CN117349596A - Battery abnormal state monitoring and early warning system based on multiple sensors - Google Patents
Battery abnormal state monitoring and early warning system based on multiple sensors Download PDFInfo
- Publication number
- CN117349596A CN117349596A CN202311640449.XA CN202311640449A CN117349596A CN 117349596 A CN117349596 A CN 117349596A CN 202311640449 A CN202311640449 A CN 202311640449A CN 117349596 A CN117349596 A CN 117349596A
- Authority
- CN
- China
- Prior art keywords
- category
- value
- processing temperature
- temperature value
- updated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 48
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 241
- 238000000034 method Methods 0.000 claims abstract description 66
- 230000008569 process Effects 0.000 claims abstract description 48
- 238000012937 correction Methods 0.000 claims abstract description 39
- 238000003379 elimination reaction Methods 0.000 claims abstract description 11
- 230000008030 elimination Effects 0.000 claims abstract description 9
- 230000011218 segmentation Effects 0.000 claims description 46
- 230000008859 change Effects 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003487 electrochemical reaction Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000027756 respiratory electron transport chain Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/374—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] with means for correcting the measurement for temperature or ageing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The invention relates to the technical field of electrical performance testing, in particular to a battery abnormal state monitoring and early warning system based on multiple sensors, which comprises a data acquisition module and a data processing module, wherein the data acquisition module is used for: acquiring monitoring data of each set time of a battery to be monitored, wherein the monitoring data comprises a temperature value and an electric parameter value; and performing baseline elimination treatment on the temperature values to obtain reference values and treatment temperature values, performing two-class denoising treatment on the treatment temperature values, determining a noise degree correction value of each treatment temperature value in the second class after each update in the denoising treatment process, and performing denoising treatment on the corresponding treatment temperature values by using the noise degree correction value to finally obtain the denoised treatment temperature values. And judging the abnormal state of the battery according to the denoised processing temperature value and the reference value. The invention effectively improves the reliability of monitoring the abnormal state of the battery temperature.
Description
Technical Field
The invention relates to the technical field of electrical performance testing, in particular to a battery abnormal state monitoring and early warning system based on multiple sensors.
Background
In the process of monitoring the abnormal state of the battery temperature, denoising is often required to be carried out on temperature data acquired by a sensor, and abnormal judgment of the battery temperature is carried out based on the temperature data after denoising. When denoising the temperature data, an iterative threshold segmentation algorithm can be utilized to segment the noise points in the temperature data by continuously updating the segmentation threshold, and the segmented noise points are denoised.
In consideration of the process of acquiring the battery temperature data by adopting the sensor, due to different noise sources of the surrounding environment of the battery and different noise pollution degrees of the temperature data of different acquisition points, in the process of dividing the noise points in the temperature data by using an iterative threshold dividing algorithm, the average value of the two types of temperature data is used as a judgment standard for updating the dividing threshold, only the noise point with higher noise pollution degree can be divided, but the noise point with relatively lower noise pollution degree cannot be divided, and the noise point cannot be naturally denoised, so that a good denoising effect cannot be achieved, and reliable monitoring of the abnormal state of the battery temperature is not facilitated.
Disclosure of Invention
The invention aims to provide a battery abnormal state monitoring and early warning system based on multiple sensors, which is used for solving the problem of low reliability of monitoring the battery temperature abnormal state caused by poor denoising effect of the existing battery temperature data.
In order to solve the technical problems, the invention provides a battery abnormal state monitoring and early warning system based on multiple sensors, which comprises:
the data acquisition module is used for: acquiring monitoring data of each set time of a battery to be monitored, wherein the monitoring data comprises a temperature value and an electric parameter value;
a data processing module for: performing baseline elimination processing on the temperature value to obtain a reference value and a processing temperature value, performing two-class denoising processing on the processing temperature value to obtain a denoised processing temperature value, and performing abnormal state judgment on the battery according to the denoised processing temperature value and the reference value, wherein the two-class denoising processing comprises the following steps:
determining a current segmentation threshold according to the processing temperature values in a first category and a second category, wherein the processing temperature value in the first category belongs to noise, and the processing temperature value in the second category belongs to normal data;
Comparing the current segmentation threshold value with the previous segmentation threshold value, judging whether an iteration termination condition is met, and if so, determining the processing temperature values in the current first category and the second category as the denoised processing temperature values; if the iteration termination condition is not met, reclassifying the processing temperature values in the current first category and the current second category by using the current segmentation threshold value to obtain updated first category and second category;
determining the noise degree of each processing temperature value in the updated second category according to the processing temperature value, the temperature value and the reference value, which are adjacent to the set time and correspond to each processing temperature value in the updated second category;
and correcting the noise degree according to the stable change condition of the electrical parameter value of each processing temperature value in the updated second category at the adjacent set time to obtain a noise degree correction value, denoising each processing temperature value in the updated second category by using the noise degree correction value, and finally obtaining the processing temperature value in the updated second category.
Further, determining a noise level for each of the process temperature values in the updated second category includes:
Determining a reference neighborhood time window by taking the set time corresponding to each processing temperature value in the updated second category as a central time, and respectively determining sub-neighborhood time windows at two sides of the reference neighborhood time window;
performing curve fitting according to the processing temperature values at each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category to obtain a fitted curve, and determining the number of extreme points of the fitted curve;
determining the sum of the reference value and the processing temperature value at each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category and the absolute value of the difference value between the sum and the temperature value;
constructing a reference processing temperature value sequence according to the processing temperature values of each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category, constructing a processing temperature value sequence according to the processing temperature values of each set time in a neighborhood time window of the set time corresponding to each processing temperature value in the updated second category, and determining the structural similarity of the reference processing temperature value sequence and the processing temperature value sequence;
And determining the noise degree of each processing temperature value in the updated second category according to the number of extreme points, the absolute value of the difference value and the structural similarity.
Further, determining the noise degree of each processing temperature value in the updated second category, where the corresponding calculation formula is:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a noise level for each of said process temperature values in said updated second category; />Representing the number of extreme points of the fitting curve corresponding to each processing temperature value in the updated second category; />Representing each of the process temperature values in the updated second categoryThe temperature value of the j-th set time in the reference neighborhood time window of the corresponding set time; />The reference value of the j-th set time in a reference neighborhood time window representing the set time corresponding to each processing temperature value in the updated second category; />Representing the processing temperature value at the j-th set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category; q represents the total number of set times in a reference neighborhood time window of set times corresponding to each of the process temperature values in the updated second category; the absolute value sign is taken; / >And representing the average value of the structural similarity corresponding to each processing temperature value in the updated second category.
Further, correcting the noise level to obtain a noise level correction value, including:
the electrical parameter values include a voltage value and a current value;
performing curve fitting according to the voltage values at each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category to obtain a first fitting error;
performing curve fitting according to the current values of each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category to obtain a second fitting error;
correcting the noise degree according to the first fitting error and the second fitting error to obtain an initial noise degree correction value, wherein the first fitting error and the second fitting error are in negative correlation with the initial noise degree correction value;
and normalizing the initial noise level correction value to obtain a final noise level correction value.
Further, denoising each processing temperature value in the updated second category by using the noise degree correction value to finally obtain a processing temperature value in the updated second category, wherein a corresponding calculation formula is as follows:
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a denoised i-th said process temperature value in said updated second category; />Representing an ith of said process temperature values in said updated second category; />Representing a noise level correction value corresponding to an ith processing temperature value in the updated second category; />An exponential function based on a natural constant e is represented.
Further, determining the current segmentation threshold includes:
and determining a current segmentation threshold value by using a threshold iterative segmentation algorithm according to the processing temperature values in the current first category and the second category.
Further, the iteration termination condition is that the absolute value of the difference between the current segmentation threshold and the previous segmentation threshold is smaller than a set absolute value threshold.
Further, reclassifying the processing temperature value in the current first category and the processing temperature value after the second category by using the current segmentation threshold value to obtain updated first category and second category, including:
reclassifying the processing temperature values in the current first category and the current second category by using the current segmentation threshold value to obtain two categories;
arranging the set time corresponding to all the processing temperature values in each category according to the sequence to obtain a set time sequence corresponding to each category;
Calculating the absolute value of the difference value of every two adjacent set moments in the set moment sequence corresponding to each category, thereby obtaining each time interval corresponding to each category;
according to the average value and the variance of each time interval corresponding to each category, determining the noise possibility corresponding to each category, wherein the average value and the variance of each time interval form a positive correlation relation with the noise possibility;
and distinguishing the two categories according to the noise probability corresponding to the two categories to obtain an updated first category and a second category, wherein the noise probability of the updated first category is greater than that of the updated second category.
Further, determining the noise probability corresponding to each category includes:
a product value of the mean and the variance of the respective time intervals corresponding to each category is determined and the product value is determined as a noise likelihood corresponding to each category.
Further, the battery abnormal state judgment includes:
determining the addition value of the denoised processing temperature value and the corresponding reference value as a denoised temperature value;
and comparing the denoised temperature value with a set temperature threshold, and judging that the abnormal state of the battery occurs when the denoised temperature value is larger than the set temperature threshold, or judging that the abnormal state of the battery does not occur.
The invention has the following beneficial effects: in order to eliminate the influence of the battery change trend on the judgment of noise data, baseline elimination processing is carried out on the temperature value, and a reference value and a processing temperature value are obtained. In the process of carrying out two-class denoising treatment on the treatment temperature values, each time of threshold segmentation is carried out, all the treatment temperature values are divided into two classes, according to the data change condition of the surrounding neighborhood set time of the treatment temperature values belonging to noise, the analysis and judgment are carried out on the treatment temperature values belonging to noise by combining the voltage and current data change condition of the battery, the degree of influence of the noise on the treatment temperature values is accurately measured, the corresponding noise degree is determined, and according to the noise degree, the treatment temperature values of different degrees of influence of the noise are subjected to adaptive effective denoising correction, so that a better denoising effect is achieved, and finally the denoised battery temperature value is obtained. Based on the denoised battery temperature value, abnormal battery temperature monitoring is carried out, and reliability and accuracy of abnormal battery temperature state monitoring are effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a battery abnormal state monitoring and early warning system based on multiple sensors according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for implementing a multi-sensor based battery abnormal state monitoring and early warning system according to an embodiment of the present invention;
fig. 3 is a flowchart of two-class denoising processing for processing temperature values at each set time according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description is given below of the specific implementation, structure, features and effects of the technical solution according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. In addition, all parameters or indices in the formulas referred to herein are values after normalization that eliminate the dimensional effects.
In order to solve the problem of low reliability of monitoring abnormal battery temperature states caused by poor denoising effect of the existing battery temperature data, the embodiment provides a multi-sensor-based battery abnormal state monitoring and early warning system, wherein the software system is composed of modules which realize corresponding functions, and a corresponding structural schematic diagram is shown in fig. 1. The system is characterized in that a battery abnormal state monitoring and early warning method based on multiple sensors is realized, each module in the system corresponds to each step in the method, and a flow chart corresponding to the method is shown in fig. 2. The various modules of the system are described in detail below in connection with specific steps in the method.
The data acquisition module is used for: and acquiring monitoring data of each set time of the battery to be monitored, wherein the monitoring data comprises a temperature value and an electric parameter value.
In order to monitor the abnormal temperature state of the battery, temperature data, voltage data and current data of the battery in the running process are synchronously acquired by using a temperature sensor, a voltage sensor and a current sensor respectively. The collected frequency can be reasonably set according to the needs, and the embodiment sets the frequency asI.e. every->Data is collected once. And taking each acquisition time as a set time, so that the temperature value, the voltage value and the current value of the battery at each set time in the current latest period of time can be obtained. The voltage value and the current value are collectively referred to herein as an electrical parameter value.
A data processing module for: and performing baseline elimination treatment on the temperature value to obtain a reference value and a treatment temperature value, performing two-class denoising treatment on the treatment temperature value to obtain a denoised treatment temperature value, and judging the abnormal state of the battery according to the denoised treatment temperature value and the reference value.
Since electrochemical reactions inside the battery involve electron transfer and ion movement during operation of the battery, heat is released, resulting in an increase in the temperature of the battery. This means that there is an overall trend in the temperature data of the battery, which is caused by the electrochemical reactions inside the battery. In order to facilitate the subsequent denoising of the temperature data of the battery, the overall change trend in the temperature data needs to be removed, so that the finally obtained temperature data can better highlight the local change characteristics of the temperature. Therefore, according to the temperature values at each set time, curve fitting is performed by using a polynomial fitting technology to obtain a temperature value curve, and then baseline elimination processing is performed on the temperature value curve by eliminating a baseline drift technology so as to eliminate the overall change trend in the temperature values, thereby obtaining the reference value and the processing temperature value at each set time. The reference value here means the removed baseline value at each set time by the baseline elimination process, and the process temperature value means the remaining temperature value at each set time by the baseline elimination process. It should be understood that, since the baseline wander elimination technique is utilized, the specific implementation process of performing baseline elimination processing on the curve belongs to the prior art, and will not be described herein.
For the processing temperature values at each set moment, in order to conveniently identify noise points therein and perform denoising processing, in the present iterative threshold segmentation algorithm, in the embodiment, in the result of each threshold segmentation, the segmented processing temperature values belonging to the noise points are subjected to denoising processing, and then the values thereof are correspondingly close to normal data, so that in the iterative process, the processing temperature values with higher noise pollution degree are subjected to denoising processing first, and as the noise points are eliminated, the new threshold values are gradually closed to the normal data, and the processing temperature values with lower noise pollution degree are subjected to denoising processing, thereby finally realizing accurate denoising of the processing temperature values.
Based on the analysis, the processing temperature values at each set time are subjected to two-class denoising processing to obtain denoised processing temperature values, and specific steps for performing the two-class denoising processing will be described in detail in the following, and will not be described in detail here. According to the denoised processing temperature value and the corresponding reference value, the abnormal state of the battery can be judged, namely: determining the addition value of the denoised processing temperature value and the corresponding reference value as a denoised temperature value; and comparing the denoised temperature value with a set temperature threshold, and judging that the abnormal state of the battery occurs when the denoised temperature value is larger than the set temperature threshold, or judging that the abnormal state of the battery does not occur. The set temperature threshold can be set reasonably according to the needs, and the value of the set temperature threshold is set to be 42 ℃ in the embodiment. When the abnormal state of the battery is judged, the system sends out an early warning signal to remind a worker of carrying out abnormal maintenance on the battery.
As shown in fig. 3, the specific steps of the two-class denoising process for the processing temperature values at each set time according to the present embodiment are shown, including:
determining a current segmentation threshold according to the processing temperature values in a first category and a second category, wherein the processing temperature value in the first category belongs to noise, and the processing temperature value in the second category belongs to normal data;
comparing the current segmentation threshold value with the previous segmentation threshold value, judging whether an iteration termination condition is met, and if so, determining the processing temperature values in the current first category and the second category as the denoised processing temperature values; if the iteration termination condition is not met, reclassifying the processing temperature value in the current first category and the processing temperature value after the processing temperature value in the second category by using the current segmentation threshold value to obtain updated first category and second category;
determining the noise degree of each processing temperature value in the updated second category according to the processing temperature value, the temperature value and the reference value, which are adjacent to the set time and correspond to each processing temperature value in the updated second category;
and correcting the noise degree according to the stable change condition of the electrical parameter value of each processing temperature value in the updated second category at the adjacent set time to obtain a noise degree correction value, denoising each processing temperature value in the updated second category by using the noise degree correction value, and finally obtaining the processing temperature value in the updated second category.
For the above steps, for easy understanding, the average value of the maximum value and the minimum value of the processing temperature values is determined according to the processing temperature values at each set time, and the average value is used as an initial dividing threshold value, and the processing temperature values at each set time are divided by using the initial dividing threshold value to obtain two categories. Further, according to the distribution condition of the set time corresponding to each processing temperature value in each classification, the noise possibility corresponding to each classification is determined, and based on the corresponding noise possibility, the two classifications are screened, and a first classification belonging to noise and a second classification belonging to normal data in the two classifications are screened. Since the noise probability corresponding to each category is determined, the specific step of screening the first category and the second category of the two categories will be described in detail in the following, and will not be described here.
After determining the first and second categories, the first and second categories are referred to herein as current first and second categories, and according to the processing temperature values in the current first and second categories, a current segmentation threshold is determined using a threshold iterative segmentation algorithm, that is, an average value of each processing temperature value in the current first category is determined, to obtain a first average value, and an average value of each processing temperature value in the current second category is determined, to obtain a second average value, where the average value of the first average value and the second average value is used as the current segmentation threshold.
The current segmentation threshold is compared with the previous segmentation threshold, wherein the previous segmentation threshold refers to the initial segmentation threshold, and whether the iteration termination condition is met or not is judged. In this embodiment, the iteration termination condition is that the absolute value of the difference between the current segmentation threshold and the previous segmentation threshold is smaller than the set absolute value of the difference threshold. If the iteration termination condition is met, determining the processing temperature values in the current first category and the second category as the denoised processing temperature values, and stopping the iteration process. And if the iteration termination condition is not met, reclassifying the processing temperature values in the current first category and the current second category by using the current segmentation threshold value to obtain updated first category and second category.
In consideration of irregularities of noise occurrence and relatively small occurrence times compared with other normal data, the possibility that the processing temperature value in each category belongs to noise data can be evaluated through the average time interval of the adjacent processing temperature values in the two categories and the irregularity of the change of the time interval corresponding to the adjacent processing temperature values, the noise possibility of each category is determined, and accordingly one category with high noise possibility is judged and is taken as the updated first category, and the other category is taken as the updated second category.
Based on the above analysis, in the present embodiment, the updated first category and second category are obtained, including: reclassifying the processing temperature values in the current first category and the current second category by using the current segmentation threshold value to obtain two categories; arranging the set time corresponding to all the processing temperature values in each category according to the sequence to obtain a set time sequence corresponding to each category; calculating the absolute value of the difference value of every two adjacent set moments in the set moment sequence corresponding to each category, thereby obtaining each time interval corresponding to each category; according to the average value and the variance of each time interval corresponding to each category, determining the noise possibility corresponding to each category, wherein the average value and the variance of each time interval form a positive correlation relation with the noise possibility; and distinguishing the two categories according to the noise probability corresponding to the two categories to obtain an updated first category and a second category, wherein the noise probability of the updated first category is greater than that of the updated second category.
In this embodiment, preferably, a product value of an average value and a variance of each time interval corresponding to each category is determined, and the product value is determined as a noise probability corresponding to each category, and the corresponding calculation formula is:
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing the noise probability corresponding to each category;representing the average value of the absolute values of the differences between every two adjacent set moments in the set moment sequences corresponding to each category; />The absolute value of the difference between the ith setting time and the (i+1) th setting time in the setting time sequence corresponding to each category is shown; m represents the total number of set time points in the set time point sequence corresponding to each category; />The variance of the absolute value of the difference between every two adjacent set time points in the set time point sequence corresponding to each category is shown.
In the above formula for calculating the noise probability, the average time interval corresponding to a certain categoryThe larger the process temperature values in the category, which account for a smaller number of overall process temperature values and the more discrete the data distribution is, the higher the likelihood that the process temperature values in the category belong to noise. At the same time, the variance of the time interval corresponding to the categoryThe larger the time interval between adjacent process temperature values in the category, the more irregular the time interval between adjacent process temperature values, i.e., the time interval between adjacent process temperature valuesThe more unstable, the higher the likelihood that the process temperature values in this category belong to noise.
After the respective noise probabilities corresponding to the two categories are determined by the calculation formula, the two noise probabilities are compared, the category corresponding to the larger noise probability is used as the updated first category, and the category corresponding to the smaller noise probability is used as the updated second category. The processing temperature values in the first category belong to noise and the processing temperature values in the second category belong to normal data.
For each processing temperature value in the updated first category, analyzing the degree of influence of noise, determining the corresponding noise degree, and correcting the corresponding noise degree according to the determined noise degree. In determining the noise level corresponding to each of the processing temperature values in the first category, it may be indicated by the degree of the rule of the change of the processing temperature value in the local range, and if the change is more irregular, it is indicated that the degree of influence of noise on the corresponding processing temperature value is greater, the noise level is greater. Meanwhile, the difference between the change of the processing temperature values in the two side ranges of the local range and the change of the processing temperature values in the local range is discussed, and if the difference between the change of the processing temperature values in the two side ranges of the local range and the change of the processing temperature values in the local range is large, the reliability of the noise degree calculated according to the rule degree of the change of the processing temperature values in the local range of the current processing temperature value point is higher.
In this embodiment, preferably, determining the noise level of each of the processing temperature values in the updated second category includes: determining a reference neighborhood time window by taking the set time corresponding to each processing temperature value in the updated second category as a central time, and respectively determining sub-neighborhood time windows at two sides of the reference neighborhood time window; performing curve fitting according to the processing temperature values at each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category to obtain a fitted curve, and determining the number of extreme points of the fitted curve; determining the sum of the reference value and the processing temperature value at each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category and the absolute value of the difference value between the sum and the temperature value; constructing a reference processing temperature value sequence according to the processing temperature values of each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category, constructing a processing temperature value sequence according to the processing temperature values of each set time in a neighborhood time window of the set time corresponding to each processing temperature value in the updated second category, and determining the structural similarity of the reference processing temperature value sequence and the processing temperature value sequence; and determining the noise degree of each processing temperature value in the updated second category according to the number of extreme points, the absolute value of the difference value and the structural similarity.
For each processing temperature value in the updated second category, the reference neighborhood time window refers to a first time period with the set time corresponding to the processing temperature value as the center, and the first time period is a local range of the corresponding processing temperature value. The neighborhood time window refers to a second time period at two sides of the reference neighborhood time window, and the second time period is a side range of the local range corresponding to the processing temperature value. The first time period and the second time period can be reasonably set according to the needs, the first time period is set to be 0.6s, the second time period is set to be 0.3s, and the setting time corresponding to the processing temperature value is recorded asAnd the time is +.>The time period corresponding to the reference neighborhood time window corresponding to the processing temperature value is +.>The time period corresponding to the neighborhood time window on the left side corresponding to the processing temperature value is +.>Where isThe time period corresponding to the right neighborhood time window corresponding to the temperature value is +.>。
Next, an absolute value of a sum of a reference value corresponding to each set time in the reference neighborhood time window of the process temperature value and a difference between the sum and the temperature value is determined. And performing curve fitting on the processing temperature values at each set time in the reference neighborhood time window of the processing temperature values to obtain a fitting curve, and determining the number of extreme points of the fitting curve. Meanwhile, the processing temperature values at all the set moments in the reference neighborhood moment window of the processing temperature values are arranged according to the set moment sequence to form a reference processing temperature value sequence, and the processing temperature values at all the set moments in each sub-neighborhood moment window of the processing temperature values are arranged according to the set moment sequence to form a processing temperature value sequence. The degree of similarity of each sequence of process temperature values to the reference sequence of process temperature values is measured to determine the structural similarity of the reference sequence of process temperature values and the sequence of process temperature values. Since there are various methods for measuring the similarity of two sequences, the choice of the method is not particularly limited here.
On the basis, according to the number of extreme points, the absolute value of the difference value and the structural similarity, determining the noise degree of each processing temperature value in the updated second category, wherein the corresponding calculation formula is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a noise level for each of said process temperature values in said updated second category; />Representing a fitted curve corresponding to each of the process temperature values in the updated second categoryThe number of extreme points of the line; />The temperature value of the j-th set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category; />The reference value of the j-th set time in a reference neighborhood time window representing the set time corresponding to each processing temperature value in the updated second category; />Representing the processing temperature value at the j-th set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category; q represents the total number of set times in a reference neighborhood time window of set times corresponding to each of the process temperature values in the updated second category; the absolute value sign is taken; / >And representing the average value of the structural similarity corresponding to each processing temperature value in the updated second category.
In the above-described calculation formula of the noise probability,representing the initial noise level of each of the process temperature values in the updated second category, +.>And representing the temperature value loss average value of each processing temperature value in the updated second category, and when the number of extreme points of the fitting curve is larger and the temperature value body loss average value is larger, indicating that the degree of influence of noise on the corresponding processing temperature value is larger, the value of the initial noise degree is larger.And representing the average structural similarity of the reference processing temperature value sequence and the processing temperature value sequence corresponding to each processing temperature value in the updated second category, wherein the average structural similarity represents the similarity degree of the processing temperature value change of the local range of each processing temperature value in the updated second category and the processing temperature value change in the two side ranges of the local range, and when the similarity degree is lower, namely the change difference degree is larger, the confidence degree of the initial noise degree is higher, and the corresponding final noise degree is larger.
The temperature change can influence the internal resistance of the battery, the internal resistance of the battery can be reduced when the temperature is increased, and meanwhile, under ideal conditions, the current of the battery can not be obviously changed in the normal operation process of the battery, and the battery is kept relatively stable. Then the ohm's law can make the internal resistance of the battery decrease and the terminal voltage increase under the condition of constant current. It can be seen that the change in the temperature of the battery has a relationship with the voltage and current, so that the abnormal point of the temperature data can be corrected by using the voltage and current data. The corrected logical relationship is: the more severe the data changes in the voltage data and the current data in the same time interval over a period of time, the more likely the temperature value changes are due to voltage and current changes, at which time the calculated noise level should be reduced.
Based on the above analysis, in the present embodiment, it is preferable that the correction of the noise level of each processing temperature value in the updated second category based on the change condition of the voltage and current data includes: performing curve fitting according to the voltage values at each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category to obtain a first fitting error; performing curve fitting according to the current values of each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category to obtain a second fitting error; correcting the noise degree according to the first fitting error and the second fitting error to obtain an initial noise degree correction value, wherein the first fitting error and the second fitting error are in negative correlation with the initial noise degree correction value; and normalizing the initial noise level correction value to obtain a final noise level correction value.
When curve fitting is performed, a polynomial fitting technology can be used for curve fitting, and a fitting error exists in the fitting process, so that a first fitting error when fitting a voltage value and a second fitting error when fitting a current value can be obtained. Since the curve fitting is performed by using a polynomial fitting technique, and a process of obtaining a fitting error in the fitting process belongs to the prior art, the description is omitted here. When the data change is more severe, that is, the data change is less stable, the more complex the relationship between the data points, the larger the fitting error will be under the same curve fitting algorithm.
Correcting the noise degree of each processing temperature value in the updated second category according to the first fitting error and the second fitting error to obtain a noise degree correction value, wherein the corresponding calculation formula is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>A noise level correction value representing each of the process temperature values in the updated second category; />Representing a noise level for each of the process temperature values in the updated second category; />A first fitting error representing each of the process temperature values in the updated second category; />A second fitting error representing each of the process temperature values in the updated second category; />An exponential function based on a natural constant e; />() Representing a normalization function for correcting the initial noise level>Normalized to the range of 0-1.
In the above formula for calculating the noise level correction value, when the first fitting error is larger, the voltage value of each set time in the corresponding reference neighborhood time window is unstable, the voltage value is more severely changed, and when the second fitting error is larger, the current value is more unstable, and at this time, the temperature value is more changed due to voltage and current changes than noise, and the calculated noise level should be reduced.
And carrying out denoising on each processing temperature value in the updated second category by utilizing the determined noise degree correction value, and finally obtaining the processing temperature value in the updated second category, wherein the corresponding calculation formula is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a denoised i-th said process temperature value in said updated second category; />Representing an ith of said process temperature values in said updated second category; />Representing a noise level correction value corresponding to an ith processing temperature value in the updated second category; />Expressed by oneselfThe constant e is then an exponential function of the base.
In the above calculation formula of the processing temperature value, when the noise level correction value is larger, it means that the degree of influence of noise on the corresponding processing temperature value is larger, then larger correction is made on the corresponding processing temperature value, that is, the corresponding processing temperature value is multiplied by a smaller weight, so that negative correlation mapping is performed on the noise level correction value by using an exponential function, thereby realizing accurate correction, that is, accurate denoising, of the processing temperature value.
And correcting, namely denoising, the processing temperature value in the updated second category by utilizing the noise degree correction value, finally obtaining an updated first category, taking the finally obtained updated first category and the updated second category as the current first category and the second category, determining a current segmentation threshold value by utilizing a threshold iterative segmentation algorithm according to the processing temperature value in the current first category and the processing temperature value in the second category, namely updating the segmentation threshold value of one iteration, repeating iteration until the above-mentioned iteration termination condition is met, and finally realizing two-category denoising processing of the processing temperature value and obtaining the denoised processing temperature value. Based on the denoised processing temperature value and combined with the reference value, the abnormal state judgment of the battery can be finally realized, and the detailed description of the specific process is omitted here.
The invention obtains the processing temperature value by carrying out baseline elimination processing on the temperature value of the battery, in the two-class denoising processing on the processing temperature value, all the processing temperature values are divided into two classes by carrying out threshold segmentation each time, and the analysis and judgment are carried out on the processing temperature value belonging to noise by combining the voltage and current data change condition of the battery, the degree of the noise influence is accurately measured, the corresponding noise degree is determined, and the processing temperature values with different degrees of the noise influence are subjected to adaptive effective denoising correction according to the noise degree, thereby achieving better denoising effect and finally obtaining the denoised battery temperature value. Based on the denoised battery temperature value, abnormal battery temperature monitoring is carried out, and reliability and accuracy of abnormal battery temperature state monitoring are effectively improved.
It should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. A battery abnormal state monitoring and early warning system based on multiple sensors is characterized by comprising:
the data acquisition module is used for: acquiring monitoring data of each set time of a battery to be monitored, wherein the monitoring data comprises a temperature value and an electric parameter value;
a data processing module for: performing baseline elimination processing on the temperature value to obtain a reference value and a processing temperature value, performing two-class denoising processing on the processing temperature value to obtain a denoised processing temperature value, and performing abnormal state judgment on the battery according to the denoised processing temperature value and the reference value, wherein the two-class denoising processing comprises the following steps:
determining a current segmentation threshold according to the processing temperature values in a first category and a second category, wherein the processing temperature value in the first category belongs to noise, and the processing temperature value in the second category belongs to normal data;
comparing the current segmentation threshold value with the previous segmentation threshold value, judging whether an iteration termination condition is met, and if so, determining the processing temperature values in the current first category and the second category as the denoised processing temperature values; if the iteration termination condition is not met, reclassifying the processing temperature values in the current first category and the current second category by using the current segmentation threshold value to obtain updated first category and second category;
Determining the noise degree of each processing temperature value in the updated second category according to the processing temperature value, the temperature value and the reference value, which are adjacent to the set time and correspond to each processing temperature value in the updated second category;
and correcting the noise degree according to the stable change condition of the electrical parameter value of each processing temperature value in the updated second category at the adjacent set time to obtain a noise degree correction value, denoising each processing temperature value in the updated second category by using the noise degree correction value, and finally obtaining the processing temperature value in the updated second category.
2. The multi-sensor based battery abnormal state monitoring and early warning system of claim 1, wherein determining the noise level of each of the process temperature values in the updated second category comprises:
determining a reference neighborhood time window by taking the set time corresponding to each processing temperature value in the updated second category as a central time, and respectively determining sub-neighborhood time windows at two sides of the reference neighborhood time window;
performing curve fitting according to the processing temperature values at each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category to obtain a fitted curve, and determining the number of extreme points of the fitted curve;
Determining the sum of the reference value and the processing temperature value at each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category and the absolute value of the difference value between the sum and the temperature value;
constructing a reference processing temperature value sequence according to the processing temperature values of each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category, constructing a processing temperature value sequence according to the processing temperature values of each set time in a neighborhood time window of the set time corresponding to each processing temperature value in the updated second category, and determining the structural similarity of the reference processing temperature value sequence and the processing temperature value sequence;
and determining the noise degree of each processing temperature value in the updated second category according to the number of extreme points, the absolute value of the difference value and the structural similarity.
3. The multi-sensor based battery abnormal state monitoring and early warning system according to claim 2, wherein the noise degree of each processing temperature value in the updated second category is determined, and the corresponding calculation formula is:
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a noise level for each of said process temperature values in said updated second category; />Representing the number of extreme points of the fitting curve corresponding to each processing temperature value in the updated second category; />The temperature value of the j-th set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category; />The reference value of the j-th set time in a reference neighborhood time window representing the set time corresponding to each processing temperature value in the updated second category; />Representing the processing temperature value at the j-th set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category; q represents the total number of set times in a reference neighborhood time window of set times corresponding to each of the process temperature values in the updated second category; the absolute value sign is taken; />And representing the average value of the structural similarity corresponding to each processing temperature value in the updated second category.
4. The multi-sensor based battery abnormal state monitoring and early warning system according to claim 2, wherein the noise level is corrected to obtain a noise level correction value, comprising:
The electrical parameter values include a voltage value and a current value;
performing curve fitting according to the voltage values at each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category to obtain a first fitting error;
performing curve fitting according to the current values of each set time in a reference neighborhood time window of the set time corresponding to each processing temperature value in the updated second category to obtain a second fitting error;
correcting the noise degree according to the first fitting error and the second fitting error to obtain an initial noise degree correction value, wherein the first fitting error and the second fitting error are in negative correlation with the initial noise degree correction value;
and normalizing the initial noise level correction value to obtain a final noise level correction value.
5. The multi-sensor-based battery abnormal state monitoring and early warning system according to claim 1, wherein each of the processing temperature values in the updated second category is denoised by using the noise level correction value, and finally the processing temperature value in the updated second category is obtained, and a corresponding calculation formula is as follows:
The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a denoised i-th said process temperature value in said updated second category; />Representing an ith of said process temperature values in said updated second category; />Representing a noise level correction value corresponding to an ith processing temperature value in the updated second category; />An exponential function based on a natural constant e is represented.
6. The multi-sensor based battery abnormal state monitoring and early warning system of claim 1, wherein determining the current segmentation threshold comprises:
and determining a current segmentation threshold value by using a threshold iterative segmentation algorithm according to the processing temperature values in the current first category and the second category.
7. The multi-sensor based battery abnormal state monitoring and early warning system according to claim 1, wherein the iteration termination condition is that the absolute value of the difference between the current segmentation threshold and the previous segmentation threshold is smaller than a set absolute value threshold.
8. The multi-sensor based battery abnormal state monitoring and early warning system according to claim 1, wherein reclassifying the processing temperature value in the current first category and the processing temperature value after the processing temperature value in the second category by using the current segmentation threshold value to obtain updated first category and second category comprises:
Reclassifying the processing temperature values in the current first category and the current second category by using the current segmentation threshold value to obtain two categories;
arranging the set time corresponding to all the processing temperature values in each category according to the sequence to obtain a set time sequence corresponding to each category;
calculating the absolute value of the difference value of every two adjacent set moments in the set moment sequence corresponding to each category, thereby obtaining each time interval corresponding to each category;
according to the average value and the variance of each time interval corresponding to each category, determining the noise possibility corresponding to each category, wherein the average value and the variance of each time interval form a positive correlation relation with the noise possibility;
and distinguishing the two categories according to the noise probability corresponding to the two categories to obtain an updated first category and a second category, wherein the noise probability of the updated first category is greater than that of the updated second category.
9. The multi-sensor based battery abnormal state monitoring and early warning system according to claim 8, wherein determining the noise probability corresponding to each category comprises:
A product value of the mean and the variance of the respective time intervals corresponding to each category is determined and the product value is determined as a noise likelihood corresponding to each category.
10. The multi-sensor based battery abnormal state monitoring and early warning system according to claim 1, characterized in that,
the method for judging the abnormal state of the battery comprises the following steps:
determining the addition value of the denoised processing temperature value and the corresponding reference value as a denoised temperature value;
and comparing the denoised temperature value with a set temperature threshold, and judging that the abnormal state of the battery occurs when the denoised temperature value is larger than the set temperature threshold, or judging that the abnormal state of the battery does not occur.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311640449.XA CN117349596B (en) | 2023-12-04 | 2023-12-04 | Battery abnormal state monitoring and early warning system based on multiple sensors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311640449.XA CN117349596B (en) | 2023-12-04 | 2023-12-04 | Battery abnormal state monitoring and early warning system based on multiple sensors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117349596A true CN117349596A (en) | 2024-01-05 |
| CN117349596B CN117349596B (en) | 2024-03-29 |
Family
ID=89355992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311640449.XA Active CN117349596B (en) | 2023-12-04 | 2023-12-04 | Battery abnormal state monitoring and early warning system based on multiple sensors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117349596B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117870943A (en) * | 2024-01-22 | 2024-04-12 | 中国三峡建工(集团)有限公司 | Multi-sensor-based data optimization acquisition system in grouting process |
| CN118028980A (en) * | 2024-04-12 | 2024-05-14 | 浙江康鹏半导体有限公司 | Intelligent temperature monitoring method for gallium arsenide semiconductor growth |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190360868A1 (en) * | 2017-02-27 | 2019-11-28 | Shenzhen Huayuan Micro Electronic Technology Co., Ltd. | Wireless temperature measurement system and signal processing method thereof |
| CN113865750A (en) * | 2021-08-23 | 2021-12-31 | 上海探寻信息技术有限公司 | Temperature measurement calibration method of non-contact equipment and non-contact equipment |
| CN114487856A (en) * | 2020-10-26 | 2022-05-13 | 奥动新能源汽车科技有限公司 | Thermal runaway early warning method and system for battery replacement station |
| WO2023028789A1 (en) * | 2021-08-30 | 2023-03-09 | 宁德时代新能源科技股份有限公司 | Temperature determination method, current threshold determination method, and battery management system |
| CN116046187A (en) * | 2023-04-03 | 2023-05-02 | 探长信息技术(苏州)有限公司 | A unusual remote monitoring system of temperature for communication cabinet |
| CN116722249A (en) * | 2023-07-20 | 2023-09-08 | 江西德泰智控电源有限公司 | Battery thermal runaway early warning protection system and protection method thereof |
| CN116885319A (en) * | 2023-09-06 | 2023-10-13 | 广东技术师范大学 | Temperature control method and system for lithium ion battery |
| CN116955091A (en) * | 2023-09-20 | 2023-10-27 | 深圳市互盟科技股份有限公司 | Data center fault detection system based on machine learning |
| US20230385378A1 (en) * | 2020-12-04 | 2023-11-30 | Chengdu Panoai Intelligent Technology Co., Ltd | Signal analysis method and system based on model for acquiringand identifying noise panoramic distribution |
-
2023
- 2023-12-04 CN CN202311640449.XA patent/CN117349596B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190360868A1 (en) * | 2017-02-27 | 2019-11-28 | Shenzhen Huayuan Micro Electronic Technology Co., Ltd. | Wireless temperature measurement system and signal processing method thereof |
| CN114487856A (en) * | 2020-10-26 | 2022-05-13 | 奥动新能源汽车科技有限公司 | Thermal runaway early warning method and system for battery replacement station |
| US20230385378A1 (en) * | 2020-12-04 | 2023-11-30 | Chengdu Panoai Intelligent Technology Co., Ltd | Signal analysis method and system based on model for acquiringand identifying noise panoramic distribution |
| CN113865750A (en) * | 2021-08-23 | 2021-12-31 | 上海探寻信息技术有限公司 | Temperature measurement calibration method of non-contact equipment and non-contact equipment |
| WO2023028789A1 (en) * | 2021-08-30 | 2023-03-09 | 宁德时代新能源科技股份有限公司 | Temperature determination method, current threshold determination method, and battery management system |
| CN116046187A (en) * | 2023-04-03 | 2023-05-02 | 探长信息技术(苏州)有限公司 | A unusual remote monitoring system of temperature for communication cabinet |
| CN116722249A (en) * | 2023-07-20 | 2023-09-08 | 江西德泰智控电源有限公司 | Battery thermal runaway early warning protection system and protection method thereof |
| CN116885319A (en) * | 2023-09-06 | 2023-10-13 | 广东技术师范大学 | Temperature control method and system for lithium ion battery |
| CN116955091A (en) * | 2023-09-20 | 2023-10-27 | 深圳市互盟科技股份有限公司 | Data center fault detection system based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 顾伟;杜景琦;: "发电设备在线数据的误差处理", 软件, no. 09, pages 158 - 162 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117870943A (en) * | 2024-01-22 | 2024-04-12 | 中国三峡建工(集团)有限公司 | Multi-sensor-based data optimization acquisition system in grouting process |
| CN118028980A (en) * | 2024-04-12 | 2024-05-14 | 浙江康鹏半导体有限公司 | Intelligent temperature monitoring method for gallium arsenide semiconductor growth |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117349596B (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117349596B (en) | Battery abnormal state monitoring and early warning system based on multiple sensors | |
| CN112284440B (en) | Sensor data deviation self-adaptive correction method | |
| CN114114039B (en) | Method and device for evaluating consistency of single battery cells of battery system | |
| CN115876258B (en) | Livestock and poultry breeding environment abnormity monitoring and alarming system based on multi-source data | |
| CN117783745B (en) | Data online monitoring method and system for battery replacement cabinet | |
| CN117235557B (en) | Electrical equipment fault rapid diagnosis method based on big data analysis | |
| CN117493921B (en) | Artificial intelligence energy-saving management method and system based on big data | |
| CN117034177B (en) | Intelligent monitoring method for abnormal data of power load | |
| CN116522268B (en) | Line loss anomaly identification method for power distribution network | |
| CN117571107B (en) | Intelligent unattended wagon balance anomaly monitoring system | |
| CN116298984A (en) | Lithium ion battery capacity jump point and battery attenuation degree identification method | |
| CN114580572B (en) | Abnormal value identification method and device, electronic equipment and storage medium | |
| CN118378199A (en) | Real-time anomaly detection method in big data analysis platform | |
| CN118258861A (en) | Data acquisition optimization method for monitoring concentration of edible gum | |
| CN112416661B (en) | Multi-index time sequence anomaly detection method and device based on compressed sensing | |
| CN116805045A (en) | Meteorological prediction model correction method, device, equipment and readable storage medium | |
| CN113408383B (en) | Audible noise invalid data judgment method based on bounded beta (g, h) distribution and MWKPCA | |
| CN116990697A (en) | Method for detecting abnormal single body in lithium battery pack based on probability distribution | |
| CN115219907A (en) | Lithium battery SOC estimation method, system, medium, equipment and terminal | |
| CN118427537B (en) | Intelligent data acquisition method and system for semiconductor equipment | |
| CN113051809A (en) | Virtual health factor construction method based on improved restricted Boltzmann machine | |
| CN116070150B (en) | Abnormality monitoring method based on operation parameters of breathing machine | |
| CN117250520B (en) | Safety analysis and evaluation method and system for large-scale battery energy storage power station | |
| CN116661522B (en) | Intelligent temperature regulation and control method for temperature change test box based on data processing | |
| CN118427537A (en) | Intelligent data acquisition method and system for semiconductor equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |