A battery module with explosion prevention and life prediction and control method

Abstract

The present invention discloses a battery module with anti-explosion and life prediction and a control method. The battery module includes a plurality of battery assemblies arranged in parallel, each battery assembly includes a plurality of battery bodies arranged in parallel; a plurality of aluminum bars fixedly arranged on adjacent battery bodies; a plurality of battery collectors welded on corresponding aluminum bars; a plurality of expansion force communication sensors respectively attached to corresponding battery assemblies; a battery intelligent controller electrically connected to the plurality of battery collectors and the plurality of expansion force communication sensors; a water-cooling plate closely connected to the plurality of battery assemblies; and a shell fixedly connected to the water-cooling plate. The present invention largely solves the problem of how to perform anti-explosion and life prediction for existing battery modules through the mutual cooperation of a battery remaining life prediction intelligent deep learning module and an expansion force intelligent deep learning module.

Description

Technical Field

[0001] The present invention relates to the field of energy storage technology, and in particular to a battery module with explosion prevention and life prediction functions and a control method. Background Art

[0002] During high-rate or multi-cycle charge and discharge processes, the surface of the battery will swell. The bracket of the battery module is prone to bursting under the huge battery expansion force, causing the battery shell to swell and leak or even explode, which poses a fatal blow to the safety of the energy storage industry. How to control and eliminate the hazards caused by the battery expansion force during the charge and discharge process has become another technical problem in the energy storage industry. How to better monitor the expansion process of the battery module and predict the time life of the battery module expansion limit is the key point to solve the existing technology. Therefore, a battery module with explosion-proof and life prediction and a control method are provided to solve the problem of how to prevent explosion and predict life of the existing battery module. Summary of the invention

[0003] One of the purposes of the present invention is to provide a battery module with explosion prevention and life prediction and a control method, so as to solve the problem of how to perform explosion prevention and life prediction for existing battery modules.

[0004] The battery module and control method with anti-explosion and life prediction of the present invention can be realized by the following technical solutions:

[0005] The present invention provides a battery module with explosion prevention and life prediction, including a plurality of battery assemblies, which are arranged in parallel, and a safety gap is arranged between two adjacent battery assemblies; each of the battery assemblies includes a plurality of battery bodies arranged in parallel; a plurality of aluminum bars, which are respectively fixedly arranged on adjacent battery bodies; a plurality of battery collectors, which are respectively welded on the corresponding aluminum bars, and the battery collectors can collect the temperature, current, voltage and internal resistance parameters of the corresponding battery bodies in real time through the aluminum bars; a plurality of expansion force communication sensors, which are respectively closely attached to the corresponding battery assemblies, and the expansion force communication sensors can collect the expansion force of the corresponding battery assemblies in real time; a battery intelligent controller, which is respectively electrically connected to the plurality of battery collectors and the plurality of expansion force communication sensors; a water cooling plate, which is respectively in close contact with the plurality of battery assemblies; a shell, which is fixedly connected to the water cooling plate, and the two form a closed hollow cavity;

[0006] Among them, the battery intelligent controller includes a battery remaining life prediction intelligent deep learning module and an expansion force intelligent deep learning module; the battery remaining life prediction intelligent deep learning module selects the function with the best fitting effect based on the temperature, current, voltage, and internal resistance data collected by the battery collector, or performs big data deep learning analysis based on the capacity decay change trend as a battery life empirical model to predict the battery remaining life; the expansion force intelligent deep learning module performs big data deep learning analysis based on the expansion force parameters collected by the expansion force communication sensor to predict the predicted expansion force life of the battery module structure; at the same time, the battery intelligent controller can make priority judgments on the predicted expansion force predicted life of the battery module structure and the remaining battery life.

[0007] In one embodiment, the battery assembly further includes a front end plate and a rear end plate respectively arranged at both ends of the plurality of battery bodies; and at least one steel belt respectively fastening and binding the plurality of battery bodies, the front end plate and the rear end plate.

[0008] In one embodiment, a receiving cavity is provided in the front end plate, and the expansion force communication sensor is provided in the receiving cavity. The expansion force communication sensor can be closely contacted and connected with the adjacent battery body.

[0009] In one embodiment, at least one of the steel bands sequentially fastens and connects the front end plate, the expansion force communication sensor, the multiple battery bodies, and the rear end plate; after the steel band is bundled, the initial expansion force of the expansion force communication sensor is the tension generated after the steel band is bundled, and the increased pressure value monitored by the expansion force communication sensor later is the expansion force between the multiple battery bodies.

[0010] In one embodiment, the battery remaining life prediction intelligent deep learning module includes a model method and a data-driven method.

[0011] In one embodiment, the expansion force intelligent deep learning module summarizes the fitting curve and functional relationship between battery expansion force, time and rate through deep learning of the cyclic charging and discharging process at different charging and discharging rates, and directly calls the expansion force intelligent deep learning module in the battery module to predict the expansion force and life of the battery module structure.

[0012] In one embodiment, the expansion force intelligent deep learning module cycles charge and discharge the battery module at charge and discharge rates of 1CP, 0.75CP, 0.5CP and 0.25CP respectively, until the battery surface expansion force exceeds the battery limit expansion force, which is a complete test data learning process; the expansion force intelligent deep learning module records the historical data of battery expansion force and time, and generates a fitting curve of expansion force and time according to the expansion force data and time of the entire test process of cyclic charge and discharge at different rates.

[0013] In one embodiment, the water cooling plate is made of an aluminum alloy with high thermal conductivity and high strength.

[0014] In one embodiment, the water cooling plate includes an upper flat plate and a lower flow channel plate; the upper flat plate is provided with a water inlet and a water return port, the low-temperature coolant enters from the water inlet, passes through the lower flow channel plate and flows out from the water return port; the upper flat plates are respectively in contact with the bottom of the plurality of battery assemblies, and a heat-conductive interface material is filled between the two.

[0015] The present invention provides a control method with explosion prevention and life prediction, which is applied to any of the above-mentioned battery modules with explosion prevention and life prediction, and comprises the following steps:

[0016] The battery module is powered on, and the initial expansion force of the expansion force communication sensor is defined as F0. The battery collector and the expansion force communication sensor respectively collect the initial values ​​defined by the system, and upload them to the battery intelligent controller for analysis and confirmation. After the battery module temperature T, battery module voltage U, battery module current I, battery module internal resistance R, and real-time battery expansion force F parameters are in a normal initial state, the battery intelligent controller issues a cyclic charge and discharge instruction, and the battery module starts charging and discharging;

[0017] The battery collector and the expansion force communication sensor respectively start the corresponding operation parameter mode of real-time collection, and the battery intelligent controller performs intelligent deep learning on the collected battery module temperature T, battery module voltage U, battery module current I, battery module internal resistance R, and real-time battery expansion force F parameters, and outputs the analysis result of the comparison between the real-time battery expansion force F and the battery surface tolerance limit expansion force F1 and the life time when the real-time battery expansion force F reaches 0.8 times the battery module surface tolerance limit expansion force F1 when the number of charge and discharge cycles is N=5 times, and outputs the predicted value of the predicted life S of the battery module structure expansion force and the value of the remaining life RUL of the battery module, and compares the two;

[0018] When the real-time battery expansion force F collected by the expansion force communication sensor is 0.2F1>F>F0, the battery intelligent controller issues a 1CP rate cyclic charge and discharge instruction, and the battery module is cyclically charged and discharged at a 1CP rate;

[0019] When the real-time battery expansion force F collected by the expansion force communication sensor is 0.5F1>F≥0.2F1, the battery intelligent controller issues a 0.5CP rate cyclic charge and discharge instruction, and the battery module is cyclically charged and discharged at a rate of 0.5CP;

[0020] When the real-time battery expansion force F collected by the expansion force communication sensor is 0.8F1>F≥0.5F1, the battery intelligent controller issues a 0.25CP rate cyclic charge and discharge instruction, and the battery module is cyclically charged and discharged at a rate of 0.25CP;

[0021] When the real-time battery expansion force F collected by the expansion force communication sensor is F1>F≥0.8F1, the battery intelligent controller issues an expansion force life warning instruction, the warning light flashes at a high frequency and emits a buzzer, and the battery module automatically cuts off the power and stops cyclic charging and discharging;

[0022] When the predicted life S of the battery module structure expansion force is less than or equal to the remaining life RUL of the battery module, the predicted life of the battery module is the value of the predicted life S of the battery module structure expansion force;

[0023] When the predicted life S of the battery module structure expansion force is greater than the remaining life RUL of the battery module, the predicted life of the battery module takes the value of the remaining life RUL of the battery module;

[0024] Whenever N=5 times, the battery intelligent controller simultaneously outputs the iteratively updated predicted battery module structural expansion force life Sn and the iteratively updated remaining battery module life RULn;

[0025] When N≠5, the battery intelligent controller performs intelligent deep learning on the accumulated charging and discharging parameters.

[0026] Compared with the prior art, the battery module and control method with explosion prevention and life prediction of the present invention have the following beneficial effects:

[0027] The present invention provides a battery module with anti-explosion and life prediction and a control method. By setting an expansion force communication sensor, the expansion force of the battery can be monitored in real time. Through the learning and analysis of the expansion force intelligent deep learning module, the components of the battery module will not be cracked due to fatigue loss caused by the huge expansion force of the battery. At the same time, the expansion force between batteries can be controlled by the automatic control of the battery expansion force by the expansion force intelligent deep learning module. The charge and discharge rate can be reduced or increased according to the expansion force between batteries. The remaining life of the battery module can be continuously updated by the battery remaining life prediction intelligent deep learning module, so that the user can monitor the remaining life of the battery module in real time. The mutual cooperation of the battery remaining life prediction intelligent deep learning module and the expansion force intelligent deep learning module solves the problem of how to prevent explosion and predict the life of the existing battery module to a large extent. The cycle life of the battery module can be extended to a certain extent, and the battery module has the characteristics of higher safety, low maintenance cost, low failure probability and high operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 It is a side view structural schematic diagram of a battery module with anti-explosion and life prediction functions according to the present invention;

[0030] Figure 2 yes Figure 1 The schematic diagram of the top view of the structure of a battery module with anti-explosion and life prediction function according to the present invention is shown;

[0031] Figure 3 The present invention is a flow chart of a control method with anti-explosion and life prediction.

[0032] Markings in the figure: 11, battery assembly; 111, battery body; 112, front end plate; 113, rear end plate; 114, steel belt; 12, aluminum bar; 13, battery collector; 14, expansion force communication sensor; 15, battery intelligent controller; 16, water cooling plate; 17, shell. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0034] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] See also Figure 1 and Figure 2 As shown, a battery module with explosion prevention and life prediction of the present invention includes multiple battery components 11, multiple aluminum bars 12, multiple battery collectors 13, multiple expansion force communication sensors 14, a battery intelligent controller 15, a water cooling plate 16 and a shell 17; multiple battery components 11 are arranged in parallel, and a safety gap is arranged between two adjacent battery components 11, and each battery component 11 includes multiple battery bodies 111 arranged in parallel; multiple aluminum bars 12 are respectively fixedly arranged on adjacent battery bodies 111, which connect the electrodes of the adjacent battery bodies 111, and the temperature, current, voltage and internal resistance parameters of the corresponding battery bodies 111 can be collected through the aluminum bars 12; multiple battery collectors 13 are respectively welded on the corresponding aluminum bars 12, and the battery collectors 13 collect the temperature, current, voltage and internal resistance parameters of the corresponding battery bodies 111 through the aluminum bars 12; multiple expansion force communication sensors 14 are respectively closely attached to the corresponding battery components 11, which can collect the relative The expansion force of the corresponding battery assembly 11 is detected, and the collected expansion force data is converted into an electrical signal; the battery intelligent controller 15 is electrically connected to multiple battery collectors 13 and multiple expansion force communication sensors 14 respectively, and analyzes the parameters collected by the battery collector 13 and the expansion force communication sensor 14. After analysis, it can issue charge and discharge start and stop instructions and charge and discharge rate adjustment instructions to the battery module according to the imported control strategy. At the same time, the battery intelligent controller 15 is provided with a deep learning module function, which can accumulate various parameters of the battery module operation in real time for big data analysis and make a law prediction of parameter development; the water-cooling plate 16 is closely connected with the multiple battery assemblies 11 respectively, so as to conduct the heat of the multiple battery assemblies 11 and achieve the purpose of heat dissipation for the multiple battery assemblies 11; the shell 17 is fixedly connected to the water-cooling plate 16, and the two form a closed hollow cavity, thereby wrapping the multiple battery assemblies 11 and the battery intelligent controller 15, thereby improving its safety performance.

[0036] See also Figure 1 and Figure 2 As shown, in this embodiment, the battery assembly 11 also includes a front end plate 112, a rear end plate 113 and at least one steel strip 114; the front end plate 112 and the rear end plate 113 are respectively arranged at the two ends of the plurality of battery bodies 111; at least one steel strip 114 fastens and binds the plurality of battery bodies 111, the front end plate 112 and the rear end plate 113. Specifically, the front end plate 112 is made of a high-strength plate made of alloy steel, and a pressure-resistant insulating coating is sprayed on its surface. The outer dimensions of the front end plate 112 are consistent with the dimensions of the battery body 111 it contacts, and a receiving cavity is provided therein, and the expansion force communication sensor 14 is arranged in the receiving cavity. The depth of the receiving cavity is 0.1 mm less than the thickness of the expansion force communication sensor 14, so that the expansion force communication sensor 14 can be closely contacted and connected with the adjacent battery body 111. One side of the expansion force communication sensor 14 is fixed in the receiving cavity by adhesive; the rear end plate 113 is also made of alloy steel, and a pressure-resistant insulating coating is sprayed on its surface; the material of the steel strip 114 is It is a high-strength and high-toughness polymer with an insulating surface treatment, which has the characteristics of fire resistance and high temperature resistance; the steel belt 114 squeezes and fixes the front end plate 112, the expansion force communication sensor 14, multiple battery bodies 111, and the rear end plate 113 together in sequence, and its endurance is greater than the ultimate expansion force of the battery body 111. After the steel belt 114 completes the bundling, the initial expansion force of the expansion force communication sensor 14 is the tension generated after the steel belt 114 is bundled. Subsequently, due to the surface expansion caused by the charging and discharging of the battery body 111, the tension of the steel belt 114 increases, that is, the increased pressure value monitored by the expansion force communication sensor 14 is the expansion force between the multiple battery bodies 111.

[0037] See also Figure 1 and Figure 2 As shown, in this embodiment, the aluminum bar 12 is made of 6060-O material, the surface of which is smoothed and has great strength and high-precision flatness. The battery collector 13 can directly collect the temperature, current, voltage and internal resistance parameters of the corresponding battery body 111 through the aluminum bar 12; the battery collector 13 is a high-precision and extremely stable micro collector that can simultaneously collect temperature, current, voltage and internal resistance parameters. One end of the battery collector is connected to a signal line, and the various parameters collected are converted into electrical signals through the signal line and transmitted to the battery intelligent controller 15 for analysis and big data deep learning; the expansion force communication sensor 14 is a cube-shaped, thin, large-range and high-precision pressure sensor, and a pressure-resistant insulating layer is sprayed on its surface. The expansion force communication sensor 14 can collect the expansion force of the corresponding battery assembly 11 in real time, and convert the collected expansion force data into electrical signals, and transmit the expansion force signal to the battery intelligent controller 15 through its own pressure transmission signal line for analysis and big data deep learning.

[0038] See also Figure 1 and Figure 2 As shown, in this embodiment, the battery intelligent controller 15 includes a battery remaining life prediction intelligent deep learning module and an expansion force intelligent deep learning module; the battery remaining life prediction intelligent deep learning module performs big data deep learning analysis on the temperature, current, voltage, and internal resistance data collected by the battery collector 13, so as to calculate the comprehensive performance characteristics of the battery according to the various parameters collected, and evaluate and predict the remaining life RUL (Remaining Useful Life) of the battery in combination with historical data; the expansion force intelligent deep learning module performs big data deep learning analysis on the expansion force parameters collected by the expansion force communication sensor 14, and then generates a visual and intuitive curve, and fits the curve of battery expansion force and time through a large amount of historical data analysis in real time, and predicts the predicted life of the battery module structure expansion force; the battery intelligent controller 15 can make priority judgments on the predicted life based on the expansion force of the battery module structure and the remaining life RUL (Remaining Useful Life), and execute the predicted life in whichever method has the shortest predicted life, and can calculate the number of charge and discharge cycles of the battery module.

[0039] Specifically, the intelligent deep learning module for predicting the remaining battery life includes a model method and a data-driven method. The battery empirical degradation model believes that the capacity decay of the battery follows a certain inherent mathematical relationship. It is usually necessary to use different function forms to fit the battery capacity decay trajectory, and select the function with the best fitting effect as the battery life empirical model.

[0040] The functional forms of the battery life empirical model included in the battery remaining life prediction intelligent deep learning module are: single exponential model (Formula (1)), double exponential model (Formula (2)), linear model (Formula (3)), polynomial model (Formula (4)) and Verhulst model (Formula (5));

[0041] ;

[0042] Where: n is the equivalent number of cycles; Cmax is the maximum available capacity at the nth cycle; other parameters are unknown coefficients of the model.

[0043] According to the battery historical capacity data and the selected empirical model, the historical data is fitted to obtain relevant parameters, and the specified capacity failure threshold is substituted into the battery life empirical model to complete the solution and prediction of the battery's remaining life;

[0044] The semi-empirical model established based on the aging mechanism can take into account the impact of different usage conditions on battery aging performance; for the stress factors affecting battery aging, a stress model based on the Arrhenius formula (Equation (6)) and the inverse power law formula (Equation (7)) is established;

[0045] ;

[0046] Where: S(V) is the capacity decay rate; V is the stress factor; A, B, m are the parameters to be fitted; f(V) is the function of V.

[0047] Data-driven method in the intelligent deep learning module for battery remaining life prediction: Based on the changing trend of capacity decay, the development law of time series is used to infer future development trends.

[0048] Specifically, the expansion force intelligent deep learning module pre-learns the test data in a single battery cycle charge and discharge test environment, and the specific steps are as follows:

[0049] The battery module is charged and discharged cyclically at a charge and discharge rate of 1CP until the battery surface expansion force exceeds the battery limit expansion force. This is a complete test data learning process. The expansion force intelligent deep learning module records the historical data of battery expansion force and time, and generates a fitting curve of expansion force and time based on the expansion force data and time of the entire test process of 1CP rate cycle charge and discharge;

[0050] The battery module is charged and discharged cyclically at a charge and discharge rate of 0.75CP until the battery surface expansion force exceeds the battery limit expansion force. This is a complete test data learning process. The expansion force intelligent deep learning module records the historical data of battery expansion force and time, and generates a fitting curve of expansion force and time based on the expansion force data and time of the entire test process of 0.75CP rate cycle charge and discharge;

[0051] The battery module is charged and discharged cyclically at a charge and discharge rate of 0.5CP until the battery surface expansion force exceeds the battery limit expansion force. This is a complete test data learning process. The expansion force intelligent deep learning module records the historical data of battery expansion force and time, and generates a fitting curve of expansion force and time based on the expansion force data and time of the entire test process of 0.5CP rate cycle charge and discharge;

[0052] The battery module is charged and discharged cyclically at a charge and discharge rate of 0.25CP until the battery surface expansion force exceeds the battery module's limit expansion force, which is a complete test data learning process. The expansion force intelligent deep learning module records the historical data of the battery expansion force and time, and generates a fitting curve of expansion force and time based on the expansion force data and time of the entire test process of 0.25CP rate cycle charge and discharge.

[0053] The intelligent deep learning module for expansion force summarizes the fitting curve and function relationship between battery expansion force, time and rate through deep learning of the above-mentioned cyclic charging and discharging processes at different charging and discharging rates. The module is used in the battery module to directly call the experience and rules of deep learning of the intelligent deep learning module for expansion force to adjust the relationship between battery expansion force, time and charging and discharging rate during the charging and discharging process of the existing battery module, and the time when the expansion force reaches the preset expansion force value, that is, the predicted life of the expansion force of the battery module structure.

[0054] See also Figure 1 and Figure 2 As shown, the water-cooling plate 16 is made of aluminum alloy with high thermal conductivity and high strength, and includes an upper plane plate and a lower flow channel plate. The upper plane plate is provided with a water inlet and a water return port. The low-temperature coolant enters from the water inlet, flows out from the water return port after passing through the lower flow channel plate, and the upper plane plate is in contact with the bottom of the multiple battery assemblies 11 respectively; the interface material for heat conduction is filled between the multiple battery assemblies 11 and the water-cooling plate 16, so that the heat of the multiple battery assemblies 11 can be smoothly transferred to the coolant in the lower flow channel plate, and the heat is taken out by the circulating coolant, so as to achieve the purpose of heat dissipation for the multiple battery assemblies 11. Specifically, the shell 17 adopts a high-strength and tough insulating composite material.

[0055] See also Figure 3 As shown, the control method of the present invention with anti-explosion and life prediction includes the following steps:

[0056] The battery module is powered on, and the initial expansion force of the expansion force communication sensor is defined as F0. The battery collector 13 and the expansion force communication sensor 14 respectively collect the initial values ​​defined by the system, and upload them to the battery intelligent controller 15 to analyze and confirm that the battery module temperature T, battery module voltage U, battery module current I, battery module internal resistance R, and real-time battery expansion force F parameters are in a normal initial state; the battery intelligent controller 15 issues a cyclic charge and discharge instruction, and the battery module starts charging and discharging; the battery collector 13 and the expansion force communication sensor 14 start the real-time collection of the corresponding operating parameter mode, and the battery intelligent controller 15 collects the collected battery module temperature T, battery module voltage U, battery module current I , the battery module internal resistance R, and the real-time battery expansion force F parameters are intelligently learned, and the analysis results are output every N=5 charge and discharge cycles, including the comparison between the real-time battery expansion force F and the battery surface tolerance limit expansion force F1, and the life time when the real-time battery expansion force F reaches 0.8 times the battery module surface tolerance limit expansion force F1. At the same time, the predicted battery module structure expansion force predicted life S value and the battery module remaining life RUL value are output, and the battery module structure expansion force predicted life S value and the battery module remaining life RUL value are compared. The battery module predicted life is the battery module structure expansion force predicted life S value or the battery module remaining life RUL value;

[0057] When the real-time battery expansion force F collected by the expansion force communication sensor 14 is 0.2F1>F>F0, the battery intelligent controller 15 issues a 1CP rate cyclic charge and discharge instruction, and the battery module is cyclically charged and discharged at a 1CP rate;

[0058] When the real-time battery expansion force F collected by the expansion force communication sensor 14 is 0.5F1>F≥0.2F1, the battery intelligent controller 15 issues a 0.5CP rate cycle charge and discharge instruction, and the battery module is cycled charged and discharged at a rate of 0.5CP;

[0059] When the real-time battery expansion force F collected by the expansion force communication sensor 14 is 0.8F1>F≥0.5F1, the battery intelligent controller 15 issues a 0.25CP rate cycle charge and discharge instruction, and the battery module is cycled charged and discharged at a rate of 0.25CP;

[0060] When the real-time battery expansion force F collected by the expansion force communication sensor 14 is F1>F≥0.8F1, the battery intelligent controller 15 issues an expansion force life warning instruction, the warning light flashes at a high frequency and emits a buzzer, and the battery module automatically cuts off the power and stops the cycle charge and discharge;

[0061] When the predicted life S of the battery module structure expansion force is less than or equal to the remaining life RUL of the battery module, the predicted life of the battery module is the value of the predicted life S of the battery module structure expansion force;

[0062] When the predicted life S of the battery module structure expansion force is greater than the remaining life RUL of the battery module, the predicted life of the battery module takes the value of the remaining life RUL of the battery module;

[0063] Whenever N=5 times, the battery intelligent controller 15 simultaneously outputs the iteratively updated expansion force predicted life Sn and the iteratively updated battery module remaining life RULn;

[0064] When N≠5, the battery intelligent controller 15 performs intelligent deep learning on the accumulated charging and discharging parameters.

[0065] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0066] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A battery module with explosion prevention and life prediction, characterized in that: include: A plurality of battery assemblies are arranged in parallel, and a safety gap is provided between two adjacent battery assemblies; each of the battery assemblies comprises a plurality of battery bodies arranged in parallel; A plurality of aluminum bars, which are respectively fixedly disposed on adjacent battery bodies; A plurality of battery collectors, which are respectively welded on the corresponding aluminum bars, and the battery collectors can collect the temperature, current, voltage and internal resistance parameters of the corresponding battery body in real time through the aluminum bars; A plurality of expansion force communication sensors, each of which is closely attached to the corresponding battery assembly, and the expansion force communication sensors can collect the expansion force of the corresponding battery assembly in real time; A battery intelligent controller, which is electrically connected to the plurality of battery collectors and the plurality of expansion force communication sensors respectively; A water cooling plate, which is closely connected with the plurality of battery assemblies respectively; A housing fixedly connected to the water-cooling plate, the two forming a closed hollow cavity; Among them, the battery intelligent controller includes a battery remaining life prediction intelligent deep learning module and an expansion force intelligent deep learning module; the battery remaining life prediction intelligent deep learning module selects the function with the best fitting effect based on the temperature, current, voltage, and internal resistance data collected by the battery collector, or performs big data deep learning analysis based on the capacity decay change trend as a battery life empirical model to predict the battery remaining life; the expansion force intelligent deep learning module performs big data deep learning analysis based on the expansion force parameters collected by the expansion force communication sensor to predict the battery module structure expansion force predicted life; at the same time, the battery intelligent controller can make a priority judgment on the predicted battery module structure expansion force predicted life and the battery remaining life; The expansion force intelligent deep learning module summarizes the fitting curve and functional relationship between battery expansion force and time and rate through deep learning in the process of cyclic charge and discharge at different charge and discharge rates, and directly calls the expansion force intelligent deep learning module in the battery module to predict the expansion force prediction life of the battery module structure; Among them, the battery assembly also includes a front end plate and a rear end plate respectively arranged at both ends of the multiple battery bodies; at least one steel belt is used to fasten and bundle the multiple battery bodies, the front end plate and the rear end plate respectively; at least one steel belt fastens and connects the front end plate, the expansion force communication sensor, the multiple battery bodies and the rear end plate in sequence; after the steel belt completes bundling, the initial expansion force of the expansion force communication sensor is the tension generated after the steel belt is bundled, and the increased pressure value monitored by the expansion force communication sensor later is the expansion force between the multiple battery bodies.

2. A battery module with explosion prevention and life prediction according to claim 1, characterized in that: The front end plate is provided with a receiving cavity, the expansion force communication sensor is arranged in the receiving cavity, and the expansion force communication sensor can be closely contacted and connected with the adjacent battery body.

3. A battery module with explosion prevention and life prediction according to claim 1, characterized in that: The battery remaining life prediction intelligent deep learning module includes a model method and a data-driven method.

4. The battery module with explosion prevention and life prediction according to claim 1, characterized in that: The expansion force intelligent deep learning module cycles charge and discharge the battery module at charge and discharge rates of 1CP, 0.75CP, 0.5CP and 0.25CP respectively, until the battery surface expansion force exceeds the battery limit expansion force, which is a complete test data learning process; the expansion force intelligent deep learning module records the historical data of battery expansion force and time, and generates a fitting curve of expansion force and time according to the expansion force data and time of the entire test process of cyclic charge and discharge at different rates.

5. The battery module with explosion prevention and life prediction according to claim 1, characterized in that: The material used for the water cooling plate is an aluminum alloy with high thermal conductivity and high strength.

6. A battery module with explosion prevention and life prediction according to claim 5, characterized in that: The water cooling plate includes an upper flat plate and a lower flow channel plate; the upper flat plate is provided with a water inlet and a water return port, and the low-temperature coolant enters from the water inlet, passes through the lower flow channel plate and flows out from the water return port; the upper flat plates are respectively in contact with the bottoms of the plurality of battery assemblies, and a heat-conducting interface material is filled between the two.

7. A control method with explosion prevention and life prediction, which is applied to a battery module with explosion prevention and life prediction as claimed in any one of claims 1 to 6, characterized in that: The steps include: The battery module is powered on, and the initial expansion force of the expansion force communication sensor is defined as F0. The battery collector and the expansion force communication sensor respectively collect the initial values ​​defined by the system, and upload them to the battery intelligent controller for analysis and confirmation. After the battery module temperature T, battery module voltage U, battery module current I, battery module internal resistance R, and real-time battery expansion force F parameters are in a normal initial state, the battery intelligent controller issues a cyclic charge and discharge instruction, and the battery module starts charging and discharging; The battery collector and the expansion force communication sensor respectively start the corresponding operation parameter mode of real-time collection, and the battery intelligent controller performs intelligent deep learning on the collected battery module temperature T, battery module voltage U, battery module current I, battery module internal resistance R, and real-time battery expansion force F parameters, and outputs the analysis result of the comparison between the real-time battery expansion force F and the battery surface tolerance limit expansion force F1 and the life time when the real-time battery expansion force F reaches 0.8 times the battery module surface tolerance limit expansion force F1 when the number of charge and discharge cycles is N=5 times, and outputs the predicted value of the predicted life S of the battery module structure expansion force and the value of the remaining life RUL of the battery module, and compares the two; When the real-time battery expansion force F collected by the expansion force communication sensor is 0.2F1>F>F0, the battery intelligent controller issues a 1CP rate cyclic charge and discharge instruction, and the battery module is cyclically charged and discharged at a 1CP rate; When the real-time battery expansion force F collected by the expansion force communication sensor is 0.5F1>F≥0.2F1, the battery intelligent controller issues a 0.5CP rate cyclic charge and discharge instruction, and the battery module is cyclically charged and discharged at a rate of 0.5CP; When the real-time battery expansion force F collected by the expansion force communication sensor is 0.8F1>F≥0.5F1, the battery intelligent controller issues a 0.25CP rate cyclic charge and discharge instruction, and the battery module is cyclically charged and discharged at a rate of 0.25CP; When the real-time battery expansion force F collected by the expansion force communication sensor is F1>F≥0.8F1, the battery intelligent controller issues an expansion force life warning instruction, the warning light flashes at a high frequency and emits a buzzer, and the battery module automatically cuts off the power and stops cyclic charging and discharging; When the predicted life S of the battery module structure expansion force is less than or equal to the remaining life RUL of the battery module, the predicted life of the battery module is the value of the predicted life S of the battery module structure expansion force; When the predicted life S of the battery module structure expansion force is greater than the remaining life RUL of the battery module, the predicted life of the battery module takes the value of the remaining life RUL of the battery module; Whenever N=5 times, the battery intelligent controller simultaneously outputs the iteratively updated predicted battery module structural expansion force life Sn and the iteratively updated remaining battery module life RULn; When N≠5, the battery intelligent controller performs intelligent deep learning on the accumulated charging and discharging parameters.

Images