Thermal management system and method for new energy vehicles based on pressure and temperature sensors

Abstract

The present application relates to the field of intelligent management technology, and specifically discloses a new energy vehicle thermal management system and method based on a pressure temperature sensor, which uses artificial intelligence technology based on deep learning to monitor data and mine time series features of the battery temperature and coolant pressure and flow rate of the new energy vehicle to capture the time series dynamic change information of the battery temperature and coolant state, and then adaptively adjust the coolant flow rate based on the time series response mode between the battery temperature and the coolant state to achieve battery temperature management. In this way, the battery temperature can be controlled more accurately, avoiding unnecessary energy consumption, thereby improving the performance, safety and life of the battery and energy utilization.

Description

Technical Field

[0001] The present application relates to the field of intelligent management technology, and more specifically, to a new energy vehicle thermal management system and method based on a pressure and temperature sensor. Background Art

[0002] As global climate change becomes increasingly severe, reducing carbon emissions has become a global consensus. Against this backdrop, new energy vehicles, especially pure electric vehicles (BEVs), have rapidly emerged due to their zero-emission advantages. As the core component of new energy vehicles, battery temperature management is critical.

[0003] The thermal management system of traditional fuel vehicles mainly focuses on engine cooling and air conditioning systems, while new energy vehicles have added cooling requirements for electrical components such as batteries and motors. In particular, the thermal management of power batteries is more complex. Batteries generate a lot of heat during operation. If it cannot be dissipated in time, it will seriously affect the performance and safety of the battery.

[0004] At present, the thermal management systems of new energy vehicles mostly use traditional cooling methods, such as air cooling and liquid cooling. Although these methods can control the battery temperature to a certain extent, they have many limitations. For example, air cooling efficiency is low and it is difficult to meet the heat dissipation requirements of high-power battery packs. Although liquid cooling efficiency is high, traditional liquid cooling methods often control the coolant based on a preset temperature threshold, which is difficult to adapt to complex and changeable operating environments, lacks intelligence, and easily leads to frequent start and stop of the cooling system, increasing energy consumption, especially when the heat load changes greatly. Therefore, an optimized thermal management solution for new energy vehicles is expected. Summary of the invention

[0005] In order to solve the above technical problems, this application is proposed. The embodiment of the present application provides a new energy vehicle thermal management system and method based on a pressure temperature sensor, which uses artificial intelligence technology based on deep learning to perform data monitoring and time series feature mining on the battery temperature and coolant pressure and flow rate of the new energy vehicle to capture the time series dynamic change information of the battery temperature and coolant state, and then adaptively adjust the flow rate of the coolant based on the time series response mode between the battery temperature and the coolant state to achieve battery temperature management. In this way, the battery temperature can be controlled more accurately, avoiding unnecessary energy consumption, thereby improving the performance, safety and life of the battery and energy utilization.

[0006] Accordingly, according to one aspect of the present application, a new energy vehicle thermal management system based on a pressure and temperature sensor is provided, which includes: a battery temperature monitoring module, used to obtain a time series of battery temperature collected by a temperature sensor; a coolant state monitoring module, used to obtain a time series of coolant pressure values ​​and a time series of coolant flow rate values ​​collected by a pressure sensor and a flow meter; a timing encoding module, used to respectively perform timing encoding on the time series of the battery temperature, the time series of the coolant pressure values ​​and the time series of the coolant flow rate values ​​to obtain a battery temperature timing correlation feature vector, a coolant pressure timing correlation feature vector and a coolant flow rate timing correlation feature vector; a coolant state multimodal fusion module, used to interactively fuse the coolant pressure timing correlation feature vector and the coolant flow rate timing correlation feature vector to obtain a coolant state multimodal joint representation feature vector; a battery temperature management module, used to determine whether the coolant flow rate value should be increased, decreased or remained unchanged based on the correlation response characteristics between the battery temperature timing correlation feature vector and the coolant state multimodal joint representation feature vector.

[0007] In the above-mentioned new energy vehicle thermal management system based on pressure and temperature sensors, the timing encoding module is used to: input the time series of the battery temperature, the time series of the coolant pressure value, and the time series of the coolant flow rate value into a double-branch sequence encoding structure including a 1D-CNN layer and a bidirectional gated recurrent unit to obtain the battery temperature timing-related feature vector, the coolant pressure timing-related feature vector, and the coolant flow rate timing-related feature vector.

[0008] In the above-mentioned new energy vehicle thermal management system based on pressure and temperature sensors, the coolant state multimodal fusion module is used to: input the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector into the feature vector dynamic interactive fusion module based on gated response to obtain the coolant state multimodal joint representation feature vector.

[0009] In the above-mentioned new energy vehicle thermal management system based on pressure and temperature sensors, the coolant state multimodal fusion module includes: a feature cascade unit, which is used to perform feature cascade on the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector to obtain a coolant pressure-flow rate time series joint feature vector; an information fusion threshold calculation unit, which is used to input the coolant pressure-flow rate time series joint feature vector into a gated response function to obtain an information fusion response gate; a weighted fusion unit, which is used to calculate a difference with the information fusion response gate, and use the information fusion response gate and the difference as weights to calculate the position-weighted sum of the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector to obtain the coolant state multimodal joint representation feature vector.

[0010] In the above-mentioned new energy vehicle thermal management system based on pressure and temperature sensors, the information fusion threshold calculation unit is used to: use a predetermined weight vector to multiply the coolant pressure-flow rate time series joint feature vector to obtain the information interaction fusion correlation coefficient; add the information interaction fusion correlation coefficient and the predetermined bias parameter and then activate it through a sigmoid function to obtain the response gate of the information fusion.

[0011] In the above-mentioned new energy vehicle thermal management system based on pressure and temperature sensors, the battery temperature management module includes: a timing interaction response unit, which is used to input the battery temperature timing association feature vector and the coolant state multimodal joint representation feature vector into a prior distribution guided association interaction response module to obtain a battery temperature state-coolant state timing interaction response feature vector; a thermal management result generation unit, which is used to input the battery temperature state-coolant state timing interaction response feature vector into a classifier-based thermal management result generator to obtain a thermal management result, and the thermal management result is used to indicate that the flow rate value of the coolant should increase, decrease or remain unchanged.

[0012] In the above-mentioned new energy vehicle thermal management system based on pressure and temperature sensors, the timing interactive response unit includes: a position-by-position response subunit, which is used to calculate the position-by-position division between the multimodal joint representation feature vector of the coolant state and the battery temperature timing associated feature vector to obtain a battery temperature state-coolant state response feature vector; a Gaussian distribution random number generation subunit, which is used to use a Gaussian distribution random number function to generate a first Gaussian distribution function coefficient and a second Gaussian distribution function coefficient; a prior distribution constraint subunit, which is used to perform a prior distribution constraint on the battery temperature state-coolant state response feature vector based on the first Gaussian distribution function coefficient and the second Gaussian distribution function coefficient to obtain the battery temperature state-coolant state timing interactive response feature vector.

[0013] In the above-mentioned new energy vehicle thermal management system based on pressure temperature sensor, the prior distribution constraint subunit is used to: determine the first weight coefficient and the second weight coefficient of the battery temperature state-coolant state response feature vector, and use the first weight coefficient and the second weight coefficient to weight the battery temperature state-coolant state response feature vector respectively to obtain the first linear transformation battery temperature state-coolant state response feature vector and the second linear transformation battery temperature state-coolant state response feature vector; respectively calculate the first linear transformation battery temperature state-coolant state response feature vector and the second linear transformation battery temperature state- The exponential function values ​​of each eigenvalue of the coolant state response eigenvector with the natural constant as the base are used to obtain the exponential first linear transformation battery temperature state-coolant state response eigenvector and the exponential second linear transformation battery temperature state-coolant state response eigenvector; the product result of multiplying the first Gaussian distribution function coefficient by the exponential first linear transformation battery temperature state-coolant state response eigenvector and the product result of multiplying the second Gaussian distribution function coefficient by the exponential second linear transformation battery temperature state-coolant state response eigenvector are added and summed up corresponding elements to obtain the battery temperature state-coolant state time series interaction response eigenvector.

[0014] According to another aspect of the present application, a thermal management method for new energy vehicles based on a pressure and temperature sensor is provided, which includes: obtaining a time series of battery temperature collected by a temperature sensor; obtaining a time series of coolant pressure values ​​and a time series of coolant flow rate values ​​collected by a pressure sensor and a flow meter; respectively performing time series encoding on the time series of the battery temperature, the time series of the coolant pressure values ​​and the time series of the coolant flow rate values ​​to obtain a battery temperature time series correlation feature vector, a coolant pressure time series correlation feature vector and a coolant flow rate time series correlation feature vector; interactively fusing the coolant pressure time series correlation feature vector and the coolant flow rate time series correlation feature vector to obtain a coolant state multimodal joint representation feature vector; based on the correlation response characteristics between the battery temperature time series correlation feature vector and the coolant state multimodal joint representation feature vector, determining whether the coolant flow rate value should increase, decrease or remain unchanged.

[0015] Compared with the prior art, the thermal management system and method for new energy vehicles based on pressure and temperature sensors provided by the present application uses artificial intelligence technology based on deep learning to monitor data and mine time series features of the battery temperature and coolant pressure and flow rate of new energy vehicles, so as to capture the time series dynamic change information of the battery temperature and coolant state, and then adaptively adjust the flow rate of the coolant based on the time series response mode between the battery temperature and the coolant state to achieve battery temperature management. In this way, the battery temperature can be controlled more accurately, unnecessary energy consumption can be avoided, and the performance, safety and life of the battery as well as energy utilization can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 It is a block diagram of a new energy vehicle thermal management system based on a pressure and temperature sensor according to an embodiment of the present application.

[0018] Figure 2 This is a schematic diagram of the architecture of a new energy vehicle thermal management system based on a pressure and temperature sensor according to an embodiment of the present application.

[0019] Figure 3 It is a block diagram of a multi-modal fusion module of coolant state in a thermal management system of a new energy vehicle based on a pressure and temperature sensor according to an embodiment of the present application.

[0020] Figure 4 The block diagram is a battery temperature management module in a new energy vehicle thermal management system based on a pressure temperature sensor according to an embodiment of the present application.

[0021] Figure 5 It is a block diagram of a timing interactive response unit in a new energy vehicle thermal management system based on a pressure and temperature sensor according to an embodiment of the present application.

[0022] Figure 6 This is a flow chart of a thermal management method for new energy vehicles based on a pressure and temperature sensor according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] Below, the embodiments of the present application will be described in more detail in conjunction with the accompanying drawings, and the above and other purposes, features and advantages of the present application will become more apparent. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.

[0024] As mentioned in the background technology above, traditional liquid cooling methods often control the coolant based on a preset temperature threshold, which is difficult to adapt to complex and changeable operating environments, lacks intelligence, and easily leads to frequent start and stop of the cooling system, increasing energy consumption, especially when the heat load changes greatly. In response to the above technical problems, the technical concept of this application is to use artificial intelligence technology based on deep learning to monitor data and mine time series features of the battery temperature and coolant pressure and flow rate of new energy vehicles to capture the time series dynamic change information of the battery temperature and coolant state, and then adaptively adjust the flow rate of the coolant based on the time series response mode between the battery temperature and the coolant state to achieve battery temperature management. In this way, the battery temperature can be controlled more accurately, avoiding unnecessary energy consumption, thereby improving the performance, safety and life of the battery and energy utilization.

[0025] Figure 1 It is a block diagram of a new energy vehicle thermal management system based on a pressure and temperature sensor according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of the architecture of a new energy vehicle thermal management system based on a pressure and temperature sensor according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to an embodiment of the present application, a new energy vehicle thermal management system 100 based on a pressure temperature sensor includes: a battery temperature monitoring module 110, which is used to obtain a time series of battery temperature collected by a temperature sensor; a coolant state monitoring module 120, which is used to obtain a time series of coolant pressure values ​​and a time series of coolant flow rate values ​​collected by a pressure sensor and a flow meter; a timing encoding module 130, which is used to respectively perform timing encoding on the time series of the battery temperature, the time series of the coolant pressure value, and the time series of the coolant flow rate value to obtain a battery temperature timing correlation feature vector, a coolant pressure timing correlation feature vector, and a coolant flow rate timing correlation feature vector; a coolant state multimodal fusion module 140, which is used to interactively fuse the coolant pressure timing correlation feature vector and the coolant flow rate timing correlation feature vector to obtain a coolant state multimodal joint representation feature vector; a battery temperature management module 150, which is used to determine whether the coolant flow rate value should be increased, decreased, or kept unchanged based on the correlation response characteristics between the battery temperature timing correlation feature vector and the coolant state multimodal joint representation feature vector.

[0026] In the above-mentioned new energy vehicle thermal management system 100 based on pressure and temperature sensor, the battery temperature monitoring module 110 and the coolant state monitoring module 120 are used to obtain the time series of battery temperature collected by the temperature sensor, and the time series of coolant pressure value and coolant flow rate value collected by the pressure sensor and the flow meter. It should be understood that the time series data of battery temperature and coolant pressure and flow rate of new energy vehicles provide the temperature change of the battery during operation and the operating status information of the cooling system. By performing data time series analysis on battery temperature and coolant pressure and flow rate, the response and regulation effect of the cooling system to the battery temperature can be revealed, and then the flow rate of the coolant can be adaptively adjusted based on this response mode to ensure that the battery is always kept within the optimal operating temperature range, realize intelligent thermal management, and thus improve the energy efficiency and safety of new energy vehicles.

[0027] In the above-mentioned new energy vehicle thermal management system 100 based on pressure and temperature sensor, the timing encoding module 130 is used to perform timing encoding on the time series of the battery temperature, the time series of the coolant pressure value and the time series of the coolant flow rate value respectively to obtain the battery temperature timing correlation feature vector, the coolant pressure timing correlation feature vector and the coolant flow rate timing correlation feature vector. In a specific example of the present application, the encoding method for performing timing encoding on the time series of the battery temperature, the time series of the coolant pressure value and the time series of the coolant flow rate value is to input the time series of the battery temperature, the time series of the coolant pressure value and the time series of the coolant flow rate value into a double-branch sequence encoding structure including a 1D-CNN layer and a bidirectional gated recurrent unit respectively to obtain the battery temperature timing correlation feature vector, the coolant pressure timing correlation feature vector and the coolant flow rate timing correlation feature vector. It should be understood that, considering that the battery temperature, coolant pressure and flow rate usually have different physical meanings and different scales of temporal variation characteristics, in order to more fully understand the internal laws of the temporal variation of the three, in the technical solution of the present application, a dual-branch sequence encoding structure including a 1D-CNN layer and a bidirectional gated recurrent unit is used to sequence the three separately. Among them, the 1D-CNN layer can capture the local temporal feature information by performing convolution operations on the time series data; and the bidirectional gated recurrent unit (Bi-GRU) can simultaneously capture the forward and reverse long-term dependencies of the time series data through the gated recurrent units in the forward and backward directions, so as to more comprehensively understand the long-term dynamic change process of the time series data. In other words, the dual-branch structure can extract and fuse the temporal feature representations of the battery temperature, coolant pressure and flow rate at different time scales through the 1D-CNN and Bi-GRU layers, thereby enhancing the feature learning ability of the model and providing a feature basis for subsequent data temporal interaction analysis.

[0028] In the above-mentioned new energy vehicle thermal management system 100 based on pressure and temperature sensors, the coolant state multimodal fusion module 140 is used to interactively fuse the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector to obtain the coolant state multimodal joint representation feature vector. In a specific example of the present application, the encoding method of interactively fusing the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector is to input the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector into the feature vector dynamic interactive fusion module based on gated response to obtain the coolant state multimodal joint representation feature vector. It should be understood that, considering that the pressure and flow rate of the coolant reflect different aspects of the cooling system, such as the pressure bearing capacity and cooling efficiency of the system, in order to more comprehensively understand the working state of the coolant, it is necessary to comprehensively consider the coolant pressure and flow rate information. Based on this, in the technical solution of the present application, a feature vector dynamic interactive fusion module based on gated response is used to interactively fuse the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector. Specifically, the feature vector dynamic interactive fusion module learns the intrinsic correlation and interaction between the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector, and dynamically adjusts the fusion weight of the two based on the gating mechanism to generate a multi-modal joint representation feature vector of the coolant state. Through this interactive fusion method, the mutual influence and synergy between the coolant pressure and flow rate are fully considered, so that the overall operating status of the coolant system can be more comprehensively reflected, providing more accurate and effective data support for subsequent battery temperature management.

[0029] Figure 3 FIG. 1 is a block diagram of a multi-modal fusion module for coolant status in a new energy vehicle thermal management system based on a pressure and temperature sensor according to an embodiment of the present application. Figure 3 As shown, the coolant state multimodal fusion module 140 includes: a feature cascade unit 141, which is used to perform feature cascade on the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector to obtain a coolant pressure-flow rate time series joint feature vector; an information fusion threshold calculation unit 142, which is used to input the coolant pressure-flow rate time series joint feature vector into a gated response function to obtain an information fusion response gate; a weighted fusion unit 143, which is used to calculate a difference with the information fusion response gate, and use the information fusion response gate and the difference as weights to calculate the position-weighted sum of the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector to obtain the coolant state multimodal joint representation feature vector.

[0030] More specifically, the information fusion threshold calculation unit 142 is used to: use a predetermined weight vector to multiply the coolant pressure-flow rate time series joint feature vector to obtain an information interaction fusion correlation coefficient; add the information interaction fusion correlation coefficient and a predetermined bias parameter and then activate it through a sigmoid function to obtain a response gate for the information fusion.

[0031] That is, the coolant state multimodal fusion module 140 is used to: fuse the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector using the following interactive fusion formula to obtain the coolant state multimodal joint representation feature vector, wherein the interactive fusion formula is: ;in, is the coolant pressure time series correlation feature vector, is the coolant flow rate time series correlation feature vector, Indicates cascade operation, is the sigmoid function, is the predetermined weight vector, is the predetermined bias parameter, is the response gate of information fusion, is the multi-modal joint representation feature vector of the coolant state.

[0032] In the above-mentioned new energy vehicle thermal management system 100 based on pressure and temperature sensors, the battery temperature management module 150 is used to determine whether the flow rate value of the coolant should be increased, decreased, or kept unchanged based on the correlation response characteristics between the battery temperature time series correlation feature vector and the coolant state multimodal joint representation feature vector. Figure 4 FIG. 1 is a block diagram of a battery temperature management module in a new energy vehicle thermal management system based on a pressure temperature sensor according to an embodiment of the present application. Figure 4 As shown, the battery temperature management module 150 includes: a timing interaction response unit 151, which is used to input the battery temperature timing association feature vector and the coolant state multimodal joint representation feature vector into a prior distribution guided association interaction response module to obtain a battery temperature state-coolant state timing interaction response feature vector; a thermal management result generation unit 152, which is used to input the battery temperature state-coolant state timing interaction response feature vector into a classifier-based thermal management result generator to obtain a thermal management result, and the thermal management result is used to indicate that the flow rate value of the coolant should increase, decrease or remain unchanged.

[0033] Specifically, the timing interaction response unit 151 is used to input the battery temperature timing association feature vector and the coolant state multimodal joint representation feature vector into the prior distribution guided association interaction response module to obtain the battery temperature state-coolant state timing interaction response feature vector. It should be understood that considering that the temperature change of the battery is directly affected by the coolant state, therefore, in order to more accurately understand the timing interaction response relationship between the battery temperature and the coolant state, so as to make timely adjustments according to the temperature change of the battery, in the technical solution of the present application, the prior distribution guided association interaction response module is used to further analyze the battery temperature timing association feature vector and the coolant state multimodal joint representation feature vector. Specifically, the prior distribution guided associated interactive response module constructs a temporal interactive response model between battery temperature and coolant status based on Gaussian prior distribution, and provides prior knowledge for the temporal interactive response relationship between battery temperature and coolant status by introducing Gaussian prior distribution parameters, so that the model can better capture the temporal dynamic change law and mutual influence mechanism between the two, reveal the temporal dependency and response mode between the two, and thus provide more accurate and effective guidance for subsequent battery temperature management.

[0034] Figure 5 FIG. 1 is a block diagram of a timing interactive response unit in a thermal management system for a new energy vehicle based on a pressure and temperature sensor according to an embodiment of the present application. Figure 5 As shown, the timing interaction response unit 151 includes: a position-by-position response subunit 1511, which is used to calculate the position-by-position division between the coolant state multimodal joint representation feature vector and the battery temperature timing association feature vector to obtain a battery temperature state-coolant state response feature vector; a Gaussian distribution random number generation subunit 1512, which is used to use a Gaussian distribution random number function to generate a first Gaussian distribution function coefficient and a second Gaussian distribution function coefficient; a prior distribution constraint subunit 1513, which is used to perform a prior distribution constraint on the battery temperature state-coolant state response feature vector based on the first Gaussian distribution function coefficient and the second Gaussian distribution function coefficient to obtain the battery temperature state-coolant state timing interaction response feature vector.

[0035] More specifically, the prior distribution constraint subunit 1513 is used to: determine a first weight coefficient and a second weight coefficient of the battery temperature state-coolant state response feature vector, and use the first weight coefficient and the second weight coefficient to weight the battery temperature state-coolant state response feature vector to obtain a first linear transformation battery temperature state-coolant state response feature vector and a second linear transformation battery temperature state-coolant state response feature vector; respectively calculate the first linear transformation battery temperature state-coolant state response feature vector and the second linear transformation battery temperature state-coolant state response feature vector. The exponential function value with natural constant as the base of each eigenvalue of the eigenvector is used to obtain the exponential first linear transformation battery temperature state-coolant state response eigenvector and the exponential second linear transformation battery temperature state-coolant state response eigenvector; the product result of multiplying the first Gaussian distribution function coefficient by the exponential first linear transformation battery temperature state-coolant state response eigenvector and the product result of multiplying the second Gaussian distribution function coefficient by the exponential second linear transformation battery temperature state-coolant state response eigenvector are added and summed up corresponding elements to obtain the battery temperature state-coolant state time series interaction response eigenvector.

[0036] That is, the timing interaction response unit 151 is used to process the battery temperature timing association feature vector and the coolant state multimodal joint representation feature vector using the following association interaction response formula to obtain the battery temperature state-coolant state timing interaction response feature vector, wherein the association interaction response formula is: ;in, is the multi-modal joint representation feature vector of the coolant state, is the battery temperature time series associated feature vector, is the battery temperature state-coolant state time series interaction response feature vector, and denote the first weight coefficient and the second weight coefficient respectively, and They respectively represent the first Gaussian distribution function coefficient and the second Gaussian distribution function coefficient generated by the Gaussian distribution random number function.

[0037] Specifically, the thermal management result generating unit 152 is used to input the battery temperature state-coolant state time series interactive response feature vector into the classifier-based thermal management result generator to obtain a thermal management result, and the thermal management result is used to indicate whether the flow rate value of the coolant should be increased, decreased, or kept unchanged. That is, the trained classifier model is used to make thermal management decisions, and based on the powerful feature learning and classification mapping capabilities of the classifier model, the complex pattern contained in the battery temperature state-coolant state time series interactive response feature vector is identified, and the adjustment direction of the coolant flow rate is determined accordingly, thereby generating a control instruction for the cooling system to ensure that the flow rate of the coolant can be adjusted in real time according to the temperature state of the battery and the working state of the coolant. Through this automated and intelligent decision-making method, not only the efficiency of thermal management of new energy vehicles is improved, but also the stability and safety of the battery during operation are ensured.

[0038] In particular, in the above scheme, the battery temperature time series association feature vector and the coolant state multimodal joint representation feature vector respectively express the one-dimensional local time series association characteristics of the battery temperature and the one-dimensional time series distribution dynamic interaction fusion characteristics of the coolant pressure value-flow rate value. In this way, after the battery temperature time series association feature vector and the coolant state multimodal joint representation feature vector are input into the prior distribution guided association interaction response module, the battery temperature state-coolant state time series interaction response feature vector will also have feature aggregation class representation imbalance due to the difference in prior distribution guided association interaction response weight distribution caused by the mismatch between the time series distribution of the battery temperature time series association feature vector and the coolant state multimodal joint representation feature vector, and after the feature class representation is aggregated through clustering operation, the probability density distribution convergence logic of the in-class features and the out-of-class features will be inconsistent.

[0039] Therefore, in a preferred embodiment of the present application, after clustering the battery temperature state-coolant state timing interaction response feature vector, for example, clustering based on the distance between eigenvalues, further optimizing the in-class features and out-of-class features is performed, specifically including the following steps: determining the number of eigenvalues ​​in the clustering set obtained by the battery temperature state-coolant state timing interaction response feature vector through the clustering operation, that is, the number of in-class features, and subtracting the number of in-class features from the total number of eigenvalues ​​of the battery temperature state-coolant state timing interaction response feature vector to obtain the number of out-of-class features; dividing the total number of eigenvalues ​​by the number of in-class features and the number of out-of-class features respectively to obtain a class importance value and an out-of-class proportion value, and calculating the inverse of the class importance value to obtain a class constraint value; Calculate each eigenvalue of the battery temperature state-coolant state timing interaction response eigenvector as a power function with the class importance value as the exponent, add the eigenvalues ​​with the natural function as the base and the class constraint value as the exponent, and then multiply by the out-of-class proportion value to obtain a battery temperature state-coolant state timing interaction response modulation vector; perform point multiplication on the battery temperature state-coolant state timing interaction response eigenvector and the class importance value to obtain a battery temperature state-coolant state timing interaction response ontology vector; calculate the weighted sum of the battery temperature state-coolant state timing interaction response modulation vector and the battery temperature state-coolant state timing interaction response ontology vector with a weight hyperparameter to obtain an optimized battery temperature state-coolant state timing interaction response eigenvector.

[0040] That is, the battery temperature state-coolant state time series interactive response feature vector is optimized based on the feature distribution of the in-class features and the out-of-class features using the following optimization formula to obtain the optimized battery temperature state-coolant state time series interactive response feature vector, wherein the optimization formula is: ;in, represents the battery temperature state-coolant state time series interaction response feature vector, represents the total number of eigenvalues ​​of the battery temperature state-coolant state time series interaction response eigenvector, represents the number of features within a class, represents the number of out-of-class features, represents the out-of-class proportion value, represents the class importance value, Represents the class constraint value, represents the weight hyperparameter, represents the power function value of calculating each eigenvalue of the battery temperature state-coolant state time series interaction response eigenvector with the class importance value as an exponent, represents dot product, Represents the optimized battery temperature state-coolant state time series interaction response feature vector.

[0041] Here, in the technical solution of the present application, while performing a clustering operation on the battery temperature state-coolant state timing interaction response feature vector, the clustering importance measurement of the feature value of the battery temperature state-coolant state timing interaction response feature vector is combined with the class constraint measurement of the clustering operation to further perform responsive modulation with the out-of-class proportional factor, and based on the clustering scaling of the feature ontology representation of the battery temperature state-coolant state timing interaction response feature vector, the clustering operation is used to establish the simplicity and effectiveness of the overall feature purification of the feature set of the battery temperature state-coolant state timing interaction response feature vector, and the inconsistency of the convergence logic of the probability density distribution caused by the clustering operation is suppressed, so as to improve the class regression iteration effect of the feature set input of the battery temperature state-coolant state timing interaction response feature vector based on the classifier thermal management result generator, that is, to improve the speed of classification training and the accuracy of classification results.

[0042] In summary, the thermal management system of new energy vehicles based on pressure and temperature sensors according to the embodiment of the present application is explained, which uses artificial intelligence technology based on deep learning to monitor the battery temperature and coolant pressure and flow rate of new energy vehicles and mine the time series characteristics to capture the time series dynamic change information of the battery temperature and coolant state, and then adjust the coolant flow rate adaptively based on the time series response mode between the battery temperature and the coolant state to achieve battery temperature management. In this way, the battery temperature can be controlled more accurately, avoiding unnecessary energy consumption, thereby improving the performance, safety and life of the battery and energy utilization.

[0043] Figure 6 FIG. 1 is a flow chart of a new energy vehicle thermal management method based on a pressure temperature sensor according to an embodiment of the present application. Figure 6As shown, according to the thermal management method of new energy vehicles based on pressure and temperature sensors according to the embodiment of the present application, the steps include: S1, obtaining the time series of battery temperature collected by the temperature sensor; S2, obtaining the time series of coolant pressure values ​​and the time series of coolant flow rate values ​​collected by the pressure sensor and the flow meter; S3, respectively performing time series encoding on the time series of the battery temperature, the time series of the coolant pressure values ​​and the time series of the coolant flow rate values ​​to obtain a battery temperature time series correlation feature vector, a coolant pressure time series correlation feature vector and a coolant flow rate time series correlation feature vector; S4, interactively fusing the coolant pressure time series correlation feature vector and the coolant flow rate time series correlation feature vector to obtain a coolant state multimodal joint representation feature vector; S5, based on the correlation response characteristics between the battery temperature time series correlation feature vector and the coolant state multimodal joint representation feature vector, determining whether the coolant flow rate value should increase, decrease or remain unchanged.

[0044] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned new energy vehicle thermal management method based on the pressure and temperature sensor have been referred to above. Figures 1 to 5 The invention has been introduced in detail in the description of the thermal management system of new energy vehicles based on pressure temperature sensor, and therefore, its repeated description will be omitted.

[0045] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0046] In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical sub-unit, that is, it may be located in one place, or it may be distributed on multiple network sub-units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0047] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0048] In addition, it is obvious that the word "comprising" does not exclude other sub-units or steps, and the singular does not exclude the plural. Multiple sub-units stated in the system claim can also be implemented by one sub-unit through software or hardware.

[0049] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A new energy vehicle thermal management system based on a pressure and temperature sensor, characterized in that: include: A battery temperature monitoring module is used to obtain a time series of battery temperature collected by a temperature sensor; A coolant state monitoring module, used to obtain the time series of coolant pressure values ​​and the time series of coolant flow rate values ​​collected by the pressure sensor and the flow meter; a timing encoding module, used to respectively perform timing encoding on the time series of the battery temperature, the time series of the coolant pressure value and the time series of the coolant flow rate value to obtain a battery temperature timing correlation feature vector, a coolant pressure timing correlation feature vector and a coolant flow rate timing correlation feature vector; a coolant state multimodal fusion module, used to interactively fuse the coolant pressure timing correlation feature vector and the coolant flow rate timing correlation feature vector to obtain a coolant state multimodal joint representation feature vector; a battery temperature management module, used to determine whether the coolant flow rate value should be increased, decreased or kept unchanged based on the correlation response characteristics between the battery temperature timing correlation feature vector and the coolant state multimodal joint representation feature vector; Wherein, the coolant state multimodal fusion module includes: a feature cascade unit, used for performing feature cascade on the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector to obtain a coolant pressure-flow rate time series joint feature vector; an information fusion threshold calculation unit, used for inputting the coolant pressure-flow rate time series joint feature vector into a gated response function to obtain an information fusion response gate; a weighted fusion unit, used for calculating a difference with the information fusion response gate, and using the information fusion response gate and the difference as weights to calculate the position-weighted sum of the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector to obtain the coolant state multimodal joint representation feature vector; Among them, the battery temperature management module includes: a timing interaction response unit, which is used to input the battery temperature timing association feature vector and the coolant state multimodal joint representation feature vector into a prior distribution guided association interaction response module to obtain a battery temperature state-coolant state timing interaction response feature vector; a thermal management result generation unit, which is used to input the battery temperature state-coolant state timing interaction response feature vector into a classifier-based thermal management result generator to obtain a thermal management result, and the thermal management result is used to indicate that the flow rate value of the coolant should increase, decrease or remain unchanged.

2. The new energy vehicle thermal management system based on pressure and temperature sensor according to claim 1 is characterized in that: The timing encoding module is used to: input the time series of the battery temperature, the time series of the coolant pressure value, and the time series of the coolant flow rate value into a double-branch sequence encoding structure including a 1D-CNN layer and a bidirectional gated recurrent unit to obtain the battery temperature timing association feature vector, the coolant pressure timing association feature vector, and the coolant flow rate timing association feature vector.

3. The new energy vehicle thermal management system based on pressure and temperature sensor according to claim 2 is characterized in that: The coolant state multimodal fusion module is used to: input the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector into a feature vector dynamic interactive fusion module based on gated response to obtain the coolant state multimodal joint representation feature vector.

4. The new energy vehicle thermal management system based on pressure and temperature sensor according to claim 3 is characterized in that: The information fusion threshold calculation unit is used to: use a predetermined weight vector to multiply the coolant pressure-flow rate time series joint feature vector to obtain an information interaction fusion correlation coefficient; add the information interaction fusion correlation coefficient and a predetermined bias parameter and then activate it through a sigmoid function to obtain a response gate for the information fusion.

5. The new energy vehicle thermal management system based on pressure and temperature sensor according to claim 4 is characterized in that: The timing interaction response unit includes: a position-by-position response subunit, which is used to calculate the position-by-position division between the multimodal joint representation feature vector of the coolant state and the battery temperature timing association feature vector to obtain a battery temperature state-coolant state response feature vector; a Gaussian distribution random number generation subunit, which is used to generate a first Gaussian distribution function coefficient and a second Gaussian distribution function coefficient using a Gaussian distribution random number function; and a priori distribution constraint subunit, which is used to perform a priori distribution constraint on the battery temperature state-coolant state response feature vector based on the first Gaussian distribution function coefficient and the second Gaussian distribution function coefficient to obtain the battery temperature state-coolant state timing interaction response feature vector.

6. The new energy vehicle thermal management system based on pressure and temperature sensor according to claim 5 is characterized in that: The prior distribution constraint subunit is used to: determine the first weight coefficient and the second weight coefficient of the battery temperature state-coolant state response feature vector, and use the first weight coefficient and the second weight coefficient to weight the battery temperature state-coolant state response feature vector respectively to obtain a first linear transformation battery temperature state-coolant state response feature vector and a second linear transformation battery temperature state-coolant state response feature vector; respectively calculate the exponential function value with the natural constant as the base of each eigenvalue of the first linear transformation battery temperature state-coolant state response feature vector and the second linear transformation battery temperature state-coolant state response feature vector to obtain an exponential first linear transformation battery temperature state-coolant state response feature vector and an exponential second linear transformation battery temperature state-coolant state response feature vector; add and sum the corresponding elements of the product result of multiplying the first Gaussian distribution function coefficient by the exponential first linear transformation battery temperature state-coolant state response feature vector and the product result of multiplying the second Gaussian distribution function coefficient by the exponential second linear transformation battery temperature state-coolant state response feature vector to obtain the battery temperature state-coolant state time series interaction response feature vector.

7. A thermal management method for new energy vehicles based on pressure and temperature sensors, characterized in that: include: Acquire a time series of battery temperature collected by a temperature sensor; acquire a time series of coolant pressure values ​​and a time series of coolant flow rate values ​​collected by a pressure sensor and a flow meter; perform time series encoding on the time series of the battery temperature, the time series of the coolant pressure values ​​and the time series of the coolant flow rate values ​​respectively to obtain a battery temperature time series correlation feature vector, a coolant pressure time series correlation feature vector and a coolant flow rate time series correlation feature vector; interactively fuse the coolant pressure time series correlation feature vector and the coolant flow rate time series correlation feature vector to obtain a coolant state multimodal joint representation feature vector; determine whether the coolant flow rate value should increase, decrease or remain unchanged based on the correlation response characteristics between the battery temperature time series correlation feature vector and the coolant state multimodal joint representation feature vector; Among them, the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector are interactively fused to obtain a coolant state multimodal joint representation feature vector, including: feature cascading the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector to obtain a coolant pressure-flow rate time series joint feature vector; inputting the coolant pressure-flow rate time series joint feature vector into a gated response function to obtain an information fused response gate; calculating a difference with the information fused response gate, and using the information fused response gate and the difference as weights to calculate the position-weighted sum of the coolant pressure time series associated feature vector and the coolant flow rate time series associated feature vector to obtain the coolant state multimodal joint representation feature vector; Wherein, based on the correlation response characteristics between the battery temperature time series correlation feature vector and the coolant state multimodal joint representation feature vector, determining whether the flow rate value of the coolant should increase, decrease or remain unchanged includes: inputting the battery temperature time series correlation feature vector and the coolant state multimodal joint representation feature vector into a prior distribution guided correlation interaction response module to obtain a battery temperature state-coolant state time series interaction response feature vector; inputting the battery temperature state-coolant state time series interaction response feature vector into a classifier-based thermal management result generator to obtain a thermal management result, and the thermal management result is used to indicate that the flow rate value of the coolant should increase, decrease or remain unchanged.

Images