Safety detection method and device for lithium battery

Abstract

The invention discloses a safety detection method and device for a lithium battery. The method comprises the following steps: collecting target gas data escaped by a target lithium battery at a target moment through a plurality of gas sensors; determining a gas risk index corresponding to the target lithium battery based on the target gas data collected by a plurality of gas sensors; and under the condition that the gas risk index is greater than a target risk index threshold, generating target prompt information corresponding to the target lithium battery, and displaying the target prompt information. And the accuracy of safety detection of the lithium battery is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium ion battery detection, and in particular to a lithium battery safety detection method and device. Background Art

[0002] With the rapid development of the economy and society, energy storage power stations, as an important part of the power system, have received more and more attention for their safety and reliability. Therefore, it is particularly important to improve the sensitivity and accuracy of fire detection systems in energy storage power stations.

[0003] In addition, the lithium-ion batteries of energy storage power stations need to work stably for a long time, but due to the natural aging of the battery, over-charging and discharging, and the influence of external environmental factors, thermal runaway may occur when the lithium-ion battery works for a long time or is subjected to external shocks. The thermal runaway of lithium-ion batteries will not only lead to a serious decline in battery performance, but may also cause serious consequences such as fire, resulting in huge property losses and safety hazards. However, existing battery safety detection methods and means often have problems such as untimely alarms, low sensitivity, false alarms and missed alarms, and cannot guarantee the safety and stability of the operation of energy storage power stations. Summary of the invention

[0004] The present invention provides a lithium battery safety detection method and device to solve the problems of existing battery safety detection methods and means, such as untimely alarm, low sensitivity, false alarm and missed alarm, which cannot ensure the safety and stability of energy storage power station operation.

[0005] According to one aspect of the present invention, a lithium battery safety detection method is provided, the method comprising:

[0006] Collect target gas data emitted from a target lithium battery at a target time through multiple gas sensors;

[0007] Determine a gas risk index corresponding to the target lithium battery based on the target gas data collected by multiple gas sensors;

[0008] When the gas risk index is greater than the target risk index threshold, target prompt information corresponding to the target lithium battery is generated and displayed.

[0009] According to another aspect of the present invention, a safety detection device for a lithium battery is provided, the device comprising:

[0010] A gas data acquisition module, used to collect target gas data emitted from a target lithium battery at a target time through multiple gas sensors;

[0011] A risk index determination module, configured to determine a gas risk index corresponding to the target lithium battery based on the target gas data collected by a plurality of gas sensors;

[0012] The information prompt module is used to generate target prompt information corresponding to the target lithium battery and display the target prompt information when the gas risk index is greater than the target risk index threshold.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the lithium battery safety detection method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the lithium battery safety detection method described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention collects the target gas data released by the target lithium battery at the target time through multiple gas sensors; and performs high-precision synchronous collection of the target gas data released by the target lithium battery at the target time. Determine the gas risk index corresponding to the target lithium battery based on the target gas data collected by multiple gas sensors; accurately determine the gas risk index corresponding to the target lithium battery; finally, when the gas risk index is greater than the target risk index threshold, generate target prompt information corresponding to the target lithium battery, and display the target prompt information, which solves the problems of existing battery safety detection methods and means, such as untimely alarm, low sensitivity, false alarm and missed alarm, and cannot ensure the safety and stability of the energy storage power station operation, and achieves the beneficial effect of improving the accuracy of lithium battery safety detection and ensuring the safety and stability of the energy storage power station where the lithium battery is located.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of a lithium battery safety detection method provided according to Embodiment 1 of the present invention;

[0022] Figure 2 is a flow chart of a lithium battery safety detection method provided according to Embodiment 2 of the present invention;

[0023] Figure 3 is a schematic structural diagram of a lithium battery safety detection device provided according to Embodiment 3 of the present invention;

[0024] Figure 4 It is a structural schematic diagram of an electronic device for implementing the lithium battery safety detection method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment 1

[0028] Figure 1A flowchart of a lithium battery safety detection method is provided for the first embodiment of the present invention. This embodiment is applicable to the safety detection of lithium batteries. The method can be performed by a lithium battery safety detection device. The lithium battery safety detection device can be implemented in the form of hardware and / or software. The lithium battery safety detection device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0029] S110, collecting target gas data emitted from a target lithium battery at a target time through a plurality of gas sensors.

[0030] The target gas data can be understood as the gas data released during the thermal runaway of lithium ions. The target gas data includes multi-gas component data and gas concentration data.

[0031] Specifically, based on a preset sampling frequency and sampling time, multiple gas sensors are used to synchronously collect multiple real-time target gas data released during lithium-ion thermal runaway.

[0032] Optionally, after collecting the target gas data escaping from the target lithium battery at the target time through multiple gas sensors, it also includes: preprocessing the target gas data to obtain preprocessed target gas data, wherein the preprocessing includes smoothing processing and noise reduction processing.

[0033] Specifically, the target gas data is smoothed by a sliding window averaging method to reduce random fluctuations or noise in the target gas data, making the data curve smoother. The target gas data is subjected to denoising to remove noise components in the target gas data and improve the signal-to-noise ratio of the data, so as to obtain the target gas data after smoothing and denoising.

[0034] Exemplarily, the sliding window averaging method can smooth the target gas data to reduce noise and fluctuations. For a window with a length of N, it can be implemented using the following formula:

[0035]

[0036] Where x(t) is the target gas data at time t, is the target gas data output smoothly after sliding window averaging, and N is the sliding window.

[0037] S120. Determine a gas risk index corresponding to the target lithium battery based on the target gas data collected by multiple gas sensors.

[0038] Among them, the gas risk index can be understood as the gas risk value, and the gas risk index is a parameter used to evaluate gas risk.

[0039] Specifically, a gas risk value corresponding to a target lithium battery is comprehensively determined based on the target gas data collected by multiple gas sensors.

[0040] Optionally, determining the gas risk index corresponding to the target lithium battery based on the gas data collected by multiple gas sensors includes:

[0041] Determine the sensor weight corresponding to each gas sensor respectively, weight the gas data collected by the gas sensor according to the sensor weight corresponding to the gas sensor, and sum the weighted gas data corresponding to the gas sensor to obtain a gas risk index corresponding to the target lithium battery.

[0042] Specifically, the data of multiple sensors can be combined to achieve comprehensive judgment through weighted summation. The gas data collected by the gas sensor is weighted according to the sensor weight corresponding to the gas sensor through the following formula, and the weighted gas data corresponding to the gas sensor is:

[0043]

[0044] Among them, R(t) is the gas risk index, x i (t) is the target gas data collected by the i-th gas sensor, ω i The weight of the i-th gas sensor.

[0045] S130. When the gas risk index is greater than a target risk index threshold, generate target prompt information corresponding to the target lithium battery, and display the target prompt information.

[0046] Among them, the target prompt information can be understood as the risk warning information of the target lithium battery.

[0047] Specifically, the gas risk index is compared with the set target risk index threshold. When the gas risk index is greater than the target risk index threshold, target prompt information corresponding to the target lithium battery is generated, and the target prompt information is displayed in a preset prompt mode at the terminal. The preset prompt mode can be preset based on experience, such as at least one of text prompts, light prompts, and voice prompts. Optionally, when the gas risk index is greater than the target risk index threshold, the risk level corresponding to the gas risk index is determined based on the preset risk level threshold, and different risk prompt information is generated based on different risk levels. Among them, the preset risk level threshold can be preset based on experience, and this embodiment does not limit it. Exemplarily, when the gas risk index is greater than the target risk index threshold, the target lithium battery with risk, the gas component exceeding the target risk index and its current concentration are identified, and preliminary response measures are provided, such as immediate evacuation, stopping related operations, and starting the ventilation system, etc., and the time of generating the prompt information is recorded for subsequent tracking and recording.

[0048] Optionally, before generating the target prompt information corresponding to the target lithium battery, it also includes: determining the initial risk indicator threshold corresponding to each gas sensor respectively, and determining the risk weight corresponding to each of the initial risk indicator thresholds; and performing weighted summation on multiple risk weights to obtain the target risk indicator threshold.

[0049] The target risk index threshold is obtained by weighted summing the initial risk index threshold of each sensor obtained after adaptive threshold adjustment of each gas sensor.

[0050] Specifically, the adaptive threshold adjustment can dynamically adjust the threshold of abnormal detection according to the changing trend of the target gas data, which can be achieved using the following formula:

[0051] TH(t+1)=TH(t)+ΔTH;

[0052] Where TH is the threshold, ΔTH is the change in the threshold, and ΔTH is determined by the rate of change of the current data:

[0053] ΔTH=-α×r(t);

[0054] Where α is the sensitivity parameter and r(t) is the rate of change of the target gas data:

[0055] r(t)=x(t)-x(t-1);

[0056] It is worth noting that the adaptive threshold adjustment can be achieved by calculating the difference r(t) between the target gas data and the historical gas data at the previous moment, and adjusting the threshold according to the size of the difference. If the rate of change is positive, the threshold is reduced to increase the sensitivity. If the rate of change is negative, the threshold is increased to reduce false alarms.

[0057] The technical solution of the embodiment of the present invention collects the target gas data released by the target lithium battery at the target time through multiple gas sensors; and performs high-precision synchronous collection of the target gas data released by the target lithium battery at the target time. Determine the gas risk index corresponding to the target lithium battery based on the target gas data collected by multiple gas sensors; accurately determine the gas risk index corresponding to the target lithium battery; finally, when the gas risk index is greater than the target risk index threshold, generate target prompt information corresponding to the target lithium battery, and display the target prompt information, which solves the problems of existing battery safety detection methods and means, such as untimely alarm, low sensitivity, false alarm and missed alarm, and cannot ensure the safety and stability of the energy storage power station operation, and achieves the beneficial effect of improving the accuracy of lithium battery safety detection and ensuring the safety and stability of the energy storage power station where the lithium battery is located.

[0058] Embodiment 2

[0059] Figure 2 A flow chart of a lithium battery safety detection method provided in Embodiment 2 of the present invention, this embodiment is a further optimization of the above embodiment. Optionally, the method further includes: determining first concentration prediction data corresponding to the target gas data based on a multivariate regression analysis method, determining second concentration prediction data corresponding to the target gas data based on a gas concentration prediction model, wherein the gas concentration prediction model is obtained by training a pre-constructed decision tree model; determining target concentration prediction data for the target lithium battery based on the first concentration prediction data and the second concentration prediction data, and updating the target risk indicator threshold based on the target concentration prediction data to obtain an updated target risk indicator threshold.

[0060] like Figure 2 As shown, the method includes:

[0061] S210, collecting target gas data emitted from a target lithium battery at a target time through a plurality of gas sensors.

[0062] The target gas data is subjected to dimensionality reduction processing, and the gas composition data in the target gas data after dimensionality reduction processing is extracted through principal component analysis.

[0063] Exemplarily, construct a data matrix X and calculate the covariance matrix ∑ in the data matrix:

[0064]

[0065] Perform eigenvalue decomposition on the covariance matrix ∑ to obtain the eigenvector matrix W, where each column of W is an eigenvector corresponding to an eigenvalue, satisfying:

[0066] ∑W=λW;

[0067] Where λ is the diagonal matrix of eigenvalues, and the elements are the eigenvalues ​​of the covariance matrix ∑. Secondly, the original data is projected with the eigenvector matrix W to obtain the gas composition data:

[0068] Z = XW;

[0069] Where Z is the gas composition data and X is the original data matrix.

[0070] S220. Determine a gas risk index corresponding to the target lithium battery based on the target gas data collected by multiple gas sensors.

[0071] S230. When the gas risk index is greater than a target risk index threshold, generate target prompt information corresponding to the target lithium battery, and display the target prompt information.

[0072] S240. Determine first concentration prediction data corresponding to the target gas data based on a multivariate regression analysis method, and determine second concentration prediction data corresponding to the target gas data based on a gas concentration prediction model, wherein the gas concentration prediction model is obtained by training a pre-constructed decision tree model.

[0073] Among them, the first concentration prediction data can be understood as regression model concentration prediction data, and the second concentration prediction data can be understood as decision tree model concentration prediction data.

[0074] Specifically, through multivariate regression analysis, based on the gas composition data of multiple sensors, the changing trend of gas concentration data is predicted.

[0075] Optionally, the target gas data includes gas composition data, and the first concentration prediction data corresponding to the target gas data is determined by the following formula:

[0076] γ=β 0 +β 1 x 1 +β 2 x 2 +···+β n x n ;

[0077] Among them, γ represents the first concentration prediction data, x 1 、x 2 ···xn Indicates gas composition data, β 1 , β 2 ···β n represents the regression coefficient.

[0078] Among them, the regression coefficient is estimated from the historical gas data by the least square method and other methods. The least square function is:

[0079]

[0080] Among them, y i The i-th historical gas data, is the predicted value of the i-th historical gas data, m is the number of historical gas data, and S is the residual sum of squares.

[0081] Optionally, the determining, based on a pre-trained concentration prediction model, second concentration prediction data corresponding to the target gas data includes:

[0082] The target gas data is input into a pre-trained gas concentration prediction model, and second gas concentration prediction data corresponding to the target gas data is determined based on a model output result.

[0083] Optionally, before the gas data to be detected is input into a pre-trained gas concentration prediction model, it also includes: constructing a data set based on a preset number of sample gas data, and dividing the data set into a training set and a test set; training the constructed initial decision tree model based on the training set, calculating the entropy corresponding to the training set at the root node of the initial decision tree, and determining the gas data to be split and the splitting point based on at least one entropy; dividing the training set into multiple training subsets according to the gas data to be split and the splitting point, and repeatedly selecting the splitting point for each training subset to split new subsets again; when a preset stopping condition is met, testing the decision tree model that stops splitting based on the test set to obtain a model performance indicator, and when the model performance indicator meets the preset model performance indicator, determining the decision tree model that stops splitting as the gas concentration prediction model.

[0084] Specifically, the gas composition data obtained by principal component analysis is used to train the decision tree model at the same time as the multivariate regression analysis to supplement the regression model and process more complex relationships in the data. The decision tree model classifies the data through a series of splitting rules, selects splitting nodes according to data features, and constructs a binary tree, and finally outputs the classification results; the training set is constructed using sample gas data, the data set is divided into a training set and a test set, and the decision tree model is trained based on the training set. The sample gas data of the training set is placed at the root node, and a decision tree is constructed. The entropy, conditional entropy or Gini index corresponding to the training set is calculated at the root node, and the feature with the largest information gain or the largest reduction in the Gini index is selected for splitting. The data set is divided into several subsets according to the selected features and splitting points, and the splitting points are repeatedly selected for each subset, and a new subset is split again. When all the samples in the node belong to the same category or the maximum tree depth is reached or the information gain is less than the set threshold, the splitting is stopped.

[0085] At each node, the splitting feature is selected according to the following formula:

[0086]

[0087] Among them, S is the training set, S i is the subset after splitting.

[0088] Optionally, the entropy corresponding to the training set is calculated using the following formula:

[0089]

[0090] Among them, H(D) represents the entropy of the training set D, p k represents the probability of belonging to the kth data category in the training set, and K represents the total number of data categories.

[0091] For example, given feature A, the conditional entropy H(D|A) of feature A can be obtained by the following formula:

[0092]

[0093] D v is a data subset divided by the value v of feature A, |D v | represents subset D v is the size of the original dataset.

[0094] Furthermore, the information gain can be obtained by the following formula:

[0095] IG(D,A)=H(D)-H(D|A);

[0096] IG(D,A) is the information gain of feature A for data set D, that is, the feature with the largest information gain is selected as the split feature of the current node.

[0097] S250. Determine target concentration prediction data for the target lithium battery based on the first concentration prediction data and the second concentration prediction data, and update the target risk indicator threshold based on the target concentration prediction data to obtain an updated target risk indicator threshold.

[0098] Among them, the target concentration prediction data can understand the change trend data of the predicted gas concentration.

[0099] Specifically, predicting the future trend of gas concentration changes can help optimize the threshold. For example, by predicting the trend of gas concentration changes, if the predicted data shows that the gas concentration will rise steadily, the system will automatically lower the threshold and increase the sensitivity to changes in gas concentration. If the prediction shows that the concentration change tends to stabilize or decrease, the threshold will be appropriately increased to avoid false alarms.

[0100] In an embodiment of the present invention, the target concentration prediction data of the target lithium battery is determined by combining the first concentration prediction data and the second concentration prediction data. This double verification method can enhance the reliability of the prediction result. The updated target risk indicator threshold is based on more accurate concentration prediction data, so it can more accurately reflect the risk status of the lithium battery and provide more effective guidance for risk management and control.

[0101] The technical solution of the embodiment of the present invention determines the first concentration prediction data corresponding to the target gas data based on a multivariate regression analysis method, and determines the second concentration prediction data corresponding to the target gas data based on a gas concentration prediction model, wherein the gas concentration prediction model is obtained by training a pre-constructed decision tree model; comprehensively considers the influence of multiple variables on the target gas concentration, so as to more accurately predict the first concentration prediction data. This method can capture the complex relationship between variables and improve the accuracy of the prediction. Then, based on the first concentration prediction data and the second concentration prediction data, the target concentration prediction data of the target lithium battery is determined, and the target risk indicator threshold is updated based on the target concentration prediction data to obtain an updated target risk indicator threshold. The prediction can be further refined through the gas concentration prediction model, and the branching structure of the decision tree can be used to make accurate predictions according to different conditions, which helps to capture more details and further improve the accuracy of the prediction.

[0102] As an optional example of an embodiment of the present invention, the lithium battery safety detection system of this embodiment specifically includes a main control module, a multi-parameter gas detection module and a local prompt module.

[0103] Among them, the main control module is connected to the multi-parameter gas detection module through its built-in ADC (Analog to Digital Converter) interface, and determines the gas risk index corresponding to the target lithium battery based on the target gas data collected by multiple gas sensors, generates target prompt information when the gas risk index is greater than the target risk index threshold, and issues an early warning based on the target prompt information through the local prompt module.

[0104] The multi-parameter gas detection module collects target gas data escaping from a target lithium battery at a target time through multiple gas sensors.

[0105] The main control module processes the collected target gas data locally, and the local processing algorithm can select sliding window averaging method, adaptive threshold adjustment and multi-parameter collaborative judgment method.

[0106] Exemplarily, the sliding window averaging method can smooth the target gas data to reduce noise and fluctuations. For a window with a length of N, it can be implemented using the following formula:

[0107]

[0108] Where x(t) is the target gas data at time t, is the target gas data output smoothly after sliding window averaging, and N is the sliding window.

[0109] Specifically, the adaptive threshold adjustment can dynamically adjust the threshold of abnormal detection according to the changing trend of the target gas data, which can be achieved using the following formula:

[0110] TH(t+1)=TH(t)+ΔTH;

[0111] Where TH is the threshold, ΔTH is the change in the threshold, and ΔTH is determined by the rate of change of the current data:

[0112] ΔTH=-α×r(t);

[0113] Where α is the sensitivity parameter and r(t) is the rate of change of the target gas data:

[0114] r(t)=x(t)-x(t-1);

[0115] It is worth noting that the adaptive threshold adjustment can be achieved by calculating the difference r(t) between the target gas data and the historical gas data at the previous moment, and adjusting the threshold according to the size of the difference. If the rate of change is positive, the threshold is reduced to increase the sensitivity. If the rate of change is negative, the threshold is increased to reduce false alarms.

[0116] Specifically, the data of multiple sensors can be combined to achieve comprehensive judgment through weighted summation. The gas data collected by the gas sensor is weighted according to the sensor weight corresponding to the gas sensor through the following formula, and the weighted gas data corresponding to the gas sensor is:

[0117]

[0118] Among them, R(t) is the gas risk index, x i (t) is the target gas data collected by the i-th gas sensor, ω i The weight of the i-th gas sensor.

[0119] Set weight ω for each sensor in the multi-parameter gas detection module i , and calculate the weighted sum R(t), and then determine whether the weighted sum exceeds the comprehensive threshold. If it exceeds, the local alarm module triggers an alarm and performs manual intervention on the lithium-ion battery failure.

[0120] Exemplarily, in the lithium-ion battery monitoring scenario of an energy storage power station, N lithium-ion battery thermal runaway gas emission detection modules include lithium-ion battery thermal runaway gas emission detection module 1, lithium-ion battery thermal runaway gas emission detection module 2, ..., lithium-ion battery thermal runaway gas emission detection module N-1, lithium-ion battery thermal runaway gas emission detection module N, etc., where N is greater than or equal to 4. The N lithium-ion battery thermal runaway gas emission detection modules need to be placed at different monitoring points in the energy storage power station, and can monitor the status of all lithium-ion batteries in the energy storage power station in a distributed manner.

[0121] Exemplarily, dimension reduction processing is performed on the target gas data received from multiple gas sensors, and main features in the data are extracted through principal component analysis.

[0122] Exemplarily, construct a data matrix X and calculate the covariance matrix ∑ in the data matrix:

[0123]

[0124] Perform eigenvalue decomposition on the covariance matrix ∑ to obtain the eigenvector matrix W, where each column of W is an eigenvector corresponding to an eigenvalue, satisfying:

[0125] ∑W=λW;

[0126] Where λ is the diagonal matrix of eigenvalues, and the elements are the eigenvalues ​​of the covariance matrix ∑. Secondly, the original data is projected with the eigenvector matrix W to obtain the gas composition data:

[0127] Z = XW;

[0128] Where Z is the gas composition data and X is the original data matrix.

[0129] Optionally, first concentration prediction data corresponding to the target gas data is determined based on a multivariate regression analysis method, and second concentration prediction data corresponding to the target gas data is determined based on a gas concentration prediction model, wherein the gas concentration prediction model is obtained by training a pre-constructed decision tree model; target concentration prediction data of the target lithium battery is determined based on the first concentration prediction data and the second concentration prediction data, and the target risk indicator threshold is updated based on the target concentration prediction data to obtain an updated target risk indicator threshold.

[0130] The target gas data includes gas composition data, and the first concentration prediction data corresponding to the target gas data is determined by the following formula:

[0131] γ=β 0 +β 1 x 1 +β 2 x 2 +···+β n x n ;

[0132] Among them, γ represents the first concentration prediction data, x 1 、x 2 ···x n Indicates gas composition data, β 1 , β 2 ···β n represents the regression coefficient.

[0133] Among them, the regression coefficient is estimated from the historical gas data by the least square method and other methods. The least square function is:

[0134]

[0135] Among them, y i The i-th historical gas data, is the predicted value of the i-th historical gas data, m is the number of historical gas data, and S is the residual sum of squares.

[0136] Specifically, the gas composition data obtained by principal component analysis is used to train the decision tree model at the same time as the multivariate regression analysis to supplement the regression model and process more complex relationships in the data. The decision tree model classifies the data through a series of splitting rules, selects splitting nodes according to data features, and constructs a binary tree, and finally outputs the classification results; the training set is constructed using sample gas data, the data set is divided into a training set and a test set, and the decision tree model is trained based on the training set. The sample gas data of the training set is placed at the root node, and a decision tree is constructed. The entropy, conditional entropy or Gini index corresponding to the training set is calculated at the root node, and the feature with the largest information gain or the largest reduction in the Gini index is selected for splitting. The data set is divided into several subsets according to the selected features and splitting points, and the splitting points are repeatedly selected for each subset, and a new subset is split again. When all the samples in the node belong to the same category or the maximum tree depth is reached or the information gain is less than the set threshold, the splitting is stopped.

[0137] At each node, the splitting feature is selected according to the following formula:

[0138]

[0139] Among them, S is the training set, S i is the subset after splitting.

[0140] Optionally, the entropy corresponding to the training set is calculated using the following formula:

[0141]

[0142] Among them, H(D) represents the entropy of the training set D, p k represents the probability of belonging to the kth data category in the training set, and K represents the total number of data categories.

[0143] Exemplarily, given feature A, the conditional entropy H)D|A) of feature A can be obtained by the following formula:

[0144]

[0145] D v is a data subset divided by the value v of feature A, |D v | represents subset D v is the size of the original dataset.

[0146] Furthermore, the information gain can be obtained by the following formula:

[0147] IG(D,A)=H(D)-H(D|A);

[0148] IG(D,A) is the information gain of feature A for data set D, that is, the feature with the largest information gain is selected as the split feature of the current node.

[0149] The technical solution of the embodiment of the present invention monitors the escape of trace gases produced by lithium-ion batteries in the early stage before thermal runaway, thereby predicting and monitoring potential battery failures as early as possible to ensure the safe operation of the energy storage power station.

[0150] Embodiment 3

[0151] Figure 3 This is a schematic diagram of the structure of a lithium battery safety detection device provided by the third embodiment of the present invention. Figure 3 As shown, the device includes: a gas data acquisition module 310, a risk indicator determination module 320 and an information prompt module 330.

[0152] Among them, the gas data acquisition module 310 is used to collect the target gas data escaping from the target lithium battery at the target time through multiple gas sensors; the risk indicator determination module 320 is used to determine the gas risk indicator corresponding to the target lithium battery based on the target gas data collected by multiple gas sensors; the information prompt module 330 is used to generate target prompt information corresponding to the target lithium battery when the gas risk index is greater than the target risk indicator threshold, and display the target prompt information.

[0153] The technical solution of the embodiment of the present invention collects the target gas data released by the target lithium battery at the target time through multiple gas sensors; and performs high-precision synchronous collection of the target gas data released by the target lithium battery at the target time. Determine the gas risk index corresponding to the target lithium battery based on the target gas data collected by multiple gas sensors; accurately determine the gas risk index corresponding to the target lithium battery; finally, when the gas risk index is greater than the target risk index threshold, generate target prompt information corresponding to the target lithium battery, and display the target prompt information, which solves the problems of existing battery safety detection methods and means, such as untimely alarm, low sensitivity, false alarm and missed alarm, and cannot ensure the safety and stability of the energy storage power station operation, and achieves the beneficial effect of improving the accuracy of lithium battery safety detection and ensuring the safety and stability of the energy storage power station where the lithium battery is located.

[0154] Optionally, the risk indicator determination module is specifically used to:

[0155] Determine the sensor weight corresponding to each gas sensor respectively, weight the gas data collected by the gas sensor according to the sensor weight corresponding to the gas sensor, and sum the weighted gas data corresponding to the gas sensor to obtain a gas risk index corresponding to the target lithium battery.

[0156] Optionally, the device also includes a risk weight determination module and a target risk threshold determination module.

[0157] The risk weight determination module is used to determine the initial risk indicator threshold corresponding to each gas sensor and the risk weight corresponding to each initial risk indicator threshold before generating the target prompt information corresponding to the target lithium battery;

[0158] The target risk threshold determination module is used to perform weighted summation on multiple risk weights to obtain a target risk indicator threshold.

[0159] Optionally, the device also includes a concentration prediction module and a threshold adjustment module.

[0160] The concentration prediction module is used to determine the first concentration prediction data corresponding to the target gas data based on a multivariate regression analysis method, and to determine the second concentration prediction data corresponding to the target gas data based on a gas concentration prediction model, wherein the gas concentration prediction model is obtained by training a pre-constructed decision tree model;

[0161] The threshold adjustment module is used to determine the target concentration prediction data of the target lithium battery based on the first concentration prediction data and the second concentration prediction data, and to update the target risk indicator threshold based on the target concentration prediction data to obtain an updated target risk indicator threshold.

[0162] Optionally, the target gas data includes gas composition data; accordingly, the concentration prediction module is specifically used to: determine first concentration prediction data corresponding to the target gas data by the following formula:

[0163] γ=β 0 +β 1 x 1 +β 2 x 2 +···+β n x n ;

[0164] Among them, γ represents the first concentration prediction data, x 1 、x 2 ···x n Indicates gas composition data, β 1, β 2 ···β n represents the regression coefficient.

[0165] Optionally, the concentration prediction module is specifically used for:

[0166] The target gas data is input into a pre-trained gas concentration prediction model, and second gas concentration prediction data corresponding to the target gas data is determined based on a model output result.

[0167] Optionally, the device also includes a data set partitioning module, a model training module, a subset splitting module and a model determination module.

[0168] The data set division module is used to construct a data set based on a preset number of sample gas data and divide the data set into a training set and a test set before inputting the gas data to be detected into a pre-trained gas concentration prediction model;

[0169] The model training module is used to train the constructed initial decision tree model based on the training set, calculate the entropy corresponding to the training set at the root node of the initial decision tree, and determine the gas data to be split and the splitting point based on at least one entropy;

[0170] The subset splitting module is used to divide the training set into multiple training subsets according to the gas data to be split and the splitting point, and repeatedly select the splitting point for each training subset to split out new subsets again;

[0171] The model determination module is used to test the decision tree model that stops splitting based on the test set when a preset stop condition is met to obtain a model performance index. When the model performance index meets the preset model performance index, the decision tree model that stops splitting is determined as the gas concentration prediction model.

[0172] Optionally, the model training module is specifically used for:

[0173] The entropy corresponding to the training set is calculated by the following formula:

[0174]

[0175] Among them, H(D) represents the entropy of the training set D, p k represents the probability of belonging to the kth data category in the training set, and K represents the total number of data categories.

[0176] Optionally, the device also includes a preprocessing module.

[0177] Among them, the preprocessing module is used to preprocess the target gas data after collecting the target gas data escaping from the target lithium battery at the target time through multiple gas sensors to obtain preprocessed target gas data, wherein the preprocessing includes smoothing processing and noise reduction processing.

[0178] The lithium battery safety detection device provided in the embodiment of the present invention can execute the lithium battery safety detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0179] Embodiment 4

[0180] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0181] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0182] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0183] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 performs the various methods and processes described above, such as the method for safety detection of lithium batteries.

[0184] In some embodiments, the method of safety detection of lithium batteries can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method of safety detection of lithium batteries described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the method of safety detection of lithium batteries in any other appropriate manner (for example, by means of firmware).

[0185] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0186] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0187] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0188] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0189] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0190] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0191] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0192] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A lithium battery safety detection method, characterized in that: include: Collect target gas data emitted from a target lithium battery at a target time through multiple gas sensors; Determine a gas risk index corresponding to the target lithium battery based on the target gas data collected by multiple gas sensors; When the gas risk index is greater than the target risk index threshold, target prompt information corresponding to the target lithium battery is generated and displayed.

2. The method according to claim 1, characterized in that The determining of the gas risk index corresponding to the target lithium battery based on the gas data collected by multiple gas sensors includes: Determine the sensor weight corresponding to each gas sensor respectively, weight the gas data collected by the gas sensor according to the sensor weight corresponding to the gas sensor, and sum the weighted gas data corresponding to the gas sensor to obtain a gas risk index corresponding to the target lithium battery.

3. The method according to claim 1, characterized in that: Before generating the target prompt information corresponding to the target lithium battery, the method further includes: Determine an initial risk indicator threshold value corresponding to each gas sensor, and determine a risk weight corresponding to each of the initial risk indicator threshold values; A weighted sum is performed on the multiple risk weights to obtain a target risk indicator threshold.

4. The method according to claim 1, characterized in that: Also includes: Determine first concentration prediction data corresponding to the target gas data based on a multivariate regression analysis method, and determine second concentration prediction data corresponding to the target gas data based on a gas concentration prediction model, wherein the gas concentration prediction model is obtained by training a pre-constructed decision tree model; The target concentration prediction data of the target lithium battery is determined based on the first concentration prediction data and the second concentration prediction data, and the target risk indicator threshold is updated based on the target concentration prediction data to obtain an updated target risk indicator threshold.

5. The method according to claim 4, characterized in that The target gas data includes gas composition data, and the first concentration prediction data corresponding to the target gas data is determined by the following formula: γ=β0+β1x1+β2x2+···+β n x n ; Where γ represents the first concentration prediction data, x1, x2···x n Indicates gas composition data, β1, β2...β n represents the regression coefficient.

6. The method according to claim 4, characterized in that The determining, based on a pre-trained concentration prediction model, second concentration prediction data corresponding to the target gas data comprises: The target gas data is input into a pre-trained gas concentration prediction model, and second gas concentration prediction data corresponding to the target gas data is determined based on a model output result.

7. The method according to claim 6, characterized in that Before inputting the gas data to be detected into the pre-trained gas concentration prediction model, the method further includes: Building a data set based on a preset number of sample gas data, and dividing the data set into a training set and a test set; Training the constructed initial decision tree model based on the training set, calculating entropy corresponding to the training set at the root node of the initial decision tree, and determining gas data to be split and a splitting point based on at least one entropy; Dividing the training set into a plurality of training subsets according to the gas data to be split and the splitting points, and repeatedly selecting the splitting points for each training subset to split out new subsets again; When a preset stop condition is met, the decision tree model that stops splitting is tested based on the test set to obtain a model performance index. When the model performance index meets the preset model performance index, the decision tree model that stops splitting is determined as the gas concentration prediction model.

8. The method according to claim 7, characterized in that The entropy corresponding to the training set is calculated by the following formula: Among them, H(D) represents the entropy of the training set D, p k represents the probability of belonging to the kth data category in the training set, and K represents the total number of data categories.

9. The method according to claim 1, characterized in that: After collecting the target gas data emitted from the target lithium battery at the target time by using multiple gas sensors, the method further includes: The target gas data is preprocessed to obtain preprocessed target gas data, wherein the preprocessing includes smoothing processing and noise reduction processing.

10. A safety detection device for a lithium battery, characterized in that: include: A gas data acquisition module, used to collect target gas data emitted from a target lithium battery at a target time through multiple gas sensors; A risk index determination module, configured to determine a gas risk index corresponding to the target lithium battery based on the target gas data collected by a plurality of gas sensors; The information prompt module is used to generate target prompt information corresponding to the target lithium battery and display the target prompt information when the gas risk index is greater than the target risk index threshold.

Images