CN115498313A - Abnormity early warning method for air-cooled lithium ion battery energy storage container thermal management system - Google Patents
Abnormity early warning method for air-cooled lithium ion battery energy storage container thermal management system Download PDFInfo
- Publication number
- CN115498313A CN115498313A CN202211165216.4A CN202211165216A CN115498313A CN 115498313 A CN115498313 A CN 115498313A CN 202211165216 A CN202211165216 A CN 202211165216A CN 115498313 A CN115498313 A CN 115498313A
- Authority
- CN
- China
- Prior art keywords
- air
- refrigeration
- heating
- cluster
- air conditioner
- 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.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/61—Types of temperature control
- H01M10/613—Cooling or keeping cold
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/52—Indication arrangements, e.g. displays
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/65—Electronic processing for selecting an operating mode
- F24F11/67—Switching between heating and cooling modes
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/61—Types of temperature control
- H01M10/615—Heating or keeping warm
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/62—Heating or cooling; Temperature control specially adapted for specific applications
- H01M10/627—Stationary installations, e.g. power plant buffering or backup power supplies
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/63—Control systems
- H01M10/633—Control systems characterised by algorithms, flow charts, software details or the like
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/65—Means for temperature control structurally associated with the cells
- H01M10/656—Means for temperature control structurally associated with the cells characterised by the type of heat-exchange fluid
- H01M10/6561—Gases
- H01M10/6563—Gases with forced flow, e.g. by blowers
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/66—Heat-exchange relationships between the cells and other systems, e.g. central heating systems or fuel cells
- H01M10/663—Heat-exchange relationships between the cells and other systems, e.g. central heating systems or fuel cells the system being an air-conditioner or an engine
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Mechanical Engineering (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Combustion & Propulsion (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computing Systems (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to an abnormity early warning method for a heat management system of an air-cooled lithium ion battery energy storage container, which comprises the following steps: 1) Extracting data of each air conditioning system in the energy storage container, and preprocessing the data; according to the preprocessed data, probability density distribution models of the temperature difference of the inlet air and the return air of each air conditioner in the refrigeration state and the heating state are respectively established on the basis of a kernel density estimation KDE model; respectively calculating refrigeration and heating health indexes of each air conditioner according to the probability density distribution model; judging abnormal risks of the air conditioning system according to the refrigeration and heating health degree indexes of each air conditioner and giving corresponding early warning; 2) Extracting data of a battery cluster fan system in the energy storage container, and preprocessing the data; according to the preprocessed data, performing outlier analysis on the related data by adopting a DBSCAN density clustering algorithm to obtain an outlier identification result; and judging the abnormal risk of the battery cluster fan system and giving corresponding early warning according to the outlier identification result.
Description
Technical Field
The invention relates to the early warning field of a battery cluster and an air conditioner in an energy storage container, in particular to an abnormity early warning method for a heat management system of an air-cooled lithium ion battery energy storage container.
Background
1.1 background of the invention
Temperature has a great influence on the capacity, charge and discharge power, safety, and the like of the lithium ion battery. The energy storage system integrates more batteries and has larger battery capacity. The arrangement of the batteries of the energy storage system is compact, the gaps are small, the energy density of the battery module is high, the operation working conditions are complex and changeable, and frequent switching between high charge-discharge multiplying power and low charge-discharge multiplying power often occurs. This easily causes heat accumulation between the battery packs, uneven heat generation inside the system, uneven temperature distribution, large temperature difference between the batteries, and the like. Therefore, safe and stable operation of the thermal management system plays an important role in ensuring that the temperature and the humidity of the energy storage system in the whole life cycle are kept in a reasonable range.
At present, a great deal of research is carried out at home and abroad on the aspects of the structural design, the heat management strategy, the control method and the control device of the heat management system of the lithium ion battery energy storage container, and the like, but the exploration is still lacked in the aspect of the air conditioning system abnormity early warning based on the on-line monitoring data analysis of the energy storage container. The invention provides an abnormity early warning method for an air-cooled lithium ion battery energy storage container heat management system by analyzing the distribution change trend of the air inlet and outlet temperature of each air conditioner in the energy storage container and the temperature distribution rule of the battery cell in each battery cluster.
1.2 prior art relating to the invention
1.2.1 technical solution of the prior art one
An air conditioner refrigeration early warning method (CN 108826614A) and an air conditioner heating early warning method (CN 108800422A): according to the technical scheme, the temperature of the farthest point of the indoor air conditioner and the outdoor temperature are respectively detected through the two temperature sensors, the indoor temperature difference and the outdoor temperature difference are calculated through the controller of the air conditioner, and an alarm is given when the value that the indoor temperature is lower than the outdoor temperature is higher than a judgment threshold value.
1.2.2 disadvantages of Prior Art one
The technology only judges the operation state of the air conditioner by comparing the indoor and outdoor temperature difference, but for each air conditioner of the air-cooled lithium ion battery energy storage container, the refrigerating and heating set values of the air conditioner dynamically change along with the operation condition of the energy storage container, and the abnormal state of the air conditioner is difficult to accurately identify only by comparing the temperature difference at a single moment.
1.3 Prior Art related to the present invention
1.3.1 technical solution of the second prior art
A rail vehicle air conditioning unit refrigerant leakage early warning method (CN 112696791A): the technical scheme provides a rail vehicle air conditioning unit refrigerant leakage early warning method, parameter change rules of all sensors are simulated in a laboratory when the air conditioning unit normally works and is stable under different environment temperature states, a working model under the normal work of the air conditioning unit is obtained through big data modeling, and the refrigerant leakage early warning in the train operation process is realized by utilizing the big data model.
1.3.2 disadvantages of Prior Art two
The technique only proposes big data modeling by multi-sensor data, but the specific modeling process is not specifically mentioned. In addition, the early warning object is a rail vehicle air conditioning system, the operation condition and the control strategy of the early warning object are relatively single compared with those of the energy storage container, and the early warning strategy under the coordination control of multiple air conditioners is not involved, so that the early warning object is not suitable for the early warning of the air conditioning system of the energy storage container.
1.4 prior art three relating to the invention
1.4.1 technical solution of prior art III
An air conditioner fault early warning method and system (CN 110440390A): the technical scheme provides an air conditioner fault early warning method and system based on the abnormal noise times of an air conditioner outdoor unit, the abnormal current times of the air conditioner and the abnormal noise times of an indoor unit.
1.4.2 shortcomings of the third prior art
The technology needs to collect the abnormal noise times of the outdoor unit of the air conditioning system, but for the energy storage container, the noise sources of the operating environment are many, the noise is complex and changeable, and the abnormal identification based on the noise times is difficult to apply. In addition, the evaluation indexes related to the technology do not consider the temperature deviation of inlet and outlet air caused by the refrigeration/heating abnormity of the air conditioner due to the reasons of an air conditioner compressor, condensation leakage and the like, so that the refrigeration and heating abnormity of the air conditioner is difficult to accurately identify.
1.5 prior art four relating to the invention
1.5.1 technical solution of the prior art IV
A fan fault early warning method and device of a power supply system (CN 110594177A): the technical scheme provides a fan fault early warning method of a power supply system, fan rotating speed signals of a PWM fan are detected to obtain fan detecting rotating speed frequency, a fan rotating speed frequency threshold value is calculated based on the duty ratio of the PWM fan PWM signals, and fan early warning information is generated based on the fan detecting rotating speed frequency and the fan rotating speed frequency threshold value. Fan failure early warning device and method (CN 102758787A): the technology provides a fan failure early warning device and a method thereof, and the fan failure early warning is realized mainly by setting an abnormal judgment threshold value for analyzing the rotating speed and the current peak value of a fan motor power supply.
1.5.2 disadvantages of the fourth prior art
Above-mentioned technique only realizes early warning analysis through setting for the threshold value to fan rotational speed frequency, fan motor rotational speed value or current peak value, nevertheless because the operating condition of fan receives the fan connection condition in the energy storage container, fan power state, fan rotational speed, whether unobstructed many factor influence such as fan vent appear, and will lead to in cluster electric core temperature distribution to appear obviously changing when the battery cluster fan appears unusually, above-mentioned technique is only difficult to comparatively accurate discernment energy storage battery cluster fan unusually through analysis fan body relevant parameter.
Disclosure of Invention
The invention aims to realize the problem of real-time early warning of an air conditioning system and a battery cluster fan system in a container, and provides an abnormity early warning method for an air-cooled lithium ion battery energy storage container thermal management system, which realizes the early warning of the air conditioning system and the early warning of the battery cluster fan system:
early warning of an air conditioning system: in order to early warn the abnormal air-conditioning refrigeration and heating functions caused by air-conditioning condensation leakage, compressor faults and the like, the invention provides an abnormal early warning method for an air-cooled lithium ion battery energy storage container air-conditioning system by analyzing the distribution and the variation trend of the air inlet and outlet temperatures of each air conditioner in an energy storage container.
Early warning of a battery cluster fan system: in order to early warn the abnormal functions of the battery cluster fan caused by the reasons of the failure and the stop of the battery cluster fan, the abnormal wiring of a fan power supply, the blockage of a fan vent and the like, the invention provides a battery cluster fan abnormity early warning method of an air-cooled lithium ion battery energy storage container by analyzing the temperature distribution rule of battery cells in each battery cluster of the container and integrating LOF and DBSCAN density clustering algorithms.
Specifically, to achieve the above object, the present invention is achieved by the following technical solutions.
The invention provides an abnormity early warning method for an air-cooled lithium ion battery energy storage container thermal management system, wherein the energy storage container thermal management system comprises an air conditioning system and a battery cluster fan system, and the method comprises the following steps:
step 1) extracting data of an air conditioning system, and preprocessing the data; according to the preprocessed data, probability density distribution models of the temperature difference of the inlet air and the return air of each air conditioner in the refrigeration state and the heating state are respectively established on the basis of a kernel density estimation KDE model; respectively calculating refrigeration and heating health indexes of each air conditioner according to the probability density distribution model, and further performing abnormal risk judgment and early warning on the air conditioning system;
step 2) extracting data of a battery cluster fan system, and preprocessing the data; and performing outlier analysis by adopting a DBSCAN density clustering algorithm according to the preprocessed data to obtain an outlier identification result, and further performing abnormal risk judgment and early warning on the battery cluster fan system.
As one improvement of the above technical solution, the step 1) specifically includes:
step 1-1) extracting key data of each air conditioning system in a single day according to a set sampling rate, wherein the method comprises the following steps: time, each air conditioner air inlet temperature, each air conditioner return air temperature, each air conditioner refrigeration state and each air conditioner electrical heating state to carry out the preliminary treatment to data, include: eliminating data points of which the air inlet/return temperature is not in a set temperature interval and eliminating null values in original data;
step 1-2) judging whether the preprocessed data quantity meets the set early warning requirement data quantity or not, and if not, performing early warning; if yes, entering the step 1-3);
step 1-3) respectively calculating the temperature difference of the air inlet and the air return of each air conditioner in a single-day refrigeration state and a heating state according to the preprocessed data, and respectively establishing probability density distribution models of the temperature difference of the air inlet and the air return of each air conditioner in the refrigeration state and the heating state based on a kernel density estimation KDE model, wherein the KDE model adopts a self-adaptive KDE algorithm to realize automatic bandwidth selection;
step 1-4) respectively calculating refrigeration and heating health indexes of each air conditioner according to the established probability density distribution model of the temperature difference of the inlet air and the return air in the refrigeration state and the heating state of each air conditioner;
step 1-5) judging whether the indexes of the refrigeration and heating health degrees of each air conditioner exceed abnormal judgment thresholds; if the abnormal risk exceeds the preset abnormal risk, judging the abnormal risk of the air conditioning system; if not, respectively carrying out linear fitting on the refrigeration and heating health degree indexes of the air conditioners in several days, and respectively obtaining the slope coef of the refrigeration and heating health degree indexes Refrigeration system 、coef Heating apparatus And according to the slopeAnd judging the abnormal risk of the air conditioning system, and giving corresponding early warning.
As one improvement of the above technical solution, in the step 1-3), an expression of the kernel density estimation KDE model f (y) is as follows:
wherein h is the bandwidth; k (-) is a Gaussian kernel function; n is the number of actually acquired sample points of the temperature difference between the air inlet and the air return of the air conditioner in the refrigerating or heating state in a single day; y is a The temperature difference is the a sample point, namely the air inlet and return temperature difference of an air conditioner in a refrigeration or heating state at a certain moment; y is a kernel density estimation KDE model independent variable;
the expression of the Gaussian kernel function K (-) is:
as one improvement of the above technical solution, in the step 1-4), the calculation formula of the health index of each air conditioner for cooling and heating is as follows:
wherein, HLI Refrigeration ACi 、HLI Heating ACi Respectively the health indexes of air conditioner refrigeration and heating; max _ Δ T Refrigeration ACi The air inlet temperature difference value and the air return temperature difference value which correspond to the maximum probability density in the probability density distribution model of the air inlet temperature difference and the air return temperature difference of the No. i air conditioner in the refrigeration state are obtained; max _ Δ T Heating ACi The air inlet temperature difference value and the air return temperature difference value correspond to the maximum probability density in the probability density distribution model of the air inlet temperature difference and the air return temperature difference of the No. i air conditioner in the heating state; max (·) represents the maximization function; n meterAnd displaying the total number of the air conditioners.
As an improvement of the above technical solution, in the step 1-5), expressions that are respectively linearly fitted based on the refrigerating and heating health degree indexes of the air conditioners for several days in history are respectively:
HLI refrigeration ACi ＝coef Refrigeration system *x+b Refrigeration
HLI Heating ACi ＝coef Heating apparatus *x+b Heating apparatus
Wherein x is the number of data points in historical days; coef Refrigeration system The slope when linear fitting is carried out on the refrigeration health degree index based on the historical days of each air conditioner; coef Heating apparatus A slope when linear fitting is performed for the heating health degree index based on the historical days of each air conditioner; b Refrigeration Linearly fitting a bias term of the model for refrigeration health; b Heating apparatus The bias term of the model is linearly fitted to the heating health.
As an improvement of the above technical solution, in the step 1-5), the determining an abnormal risk of the air conditioning system includes:
if HLI Refrigeration ACi Exceeding an anomaly determination threshold, or HLI Refrigeration ACi Coef when the abnormality determination threshold value is not exceeded Refrigeration system <0, judging that the corresponding No. i air conditioner has high-risk refrigeration abnormity;
if HLI Refrigeration ACi Coef when abnormality determination threshold is not exceeded Refrigeration system If the air conditioner is not less than 0, judging that the corresponding No. i air conditioner has low-risk refrigeration abnormity;
if HLI Heating ACi Exceeding an anomaly determination threshold, or HLI Heating ACi Coef when the abnormality determination threshold value is exceeded Heating apparatus <0, judging that the corresponding No. i air conditioner has high-risk heating abnormity;
if HLI Heating ACi Coef when abnormality determination threshold is not exceeded Heating apparatus And if the air temperature is more than or equal to 0, judging that the corresponding i-th air conditioner has low-risk heating abnormity.
As one improvement of the above technical solution, the step 2) specifically includes:
step 2-1) extracting key data of the battery cluster fan system in a single day according to a set sampling rate, wherein the key data comprises the following steps: time, each air conditioner refrigeration state, each air conditioner heating state, the interior electric core temperature of battery cluster and fan relay state etc to carry out the preliminary treatment to data, include: eliminating data points of which the cell temperature is not within a set temperature interval and eliminating null values in the original data;
step 2-2) judging whether the preprocessed data quantity meets the set early warning requirement data quantity, if not, no early warning is needed; if yes, entering the step 2-3);
step 2-3) respectively calculating and extracting a temperature average value and a set quantile of temperature in each battery cluster, a temperature standard deviation and a variation coefficient index under the conditions of an air-conditioning refrigeration state and a fan-on state in the day, an air-conditioning heating state and a fan-on state under two working conditions, performing clustering analysis on the temperature average value and the set quantile in each battery cluster based on a DBSCAN density clustering algorithm to obtain a temperature clustering identification result in each battery cluster, and performing clustering analysis on the temperature standard deviation and the variation coefficient index in each battery cluster based on the DBSCAN density clustering algorithm to obtain a temperature discrete index clustering identification result in each battery cluster;
and 2-4) judging abnormal risks of the battery cluster fan system according to the temperature outlier identification result and the temperature dispersion index outlier identification result in each battery cluster among the battery clusters, and further giving corresponding early warning.
As an improvement of the above technical solution, in the step 2-3), the method includes performing outlier analysis on a temperature mean value and a set quantile in each battery cluster based on a DBSCAN density clustering algorithm to obtain a temperature outlier recognition result in each battery cluster, and specifically includes the following steps:
(1) input sample set D = { x = 1 ,x 2 ,...,x j ...,x m In which x is j Representing the average value of the temperature in the cluster of the j number battery cluster in the day, setting the temperature in the quantile cluster, setting neighborhood parameters (epsilon, minPts), and adopting an Euclidean distance in a sample distance measurement mode; m is the total number of battery clusters in the container;
(2) initializing a set of core objects
Initializing cluster number k =0, initializing unvisited sample set Γ = D, initializing cluster partitioning
(3) For j =1,2.
a. Finding out sample x by means of distance measurement j Epsilon neighborhood subsample set N ε (x j )；
b. Satisfying the number of sub-sample set samples to be | N ε (x j ) Sample x | ≧ MinPts j Adding a core object set omega;
c. repeating the steps a and b, and continuously updating a core object sample set omega;
(4) if the core object set
The algorithm is ended and the result is output; if the core object set
In the core object set omega, a core object o is randomly selected, and a current core object queue omega is initialized cur = o, the initialization class index k is k +1, and the current cluster sample set Ω is initialized k = o, the update unaccessed set Γ is Γ - { o };
(5) if the current cluster core object queue
Then the current cluster C is clustered k After generation, update cluster partition C = { C = { C = } 1 ,C 2 ,...,C k And updating the core object set, and updating the current core object set into an original set and C k The intersection is carried out, and the step (4) is carried out; if the current cluster core object queue
Updating the current core object to the original set and C k The intersection of (a);
(6) in the current cluster core object queue omega cur Taking out a core object o', finding out all epsilon-neighborhood subset sample sets N through neighborhood distance ε (o') make set Δ = N ε (o') # Γ, updating the current cluster sample set C k Is C k U.S. delta, updating the unvisited sample set gamma to gamma-delta, updating omega cur Is omega cur U (. DELTA.andgate. OMEGA) -o' is transferred to step (5);
(7) the output result is: cluster division C = { C 1 ,C 2 ,...,C h ,...,C k }，C h Representing the h cluster in the clusters, wherein k is the final total cluster number; outliers are defined for data points that do not belong to any cluster.
As one improvement of the above technical solution, in the step 2-4), the performing risk judgment on the battery cluster fan system includes:
if two types of outliers exist in the battery cluster at the same time, the fan corresponding to the battery cluster is at high risk;
if only one type of outlier exists in the battery cluster, the fan corresponding to the battery cluster is at a low risk.
The technical scheme of the invention has the following beneficial effects:
1. according to the invention, the abnormal early warning is carried out on the air-cooled lithium ion battery energy storage container heat management system (comprising an air conditioning system and a battery cluster fan system) by analyzing the distribution change trend of the air inlet and outlet temperatures of each air conditioner in the energy storage container and the temperature distribution rule of the battery cells in each battery cluster;
2. the method can accurately identify early abnormality of the air conditioning system and the battery cluster fan in the container and send out grading early warning information, effectively avoids the problems of battery core overheating or uneven temperature distribution and the like caused by long-term abnormality of the heat management system, and improves the operation reliability of the energy storage container.
Drawings
FIG. 1 is a block diagram of the overall process of the method of the present invention;
FIG. 2 is a schematic diagram of an anomaly early warning process of an air-cooled lithium ion battery energy storage container air conditioning system;
fig. 3 is a schematic diagram of an abnormal early warning process of a battery cluster fan of an air-cooled lithium ion battery energy storage container.
Detailed Description
The technical scheme provided by the invention is further illustrated by combining the following embodiments.
FIG. 1 is a block diagram of the overall flow of an embodiment of the method of the present invention; specifically, as shown in fig. 2 and fig. 3, schematic diagrams of an abnormality early warning process of an air-cooled lithium ion battery energy storage container air conditioning system and a battery cluster fan system according to an embodiment of the present invention are respectively shown.
1. Air conditioning system early warning
Fig. 2 is a schematic diagram of an anomaly early warning process of an air-cooled lithium ion battery energy storage container air conditioning system, and the overall design idea of the technology is as follows: theoretically, the environmental conditions (temperature, humidity and the like) near the installation position of each air conditioner in the container are similar, if each air conditioner operates normally, the refrigerating/heating output conditions of each air conditioner in a single day are smaller in difference, so that a statistical distribution model of the inlet and outlet air temperature difference delta T of the air conditioners in the refrigerating and heating states in the single day is respectively established, and the abnormal recognition can be realized by comparing the statistical distribution difference of each air conditioner. The specific early warning process comprises the following steps:
1) Extracting single-day air conditioner data: extracting key data (sampling rate is 1 min) of each air conditioning system in the container in a single day, including time, air inlet temperature of each air conditioner, air return temperature of each air conditioner, state of each air conditioner compressor and electric heating state of each air conditioner, performing data preprocessing, eliminating data points of which the air inlet/return temperature is not in a range of-35-65 ℃, and eliminating blank values in original data, wherein the sampling rate is 1 min;
2) And (3) judging the data quantity: judging whether the preprocessed data quantity meets the early warning modeling requirement (the data points after being removed are more than 900), and entering the next step if the data quantity meets the early warning modeling requirement;
3) And (3) identifying and statistically modeling refrigeration function abnormity: extracting return air temperature and inlet air temperature data of each air conditioner compressor state = =2 (namely, the compressor working state) in a single day, and calculating delta T of each air conditioner in the single day Refrigeration ACi = temperature of inlet air ACi -return air temperature ACi (ΔT Refrigeration ACi Representing the temperature difference of the inlet air and the return air of the No. i air conditioner in the container under the refrigeration state), and establishing each delta T based on Kernel Density Estimation (KDE) Refrigeration ACi The probability density distribution model of (1), wherein the KDE model adopts a self-adaptive KDE algorithm to realize automatic bandwidth selection:
in the formula: f (x) is an expression of a kernel density estimation KDE model, and h is a bandwidth; k (-) is a kernel function, and a Gaussian kernel function is selected in the application; n is the number of actually acquired sample points of the temperature difference between the air inlet and the air return of the air conditioner in the refrigerating or heating state in a single day; x is the number of i The temperature difference is the ith sample point, namely the temperature difference of the inlet air and the return air of a certain air conditioner in a refrigerating or heating state at a certain moment. The expression of the gaussian kernel function is:
4) Heating function abnormity identification statistical modeling: extracting return air temperature and inlet air temperature data of the air conditioners in the electric heating state = =1 (namely, the electric heating working state) in a single day, and calculating delta T of each air conditioner in the single day Heating ACi = return air temperature ACi Temperature of the intake air ACi (ΔT Heating ACi Representing the temperature difference between the return air and the inlet air of the No. i air conditioner in the container under the heating state), and establishing each delta T based on KDE by using the formulas (1) and (2) as well ACi The probability density distribution model of (1).
5) Calculating the indexes of the refrigeration and heating health degree of each air conditioner as follows:
HLI refrigeration ACi ＝max_ΔT Refrigeration ACi /max(max_ΔT Refrigeration AC0 ,max_ΔT Refrigeration AC1 ,...,max_ΔT Refrigeration ACi ) (3)
HLI Heating ACi ＝max_ΔT Heating ACi /max(max_ΔT Heating AC0 ,max_ΔT Heating AC1 ,...,max_ΔT Heating ACi ) (4)
In the formula: HLI Refrigeration ACi 、HLI Heating ACi Respectively are the indexes of the refrigeration and heating health degree of the air conditioner; max _ Δ T Refrigeration ACi Is No. i air conditioner delta T Refrigeration ACi The air inlet and return temperature difference value corresponding to the maximum probability density in the KDE probability density model; max _ Δ T Heating ACi Is No. i air conditioner delta T Heating ACi And return air and inlet air temperature difference values corresponding to the maximum probability density in the KDE probability density model.
6) Determining HLI Refrigeration ACi 、HLI Heating ACi Whether an abnormality determination threshold value is exceeded; if the abnormal risk exceeds the judgment threshold, judging the abnormal risk of the air conditioner; if the decision threshold is not exceeded, continuing to determine HLI based on historical five days Refrigeration ACi 、HLI Heating ACi Respectively, performing linear fitting (HLI) Refrigeration ACi ＝coef Refrigeration *x+b Refrigeration system 、HLI Heating ACi ＝coef Heating apparatus *x+b Heating apparatus Where x is the number of historical five-day data points), the slope coef is obtained Refrigeration system 、coef Heating apparatus And judging the abnormal risk of the air conditioner according to the slope.
7) And (4) judging air conditioner risks:
(1) e.g. coef Refrigeration system Slope of<0 or HLI Refrigeration ACi If the air conditioner exceeds the abnormity judgment threshold value (0.45), judging that the high-risk refrigeration abnormity exists in the air conditioner;
(2) e.g. coef Refrigeration system If the slope is greater than or equal to 0, judging that the air conditioner has low-risk refrigeration abnormity;
(3) such as coef Heating apparatus Slope of<0 or HLI Heating ACi If the abnormal judgment threshold value (0.45) is exceeded, the air conditioner is judged to have high-risk heating abnormality;
(4) such as coef Heating apparatus If the slope is larger than or equal to 0, the air conditioner is judged to have low-risk heating abnormity.
2. Battery cluster fan system early warning
Fig. 3 is a schematic diagram of an abnormal early warning process of a battery cluster fan of an air-cooled lithium ion battery energy storage container, and the overall design idea of the technology is as follows: the whole uniformity of each battery cluster electric core temperature is better in the container under battery cluster fan and energy storage air conditioner running state under the normal condition, when certain battery cluster fan is unusual, can lead to this in cluster electric core temperature distribution's discreteness increase, and this battery cluster electric core bulk temperature more obvious outlier appears, through temperature discreteness and the inter-cluster temperature outlier characteristic in the clustering algorithm discernment cluster, can realize battery cluster fan abnormal recognition. The specific early warning process is as follows:
1) Extracting single-day data: extracting key data (the sampling rate is 1 min) in a single-day box, including time, the states of air-conditioning compressors, the electric heating states of air conditioners, the temperature of a battery cell in a battery cluster, the state of a fan relay and the like, aiming at an energy storage container to be analyzed, carrying out data preprocessing, eliminating data points of which the temperature of the battery cell is not in a range of-35-65 ℃, and eliminating blank values in original data;
2) And (3) judging the data volume: judging whether the preprocessed data quantity meets the early warning modeling requirement (the data points after being removed are more than 900), and entering the next step if the data quantity meets the early warning modeling requirement;
3) Inter-cluster cell temperature outlier identification: the method comprises the steps of respectively extracting temperature average values and 80% quantiles of temperatures in clusters under two working conditions of an air conditioner refrigerating state and fan opening state, an air conditioner heating state and fan opening state in a day, carrying out outlier analysis on the temperature average values and the 80% quantiles in the clusters based on DBSCAN density clustering, and identifying outlier battery clusters, wherein the specific flow is as follows. (one battery cluster usually comprises hundreds of electric cores, the temperature quantile in the cluster refers to the quantile of the electric core temperatures (assuming that 100 electric core temperature values exist in the cluster, the 80% quantile is the 80 th value after the 100 temperature values are arranged from small to large; the quantile can be considered to be set as an adjustable variable and is set according to actual needs)
(1) Inputting: sample set D = { x 1 ,x 2 ,...,x m In which x is 1 Representing the average value of the temperature in the cluster of the No. 1 battery cluster in the day, the temperature in the 80% quantile cluster, neighborhood parameters (epsilon, minPts), and the Euclidean distance is adopted as the sample distance measurement mode;
(2) and (3) outputting: and C, cluster division.
3.1 initializing core object sets
Initializing cluster number k =0, initializing unvisited sample set Γ = D, clustering
3.2 for j =1,2.
a. Finding out a neighborhood subsample set N of the sample xj by a distance measurement mode ε (x j )；
b. Satisfying | N by the number of subsample set samples ε (x j ) | ≧ MinPts, sample x j Adding a core object sample set: Ω = Ω & { x + j }；
3.3 as core object set
Ending the algorithm, otherwise, turning to the step 2.4;
3.4 in the core object set omega, randomly selecting a core object o, initializing the current core object queue omega cur = { o }, initialize class index k = k +1, initialize current cluster sample set Ω k = { o }, update unvisited set Γ = Γ - { o };
3.5 if current Cluster core object
Then the current cluster C is clustered k After generation, update cluster partition C = { C = { C = } 1 ,C 2 ,...,C k H, updating a core object set omega = omega-C k And (4) turning to the step 3.3. Otherwise, updating the core object set omega = omega-C k ；
3.6 queue omega of current cluster core objects cur Taking out a core object o', finding out all epsilon-neighborhood subset sample sets N through neighborhood distance ε (o') let Δ = N ε (o') # Γ, update the current cluster sample set C k ＝C k And U delta, updating an unvisited sample set gamma = gamma-delta and updating omega cur ＝Ω cur U.g., (. DELTA. # n.OMEGA) -o' was converted into 3.5.
3.7 the output result is: cluster division C = { C 1 ,C 2 ,...,C k And defining as outliers for data points not identified as clusters.
4) Identifying the discrete index outlier of the inter-cluster battery cell temperature: and respectively extracting temperature standard deviation and variation coefficient indexes in each cluster under the two working conditions of the air conditioner refrigeration state and the fan starting state in the day, the air conditioner heating state and the fan starting state, performing outlier analysis based on a DBSCAN clustering algorithm, and identifying the outlier battery cluster.
5) Grading and early warning of a battery cluster fan: summarizing the results of inter-cluster battery core temperature outlier identification and inter-cluster battery core temperature dispersion index outlier identification, wherein the risk is high for the fans corresponding to the battery clusters with two types of outliers at the same time, and the risk is low for the fans corresponding to the battery clusters with only one type of outliers.
As can be seen from the above description of the present invention, the present invention realizes real-time abnormality early warning for the air conditioning system and the battery cluster fan system in the air-cooled lithium ion battery energy storage container by analyzing the distribution change trend of the air inlet and outlet temperatures of each air conditioner in the energy storage container and the temperature distribution rule of the battery cells in each battery cluster.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and are not limited. Although the present invention has been described in detail with reference to the embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (9)
1. An abnormity early warning method for an air-cooled lithium ion battery energy storage container thermal management system, wherein the energy storage container thermal management system comprises an air conditioning system and a battery cluster fan system, and the method comprises the following steps:
step 1) extracting data of an air conditioning system and preprocessing the data; according to the preprocessed data, probability density distribution models of the temperature difference of the inlet air and the return air of each air conditioner in the refrigeration state and the heating state are respectively established on the basis of a kernel density estimation KDE model; respectively calculating refrigeration and heating health indexes of each air conditioner according to the probability density distribution model, and further performing abnormal risk judgment and early warning on the air conditioning system;
step 2) extracting data of a battery cluster fan system, and preprocessing the data; and performing outlier analysis by adopting a DBSCAN density clustering algorithm according to the preprocessed data to obtain an outlier identification result, and further performing abnormal risk judgment and early warning on the battery cluster fan system.
2. The abnormality early warning method for the air-cooled lithium ion battery energy storage container thermal management system according to claim 1, wherein the step 1) specifically comprises:
step 1-1) extracting key data of each air conditioning system in a single day according to a set sampling rate, wherein the method comprises the following steps: time, each air conditioner air inlet temperature, each air conditioner return air temperature, each air conditioner refrigeration state and each air conditioner electrical heating state to carry out the preliminary treatment to data, include: eliminating data points of which the air inlet/return temperature is not in a set temperature interval and eliminating null values in original data;
step 1-2) judging whether the preprocessed data quantity meets the set early warning requirement data quantity, if not, no early warning is needed; if yes, entering the step 1-3);
step 1-3) respectively calculating the temperature difference of the air inlet and the air return of each air conditioner in a single-day refrigeration state and a heating state according to the preprocessed data, and respectively establishing probability density distribution models of the temperature difference of the air inlet and the air return of each air conditioner in the refrigeration state and the heating state based on a kernel density estimation KDE model, wherein the KDE model adopts a self-adaptive KDE algorithm to realize automatic bandwidth selection;
step 1-4) respectively calculating refrigeration and heating health indexes of each air conditioner according to the established probability density distribution model of the temperature difference of the inlet air and the return air in the refrigeration state and the heating state of each air conditioner;
step 1-5) judging whether the refrigeration and heating health degree indexes of each air conditioner exceed an abnormal judgment threshold value; if the abnormal risk exceeds the preset threshold, judging the abnormal risk of the air conditioning system; if not, based on eachRespectively carrying out linear fitting on the refrigeration and heating health degree indexes of the air conditioner in several days, and respectively obtaining the slope coef of the refrigeration and heating health degree indexes Refrigeration system 、coef Heating apparatus And judging the abnormal risk of the air conditioning system according to the slope, and further giving corresponding early warning.
3. The abnormality early warning method for the air-cooled lithium ion battery energy storage container heat management system according to claim 2, wherein in the step 1-3), the expression of a kernel density estimation KDE model f (y) is as follows:
wherein h is the bandwidth; k (-) is a Gaussian kernel function; n is the number of actually acquired sample points of the temperature difference between the air inlet and the air return of the air conditioner in the refrigerating or heating state within a single day; y is a The temperature difference is the a sample point, namely the air inlet and return temperature difference of an air conditioner in a refrigeration or heating state at a certain moment; y is a kernel density estimation KDE model independent variable;
the expression of the Gaussian kernel function K (-) is:
4. the abnormality early warning method for the air-cooled lithium ion battery energy storage container heat management system according to claim 2, wherein in the step 1-4), the calculation formula of the health degree indexes of refrigeration and heating of each air conditioner is as follows:
wherein, HLI Refrigeration ACi 、HLI Heating ACi Respectively the health indexes of air conditioner refrigeration and heating; max _ Δ T Refrigeration ACi For No. i air-conditioning in cooling conditionThe air inlet and return temperature difference value corresponding to the maximum probability density in the probability density distribution model of the air inlet and return temperature difference; max _ Δ T Heating ACi The air inlet temperature difference value and the air return temperature difference value correspond to the maximum probability density in the probability density distribution model of the air inlet temperature difference and the air return temperature difference of the No. i air conditioner in the heating state; max (·) represents the maximization function; n represents the total number of air conditioners.
5. The abnormity early warning method of the air-cooled lithium ion battery energy storage container heat management system according to claim 4, wherein in the steps 1-5), expressions which are respectively subjected to linear fitting based on the refrigeration and heating health degree indexes of each air conditioner for several days are respectively as follows:
HLI refrigeration ACi ＝coef Refrigeration system *x+b Refrigeration system
HLI Heating ACi ＝coef Heating apparatus *x+b Heating apparatus
Wherein x is the number of data points in days of history; coef Refrigeration system The slope when linear fitting is carried out on the refrigeration health degree index based on the historical days of each air conditioner; coef Heating apparatus The slope when linear fitting is carried out on the heating health degree indexes of the air conditioners for several days; b Refrigeration system Linearly fitting a bias term of the model for refrigeration health; b Heating apparatus The bias term of the model is linearly fitted to the heating health.
6. The abnormality early warning method for the air-cooled lithium ion battery energy storage container heat management system according to claim 5, wherein in the step 1-5), the judgment of the abnormal risk of the air conditioning system comprises:
if HLI Refrigeration ACi Exceeding an anomaly determination threshold, or HLI Refrigeration ACi Coef when abnormality determination threshold is not exceeded Refrigeration system <0, judging that the corresponding No. i air conditioner has high-risk refrigeration abnormity;
if HLI Refrigeration ACi Coef when abnormality determination threshold is not exceeded Refrigeration system If the number of the air conditioners is more than or equal to 0, judging that the corresponding air conditioner No. i has low-risk refrigeration abnormity;
if HLI Heating ACi Exceeding an anomaly determination threshold, or HLI Heating ACi Coef when the abnormality determination threshold value is exceeded Heating apparatus <0, judging that the corresponding No. i air conditioner has high-risk heating abnormity;
if HLI Heating ACi Coef when abnormality determination threshold is not exceeded Heating apparatus And if the air temperature is more than or equal to 0, judging that the corresponding i-th air conditioner has low-risk heating abnormity.
7. The abnormality early warning method for the air-cooled lithium ion battery energy storage container thermal management system according to claim 1, wherein the step 2) specifically comprises:
step 2-1) extracting key data of the battery cluster fan system in a single day according to a set sampling rate, wherein the key data comprises the following steps: time, each air conditioner refrigeration state, each air conditioner heating state, electric core temperature and fan relay state etc. in the battery cluster to carry out the preliminary treatment to data, include: eliminating data points of which the cell temperature is not within a set temperature interval and eliminating null values in the original data;
step 2-2) judging whether the preprocessed data quantity meets the set early warning requirement data quantity, if not, no early warning is needed; if yes, entering step 2-3);
step 2-3) respectively calculating and extracting a temperature average value and a set quantile of temperature in each battery cluster, a temperature standard deviation and a variation coefficient index under the conditions of an air-conditioning refrigeration state and a fan-on state in the day, an air-conditioning heating state and a fan-on state under two working conditions, performing clustering analysis on the temperature average value and the set quantile in each battery cluster based on a DBSCAN density clustering algorithm to obtain a temperature clustering identification result in each battery cluster, and performing clustering analysis on the temperature standard deviation and the variation coefficient index in each battery cluster based on the DBSCAN density clustering algorithm to obtain a temperature discrete index clustering identification result in each battery cluster;
and 2-4) judging abnormal risks of the battery cluster fan system according to the temperature outlier identification result and the temperature dispersion index outlier identification result in each battery cluster among the battery clusters, and further giving corresponding early warning.
8. The abnormality early warning method for the air-cooled lithium ion battery energy storage container heat management system according to claim 6, wherein in the step 2-3), the temperature mean value and the set quantile in each battery cluster are subjected to outlier analysis based on a DBSCAN density clustering algorithm to obtain the temperature outlier recognition result in each battery cluster, and the method specifically comprises the following steps:
(1) input sample set D = { x = 1 ,x 2 ,...,x j ...,x m In which x j Representing the average value of the intra-cluster temperature of the j number-of-day battery cluster, setting the intra-cluster temperature of the quantile cluster, setting neighborhood parameters (epsilon, minPts), and adopting an Euclidean distance in a sample distance measurement mode; m is the total number of battery clusters in the container;
(2) initializing a set of core objects
Initializing cluster number k =0, initializing unvisited sample set Γ = D, initializing cluster partitioning
(3) For j =1,2.
a. Finding out sample x by means of distance measurement j Epsilon neighborhood subsample set N ε (x j )；
b. Satisfying the number of sub-sample set samples to be | N ε (x j ) Sample x | ≧ MinPts j Adding a core object set omega;
c. repeating the steps a and b, and continuously updating a core object sample set omega;
(4) if the core object set
The algorithm is ended and the result is output; if the core object set
In the core object set omega, a core object o is randomly selected, and a current core object queue omega is initialized cur = o, the initialization class index k is k +1, and the current cluster sample set Ω is initialized k = { o }, update unvisited set Γ to Γ - { o };
(5) if the current cluster core object queue
Then the current cluster C is clustered k After generation, update cluster partition C = { C = { C = } 1 ,C 2 ,...,C k Updating the core object set, updating the current core object set to the original set and C k The intersection is carried out, and the step (4) is carried out; if the current cluster core object queue
Updating the current core object to the original set and C k The intersection of (a);
(6) in the current cluster core object queue omega cur Taking out a core object o', finding out all epsilon-neighborhood subset sample sets N through neighborhood distance ε (o'), let set Δ = N ε (o') # Γ, updating the current cluster sample set C k Is C k U.S. delta, updating the unvisited sample set gamma to gamma-delta, updating omega cur Is omega cur U (. DELTA.andgate. OMEGA) -o' is transferred to step (5);
(7) the output result is: cluster division C = { C 1 ,C 2 ,...,C h ,...,C k }，C h Representing the h cluster in the clusters, wherein k is the final total cluster number; outliers are defined for data points that do not belong to any cluster.
9. The abnormality early warning method for the air-cooled lithium ion battery energy storage container heat management system according to claim 6, wherein in the step 2-4), the risk judgment is performed on the battery cluster fan system, and the method comprises the following steps:
if two types of outliers exist in the battery cluster at the same time, the fan corresponding to the battery cluster is at high risk;
if only one type of outlier exists in the battery cluster, the fan corresponding to the battery cluster is at a low risk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211165216.4A CN115498313A (en) | 2022-09-23 | 2022-09-23 | Abnormity early warning method for air-cooled lithium ion battery energy storage container thermal management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211165216.4A CN115498313A (en) | 2022-09-23 | 2022-09-23 | Abnormity early warning method for air-cooled lithium ion battery energy storage container thermal management system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115498313A true CN115498313A (en) | 2022-12-20 |
Family
ID=84469848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211165216.4A Pending CN115498313A (en) | 2022-09-23 | 2022-09-23 | Abnormity early warning method for air-cooled lithium ion battery energy storage container thermal management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115498313A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116845434A (en) * | 2023-07-17 | 2023-10-03 | 北京双登慧峰聚能科技有限公司 | Temperature control method and device applied to distributed container air-cooled energy storage system |
| CN116857801A (en) * | 2023-08-15 | 2023-10-10 | 宁波奥克斯电气股份有限公司 | Gear control method and device for electric heating pipe and energy storage air conditioner |
| CN117146384A (en) * | 2023-10-30 | 2023-12-01 | 深圳市宇隆伟业科技有限公司 | Air conditioner running state monitoring method based on data driving |
| CN117168633A (en) * | 2023-10-20 | 2023-12-05 | 南通豪强电器设备有限公司 | High-low voltage complete equipment protection method and system based on temperature monitoring |
| CN117272214A (en) * | 2023-11-21 | 2023-12-22 | 罗普特科技集团股份有限公司 | Intelligent management system for safe production |
| CN117273471A (en) * | 2023-11-22 | 2023-12-22 | 天津市德丰金属制品有限公司 | Method and system for supervising steel wire production process |
| CN118228170A (en) * | 2024-03-08 | 2024-06-21 | 国网宁夏电力有限公司电力科学研究院 | Early warning method and early warning system for power monitoring index |
-
2022
- 2022-09-23 CN CN202211165216.4A patent/CN115498313A/en active Pending
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116845434A (en) * | 2023-07-17 | 2023-10-03 | 北京双登慧峰聚能科技有限公司 | Temperature control method and device applied to distributed container air-cooled energy storage system |
| CN116845434B (en) * | 2023-07-17 | 2024-04-16 | 北京双登慧峰聚能科技有限公司 | Temperature control method and device applied to distributed container air-cooled energy storage system |
| CN116857801A (en) * | 2023-08-15 | 2023-10-10 | 宁波奥克斯电气股份有限公司 | Gear control method and device for electric heating pipe and energy storage air conditioner |
| CN117168633A (en) * | 2023-10-20 | 2023-12-05 | 南通豪强电器设备有限公司 | High-low voltage complete equipment protection method and system based on temperature monitoring |
| CN117168633B (en) * | 2023-10-20 | 2024-02-02 | 南通豪强电器设备有限公司 | High-low voltage complete equipment protection method and system based on temperature monitoring |
| CN117146384A (en) * | 2023-10-30 | 2023-12-01 | 深圳市宇隆伟业科技有限公司 | Air conditioner running state monitoring method based on data driving |
| CN117146384B (en) * | 2023-10-30 | 2024-01-30 | 深圳市宇隆伟业科技有限公司 | Air conditioner running state monitoring method based on data driving |
| CN117272214A (en) * | 2023-11-21 | 2023-12-22 | 罗普特科技集团股份有限公司 | Intelligent management system for safe production |
| CN117272214B (en) * | 2023-11-21 | 2024-02-02 | 罗普特科技集团股份有限公司 | Intelligent management system for safe production |
| CN117273471A (en) * | 2023-11-22 | 2023-12-22 | 天津市德丰金属制品有限公司 | Method and system for supervising steel wire production process |
| CN118228170A (en) * | 2024-03-08 | 2024-06-21 | 国网宁夏电力有限公司电力科学研究院 | Early warning method and early warning system for power monitoring index |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115498313A (en) | Abnormity early warning method for air-cooled lithium ion battery energy storage container thermal management system | |
| Fan et al. | A framework for knowledge discovery in massive building automation data and its application in building diagnostics | |
| Sun et al. | Optimization of support vector regression model based on outlier detection methods for predicting electricity consumption of a public building WSHP system | |
| CN108376264A (en) | A kind of handpiece Water Chilling Units method for diagnosing faults based on support vector machines incremental learning | |
| CN116992322B (en) | Smart city data center management system | |
| CN112700085B (en) | Complex system steady-state operation parameter optimization method, system and medium based on association rule | |
| Ding et al. | New fault diagnostic strategies for refrigerant charge fault in a VRF system using hybrid machine learning method | |
| CN116909339B (en) | Intelligent household safety early warning method and system based on artificial intelligence | |
| CN111723925A (en) | Method, device, equipment and medium for fault diagnosis of on-road intelligent train air conditioning unit | |
| CN109344518A (en) | A kind of method for diagnosing faults of base station heat management system | |
| CN112070353A (en) | Method and system for accurately detecting energy efficiency of data center | |
| Trivedi et al. | Predictive maintenance of air conditioning systems using supervised machine learning | |
| CN110726219B (en) | Control method, device and system of air conditioner, storage medium and processor | |
| CN115264768A (en) | Building air conditioner energy-saving control method and system based on Internet of things | |
| Yang et al. | Research on energy-saving optimization of commercial central air-conditioning based on data mining algorithm | |
| JP2004234302A (en) | Process management device | |
| CN116774749A (en) | Intelligent temperature-control electric power cabinet | |
| CN116945856A (en) | Pure electric vehicle integrated thermal management system and automobile based on edge calculation | |
| CN115327930B (en) | Visual energy-saving control method and system | |
| CN110568257A (en) | continuous monitoring method and device for energy consumption of air conditioner | |
| Cheng et al. | Abnormal energy consumption detection using ensemble model for water chilling unit on HVAC system | |
| CN112241812A (en) | Low-voltage distribution network topology identification method based on unilateral optimization and genetic algorithm cooperation | |
| Xu et al. | Intelligent Data Center Safety Status Prediction based on Algorithm Ensemble | |
| CN118411007B (en) | Efficient comprehensive energy station AI intelligent management system | |
| CN118449141B (en) | Base station power supply and energy storage battery energy-saving regulation and control method and system based on cloud monitoring |
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 |