Alarm information management method and system of power supply system
By constructing a high-dimensional tensor model and dynamic adaptive threshold adjustment, combined with comprehensive alarm index processing, the shortcomings of the existing battery monitoring system in dynamic adaptation and feature extraction are solved, and efficient alarm information processing and battery status monitoring are achieved.
Patent Information
- Application Number
- CN202411490630.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-24
- Publication Date
- 2025-03-18
AI Technical Summary
The existing battery monitoring and alarm processing methods cannot dynamically adapt to changes in battery status, resulting in frequent false alarms and missed alarms, and lack effective feature extraction methods and alarm information classification and processing mechanisms, which affects the system's response speed and maintenance efficiency.
By collecting multi-dimensional data of the battery, a high-dimensional tensor model is constructed, key features are extracted, alarm determination values are generated, and dynamic adaptive thresholds are adjusted based on priority, a comprehensive alarm index is constructed to classify and prioritize the alarm information.
It realizes efficient and unified processing of complex data, reduces false alarms and missed reports, improves the monitoring accuracy and reliability of the power supply system, enhances the system's ability to adapt to changes in battery status, and improves maintenance efficiency and operation safety.
Smart Images

Figure CN119651819A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power system monitoring and management, and in particular to an alarm information management method and system for a power system. Background Art
[0002] As the complexity and diversity of modern power systems continue to increase, the operating status of batteries, as one of the core components of power systems, directly affects the safety and stability of the entire system. Traditional power system monitoring methods mainly rely on timed inspections and simple alarm triggering mechanisms, which are incapable of processing large amounts of multi-dimensional battery data. With the continuous advancement of data acquisition technology and artificial intelligence technology, the accuracy and response speed of power system monitoring have been significantly improved. However, when faced with the high-dimensional and nonlinear characteristics of battery data, existing monitoring systems are often unable to accurately extract useful information, resulting in frequent false alarms and missed alarms. In addition, existing technologies mostly trigger alarms with fixed thresholds, which fail to reflect the dynamic changes of battery status in a timely manner, thereby affecting the reliability and maintenance efficiency of the power system. Therefore, how to effectively process multi-dimensional data, accurately capture the nonlinear dynamic characteristics of batteries, and classify and adjust alarm information according to priority has become an important topic in the development of power system monitoring technology.
[0003] Although the existing technology has made certain progress in battery monitoring and alarm processing, there are still obvious shortcomings. First, traditional alarm systems mostly use fixed threshold judgments and cannot dynamically adapt to changes in battery status, which causes the system to easily generate a large number of false alarms or missed alarms when facing battery aging or environmental changes. Secondly, when processing multi-dimensional battery data, the existing system lacks effective feature extraction methods and cannot fully utilize the implicit information in the data, resulting in inaccurate alarm judgments. Thirdly, the classification and priority processing mechanism of alarm information is imperfect, and it is impossible to reasonably sort according to the importance of different alarm information, which affects the system's response speed and maintenance efficiency. Summary of the invention
[0004] In view of the above-mentioned problems, the present invention is proposed.
[0005] Therefore, the technical problem solved by the present invention is that the existing battery monitoring and alarm processing methods have the problems of being unable to dynamically adapt to changes in battery status, low accuracy, low maintenance efficiency, and low response speed.
[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for managing alarm information of a power supply system, comprising extracting battery data and converting it into a battery signal, and outputting alarm information through the battery signal; adjusting a dynamic adaptive threshold based on a priority; constructing an alarm index and classifying the output alarm information.
[0007] As a preferred solution of the alarm information management method of the power supply system of the present invention, wherein: the extraction of battery data and conversion into battery signals includes collecting multi-dimensional battery data;
[0008] Battery multi-dimensional data includes battery temperature, charge and discharge status, voltage, current, remaining capacity and historical alarm records. The battery multi-dimensional data is processed uniformly to retain the relationship between each dimension:
[0009] Through unified processing, the multi-dimensional battery data is converted into battery signals to reflect the real-time status of the battery.
[0010] As a preferred solution of the method for managing the alarm information of the power supply system of the present invention, wherein: the outputting the alarm information through the battery signal includes generating the alarm information through the battery signal, including evaluating various types of alarm signals, and generating a determination basis for each type of alarm based on the change of the battery signal;
[0011] Monitor the fluctuation of battery signals and determine in real time whether corresponding alarm information needs to be triggered.
[0012] As a preferred solution of the method for managing the alarm information of the power supply system of the present invention, wherein: the priority-based dynamic adaptive threshold adjustment includes setting initial thresholds for different types of alarm information, the thresholds are set based on historical data and expert experience, and a standardized threshold system is formed by quantifying the characteristics of different alarm categories;
[0013] Standardization removes the effects of dimension by subtracting the mean and dividing by the standard deviation;
[0014] By outputting the priority of each type of alarm, it affects the subsequent comprehensive alarm index output and the classification and output of the final alarm information.
[0015] As a preferred solution of the method for managing the alarm information of the power supply system of the present invention, wherein: the priority-based dynamic adaptive threshold adjustment includes the threshold in the alarm information being a dynamically adjusted value, which is used to determine whether to trigger an alarm and set the priority of the alarm information;
[0016] The initial threshold is set based on historical data and expert experience. The initial threshold is set according to the distribution of historical alarm data and the range;
[0017] Perform dynamic adaptive threshold adjustment, and the threshold adapts to changes in battery status in real time;
[0018] By continuously adjusting the thresholds, the system determines the alarm trigger point.
[0019] As a preferred solution of the method for managing the alarm information of the power supply system of the present invention, wherein: the construction of the alarm index and classification of the output alarm information includes synthesizing all the alarm category information of each battery, and the comprehensive alarm index combines the judgment value, the dynamic threshold and the priority to output the comprehensive alarm index;
[0020] The comprehensive alarm index combines the judgment value, dynamic threshold, priority and category weight of each type of alarm information to generate indicators. Through the indicators, the severity of the alarm information is distinguished and priority is given according to the severity.
[0021] As a preferred solution of the alarm information management method of the power supply system described in the present invention, wherein: the construction of the alarm index and the classification of the output alarm information include: i , the severity of the alarm information is divided into high severity, medium severity, and low severity;
[0022] When the severity of the alarm information is high, the comprehensive alarm index A i If the value is higher than the preset high priority threshold, the high severity alarm system will give priority to outputting high severity alarm information, notifying the operator to record and analyze high severity alarms. On the monitoring interface, the system will display high severity alarms;
[0023] When the severity of the alarm information is medium, the comprehensive alarm index A i The value of is between the high priority threshold and the medium priority threshold. The medium severity alarm persists, causing system performance to degrade. The system regularly checks the medium severity alarm to ensure that it does not evolve into a high severity alarm message, generates regular reports, and sends the medium severity alarm message to the maintenance team. The system informs the operator of the severity alarm message through a reminder, and there is no need to immediately interrupt the current operation;
[0024] When the severity of the alarm information is low, the comprehensive alarm index A i The value is lower than the medium priority threshold. Low severity alarm information will not affect the security and stability of the system. The system records low severity alarm information but does not issue an alarm to the operator. The system should perform daily monitoring of low severity alarms.
[0025] Another object of the present invention is to provide an alarm information management system for a power supply system, which can solve the problem of low maintenance efficiency in current battery monitoring and alarm processing methods by constructing an alarm index and classifying output alarm information.
[0026] As a preferred solution of the alarm information management system of the power supply system described in the present invention, it includes: a data extraction and non-linear alarm determination module, a priority output and dynamic adaptive threshold adjustment module, and a comprehensive alarm index calculation and classification output module; the data extraction and non-linear alarm determination module is used to extract the key features of the data and accurately determine the severity of various types of alarm information; the priority output and dynamic adaptive threshold adjustment module is used to improve the system's responsiveness in the face of a changing environment through priority sorting and dynamic adjustment of thresholds; the comprehensive alarm index calculation and classification output module is used to classify and output the alarm information according to the comprehensive alarm index.
[0027] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a method for managing alarm information of a power supply system.
[0028] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for managing alarm information of a power supply system.
[0029] Beneficial effects of the present invention: The alarm information management method of the power system provided by the present invention realizes unified processing of complex data by collecting multi-dimensional data of batteries, and constructs a high-dimensional tensor model of batteries, realizes efficient and unified processing of multi-dimensional data of batteries, and extracts key features to ensure accuracy and efficiency in processing highly complex data, avoid data loss or loss of related information between dimensions, and dynamically adjust the trigger threshold of the alarm information by setting an initial threshold for each type of alarm information, and combining historical data and expert experience. By dynamically adjusting the threshold, it is more accurate to determine when to trigger the alarm, thereby reducing false alarms and missed alarms, improving the monitoring accuracy and reliability of the power system, and enhancing the system's adaptability to changes in battery status. By integrating all alarm category information of each battery, combining the judgment value, dynamic threshold and priority, a comprehensive alarm index is constructed, and the alarm information is classified according to severity, effectively distinguishing and prioritizing alarm information of different severity, ensuring that operators can quickly identify and respond to the most critical alarms, and improving the operating safety and maintenance efficiency of the power system. The present invention achieves better results in terms of operating safety, maintenance efficiency and evaluation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0031] Figure 1 An overall flow chart of an alarm information management method for a power system provided in the first embodiment of the present invention.
[0032] Figure 2 A logic flow chart of an alarm information management method for a power supply system provided in the first embodiment of the present invention.
[0033] Figure 3 An overall flow chart of an alarm information management system for a power supply system provided in the third embodiment of the present invention. DETAILED DESCRIPTION
[0034] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0035] Example 1, reference Figure 1-Figure 2 , which is the first embodiment of the present invention, and which provides an alarm information management method for a power supply system, comprising:
[0036] S1: Extract battery data to build an alarm judgment value model.
[0037] Going a step further, collect multi-dimensional battery data;
[0038] Battery multi-dimensional data includes battery temperature, charge and discharge status, voltage, current, remaining capacity and historical alarm records. The battery multi-dimensional data is processed uniformly to retain the relationship between each dimension:
[0039] Through unified processing, the multi-dimensional battery data is converted into battery signals to reflect the real-time status of the battery.
[0040] A battery signal conversion model is expressed as:
[0041]
[0042] in, Represents the original high-dimensional tensor data of i batteries, including information on time, features, interaction effects, status, and alarm category dimensions. represents the core tensor, which contains the low-rank features extracted from the original tensor, U (1) Represents the pattern matrix of the time dimension, U (2) Represents the pattern matrix of feature dimensions, U (3) The pattern matrix representing the dimensions of the interaction effect, U (4)Represents the mode matrix of the state dimension, U (5) The pattern matrix representing the alarm category dimension;
[0043] The battery multi-dimensional data is converted into battery signals through the battery signal conversion model.
[0044] It should be noted that generating alarm information through battery signals includes evaluating various types of alarm signals and generating a basis for determining each type of alarm based on changes in the battery signals;
[0045] A generation model of alarm judgment basis is expressed as:
[0046]
[0047] in, represents the k-th alarm judgment value of the ith battery, Represents the core tensor Expanded into a vector, represents the weight matrix from the input layer to the hidden layer, represents the weight matrix from the hidden layer to the output layer, represents the bias vector of the hidden layer, The bias vector of the output layer, σ represents the activation function;
[0048] The output value is between 0 and 1 and is proportional to the severity of the alarm and the priority ranking.
[0049] Monitor the fluctuation of battery signals and determine in real time whether corresponding alarm information needs to be triggered.
[0050] S2: Dynamically adjust the adaptive threshold based on priority.
[0051] Furthermore, initial thresholds are set for different types of alarm information. The thresholds are set based on historical data and expert experience, and a standardized threshold system is formed by quantifying the characteristics of different alarm categories.
[0052] Standardization removes the effects of dimension by subtracting the mean and dividing by the standard deviation;
[0053] By outputting the priority of each type of alarm, it affects the subsequent comprehensive alarm index output and the classification and output of the final alarm information.
[0054] It should be noted that the threshold in the alarm information is a dynamically adjusted value used to determine whether to trigger an alarm and to set the priority of the alarm information;
[0055] The initial threshold is set based on historical data and expert experience. The initial threshold is set according to the distribution of historical alarm data and the range;
[0056] An initial threshold setting method is expressed as:
[0057]
[0058] in, represents the threshold of the k-th type of alarm information of the i-th battery at the initial time, represents the historical mean of the k-th alarm judgment value, Represents the historical standard deviation of the k-th alarm judgment value;
[0059] Perform dynamic adaptive threshold adjustment, and the threshold adapts to changes in battery status in real time;
[0060] A dynamic adaptive threshold adjustment method is expressed as:
[0061]
[0062] in, represents the current threshold of the k-th type of alarm information of the i-th battery at time t, represents the updated threshold of the k-th type of alarm information of the i-th battery at time t+1, η represents the adjustment coefficient, represents the judgment value of the kth type of alarm information of the i-th battery at time t, Represents the average judgment value of the kth type of alarm information of all batteries at time t;
[0063] If the current alarm judgment value Above average System raises threshold Prevent excessive false positives;
[0064] If the current alarm judgment value Less than average System lowering threshold
[0065] Through dynamic adjustment, the threshold adapts to changes in battery status in real time;
[0066] By continuously adjusting the thresholds, the system determines the alarm trigger point.
[0067] Dynamically adjusted threshold This is the alarm threshold after being updated at time t+1. This dynamic threshold determines the system's sensitivity to a certain type of alarm information at the next moment. A higher threshold means that the system is less sensitive to this type of alarm information, while a lower threshold means that the system is more sensitive to this type of alarm information.
[0068] The threshold in the alarm information is a dynamically adjusted value used to determine whether to trigger an alarm and to set the priority of the alarm information;
[0069] Dynamically adjusted threshold This is the alarm threshold after being updated at time t+1. This dynamic threshold determines the system's sensitivity to a certain type of alarm information at the next moment. A higher threshold means that the system is less sensitive to this type of alarm information, while a lower threshold means that the system is more sensitive to this type of alarm information.
[0070] S3: Construct an alarm index and classify the output alarm information.
[0071] Furthermore, the comprehensive alarm index A i This is an index that combines all alarm category information of each battery. The comprehensive alarm index combines the judgment value, dynamic threshold and priority, and is a key indicator that comprehensively reflects the current status of the battery. This index is usually used for the final classification and output of alarm information, and determines which alarm information should be processed first.
[0072] Comprehensive alarm index A i It is the basis for the system to ultimately determine the classification and priority output of alarm information. By integrating the impact of various types of alarm information, the system can generate a simple and effective index to guide the operator's decision-making and ensure that the most urgent and important alarm information is handled first.
[0073] All alarm category information of each battery is integrated, and the comprehensive alarm index combines the judgment value, dynamic threshold and priority, expressed as:
[0074]
[0075] Among them, A i represents the comprehensive alarm index of the ith battery, k represents the index of the alarm category, ω k represents the importance weight of the k-th alarm information, represents the judgment value of the kth type of alarm information of the i-th battery, represents the threshold value of the kth type of alarm information of the i-th battery, Indicates the priority of the kth type of alarm information of the i-th battery;
[0076] Comprehensive alarm index A i Indicators are generated by combining the judgment value, dynamic threshold, priority and category weight of each type of alarm information. The severity of the alarm information is distinguished through the indicators, and priority is given to each alarm information based on its severity.
[0077] It should be noted that based on the comprehensive alarm index A i , the severity of the alarm information is divided into high severity, medium severity, and low severity;
[0078] When the severity of the alarm information is high, the comprehensive alarm index A i If the value is higher than the preset high priority threshold, the high severity alarm system will give priority to outputting high severity alarm information, notifying the operator to record and analyze high severity alarms. On the monitoring interface, the system will display high severity alarms;
[0079] When the severity of the alarm information is medium, the comprehensive alarm index A i The value of is between the high priority threshold and the medium priority threshold. The medium severity alarm persists, causing system performance to degrade. The system regularly checks the medium severity alarm to ensure that it does not evolve into a high severity alarm message, generates regular reports, and sends the medium severity alarm message to the maintenance team. The system informs the operator of the severity alarm message through a reminder, and there is no need to immediately interrupt the current operation;
[0080] When the severity of the alarm information is low, the comprehensive alarm index A i The value is lower than the medium priority threshold. Low severity alarm information will not affect the security and stability of the system. The system records low severity alarm information but does not issue an alarm to the operator. The system should perform daily monitoring of low severity alarms.
[0081] For alarm information, a public UPS has 21 modules. There are 316 signal points in total. Two sets have 632 signal points in total. For public UPS, system quantity only needs to be collected once. Single module fault signal needs to be configured with 21 module signals. Other modules are set up in the same way according to single module fault. No threshold alarm is made for analog quantity. System quantity is transmitted by IPC monitoring module, and single module quantity is transmitted by single UPS module. A single monitoring UPS has 9 modules. There are 148 signal points in total. Two sets have 296 signal points in total. System quantity only needs to be collected once. Single module fault signal needs to be configured with 9 module signals. Other modules are set up in the same way according to single module fault. No threshold alarm is made for analog quantity. System quantity is transmitted by IPC monitoring module, and single module quantity is transmitted by single UPS module.
[0082] For the system quantity in the public UPS analog quantity, the system sets the minimum threshold of input voltage to 176Ua and the maximum threshold to 275Ua; the minimum threshold of input frequency is 45Hz and the maximum threshold is 55Hz; the minimum threshold of input current is 0Ic and the maximum threshold is 63Ic (a 9A current, the cumulative value of 7 modules in a single phase); the minimum threshold of battery voltage is 186Udc and the maximum threshold is 254Udc; the minimum threshold of battery current is 0Idc and the maximum threshold is 180Idc; the minimum threshold of bypass voltage is 186U and the maximum threshold is 254U; the minimum threshold of bypass frequency is 45Hz and the maximum threshold is 55Hz; the minimum threshold of A phase output voltage is 210Ua and the maximum threshold is 2 30Ua; the minimum threshold of the B phase output voltage is 210Ub, and the maximum threshold is 230Ub; the minimum threshold of the C phase output voltage is 210Uc, and the maximum threshold is 230Uc; the minimum threshold of the A phase output current is 0Ia, and the maximum threshold is 154Ia; the minimum threshold of the B phase output current is 0Ib, and the maximum threshold is 154Ib; the minimum threshold of the C phase output current is 0Ic, and the maximum threshold is 154Ic; the minimum threshold of the A phase load percentage is 0%, and the maximum threshold is 100%; the minimum threshold of the B phase load percentage is 0%, and the maximum threshold is 100%; the minimum threshold of the C phase load percentage is 0%, and the maximum threshold is 100%; the minimum threshold of the number of online modules is 21, and the maximum threshold is 0. The number of alarm points of the system quantity is 1.
[0083] For the single module quantity in the public UPS analog quantity, the minimum threshold of input voltage phase A is 176Ua, and the maximum threshold is 275Ua (a 22A current, the cumulative value of 7 modules in a single phase); the minimum threshold of input voltage phase B is 176Ua, and the maximum threshold is 275Ua (a 22A current, the cumulative value of 7 modules in a single phase); the minimum threshold of input voltage phase C is 176Ua, and the maximum threshold is 275Ua (a 22A current, the cumulative value of 7 modules in a single phase); the minimum threshold of input frequency is 45Hz, and the maximum threshold is 55Hz; the minimum threshold of input current phase A is 0Ia, and the maximum threshold is 20Ia; the minimum threshold of input current phase B is 0Ia, the highest threshold is 20Ia; the lowest threshold of input current phase C is 0Ia, the highest threshold is 20Ia; the lowest threshold of battery voltage is 186U, the highest threshold is 254U; the lowest threshold of battery current is 0Idc, the highest threshold is 30Idc; the lowest threshold of bypass voltage is 186U, the highest threshold is 254U; the lowest threshold of bypass frequency is 45Hz, the highest threshold is 55Hz; the lowest threshold of input voltage is 210Ua, the highest threshold is 230Ua; the lowest threshold of input frequency is 45Hz, the highest threshold is 55Hz; the lowest threshold of input current is 0Ic, the highest threshold is 30Ic; the number of single module alarm points is 21. For input quantity, it is recommended not to upload, and all modules will repeatedly alarm when the power is reversed.
[0084] Since each module will report a power failure alarm in the event of a power failure, it is recommended that each single module not report an input source alarm, but only a single module output alarm. Only the input source alarm of the first module is reported to detect the system operation status.
[0085] For monitoring the system quantity in the UPS analog quantity, the system sets the minimum threshold of input voltage to 176Ua and the maximum threshold to 275Ua; the minimum threshold of input frequency is 45Hz and the maximum threshold is 55Hz; the minimum threshold of input current is 0Ic and the maximum threshold is 63Ic (a 9A current, the cumulative value of 7 modules in a single phase); the minimum threshold of battery voltage is 186Udc and the maximum threshold is 254Udc; the minimum threshold of battery current is 0Idc and the maximum threshold is 180Idc; the minimum threshold of bypass voltage is 186U and the maximum threshold is 254U; the minimum threshold of bypass frequency is 45Hz and the maximum threshold is 55Hz; the minimum threshold of A phase output voltage is 210Ua and the maximum threshold is 2 30Ua; the minimum threshold of the B phase output voltage is 210Ub, and the maximum threshold is 230Ub; the minimum threshold of the C phase output voltage is 210Uc, and the maximum threshold is 230Uc; the minimum threshold of the A phase output current is 0Ia, and the maximum threshold is 154Ia; the minimum threshold of the B phase output current is 0Ib, and the maximum threshold is 154Ib; the minimum threshold of the C phase output current is 0Ic, and the maximum threshold is 154Ic; the minimum threshold of the A phase load percentage is 0%, and the maximum threshold is 100%; the minimum threshold of the B phase load percentage is 0%, and the maximum threshold is 100%; the minimum threshold of the C phase load percentage is 0%, and the maximum threshold is 100%; the minimum threshold of the number of online modules is 21, and the maximum threshold is 0. The number of alarm points of the system quantity is 1.
[0086] For monitoring single module quantity in UPS analog quantity, the minimum threshold of input voltage phase A is 176Ua, and the maximum threshold is 275Ua (a 22A current, the accumulated value of 7 modules in a single phase); the minimum threshold of input voltage phase B is 176Ua, and the maximum threshold is 275Ua (a 22A current, the accumulated value of 7 modules in a single phase); the minimum threshold of input voltage phase C is 176Ua, and the maximum threshold is 275Ua (a 22A current, the accumulated value of 7 modules in a single phase); the minimum threshold of input frequency is 45Hz, and the maximum threshold is 55Hz; the minimum threshold of input current phase A is 0Ia, and the maximum threshold is 20Ia; the minimum threshold of input current phase B is The minimum threshold of input current phase C is 0Ia, and the maximum threshold is 20Ia; the minimum threshold of battery voltage is 186U, and the maximum threshold is 254U; the minimum threshold of battery current is 0Idc, and the maximum threshold is 30Idc; the minimum threshold of bypass voltage is 186U, and the maximum threshold is 254U; the minimum threshold of bypass frequency is 45Hz, and the maximum threshold is 55Hz; the minimum threshold of input voltage is 210Ua, and the maximum threshold is 230Ua; the minimum threshold of input frequency is 45Hz, and the maximum threshold is 55Hz; the minimum threshold of input current is 0Ic, and the maximum threshold is 30Ic; the number of single module alarm points is 9. For input quantity, it is recommended not to upload, and all modules will repeatedly alarm when the power is reversed.
[0087] Since each module will report a power failure alarm in the event of a power failure, it is recommended that each single module not report an input source alarm, but only a single module output alarm. Only the input source alarm of the first module is reported to detect the system operation status.
[0088] For DC analog quantity, the minimum threshold of the AC A phase voltage of the DC charging power cabinet 1 in the system quantity is 176Uan, and the maximum threshold is 275Uan; the minimum threshold of the AC B phase voltage of the DC charging power cabinet 1 is 176Ubn, and the maximum threshold is 275Ubn; the minimum threshold of the AC C phase voltage of the DC charging power cabinet 1 is 176Ucn, and the maximum threshold is 275Ucn; the minimum threshold of the combined mother voltage of the No. 1 DC charging power cabinet is 190Udc, and the maximum threshold is 265Udc; the battery voltage of the No. 1 DC charging power cabinet is the lowest The threshold is 190Udc, and the maximum threshold is 265Udc; the minimum threshold of the battery current of No. 1 DC charging power cabinet is 0Idc, and the maximum threshold is 300Idc; the minimum threshold of the AC-series DC voltage of No. 1 DC charging power cabinet is 0Udc, and the maximum threshold is 10Udc; the minimum threshold of the positive voltage to ground of No. 1 DC charging power cabinet is 80Udc, and the maximum threshold is 132Udc; the minimum threshold of the negative voltage to ground of No. 1 DC charging power cabinet bus is 80Udc, and the maximum threshold is 132Udc; the number of alarm points of the system quantity is 1.
[0089] For the battery simulation quantity, for the battery pack voltage in the system quantity, the minimum threshold is 190Udc and the maximum threshold is 265Udc; the minimum threshold of the battery pack floating current is -200dc and the maximum threshold is 200Idc; the minimum threshold of the battery pack floating current is 0Idc and the maximum threshold is 200Idc; the minimum threshold of the battery pack ambient temperature is 7℃ and the maximum threshold is 42℃. For the single battery quantity, the minimum threshold of the battery voltage is 1.8Idc and the maximum threshold is 2.5Idc; the minimum threshold of the battery internal resistance is 260μΩ and the maximum threshold is 510μΩ; the number of alarm points is 1.
[0090] Embodiment 2, an embodiment of the present invention, provides an alarm information management method for a power supply system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.
[0091] First, the experimental object is a power system containing 100 batteries, where each battery collects multi-dimensional data, including time, characteristics, interaction effects, status, and alarm categories. To ensure the objectivity of the experiment, the system is divided into two groups during the experiment: an experimental group and a control group. The experimental group applies the alarm information management method of the present invention, while the control group uses the existing fixed threshold alarm method.
[0092] In the experimental group, multi-dimensional data of 100 batteries were first collected to construct a high-dimensional tensor model to capture the relationship between different dimensions. Then, a deep neural network was used to perform nonlinear judgment on the data, extract the characteristics of various types of alarm information and generate alarm judgment values. In order to ensure that the system can adapt to real-time changes in battery status, the experimental group applied a priority-based dynamic adaptive threshold adjustment mechanism. This mechanism standardizes the alarm judgment value and dynamically adjusts the trigger threshold according to the priority of each type of alarm information, ultimately ensuring that the alarm system responds reasonably to various abnormal situations in actual operation.
[0093] During the implementation of the experiment, the performance of the experimental group and the control group in three key indicators, namely, operational safety, maintenance efficiency, and evaluation accuracy, was specifically compared. The dynamic adaptive threshold in the experimental group can adjust the threshold according to real-time data, thereby reducing false alarms and missed alarms. Through the comprehensive alarm index, the experimental group further classified the alarm information, dividing all alarm information into three levels of high, medium, and low according to the severity, and giving priority to response accordingly. The control group used the traditional fixed threshold method, which was unable to dynamically adjust the alarm sensitivity according to the actual situation, which may result in a higher false alarm rate and missed alarm rate.
[0094] During the experiment, the multi-dimensional data of each battery was monitored in real time, with particular attention paid to changes in parameters such as battery temperature, voltage, current, and operating status. During the 30-day test period, each system handled the same operating environment, recording the performance of each battery in different dimensions and the system's response to various alarm messages.
[0095] Table 1 Experimental data table
[0096]
[0097]
[0098] Through detailed analysis of the data of the experimental group and the control group, it can be clearly seen that the method of the present invention shows significant advantages in all key indicators. First of all, from the perspective of the number of alarm triggers, the number of alarm triggers in the experimental group is significantly lower than that in the control group. This shows that the dynamic adaptive threshold adjustment mechanism applied by the experimental group effectively reduces the number of unnecessary alarms, enhances the system's accurate judgment of abnormal situations, and avoids frequent false alarms caused by improper threshold setting in traditional fixed threshold methods. Specifically, the average number of alarm triggers for each battery in the experimental group was 4.5 times, while that in the control group was as high as 11.5 times.
[0099] Secondly, the number of false alarms and missed alarms in the experimental group was significantly less than that in the control group. In the experimental group, by dynamically adjusting the threshold, the system was more accurate in setting the alarm trigger point, thereby reducing the number of false alarms. At the same time, there was no missed alarm in the experimental group, indicating that the system can accurately capture every real abnormal situation. The control group had a higher false alarm rate and a certain amount of missed alarms because the fixed threshold could not adapt to real-time data changes. Obviously, this situation will affect the stability of the power supply system in actual applications.
[0100] Thirdly, the analysis of the comprehensive alarm index further verified the superiority of the experimental group. The comprehensive alarm index of the batteries in the experimental group was generally higher than that in the control group, indicating that the experimental group was able to better integrate various types of alarm data and generate a more valuable index when processing alarm information. Through this index, the system can more reasonably classify and prioritize alarm information of different severity levels, while the control group, due to the lack of dynamic adjustment mechanism and comprehensive index analysis, processed alarm information more roughly and found it difficult to make the best response to different situations.
[0101] Finally, the comparison of maintenance time shows that the maintenance efficiency of the experimental group in actual operation is also much higher than that of the control group. Since the classification of alarm information in the experimental group is more accurate, and the triggering and processing of alarm information is more reasonable, the time required in the subsequent maintenance process is shorter, which reduces the downtime of the system and improves the operation efficiency. The control group oscillates between frequent false alarms and missed alarms, which not only wastes a lot of time, but also increases the workload of maintenance personnel, and ultimately affects the overall performance of the system.
[0102] In summary, the present invention achieves better results in terms of operational safety, maintenance efficiency and evaluation accuracy.
[0103] Example 3, reference Figure 3 , which is an embodiment of the present invention, provides an alarm information management system for a power supply system, including a data extraction and nonlinear alarm determination module, a priority output and dynamic adaptive threshold adjustment module, and a comprehensive alarm index calculation and classification output module.
[0104] The data extraction and nonlinear alarm determination module is used to extract the key features of the data and accurately determine the severity of various types of alarm information. The priority output and dynamic adaptive threshold adjustment module is used to improve the system's responsiveness in the face of a changing environment by sorting priorities and dynamically adjusting thresholds. The comprehensive alarm index calculation and classification output module is used to classify and output alarm information according to the comprehensive alarm index.
[0105] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0106] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0107] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.
[0108] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.
[0109] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A method for managing alarm information of a power supply system, characterized in that: include: Extract battery data and convert it into battery signals, and output alarm information through battery signals; Adjust dynamic adaptive thresholds based on priority; Construct an alarm index and classify the output alarm information.
2. The method for managing the alarm information of the power supply system according to claim 1, characterized in that: The extracting battery data and converting it into battery signals includes collecting multi-dimensional battery data; Battery multi-dimensional data includes battery temperature, charge and discharge status, voltage, current, remaining capacity and historical alarm records. The battery multi-dimensional data is processed uniformly to retain the relationship between each dimension: Through unified processing, the multi-dimensional battery data is converted into battery signals to reflect the real-time status of the battery.
3. The method for managing the alarm information of the power supply system according to claim 2, characterized in that: Outputting alarm information through the battery signal includes generating alarm information through the battery signal, including evaluating various types of alarm signals, and generating a determination basis for each type of alarm based on changes in the battery signal; Monitor the fluctuation of battery signals and determine in real time whether corresponding alarm information needs to be triggered.
4. The method for managing the alarm information of the power supply system according to claim 3, characterized in that: The priority-based dynamic adaptive threshold adjustment includes setting initial thresholds for different types of alarm information. The thresholds are set based on historical data and expert experience, and a standardized threshold system is formed by quantifying the characteristics of different alarm categories. Standardization removes the effects of dimension by subtracting the mean and dividing by the standard deviation; By outputting the priority of each type of alarm, it affects the subsequent comprehensive alarm index output and the classification and output of the final alarm information.
5. The method for managing the alarm information of the power supply system according to claim 4, characterized in that: The priority-based dynamic adaptive threshold adjustment includes a threshold in the alarm information being a dynamically adjusted value for determining whether to trigger an alarm and setting the priority of the alarm information; The initial threshold is set based on historical data and expert experience. The initial threshold is set according to the distribution of historical alarm data and the range; Perform dynamic adaptive threshold adjustment, and the threshold adapts to changes in battery status in real time; By continuously adjusting the thresholds, the system determines the alarm trigger point.
6. The method for managing the alarm information of the power supply system according to claim 5, characterized in that: The constructing of the alarm index and classifying the output alarm information includes synthesizing all alarm category information of each battery, combining the judgment value, dynamic threshold and priority, and outputting the comprehensive alarm index; The comprehensive alarm index combines the judgment value, dynamic threshold, priority and category weight of each type of alarm information to generate indicators. Through the indicators, the severity of the alarm information is distinguished and priority is given according to the severity.
7. The method for managing alarm information of a power supply system according to claim 6, characterized in that: The constructing of the alarm index and classifying the output alarm information includes classifying the severity of the alarm information into high severity, medium severity, and low severity based on the comprehensive alarm index; When the severity of the alarm information is high, the value of the comprehensive alarm index is higher than the preset high priority threshold, and the high severity alarm system outputs the high severity alarm information first, notifies the operator to record and analyze the high severity alarm, and the system displays the high severity alarm on the monitoring interface; When the severity of the alarm information is medium, the value of the comprehensive alarm index is between the high priority threshold and the medium priority threshold. The medium severity alarm persists, causing system performance to degrade. The system regularly checks the medium severity alarm to ensure that it does not evolve into a high severity alarm information, generates regular reports, and sends the medium severity alarm information to the maintenance team. The system informs the operator of the severity alarm information by reminding, and there is no need to immediately interrupt the current operation; When the severity of the alarm information is low severity, the value of the comprehensive alarm index is lower than the medium priority threshold. The low severity alarm information will not affect the safety and stability of the system. The system records the low severity alarm information but does not issue an alarm to the operator. The system should conduct daily monitoring of low severity alarms.
8. A system using the power supply system alarm information management method according to any one of claims 1 to 7, characterized in that: It includes data extraction and nonlinear alarm determination module, priority output and dynamic adaptive threshold adjustment module, comprehensive alarm index calculation and classification output module; The data extraction and nonlinear alarm determination module is used to extract key features of the data and accurately determine the severity of various types of alarm information; The priority output and dynamic adaptive threshold adjustment module is used to improve the responsiveness of the system in the face of changing environments by prioritizing and dynamically adjusting the threshold; The comprehensive alarm index calculation and classification output module is used to classify and output alarm information according to the comprehensive alarm index.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the alarm information management method of the power supply system described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for managing alarm information of a power supply system according to any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Graded early warning method for thermal runaway of battery
CN120490885A
