Battery health state prediction method

Abstract

The invention provides a battery health state prediction method, which comprises the following steps that: in the charging and discharging process of a battery, the contraction or expansion degrees of different positions on an anode plate of the battery at the same moment are different, correspondingly, the dependent variables of the different positions on the anode plate at the same moment are different, and the state of health of the battery is predicted on the basis of the characteristic. Constructing a network model according to the dependent variables at different positions on the anode plate; and predicting the current charge state of the battery according to the dependent variables and the strain rates at different positions on the anode plate at the current moment on the basis of the corresponding network model, and / or predicting the health state of the battery according to the maximum strain and the residual strain on the anode plate in each cycle period until the current moment on the basis of the corresponding network model. According to the invention, distributed high-precision comprehensive prediction can be carried out on the operation state of the battery anode plate on the premise of not depending on an electrochemical test technology.

Description

Technical Field

[0001] The invention belongs to the field of optical fiber sensing, and in particular relates to a method for predicting the health status of a battery. Background Art

[0002] Traditional methods for predicting the health status of lithium batteries rely on establishing electrochemical field models through theoretical calculations and measuring key electrical information to predict the battery status. It is challenging to predict the battery status through a single theoretical model due to the need to consider multiple nonlinear, coupled and dynamic influencing factors, which limits the accuracy of the prediction. With the advancement of artificial intelligence, neural networks have been applied to estimate the battery status. Using simple electrochemical parameters such as voltage, current and temperature during battery operation, accurate estimates of the battery state of charge (SOC) and state of health (SOH) can be achieved. However, these methods rely on data from specific locations within the battery, such as voltage, current and surface temperature, which may not fully reflect the internal electrochemical reaction mechanism. To date, there is no effective method that can achieve distributed in-situ monitoring inside lithium batteries and achieve high-precision prediction of battery operating status without relying on electrochemical testing technology. Summary of the invention

[0003] The present invention provides a battery health status prediction method to solve the problem that it is currently impossible to perform distributed high-precision and comprehensive prediction of the operating status of a battery anode plate without relying on electrochemical testing technology.

[0004] According to a first aspect of an embodiment of the present invention, a method for predicting a battery health state is provided, comprising:

[0005] Step S100, during the battery charging and discharging process, the shrinkage or expansion degree at different positions of the anode plate of the battery at the same time is different, and correspondingly, the strain amount at different positions of the anode plate at the same time is different. Based on this characteristic, a network model is constructed according to the strain amount at different positions of the anode plate;

[0006] Step S200, based on the corresponding network model, according to the strain and strain rate at different positions on the anode plate at the current moment, the current charge state of the battery is predicted, and / or based on the corresponding network model, according to the maximum strain and residual strain on the anode plate in each cycle so far, the health state of the battery is predicted, wherein the strain rate is the difference in strain per unit time at the corresponding position on the anode plate, the maximum strain is the maximum strain on the anode plate measured in the corresponding cycle minus the minimum strain, and the residual strain is the last strain measured on the anode plate in the corresponding cycle minus the first strain.

[0007] In an optional implementation, the step S100 specifically includes: constructing a feedforward neural network, wherein the feedforward neural network includes an input layer, a hidden layer, and an output layer connected in sequence, the input of the input layer is the strain and strain rate at different positions on the anode plate at the same time, and the output of the output layer is the current charge state of the battery;

[0008] The step S200 specifically includes: based on the feedforward neural network, according to the strain amount and strain rate at different positions on the anode plate at the current moment, predicting the current charge state of the battery.

[0009] In another optional implementation, the feedforward neural network is constructed in step S100 according to the following steps:

[0010] The charging or discharging process of the battery during use is respectively regarded as a cycle, and all strain amounts and strain velocities at different positions on the anode plate in different cycles are regarded as training sets, which are input into the feedforward neural network for pre-training;

[0011] The predicted charge state of the battery output by the output layer is compared with the actual charge state of the battery, and the various parameters in the feedforward neural network are adjusted according to the comparison result to obtain the optimal parameter set; the parameter set includes the number of hidden layers, the number of neurons in each hidden layer, the weight of each input quantity in the input layer to each neuron in the first hidden layer, the weight of each neuron in each hidden layer to each neuron in the next hidden layer, and the weight of each neuron in the last hidden layer to each output quantity in the output layer.

[0012] In another optional implementation, the output of the output layer is the current overall charge state of the battery or the current charge states at different corresponding positions on the battery.

[0013] In another optional implementation, the step S100 specifically includes: constructing a long short-term memory network, wherein the long short-term memory network includes an input layer, a long short-term memory network layer, a fully connected layer and an output layer connected in sequence, the input of the input layer is the maximum strain and residual strain on the anode plate in each cycle so far, and the output of the output layer is the current health state of the battery; the step S200 specifically includes: based on the long short-term memory network, predicting the health state of the battery according to the maximum strain and residual strain on the anode plate in the current cycle.

[0014] In another optional implementation, the cycle period is the time period corresponding to each charging or discharging process during the use of the battery; the output layer in the long short-term memory network outputs a timing signal without periodic changes, and the current health status of the battery is the current maximum capacity of the battery divided by the initial capacity of the battery.

[0015] In another optional implementation, the strain amounts at different positions on the anode plate are measured according to the following steps:

[0016] Step S1, the sensing optical fiber is arranged to cover the upper surface of the anode plate of the battery in a serpentine manner in a first direction, the first optical fiber segment is arranged along the second direction after each bending of the sensing optical fiber, and each two adjacent first optical fiber segments are connected by a corresponding second optical fiber segment, and the first direction is perpendicular to the second direction;

[0017] Step S2: for each first optical fiber segment, two ends of the first optical fiber segment outside the anode plate are respectively fixed to the protective shell under the anode plate, so that the first optical fiber segment is applied with corresponding prestress to ensure that the first optical fiber segment is always in a stretched state during the monitoring process;

[0018] Step S3, connecting one end of the sensing optical fiber to a strain measurement and analysis system, and performing a press test on both ends of each first optical fiber segment to calibrate the position of each first optical fiber segment;

[0019] Step S4, the strain measurement and analysis system determines the strain amount at each measuring point on the first optical fiber segment according to the scattered signal transmitted back by each first optical fiber segment and the calibrated positions of both ends of the first optical fiber segment; reconstructs the two-dimensional strain field of the first optical fiber segment according to the strain amount at each measuring point on the first optical fiber segment; and obtains the three-dimensional strain field of the anode plate composed of the two-dimensional strain fields of the first optical fiber segments according to the layout relationship between the first optical fiber segments.

[0020] In another optional implementation, the anode plate, the isolation layer and the cathode plate are sequentially arranged on the protective shell from top to bottom.

[0021] In another optional implementation, the second optical fiber segment is laid on the protective shell under the anode plate, and in the step S4, before reconstructing the two-dimensional strain field of the first optical fiber segment according to the strain amount at each measurement point on the first optical fiber segment, it also includes:

[0022] The strain measurement and analysis system determines the strain of each second optical fiber segment based on the scattered signal transmitted back by each second optical fiber segment and the calibrated two end positions of the first optical fiber segment; determines the corresponding temperature of the second optical fiber segment based on the strain of the second optical fiber segment; adds the temperatures of each second optical fiber segment and takes an average value to obtain the average temperature of the battery; converts the average temperature into the corresponding strain; and subtracts the strain corresponding to the average temperature from the strain at each measuring point on the first optical fiber segment.

[0023] In another optional implementation, each second optical fiber segment completely covers the protective shell on the corresponding side in the second direction, and the lengths of the second optical fiber segments are equal.

[0024] The beneficial effects of the present invention are:

[0025] 1. The present invention is based on the characteristic that different strains exist at different positions on the anode plate at the same time during the battery charging and discharging process. Only by measuring the strains at different positions on the anode plate separately can sufficient data be obtained to establish a network model. Since there is a strict correspondence between the strain change process and the battery charging and discharging process, the strain reflects the chemical reaction process inside the battery to a certain extent. Therefore, the present invention associates the strain, strain rate and charge state of the battery to construct a corresponding network model, which can ensure the accuracy of the prediction of the current charge state of the battery. In addition, the network model inputs the strain and strain rate at different positions on the anode plate at the same time, which can reflect the overall strain of the anode plate. and strain rate, so as to more comprehensively reflect the current charge state of the battery and further improve the prediction accuracy of the current charge state of the battery; the present invention associates the maximum strain and residual strain on the anode plate in the cycle with the health state of the battery and constructs a corresponding network model, which can ensure the prediction accuracy of the current health state of the battery. In addition, the network model inputs the maximum strain and residual strain on the anode plate in each cycle so far, and considers the historical data during the use of the battery, which can further improve the prediction accuracy of the current health state of the battery; the present invention can perform distributed high-precision and comprehensive prediction of the operating state of the battery anode plate without relying on electrochemical testing technology;

[0026] 2. When constructing a feedforward neural network, the present invention takes into account different stages in the use of the battery, the charging and discharging process of the battery at different stages, and all strain amounts and strain rates at different positions on the anode plate at different stages and in corresponding charging or discharging states of the battery. Therefore, based on the optimal parameter set obtained during the construction process, the feedforward neural network can comprehensively and accurately predict the current charge state of the battery during the entire use of the battery and any charging or discharging state during the use of the battery;

[0027] 3. The present invention covers the anode plate of the battery with the sensing optical fiber in a first direction and in a second direction perpendicular to the first direction, so that the strain of the entire anode plate can be monitored; when the first optical fiber segment is arranged directly above the anode plate, the two ends of the first optical fiber segment are respectively fixed on the protective shell under the anode plate, and prestress is applied to the first optical fiber segment, so that the first optical fiber segment is always kept in a stretched state during the monitoring process, so that the first optical fiber segment can accurately detect the deformation of the anode plate during the monitoring process; the present invention can realize the three-dimensional strain field reconstruction of the anode plate according to the calibrated two-end positions of each first optical fiber segment, the scattered signals transmitted back by each first optical fiber segment, and the arrangement relationship between each first optical fiber segment; the present invention implants the sensing optical fiber into the battery, which will not affect the battery performance while realizing stress monitoring; and the present invention adopts distributed monitoring, which can obtain the strain field of the entire surface of the lithium battery anode material instead of the strain information of a single point position compared with a single-point sensor, and has higher reliability; the present invention constructs a network model based on the reconstructed three-dimensional strain field of the anode plate, which can further improve the construction accuracy;

[0028] 4. The present invention uses the sum of the strains of all the measuring points on the second optical fiber segment as the strain of the second optical fiber segment, and determines the corresponding temperature of the second optical fiber segment by establishing the relationship between the strain of the second optical fiber segment and the temperature. Since the strain of the second optical fiber segment is large, the accuracy of reflecting its temperature based on the strain of the second optical fiber segment is higher; after determining the temperature of each second optical fiber segment, the temperature of each second optical fiber segment is added and then divided by the number of second optical fiber segments to obtain the average temperature of the battery. The accuracy of the average battery temperature obtained in this way is also higher; the present invention subtracts the strain caused by the average temperature of the battery from the strain detected on the first optical fiber segment, so as to obtain the accurate deformation of the anode plate on the first optical fiber segment. Strain, thereby improving the accuracy of reconstruction of the three-dimensional strain field of the anode plate; when eliminating the influence of the temperature corresponding variable measurement, the present invention establishes two types of corresponding relationships related to temperature. One type of temperature relationship is to associate the total strain of the second optical fiber segment and the temperature of the area where the second optical fiber segment is located on the protective shells on both sides under the anode plate, and the other type of temperature relationship is to associate the average temperature of the protective shells on both sides under the anode plate and the strain of the first optical fiber segment on the anode plate caused by the average temperature. Both of these relationships are to establish the relationship between the optical fiber and the protective shell temperature. The relationship establishment is simple, and when a parameter in one of the relationships changes, only the relationship needs to be adjusted without having to re-establish the entire relationship. Therefore, the flexibility of temperature elimination is higher;

[0029] 5. The present invention enables each second optical fiber segment to completely cover the protective shell on the corresponding side in the second direction. Since the contact length between the second optical fiber segment and the protective shell is longer, it is easier for the heat to quickly reach thermal equilibrium, thereby reducing the difference in the impact of temperature on the first optical fiber segment and the second optical fiber segment. The present invention enables the lengths of each second optical fiber segment to be equal, so that a unified standard can be used to determine the corresponding temperature of the second optical fiber segment based on the relationship between the strain of the second optical fiber segment and the temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flow chart of an embodiment of a method for predicting a battery health state of the present invention;

[0031] Figure 2 It is a schematic diagram of the structure of an embodiment of a feedforward neural network for predicting the battery charge state of the present invention;

[0032] Figure 3 It is a schematic diagram of the structure of an embodiment of a long short-term memory network for predicting the health status of a battery according to the present invention;

[0033] Figure 4 It is a layout diagram of the sensing optical fiber of the present invention;

[0034] Figure 5 is a cross-sectional view of the arrangement of the sensing optical fiber of the present invention;

[0035] Figure 6 It is a schematic diagram of the reconstruction of the three-dimensional strain field of the anode plate of the present invention. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention and to make the above-mentioned purposes, features and advantages of the embodiments of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings.

[0037] In the description of the present invention, unless otherwise specified and limited, it should be noted that the term "connection" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the internal connection between two elements. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0038] See also Figure 1 , is a flow chart of an embodiment of the battery health status prediction method of the present invention. Figure 2 and Figure 3 As shown, the method may include:

[0039] Step S100, during the battery charging and discharging process, the degree of contraction or expansion at different positions on the anode plate of the battery at the same time is different, and correspondingly, the amount of strain at different positions on the anode plate at the same time is different. Based on this characteristic, a network model is constructed according to the amount of strain at different positions on the anode plate.

[0040] In this embodiment, the battery can be a lithium battery. Under normal circumstances (except for the occurrence of dead lithium, etc.), the change process of the anode plate strain has a strict corresponding relationship with the charging and discharging process of the battery. When the battery is charged, the strain at each position on the anode plate will decrease, but the degree of strain reduction at different positions at the same time may be different. When the battery is discharged, the strain at each position on the anode plate will increase, and similarly, the degree of strain increase at different positions at the same time may also be different. The present invention is based on this feature. By measuring the strain at different positions on the anode plate separately, sufficient data can be obtained to establish a corresponding network model.

[0041] The network model constructed by the present invention may include a feedforward neural network and a long short-term memory network, wherein Figure 2 As shown, the feedforward neural network may include an input layer, a hidden layer, and an output layer connected in sequence, the input of the input layer being the strain and strain rate at different positions on the anode plate at the same time, and the output of the output layer being the current charge state of the battery. The strain rate may be the strain difference per unit time at the corresponding position on the anode plate (for example, the strain difference between the corresponding position on the anode plate at the current moment and the previous moment). The output layer may be the output of the output layer being the current charge state of the battery as a whole or the current charge state at different corresponding positions on the battery.

[0042] In step S100, the feedforward neural network can be constructed according to the following steps:

[0043] The charge and discharge process of the battery during use is taken as a corresponding cycle (each charging process can be taken as a cycle, and each discharging process can be taken as a cycle), and all the strains and strain velocities at different positions on the anode plate in different cycles are taken as training sets, which are input into the feedforward neural network for pre-training;

[0044] The predicted charge state of the battery output by the output layer is compared with the actual charge state of the battery, and the various parameters in the feedforward neural network are adjusted according to the comparison result to obtain the optimal parameter set; the parameter set includes the number of hidden layers, the number of neurons in each hidden layer, the weight of each input quantity in the input layer to each neuron in the first hidden layer, the weight of each neuron in each hidden layer to each neuron in the next hidden layer, and the weight of each neuron in the last hidden layer to each output quantity in the output layer. In one example, the hidden layer can be only two layers, each hidden layer includes 16 neurons, and the number of layers and the number of neurons in the hidden layer can also be adjusted according to actual conditions.

[0045] The present invention takes into account the different stages in the use of the battery, the charging and discharging process of the battery at different stages, and all strain quantities and strain rates at different positions on the anode plate at different stages and when the battery is in the corresponding charging or discharging state when constructing the feedforward neural network. Therefore, based on the optimal parameter set obtained during the construction process, the feedforward neural network can comprehensively and accurately predict the current charge state of the battery during the entire use process of the battery and in any charging or discharging state during the use of the battery.

[0046] In addition, if Figure 3 As shown, the long short-term memory network includes an input layer connected in sequence, a long short-term memory network layer with time correlation (i.e., LSTM layer), a fully connected layer, and an output layer. The input of the input layer is the maximum strain and residual strain on the anode plate in each cycle so far, and the output of the output layer is the current health state of the battery. The cycle period can be the time period corresponding to each charging or discharging process during the use of the battery. The output layer in the long short-term memory network outputs a time series signal without periodic changes, and the current health state of the battery can be the current maximum capacity of the battery divided by the initial capacity of the battery.

[0047] In this embodiment, the maximum strain of each cycle is related to the active material of the battery. The active material is consumed less as the battery is recycled, resulting in a decrease in the maximum strain. Correspondingly, with the reduction of active material, the life of the battery will also be reduced. In addition, as the battery is recycled, the ions cannot be completely precipitated after being embedded in the anode material, which will cause the emergence of dead lithium, further causing the residual strain to accumulate and affect the life of the battery. It can be seen that the present invention associates the maximum strain and residual strain with the health status of the battery, which can ensure the accuracy of determining the health status of the battery.

[0048] Step S200, based on the corresponding network model, according to the strain and strain rate at different positions on the anode plate at the current moment, the current charge state of the battery is predicted, and / or based on the corresponding network model, according to the maximum strain and residual strain on the anode plate in each cycle so far, the health state of the battery is predicted, wherein the strain rate is the difference in strain per unit time at the corresponding position on the anode plate, the maximum strain is the maximum strain on the anode plate measured in the corresponding cycle minus the minimum strain, and the residual strain is the last strain measured on the anode plate in the corresponding cycle minus the first strain.

[0049] It can be seen from the above embodiments that the present invention is based on the characteristic that the strain amounts at different positions on the anode plate at the same time are different during the battery charging and discharging process. Only by separately measuring the strain amounts at different positions on the anode plate can sufficient data be obtained to establish a network model. Since there is a strict correspondence between the strain change process and the battery charging and discharging process, the strain amount reflects the chemical reaction process inside the battery to a certain extent. Therefore, the present invention associates the strain amount, strain rate and charge state of the battery to construct a corresponding network model, which can ensure the accuracy of the prediction of the current charge state of the battery. In addition, the network model inputs the strain amount and strain rate at different positions on the anode plate at the same time, which can reflect the overall charge state of the anode plate. The volume strain and strain rate can more comprehensively reflect the current charge state of the battery, and further improve the prediction accuracy of the current charge state of the battery; the present invention associates the maximum strain and residual strain on the anode plate in the cycle period with the health state of the battery, and constructs a corresponding network model, which can ensure the prediction accuracy of the current health state of the battery. In addition, the network model inputs the maximum strain and residual strain on the anode plate in each cycle period so far, and considers the historical data during the use of the battery, which can further improve the prediction accuracy of the current health state of the battery; the present invention can perform distributed high-precision and comprehensive prediction of the operating state of the battery anode plate without relying on electrochemical testing technology.

[0050] The above embodiments involve four parameters: strain, strain rate, maximum strain, and residual strain. When the strain on the anode plate is measured using a sensing optical fiber, the measured strain is not only affected by the contraction or expansion of the anode plate, but also by the heat emitted by the anode plate. Although the strain rate, maximum strain, and residual strain are all two strains subtracted from each other, different contractions or expansions correspond to different temperatures, and subtracting two strains with different values ​​cannot eliminate the influence of temperature. For this reason, the present invention designs a method for laying the sensing optical fiber on the anode plate. Figures 4 to 6 As shown, the present invention measures the strain at different positions on the anode plate according to the following steps:

[0051] Step S1, cover the upper surface of the anode plate 2 of the battery with the sensing optical fiber in a serpentine manner in the first direction, and each time the sensing optical fiber 1 bends and runs along the second direction is the first optical fiber segment 11, and each adjacent two first optical fiber segments 11 are connected by the corresponding second optical fiber segment 12, and the first direction is perpendicular to the second direction.

[0052] In this embodiment, the first direction can be the length direction of the anode plate 2, and the second direction can be the width direction of the anode plate 2. The sensing optical fiber is composed of a plurality of first optical fiber segments 11 parallel to the second direction and arranged at intervals, and a plurality of second optical fiber segments 12 for connecting each adjacent first optical fiber segment. The first optical fiber segment 12 completely covers the anode plate in the second direction (i.e., the width direction of the anode plate), and the layout interval of the mutually parallel second optical fiber segments 12 is greater than 1 mm. The second optical fiber segments 12 are located on both sides of the anode plate 2, and the second optical fiber segments 12 on both sides can be staggered. The sensing optical fiber can be packaged in the protective shell of the battery along with the anode plate 2. The sensing optical fiber should have a high temperature resistant coating layer, such as a polyimide coating, a gold coating, etc., to ensure that the optical fiber to be tested will not break when the battery is packaged. When the battery is charged and discharged, the ions in the battery will precipitate (such as lithium ions in a lithium battery), and the anode plate 2 will undergo a chemical reaction, causing the anode plate to shrink or expand, so that the first optical fiber segment covering the anode plate is compressed or stretched in the axial direction of the optical fiber, generating an axial strain of the optical fiber.

[0053] Step S2, for each first optical fiber segment 11, the two ends 13 of the first optical fiber segment 11 located outside the anode plate 2 are respectively fixed to the protective shell 3 under the anode plate 2 (fixing can be carried out using ear glue, etc.), so that the first optical fiber segment 11 is applied with corresponding prestress to ensure that the first optical fiber segment 11 always remains in a stretched state during the monitoring process.

[0054] In this embodiment, combined with Figure 5 As shown, the protective shell 3 is provided with the anode plate 2, the isolation layer 4 and the cathode plate 5 in order from top to bottom, and another protective shell may be provided on the anode plate 2. The battery may be a lithium battery, and the protective shell 3 may be an aluminum plastic shell for packaging the battery and ensuring that the electrolyte does not leak out; the cathode plate 5 may be a lithium electrode; the isolation layer may be a piece of diaphragm paper, firstly to ensure that the anode and cathode materials are separated and do not react, and secondly to ensure that the anode strain of the lithium battery is not interfered by the cathode; the anode plate 3 may be replaced with various materials, such as a mixed electrode of silicon dioxide (SiO) and graphite (C).

[0055] Step S3 , connecting one end of the sensing optical fiber to a strain measurement and analysis system, and performing a press test on both ends 13 of each first optical fiber segment 11 to calibrate the position of each first optical fiber segment 11 .

[0056] Step S4, the strain measurement and analysis system can determine the strain at each measuring point on the first optical fiber segment 11 according to the scattered signal transmitted back by each first optical fiber segment 11 and the calibrated two-end positions of the first optical fiber segment 11; reconstruct the two-dimensional strain field of the first optical fiber segment 11 according to the strain at each measuring point on the first optical fiber segment 11; obtain the three-dimensional strain field of the anode plate 2 composed of the two-dimensional strain fields of each first optical fiber segment according to the layout relationship between the first optical fiber segments 11. In this embodiment, the strain measurement and analysis system may include an OFDR system (such as a phase-type optical frequency domain reflectometer φ-OFDR) and a data processing device, wherein the OFDR system detects the axial strain generated on the sensing optical fiber according to the scattered signal transmitted back by the sensing optical fiber, and the data processing unit reconstructs the three-dimensional strain field of the battery according to the detected strain, so as to realize the distributed in-situ monitoring of the anode plate in the battery.

[0057] The present invention covers the anode plate of the battery with a sensing optical fiber in a first direction and in a second direction perpendicular to the first direction, so that the strain of the entire anode plate can be monitored; when arranging the first optical fiber segment located directly above the anode plate, the two ends of the first optical fiber segment are respectively fixed on the protective shell under the anode plate, and prestress is applied to the first optical fiber segment, so that the first optical fiber segment is always kept in a stretched state during the monitoring process, so that the first optical fiber segment can accurately detect the deformation of the anode plate during the monitoring process; the present invention can realize the three-dimensional strain field reconstruction of the anode plate according to the calibrated two-end positions of each first optical fiber segment, the scattered signals transmitted back by each first optical fiber segment, and the arrangement relationship between each first optical fiber segment; the present invention implants the sensing optical fiber into the battery, which will not affect the battery performance while realizing stress monitoring; and the present invention adopts distributed monitoring, which can obtain the strain field of the entire surface of the lithium battery anode material instead of the strain information of a single point position compared with a single-point sensor, and has higher reliability; the present invention constructs a network model based on the reconstructed three-dimensional strain field of the anode plate, which can further improve the construction accuracy.

[0058] During the battery charging and discharging process, the anode plate undergoes chemical reactions, which not only deforms the anode plate but also generates a certain amount of heat. Therefore, the first optical fiber segment 11 in the sensing optical fiber will not only be strained due to the deformation of the anode plate, but also strained due to the temperature. In order to eliminate the interference of temperature, the second optical fiber segment can be laid on the protective shell under the anode plate. In the step S4, before reconstructing the two-dimensional strain field of the first optical fiber segment according to the strain at each measurement point on the first optical fiber segment, it can also include:

[0059] The strain measurement and analysis system determines the strain of each second optical fiber segment based on the scattered signal transmitted back by each second optical fiber segment and the calibrated two end positions of the first optical fiber segment; determines the corresponding temperature of the second optical fiber segment based on the strain of the second optical fiber segment; adds the temperatures of each second optical fiber segment and takes an average value to obtain the average temperature of the battery; converts the average temperature into the corresponding strain; and subtracts the strain corresponding to the average temperature from the strain at each measuring point on the first optical fiber segment.

[0060] The strain of the sensing fiber affected by temperature is usually small. If, when determining the average temperature of the battery, the strain at each measuring point on all the second optical fiber segments is added and then divided by the number of all measuring points to obtain the average strain, and the average temperature is determined by establishing a relationship between the average strain and the average temperature, then due to the small average strain, the accuracy of reflecting the average temperature based on the average strain is not high. However, the present invention uses the sum of the strains of all measuring points on the second optical fiber segment as the strain of the second optical fiber segment, and determines the corresponding temperature of the second optical fiber segment by establishing a relationship between the strain of the second optical fiber segment and the temperature. Since the strain of the second optical fiber segment is large, the accuracy of reflecting its temperature based on the strain of the second optical fiber segment is high; after determining the temperature of each second optical fiber segment, the temperature of each second optical fiber segment is added and then divided by the number of second optical fiber segments to obtain the average temperature of the battery, and the accuracy of the average temperature of the battery obtained in this way is also high; the present invention subtracts the strain caused by the average temperature of the battery from the strain detected on the first optical fiber segment, and can obtain the accurate strain caused by the deformation of the anode plate on the first optical fiber segment, thereby improving the accuracy of the reconstruction of the three-dimensional strain field of the anode plate. In addition, when eliminating the influence of temperature corresponding variable measurement, the present invention establishes two types of corresponding relationships related to temperature. One type of temperature relationship is to associate the total strain of the second optical fiber segment and the temperature of the area where the second optical fiber segment is located on the protective shell on both sides under the anode plate. The other type of temperature relationship is to associate the average temperature of the protective shell on both sides under the anode plate and the strain of the first optical fiber segment on the anode plate caused by the average temperature. Both of these relationships establish the relationship between the optical fiber and the temperature of the protective shell. The relationship is simple to establish, and when a parameter in one of the relationships changes (for example, the coverage of the corresponding area on the protective shell by the second optical fiber segment, etc.), only the relationship needs to be adjusted without having to re-establish the entire relationship. Therefore, the temperature elimination has higher flexibility.

[0061] Among them, since the anode plate generates heat during the battery charging and discharging process, the heat can be transferred from the anode plate to the first sensing optical fiber segment and then to the second optical fiber segment. On the other hand, the heat can be transferred to the protective shell through the isolation layer and the cathode layer in sequence for heat dissipation. Since the second optical fiber segment is laid on the protective shell, the heat dissipation forms a closed-loop path, and the temperature has little effect on the first optical fiber segment and its corresponding second optical fiber segment. The present invention can also make each second optical fiber segment 12 completely cover the protective shell 3 on the corresponding side in the second direction. Since the contact length between the second optical fiber segment and the protective shell is longer, it is easier for the heat to quickly reach thermal equilibrium, reducing the difference in the effect of temperature on the first optical fiber segment and the second optical fiber segment. The lengths of each second optical fiber segment 12 of the present invention can also be equal, and the shapes of each second optical fiber segment can also be the same. In this way, a unified standard can be adopted to determine the corresponding temperature of the second optical fiber segment based on the relationship between the strain of the second optical fiber segment and the temperature.

[0062] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0063] It will be appreciated that the invention is not limited to the precise construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from its scope. The scope of the invention is governed solely by the appended claims.

Claims

1. A method for predicting battery health status, characterized in that: include: Step S100, during the battery charging and discharging process, the shrinkage or expansion degree at different positions of the anode plate of the battery at the same time is different, and correspondingly, the strain amount at different positions of the anode plate at the same time is different. Based on this characteristic, a network model is constructed according to the strain amount at different positions of the anode plate; Step S200, based on the corresponding network model, according to the strain and strain rate at different positions on the anode plate at the current moment, the current charge state of the battery is predicted, and / or based on the corresponding network model, according to the maximum strain and residual strain on the anode plate in each cycle so far, the health state of the battery is predicted, wherein the strain rate is the difference in strain per unit time at the corresponding position on the anode plate, the maximum strain is the maximum strain on the anode plate measured in the corresponding cycle minus the minimum strain, and the residual strain is the last strain measured on the anode plate in the corresponding cycle minus the first strain.

2. The battery health status prediction method according to claim 1, characterized in that: The step S100 specifically includes: constructing a feedforward neural network, wherein the feedforward neural network includes an input layer, a hidden layer and an output layer connected in sequence, the input of the input layer is the strain and strain rate at different positions on the anode plate at the same time, and the output of the output layer is the current charge state of the battery; The step S200 specifically includes: based on the feedforward neural network, according to the strain amount and strain rate at different positions on the anode plate at the current moment, predicting the current charge state of the battery.

3. The battery health status prediction method according to claim 2, characterized in that: In step S100, the feedforward neural network is constructed according to the following steps: The charging or discharging process of the battery during use is respectively regarded as a cycle, and all strain amounts and strain velocities at different positions on the anode plate in different cycles are regarded as training sets, which are input into the feedforward neural network for pre-training; The predicted charge state of the battery output by the output layer is compared with the actual charge state of the battery, and the various parameters in the feedforward neural network are adjusted according to the comparison result to obtain the optimal parameter set; the parameter set includes the number of hidden layers, the number of neurons in each hidden layer, the weight of each input quantity in the input layer to each neuron in the first hidden layer, the weight of each neuron in each hidden layer to each neuron in the next hidden layer, and the weight of each neuron in the last hidden layer to each output quantity in the output layer.

4. The battery health status prediction method according to claim 2 or 3, characterized in that: The output of the output layer is the current charge state of the battery as a whole or the current charge state at different corresponding positions on the battery.

5. The battery health status prediction method according to claim 1, characterized in that: The step S100 specifically includes: constructing a long short-term memory network, wherein the long short-term memory network includes an input layer, a long short-term memory network layer, a fully connected layer and an output layer connected in sequence, the input of the input layer is the maximum strain and residual strain on the anode plate in each cycle so far, and the output of the output layer is the current health state of the battery; The step S200 specifically includes: based on the long short-term memory network, according to the maximum strain and residual strain on the anode plate in the current cycle, predicting the health status of the battery.

6. The battery health status prediction method according to claim 5, characterized in that: The cycle period is the time period corresponding to each charging or discharging process during the use of the battery; the output layer in the long short-term memory network outputs a timing signal without periodic changes, and the current health state of the battery is the current maximum capacity of the battery divided by the initial capacity of the battery.

7. The battery health status prediction method according to claim 1, characterized in that: Follow the steps below to measure the strain at different locations on the anode plate: Step S1, the sensing optical fiber is arranged to cover the upper surface of the anode plate of the battery in a serpentine manner in a first direction, the first optical fiber segment is arranged along the second direction after each bending of the sensing optical fiber, and each two adjacent first optical fiber segments are connected by a corresponding second optical fiber segment, and the first direction is perpendicular to the second direction; Step S2: for each first optical fiber segment, two ends of the first optical fiber segment outside the anode plate are respectively fixed to the protective shell under the anode plate, so that the first optical fiber segment is applied with corresponding prestress to ensure that the first optical fiber segment is always in a stretched state during the monitoring process; Step S3, connecting one end of the sensing optical fiber to a strain measurement and analysis system, and performing a press test on both ends of each first optical fiber segment to calibrate the position of each first optical fiber segment; Step S4, the strain measurement and analysis system determines the strain amount at each measuring point on the first optical fiber segment according to the scattered signal transmitted back by each first optical fiber segment and the calibrated positions of both ends of the first optical fiber segment; reconstructs the two-dimensional strain field of the first optical fiber segment according to the strain amount at each measuring point on the first optical fiber segment; and obtains the three-dimensional strain field of the anode plate composed of the two-dimensional strain fields of the first optical fiber segments according to the layout relationship between the first optical fiber segments.

8. The battery health status prediction method according to claim 7, characterized in that: The anode plate, the isolation layer and the cathode plate are arranged on the protective shell in sequence from top to bottom.

9. The battery health status prediction method according to claim 7 or 8, characterized in that: The second optical fiber segment is laid on the protective shell under the anode plate. In the step S4, before reconstructing the two-dimensional strain field of the first optical fiber segment according to the strain amount at each measuring point on the first optical fiber segment, the step further includes: The strain measurement and analysis system determines the strain of each second optical fiber segment based on the scattered signal transmitted back by each second optical fiber segment and the calibrated two end positions of the first optical fiber segment; determines the corresponding temperature of the second optical fiber segment based on the strain of the second optical fiber segment; adds the temperatures of each second optical fiber segment and takes an average value to obtain the average temperature of the battery; converts the average temperature into the corresponding strain; and subtracts the strain corresponding to the average temperature from the strain at each measuring point on the first optical fiber segment.

10. The battery health status prediction method according to claim 9, characterized in that: Each second optical fiber segment completely covers the protective shell on the corresponding side in the second direction, and the lengths of the second optical fiber segments are equal.

Images