain alarm information according to the set thresholds and rules, and classify and identify the alarm information;

[0063] Combination module: Obtain the accident of the energy storage power station according to the classified alarm information, and combine the relevant alarm information and notification information into accident information according to the time window, taking the time interval before and after the accident as the constraint condition;

[0064] The second acquisition module: trains the machine learning model through historical accident events, classifies the accident information into different levels according to the trained model, and obtains the corresponding accident information classification attributes;

[0065] Upgrade and downgrade module: Upgrade or downgrade the classification attributes of the accident information to achieve dynamic processing of the alarm information of the energy storage power station.

[0066] In this embodiment, key equipment of the energy storage power station includes: a battery pack, an inverter, and a control system.

[0067] In this embodiment, the sensor refers to that for a battery pack, a current sensor may be selected to detect the current distribution of the battery pack; for a motor, a vibration sensor may be selected to detect parameters such as the motor speed.

[0068] In this embodiment, the operation status may be: normal operation, abnormal operation, or stopped operation.

[0069] In this embodiment, the operating data may be: temperature, pressure and vibration.

[0070] In this embodiment, the alarm information refers to the alarm information issued when certain data exceeds a threshold or violates a rule.

[0071] In this embodiment, the alarms can be divided into emergency alarms and non-emergency alarms according to the severity; the alarm information can be divided into bearing faults and electrical faults according to the categories.

[0072] In this embodiment, the identification may be, for example, an emergency alarm message, which may display "W", and if it is a non-emergency alarm, which may display "N".

[0073] In this embodiment, accidents of the energy storage power station may be: battery overcharge / over discharge, abnormal electrochemical reaction, control system and communication system failure.

[0074] In this embodiment, the time window refers to an area or range where a certain event may occur or a certain situation may arise within a specific time period.

[0075] In this embodiment, the alarm information is usually data or signals used in monitoring and alarm systems, indicating that a specific condition or threshold has been triggered or exceeded, and corresponding measures need to be taken to avoid potential danger or damage. For example, in an energy storage power station, if the battery temperature is too high, the system will issue an alarm message to remind the operator to take measures to prevent safety problems caused by battery overheating.

[0076] In this embodiment, the notification information generally refers to information sent to ensure timely communication, such as notification of equipment maintenance plan, upgrade notification, safety training notification, etc.

[0077] In this embodiment, the accident information level classification may be: emergency, major accident, secondary accident, fault accident, and management accident.

[0078] In this embodiment, the accident information classification attribute may be classified according to the accident type, accident severity, accident impact scope, accident consequence, and accident cause.

[0079] The beneficial effects of the above technical solution are: by obtaining the operating data of the energy storage power station equipment, obtaining the alarm information according to the set thresholds and rules, and dynamically processing the alarm information, it is possible to intelligently process a large number of complex types of alarm information, thereby improving the information processing capabilities of the monitoring system. At the same time, the operating personnel do not need to perform voluminous manual information processing operations, which greatly improves the efficiency and level of equipment monitoring, accident handling and other operating operations.

[0080] Embodiment 2:

[0081] Based on Example 1, the first acquisition module of the embodiment of the present invention includes:

[0082] The first acquisition unit: acquires the working characteristics and working environment of key equipment in the energy storage power station, and acquires corresponding sensors according to the working characteristics and working environment;

[0083] The first determination unit: determines the number and location of sensors according to the working area of ​​key equipment;

[0084] Setting unit: connecting the sensor to the state acquisition system, and setting the state acquisition interval and threshold;

[0085] Operation status acquisition unit: acquires real-time feedback information of sensors according to the status acquisition interval and threshold, and acquires the operation status of key equipment in real time based on the real-time feedback information;

[0086] Operation data acquisition unit: acquires corresponding operation data according to the operation status.

[0087] In this embodiment, the working characteristics of the key equipment of the energy storage power station include: high reliability and safety, high efficiency and energy density, durability and reliability.

[0088] In this embodiment, the working environment of the key equipment of the energy storage power station may be an environment with high and low temperatures, humidity, electromagnetic interference, dust and pollution.

[0089] In this embodiment, the corresponding sensor refers to, for example: for a battery pack, a current sensor can be selected to detect the current distribution of the battery pack; for a motor, a vibration sensor can be selected to detect parameters such as the motor speed.

[0090] In this embodiment, the status acquisition system is an automated system for monitoring and managing the status of an object or device.

[0091] In this embodiment, the status collection interval may be to collect the status once every five minutes.

[0092] In this embodiment, the status acquisition threshold refers to a critical value set in the battery management system, which is used to determine whether the status of the battery pack is abnormal. When any parameter of the battery pack (such as voltage, current, temperature, etc.) exceeds the status threshold range, the battery management system will consider that there is a problem with the status of the battery pack and take corresponding protective measures.

[0093] The beneficial effects of the above technical solution are: obtaining corresponding sensors through the working characteristics and environment of key equipment, setting collection intervals and thresholds, determining the operating status of key equipment, and ensuring the real-time and accuracy of data acquisition.

[0094] Based on Example 2, the classification module of the embodiment of the present invention includes:

[0095] Conversion unit: converting the operation data into a format suitable for storage and analysis;

[0096] Identification unit: Identify the converted data according to the set thresholds and rules to obtain problematic data points;

[0097] A second acquisition unit: acquiring alarm information based on the trigger condition according to the problematic data point;

[0098] The first classification unit is used to classify the alarm information according to type and severity, and to assign a unique identifier to each alarm information.

[0099] In this embodiment, the format in which the operational data is suitable for storage and analysis generally depends on the type of data, such as:

[0100] Structured data (e.g., tables): If the data is structured, such as time series data, survey results, etc., then the most suitable format may be comma-separated values ​​or relational;

[0101] Unstructured data (e.g. documents, images, audio, etc.): If the data is unstructured, such as text logs, image sensor data, voice recordings, etc., then the most suitable format may be JavaScript Object Identifier, Extensible Markup Language, or their derivatives.

[0102] Time series data: If the data is a continuous time series, then the most appropriate format may be Time SeriesVertical, JSONTIMESTAMP, or PLIST.

[0103] In this embodiment, the trigger condition may be: determining when to trigger an alarm, for example, when the device detects a data point that exceeds a normal range, when a system fails, or when a certain condition occurs.

[0104] The beneficial effects of the above technical solution are: preprocessing the operating data and obtaining problematic data points, obtaining alarm information based on trigger conditions, and classifying and identifying them, which helps to improve the organization and search efficiency of alarm information. At the same time, potential problems of operating equipment can be quickly discovered based on the alarm information.

[0105] Embodiment 4:

[0106] Based on the third embodiment, the combined module of the embodiment of the present invention includes:

[0107] A first extraction unit: extracting key information from the classified alarm information, and determining different accidents occurring in the energy storage power station according to the key information;

[0108] The first collection unit: collects the timestamp and other relevant information of the accident based on system logs and monitoring indicators;

[0109] The third acquisition unit: taking a time interval before and after the accident as a constraint condition, acquires multiple corresponding time windows;

[0110] The fourth acquisition unit: filters the timestamps of different accidents and other related information based on the corresponding time window to obtain relevant warning information and notification information;

[0111] Combination unit: combines the relevant alarm information and notification information filtered out in each time window into accident information, and merges them into a total accident information list.

[0112] In this embodiment, the key information in the alarm information includes: time, location, type, and frequency.

[0113] In this embodiment, the timestamp of the accident occurrence refers to the exact time when the accident occurs, which is a digital time mark and can be accurate to seconds.

[0114] In this embodiment, other relevant information may include: cause of the accident and nature of the accident.

[0115] In this embodiment, the accident information list is a document or table that records and summarizes various detailed information related to production safety incidents.

[0116] The beneficial effects of the above technical solution are: obtaining the timestamps and related information of different accidents, and filtering based on the time window, combining the filtered alarm information and notification information into accident information, which can improve the dynamic processing efficiency of alarm information and enhance the operation level of the system.

[0117] Embodiment 5:

[0118] Based on Example 4, the second acquisition module of this embodiment of the present invention includes:

[0119] The second collection unit: collects relevant information of historical accident events from historical data, and performs cleaning and conversion;

[0120] The second extraction unit: extracts the level features of historical accident events from the cleaned and converted information;

[0121] Model training unit: training the machine learning model based on the supervised learning algorithm according to the collected historical accident event data and the extracted historical accident event level features;

[0122] The fifth acquisition unit is used to classify the accident information into different levels according to the trained model, and to obtain the accident information classification attribute corresponding to each accident event according to the classification result output by the model.

[0123] In this embodiment, the relevant information of the accident event may be: the time, location, and cause of the accident.

[0124] In this embodiment, the characteristics of the event level are usually evaluated based on factors such as the scope of impact, severity, and impact on the normal operation of the system, for example:

[0125] Low level: The event has a small impact on the system and may be a local problem caused by a single error.

[0126] Medium level: The event has some impact on the system and may be caused by multiple errors or a combination of single errors.

[0127] High level: The event had a significant impact on the system and could be caused by a series of errors or a single serious error.

[0128] Extremely serious level: The event has a serious impact on the system and may be caused by an extremely serious error or a single catastrophic error.

[0129] In this embodiment, the accident information classification attribute refers to the classification and description of the accident after the accident occurs based on factors such as the nature, cause, and impact of the accident, such as: accident type, accident level, accident cause, time node, and location information.

[0130] The beneficial effects of the above technical solution are: preprocessing the relevant information of historical accident events and extracting hierarchical features, training the machine learning model, and classifying the accident information into different levels of accidents, obtaining the corresponding accident information classification attributes, and through clear accident information classification attributes, the corresponding accident type can be quickly located according to these attributes, thereby improving the efficiency of accident handling.

[0131] Embodiment 6:

[0132] Based on the fifth embodiment, the lifting and lowering frame module of the embodiment of the present invention includes:

[0133] A second classification unit: classifying the accident type according to the classification attribute of the accident information;

[0134] Comparison unit: obtains the corresponding number of accident occurrences according to the classification results, and compares them with the preset number;

[0135] Upgrading unit: obtains comparison results, and when a low-level information appears multiple times and meets certain judgment conditions, the information is upgraded;

[0136] Degradation unit: When a high-level message appears repeatedly and is confirmed several times, it will be automatically downgraded to a low-level message when it appears again within a set time, realizing dynamic processing of the alarm information of the energy storage power station.

[0137] In this embodiment, the types of accidents that may occur in the energy storage power station include, but are not limited to: battery thermal runaway, battery mechanical damage, electrical short circuit or open circuit.

[0138] In this embodiment, the preset number of times is 5 times.

[0139] In this embodiment, for example, poor circuit connection between batteries is low-level information. When this low-level information occurs more than 5 times and causes circuit short circuit or open circuit more than 3 times, this low-level information is upgraded to high-level information.

[0140] The beneficial effects of the above technical solution are: classifying accident types through accident information classification attributes, obtaining the corresponding number of accident occurrences, and comparing them with the preset number of times, and performing up / downgrading on multiple levels of information according to the comparison results, thereby improving the ability to identify key alarm information. At the same time, frequently occurring low-level information is upgraded to high-level information, which reduces the system's sensitivity to low-level information and improves the system's robustness. Furthermore, when high-level information appears again after a certain period of time, it is downgraded to low-level information, which reduces the system's attention to high-level information and further reduces the system's computational complexity and resource consumption.

[0141] Embodiment 7:

[0142] Based on Example 6, before installing sensors near key equipment in the energy storage power station, the embodiment of the present invention further includes:

[0143] The first determination module: obtains the configuration resources of the storage power station, and determines the online data information and offline data information of the energy storage power station according to the configuration resources;

[0144] The first generation module: obtains the information type of online data information and offline data information, configures information fusion rules, and generates an information quantity list table according to the information fusion rules;

[0145] The second generation module: determines the scheduling information parameters according to the information quantity list table, and generates the information parameter requirement table according to the scheduling information parameters;

[0146] The third acquisition module: determines the matching measurement point based on the information parameter requirement table, and obtains the equipment components at the corresponding positions of the matching measurement points in the energy storage power station;

[0147] The second determination module: obtains key operating characteristic information of the equipment component, and determines a finite state data set of the equipment component according to the key operating characteristic information;

[0148] Fourth acquisition module: acquiring the safety monitoring rule configuration file and the safety monitoring strategy configuration file of the energy storage power station;

[0149] The third determination module: determines the monitoring safety factors for the energy storage power station according to the safety monitoring rule configuration file and the safety monitoring strategy configuration file;

[0150] The fourth determination module is to determine the linkage decision parameters between the device components and the monitoring safety factors, and determine the key devices for data collection according to the linkage decision parameters.

[0151] In this embodiment, the configuration resources of the energy storage power station include: battery type, battery capacity, and battery management system.

[0152] In this embodiment, the online data information includes: battery status, charging and discharging records, and environmental data.

[0153] In this embodiment, the offline data information includes:

[0154] System architecture: This includes the number and type of battery packs, inverters, controllers and other key equipment, and how they are connected.

[0155] Equipment operation records: including equipment start-up, stop, failure and maintenance records, as well as equipment usage and error information.

[0156] Production data: including the total capacity, power generation and cost, electricity price and other data of energy storage power stations.

[0157] In this embodiment, the information inventory table is a table or list used to record and organize information, and generally includes information on the classification, source, format, type, date, and content of the information.

[0158] In this embodiment, the scheduling information parameters refer to variables used to define the execution conditions and priorities of tasks in the task scheduling system. These parameters can control how tasks are assigned, triggered and executed, such as: task name, task description, and task type.

[0159] In this embodiment, the information parameter requirement table is a tool for recording the information required in the project.

[0160] In this embodiment, the matching test point refers to a test point that matches the information parameter requirement table, such as a battery pack.

[0161] In this embodiment, the equipment components of the energy storage power station include: a battery box, a battery charging and replacing device, an inverter, and a controller.

[0162] In this embodiment, the finite state data set of the device component refers to a data model used in the device monitoring and management system, which divides the state of the device component into a limited number of states and numbers each state in the system to record the operating status and history of the device.

[0163] In this embodiment, the safety monitoring rule configuration file of the energy storage power station is a tool for setting the safety monitoring rules of the energy storage power station.

[0164] In this embodiment, the security monitoring policy configuration file refers to a set of instructions for configuring the security protection of network security devices or the entire network, including: device type and quantity, security policy, alarm and reporting mechanism.

[0165] In this embodiment, the monitoring safety factors of the energy storage power station include: electrical safety, information security, and environmental safety.

[0166] In this embodiment, the linkage decision parameters refer to parameters that act together or influence each other in multiple decision processes.

[0167] The beneficial effects of the above technical solution are: determining the monitoring safety factors for the energy storage power station according to the safety monitoring rule configuration file and the safety monitoring strategy configuration file, and determining the linkage decision parameters between the equipment components, thereby determining the key equipment for data collection, and being able to more accurately monitor the operating status and safety status of the equipment, timely discover and handle problems, and at the same time, issue more accurate alarm information.

[0168] Embodiment 8:

[0169] Based on Example 7, the second extraction unit of the embodiment of the present invention includes:

[0170] Extraction subunit: extracting event components of accident events from pre-processed information, and extracting safety risk factors from event components;

[0171] The first determination subunit: determining the disaster description parameters of the safety risk factors, and determining the emergency risk coefficient of the safety risk factors according to the disaster description parameters;

[0172] Sorting subunit: sort the risk level of each accident event according to the emergency risk coefficient and obtain the sorting result;

[0173] The second determination subunit determines the current risk level of the accident event and the accident description features of the accident event at the current risk level based on the sorting result.

[0174] In this embodiment, the event components of the accident event may include: human factors, environmental factors, management factors, and technical factors.

[0175] In this embodiment, the disaster description parameters are generally used to evaluate and describe potential accidents or catastrophic events including: potential damage, possibility of accident occurrence, and scope of accident impact.

[0176] In this embodiment, the emergency risk coefficient refers to the urgency of a safety accident caused by a safety risk factor.

[0177] In this embodiment, the accident description features refer to key elements that need to be considered when describing and recording an accident, such as: time, location, accident type, and accident cause.

[0178] The beneficial effects of the above technical solution are: determining the emergency risk coefficient of the safety risk factor through the disaster description parameters of the safety risk factor, and sorting the risk level, obtaining the accident description characteristics of the accident event at the current risk level, being able to quickly determine the priority order of the accident, better monitor the accident, issue accurate alarm information, and make timely and accurate response strategies.

[0179] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0180] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic processing system for alarm information of an energy storage power station, characterized in that: include: The first acquisition module: install sensors near the key equipment of the energy storage power station to monitor the operating status of the key equipment in real time and obtain corresponding operating data based on the operating status; Classification module: pre-process the operation data, obtain alarm information according to the set thresholds and rules, and classify and identify the alarm information; Combination module: Obtain the accident of the energy storage power station according to the classified alarm information, and combine the relevant alarm information and notification information into accident information according to the time window, taking the time interval before and after the accident as the constraint condition; The second acquisition module: trains the machine learning model through historical accident events, classifies the accident information into different levels according to the trained model, and obtains the corresponding accident information classification attributes; Upgrade and downgrade module: Upgrade or downgrade the classification attributes of the accident information to achieve dynamic processing of the alarm information of the energy storage power station.

2. The energy storage power station alarm information dynamic processing system according to claim 1 is characterized in that: The first acquisition module includes: The first acquisition unit: acquires the working characteristics and working environment of key equipment in the energy storage power station, and acquires corresponding sensors according to the working characteristics and working environment; The first determination unit: determines the number and location of sensors according to the working area of ​​key equipment; Setting unit: connecting the sensor to the state acquisition system, and setting the state acquisition interval and threshold; Operation status acquisition unit: acquires real-time feedback information of sensors according to the status acquisition interval and threshold, and acquires the operation status of key equipment in real time based on the real-time feedback information; Operation data acquisition unit: acquires corresponding operation data according to the operation status.

3. The energy storage power station alarm information dynamic processing system according to claim 1 is characterized in that: Classification modules, including: Conversion unit: converting the operation data into a format suitable for storage and analysis; Identification unit: Identify the converted data according to the set thresholds and rules to obtain problematic data points; A second acquisition unit: acquiring alarm information based on the trigger condition according to the problematic data point; The first classification unit is used to classify the alarm information according to type and severity, and to assign a unique identifier to each alarm information.

4. The energy storage power station alarm information dynamic processing system according to claim 1 is characterized in that: Combination modules including: A first extraction unit: extracting key information from the classified alarm information, and determining different accidents occurring in the energy storage power station according to the key information; The first collection unit: collects the timestamp and other relevant information of the accident based on system logs and monitoring indicators; The third acquisition unit: taking a time interval before and after the accident as a constraint condition, acquires multiple corresponding time windows; The fourth acquisition unit: filters the timestamps of different accidents and other related information based on the corresponding time window to obtain relevant warning information and notification information; Combination unit: combines the relevant alarm information and notification information filtered out in each time window into accident information, and merges them into a total accident information list.

5. The energy storage power station alarm information dynamic processing system according to claim 1 is characterized in that: The second acquisition module includes: The second collection unit: collects relevant information of historical accident events from historical data, and performs cleaning and conversion; The second extraction unit: extracts the level features of historical accident events from the cleaned and converted information; Model training unit: training the machine learning model based on the supervised learning algorithm according to the collected historical accident event data and the extracted historical accident event level features; The fifth acquisition unit is used to classify the accident information into different levels according to the trained model, and to obtain the accident information classification attribute corresponding to each accident event according to the classification result output by the model.

6. The energy storage power station alarm information dynamic processing system according to claim 1 is characterized in that: Slow & fast frame module, including: A second classification unit: classifying the accident type according to the classification attribute of the accident information; Comparison unit: obtains the corresponding number of accident occurrences according to the classification results, and compares them with the preset number; Upgrading unit: obtains comparison results, and when a low-level information appears multiple times and meets certain judgment conditions, the information is upgraded; Degradation unit: When a high-level message appears repeatedly and is confirmed several times, it will be automatically downgraded to a low-level message when it appears again within a set time, realizing dynamic processing of the alarm information of the energy storage power station.

7. The energy storage power station alarm information dynamic processing system according to claim 1 is characterized in that: Before installing sensors near key equipment in energy storage power stations, it also includes: The first determination module: obtains the configuration resources of the storage power station, and determines the online data information and offline data information of the energy storage power station according to the configuration resources; The first generation module: obtains the information type of online data information and offline data information, configures information fusion rules, and generates an information quantity list table according to the information fusion rules; The second generation module: determines the scheduling information parameters according to the information quantity list table, and generates the information parameter requirement table according to the scheduling information parameters; The third acquisition module: determines the matching measurement point based on the information parameter requirement table, and obtains the equipment components at the corresponding positions of the matching measurement points in the energy storage power station; The second determination module: obtains key operating characteristic information of the equipment component, and determines a finite state data set of the equipment component according to the key operating characteristic information; Fourth acquisition module: acquiring the safety monitoring rule configuration file and the safety monitoring strategy configuration file of the energy storage power station; The third determination module: determines the monitoring safety factors for the energy storage power station according to the safety monitoring rule configuration file and the safety monitoring strategy configuration file; The fourth determination module is to determine the linkage decision parameters between the device components and the monitoring safety factors, and determine the key devices for data collection according to the linkage decision parameters.

8. The energy storage power station alarm information dynamic processing system according to claim 5 is characterized in that: The second extraction unit comprises: Extraction subunit: extracting event components of accident events from pre-processed information, and extracting safety risk factors from event components; The first determination subunit: determining the disaster description parameters of the safety risk factors, and determining the emergency risk coefficient of the safety risk factors according to the disaster description parameters; Sorting subunit: sort the risk level of each accident event according to the emergency risk coefficient and obtain the sorting result; The second determination subunit determines the current risk level of the accident event and the accident description features of the accident event at the current risk level based on the sorting result.

Images