Battery global temperature and pressure distribution monitoring system and method

Abstract

The invention relates to the technical field of battery monitoring, and discloses a battery global temperature and pressure distribution monitoring system and method, and the system comprises a distributed sensing unit, a signal processing unit, a data analysis unit, an intelligent decision-making unit, a wireless communication module, and a man-machine interaction terminal. Battery temperature and pressure data are acquired through a high-density flexible sensor array, fine sensing is realized by combining multi-dimensional feature extraction and an anomaly detection algorithm, and a response strategy is generated by using a rule engine; the battery state can be comprehensively monitored, local abnormity can be captured in time, safety and reliability are improved, the method is suitable for the field of power batteries and energy storage systems, the problem that in the prior art, due to insufficient sensor arrangement density, monitoring of the internal state of the battery is not comprehensive is solved, and safety is improved. And the real-time monitoring of the global temperature and pressure distribution of the battery and the intelligent response of the abnormal state are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery monitoring, in particular to a battery global temperature and pressure distribution monitoring system and method. BACKGROUND

[0002] As the core component of modern energy storage and supply, the performance and safety of batteries are directly related to the stable operation and service life of various electronic devices, electric vehicles and energy storage systems. With the rapid development of new energy technology, the application scenarios of batteries are becoming increasingly widespread, and the demand for real-time monitoring of their internal state has also increased. Temperature and pressure are key parameters that reflect the health status of batteries, and the uniformity of their distribution has a significant impact on the safety, efficiency and lifespan of batteries. However, due to the complex internal structure of batteries and the variable working environment, it is still challenging to comprehensively grasp the global temperature and pressure distribution.

[0003] In the prior art, battery monitoring systems usually rely on a limited number of sensors to collect data at key points. This solution can reflect the overall state of the battery to some extent, but due to the insufficient density of sensor arrangement, it is difficult to fully capture the subtle changes inside the battery. For example, during high-rate charging and discharging, local overheating or pressure abnormalities may occur inside the battery, which may be ignored by sparse monitoring points. In addition, traditional monitoring methods are mostly focused on single points or local areas, lacking dynamic perception ability for global distribution, resulting in potential risks that cannot be timely warned. Especially in large-scale battery pack applications, the differences between individual batteries may further amplify the impact of local abnormalities, thereby threatening the safe operation of the entire system.

[0004] Therefore, how to design a system and method that can realize real-time monitoring of the global temperature and pressure distribution of batteries, so as to accurately identify potential abnormal states inside the battery and provide reliable data support, has become an important problem to be solved in the current battery monitoring field. SUMMARY

[0005] The technical problem to be solved by the present application is to provide a battery global temperature and pressure distribution monitoring system and method to overcome the problem of incomplete monitoring of the internal state of the battery and the difficulty of timely capturing local abnormalities due to insufficient density of sensor arrangement in the prior art. By constructing a high-density distributed sensor network and a multi-dimensional data fusion analysis mechanism, fine perception of the global temperature and pressure distribution of the battery is achieved, and combined with intelligent data processing algorithms, the identification ability of potential abnormal states is improved.

[0006] In order to achieve the above object, the application provides a battery global temperature and pressure distribution monitoring system, comprising: a distributed sensing unit for real-time acquisition of temperature and pressure data on the surface and inside of the battery; a signal processing unit connected with the distributed sensing unit, for filtering, amplifying and digitizing the received original signal; a data analysis unit connected with the signal processing unit, for spatial distribution modeling and anomaly detection of the processed data based on a multi-dimensional feature extraction algorithm; an intelligent decision unit connected with the data analysis unit, for generating early warning information and triggering corresponding response instructions according to the anomaly detection result; a wireless communication module connected with the intelligent decision unit, for transmitting the monitoring data and early warning information to a remote monitoring platform; and a human-computer interaction terminal connected with the wireless communication module through a secure communication link, for displaying the battery operating state, historical data trend and abnormal alarm information.

[0007] Preferably, the distributed sensing unit adopts a thin film sensor array made of flexible substrate material, the sensor array is composed of multiple micro-thermistor and piezoelectric film, and each sensor node has an independent address code. The sensor array is fixed on the surface of the battery shell by conductive adhesive or embedding, and is connected with the signal processing unit through a flexible circuit board. The flexible substrate material is selected as a polyimide film with a thickness not exceeding 0.2 mm, so as to ensure that the sensor array can closely adhere to the surface of the battery, and at the same time avoid causing additional stress to the battery structure.

[0008] Preferably, the signal processing unit is internally provided with a low-noise amplifier, a band-pass filter and an analog-to-digital conversion module. The low-noise amplifier adjusts the gain of the received weak analog signal, and the gain range is adjustable from 10 times to 100 times; the cut-off frequency of the band-pass filter is set to 10 Hz to 1 kHz, so as to filter out high-frequency noise and direct current offset; the analog-to-digital conversion module adopts a 24-bit resolution Σ-Δ type ADC chip with a sampling frequency of 1 kHz, and outputs the digital signal converted from the analog signal to the data analysis unit.

[0009] Preferably, the data analysis unit is internally integrated with a spatial distribution modeling module, a feature extraction module and an anomaly detection module. The spatial distribution modeling module performs three-dimensional modeling on the temperature and pressure field on the surface and inside of the battery based on the finite element analysis method, and the model grid size is 1 mm x 1 mm x 1 mm; the feature extraction module extracts key features such as temperature gradient, pressure change rate and local extreme value from the modeling result; the anomaly detection module classifies the extracted features through a support vector machine algorithm to determine whether there is an abnormal state. When an anomaly is detected, the anomaly detection module generates a report containing the abnormal position, type and severity, and sends it to the intelligent decision unit.

[0010] Preferably, the intelligent decision unit adopts a logic control architecture based on a rule engine, which has multiple abnormal response strategies pre-installed. When receiving an abnormal detection report, the intelligent decision unit selects a corresponding response strategy according to the type and severity of the abnormality, such as triggering an alarm, adjusting the charging and discharging parameters, or cutting off the external load. The intelligent decision unit also has a self-learning function, which optimizes the accuracy of abnormality discrimination by updating the rule library online.

[0011] Preferably, the wireless communication module adopts a dual-band RF transceiver chip, supporting wireless communication protocols in 2.4GHz and 5GHz frequency bands. The wireless communication module is connected to the intelligent decision unit through an SPI interface and realizes data transmission through an antenna array. The antenna array is composed of four directional antennas, each with a gain of 5dBi and a coverage range of 30 meters. The wireless communication module uses the AES-256 encryption algorithm to encrypt data packets during data transmission, ensuring the security of data transmission.

[0012] Preferably, the battery full-domain temperature and pressure distribution monitoring method includes the following steps: S1: The distributed sensing unit continuously and real-time collects temperature and pressure data on the surface and inside the battery, and transmits the original signals to the signal processing unit through the flexible circuit board; S2: The signal processing unit sequentially performs low-noise amplification, band-pass filtering, and analog-to-digital conversion processing on the received original signals, and transmits the processed digital signals to the data analysis unit; S3: The data analysis unit performs three-dimensional modeling on the processed data based on the spatial distribution modeling module, and extracts key features through the feature extraction module; S4: The abnormality detection module classifies the extracted features to determine whether there is an abnormal state, and generates an abnormal detection report if an abnormality is detected; S5: The intelligent decision unit receives the abnormal detection report, selects a corresponding response strategy according to the pre-installed rule engine, and transmits the monitoring data and warning information to the remote monitoring platform through the wireless communication module; S6: The human-computer interaction terminal receives and displays the monitoring data and warning information, and the operator can take appropriate measures according to the display content.

[0013] Preferably, in step S3, the spatial distribution modeling module uses the finite element analysis method to perform three-dimensional modeling of the temperature and pressure field on the surface and inside the battery. The modeling process includes the following sub-steps: S3-1: Divide the battery surface into several uniformly distributed grid elements, each with a size of 1mm×1mm; S3-2: Based on the data collected by the sensor array, calculate the temperature and pressure values of each grid element; S3-3: Use an interpolation algorithm to fill in the data for the areas without sensor nodes, generating a complete three-dimensional distribution map.

[0014] Preferably, in step S4, the anomaly detection module classifies the extracted features through a support vector machine algorithm. The training process of the support vector machine algorithm includes the following sub-steps: S4-1: collect historical data under normal and abnormal conditions to construct a training data set; S4-2: normalize the training data set to make the value range of each feature [0, 1]; S4-3: select a radial basis function as a kernel function and set the initial values of the penalty parameter C and the kernel parameter gamma; S4-4: optimize the values of parameters C and gamma through cross-validation method until the classification accuracy rate reaches more than 95%.

[0015] Preferably, in step S5, the intelligent decision unit selects the corresponding response strategy according to the abnormal type and severity. The selection process of the response strategy includes the following sub-steps: S5-1: analyze the anomaly detection report to extract the abnormal type and severity information; S5-2: match the pre-set strategy in the rule engine to filter out all candidate strategies that meet the conditions; S5-3: select the strategy with the highest priority as the final response strategy according to the priority sorting algorithm; S5-4: execute the selected response strategy and record the execution result.

[0016] Preferably, in step S6, the man-machine interaction terminal displays the monitoring data and warning information through a graphical interface. The graphical interface includes the following functional modules: real-time data display module for dynamically displaying the temperature and pressure distribution map of the battery surface and internal; historical data query module for retrieving and playing back historical monitoring data; abnormal alarm module for displaying the anomaly detection report and response strategy execution result; system setting module for configuring wireless communication parameters and rule engine parameters.

[0017] Compared with the prior art, the application has the following beneficial effects: 1. Through the cooperative work of the distributed sensing unit, signal processing unit, data analysis unit, intelligent decision unit, wireless communication module and man-machine interaction terminal, the problem of incomplete monitoring of the internal state of the battery caused by insufficient sensor arrangement density in the prior art is overcome, and real-time monitoring of the global temperature and pressure distribution of the battery and intelligent response to abnormal state are realized.

[0018] 2. The battery temperature and pressure data are collected by the high-density flexible sensor array, combined with multi-dimensional feature extraction and anomaly detection algorithm to realize fine perception, and the response strategy is generated by using the rule engine. The application can comprehensively monitor the battery state, timely capture local abnormalities, improve safety and reliability, and is suitable for power battery and energy storage system fields. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 The flowchart of the battery global temperature and pressure distribution monitoring system of the application; Figure 2A schematic diagram illustrating the layout process of the distributed sensing unit for invention; Figure 3 This is a flowchart of the data analysis unit of the present invention; Figure 4 This is a schematic diagram of the graphical interface process for the invention of a human-computer interaction terminal. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] like Figure 1 As shown in the diagram, the overall system structure clearly illustrates the connections between functional units and the direction of data flow. The distributed sensing unit, as the system's data acquisition front-end, is responsible for real-time acquisition of temperature and pressure data from the battery surface and interior, and transmits the raw signals to the signal processing unit via a flexible circuit board. The distributed sensing unit consists of a thin-film sensor array, arranged as shown in the diagram. Figure 2 As shown, the sensor array is made of a flexible substrate material, specifically a polyimide film with a thickness not exceeding 0.2 mm, to ensure a tight fit to the battery surface without causing additional stress to the battery structure. The sensor array consists of multiple miniature thermistors and piezoelectric films, each sensor node having an independent address code for easy location and identification during subsequent data processing. The sensor array is fixed to the battery casing surface by conductive adhesive bonding or embedding and connected to the signal processing unit via a flexible circuit board. The flexible circuit board design not only ensures reliable signal transmission but also avoids mechanical damage that might be caused by rigid connections.

[0022] The signal processing unit receives the raw signal from the distributed sensing unit and sequentially performs low-noise amplification, bandpass filtering, and analog-to-digital conversion. Internally, the signal processing unit includes a low-noise amplifier, a bandpass filter, and an analog-to-digital conversion module. The low-noise amplifier adjusts the gain of the received weak analog signal, with a gain range adjustable from 10 to 100 times to accommodate input requirements of varying signal strengths. The bandpass filter's cutoff frequency is set from 10Hz to 1kHz to filter out high-frequency noise and DC offset, thereby improving signal quality. The analog-to-digital conversion module uses a 24-bit resolution Σ-Δ ADC chip with a sampling frequency of 1kHz. This chip converts the filtered and amplified analog signal into a digital signal before outputting it to the data analysis unit. The signal processing unit and the data analysis unit are connected via a high-speed data bus to ensure real-time and stable data transmission.

[0023] After receiving the digital signal output from the signal processing unit, the data analysis unit performs 3D modeling of the data based on the spatial distribution modeling module and extracts key features through the feature extraction module. The spatial distribution modeling module uses the finite element analysis method to perform 3D modeling of the temperature and pressure fields on the battery surface and inside the battery. The specific process is as follows: Figure 3 As shown. First, the battery surface is divided into several uniformly distributed grid cells, each with a size of 1mm × 1mm. Then, based on the data collected by the sensor array, the temperature and pressure values ​​of each grid cell are calculated. For areas without sensor nodes, an interpolation algorithm is used to fill in the data and generate a complete three-dimensional distribution map. The feature extraction module extracts key features such as temperature gradient, pressure change rate, and local extrema from the modeling results. These features provide basic data support for subsequent anomaly detection. The anomaly detection module classifies the extracted features using the support vector machine algorithm to determine whether an abnormal state exists. The training process of the support vector machine algorithm includes collecting historical data under normal and abnormal states to construct a training dataset, and normalizing the training dataset so that the value range of each feature is [0,1]. The radial basis function is selected as the kernel function, and the initial values ​​of the penalty parameter C and the kernel parameter γ are set. The values ​​of parameters C and γ are optimized using cross-validation until the classification accuracy reaches more than 95%. When an anomaly is detected, the anomaly detection module generates a report containing the location, type, and severity of the anomaly and sends it to the intelligent decision-making unit.

[0024] The intelligent decision-making unit adopts a rule-engine-based logic control architecture, within which multiple anomaly response strategies are pre-defined. After receiving anomaly detection reports generated by the anomaly detection module, the intelligent decision-making unit parses the report content to extract anomaly type and severity information. Based on the pre-defined strategies in the rule engine, it filters out all candidate strategies that meet the criteria and selects the strategy with the highest priority as the final response strategy using a priority ranking algorithm. For example, when a local overheating is detected, the intelligent decision-making unit may trigger an alarm and adjust charging and discharging parameters to reduce battery load. The intelligent decision-making unit also has a self-learning function, continuously optimizing anomaly detection accuracy by updating the rule base online. The intelligent decision-making unit connects to the wireless communication module via an SPI interface for transmitting monitoring data and early warning information to a remote monitoring platform.

[0025] The wireless communication module adopts a dual-band RF transceiver chip, supporting wireless communication protocols in 2.4 GHz and 5 GHz frequency bands. The wireless communication module realizes data transmission through an antenna array composed of four directional antennas, each with a gain of 5 dBi and a coverage range of 30 meters. During data transmission, the wireless communication module uses the AES-256 encryption algorithm to encrypt data packets, ensuring the security of data transmission. The wireless communication module is connected to the human-computer interaction terminal through a secure communication link, used to display battery operating status, historical data trends, and abnormal alarm information.

[0026] The human-computer interaction terminal displays monitoring data and warning information through a graphical interface, as shown in Figure 4 The graphical interface includes real-time data display module, historical data query module, abnormal alarm module, and system setting module. The real-time data display module is used to dynamically display the temperature and pressure distribution of the battery surface and interior, allowing the operator to intuitively understand the current operating status of the battery. The historical data query module is used to retrieve and replay historical monitoring data, facilitating the operator to analyze the long-term running trend of the battery. The abnormal alarm module is used to display abnormal detection reports and response strategy execution results, allowing the operator to take appropriate measures according to the alarm content. The system setting module is used to configure wireless communication parameters and rule engine parameters, ensuring that the system can be flexibly adjusted according to actual needs.

[0027] In actual application scenarios, the system can be deployed in the power battery pack of an electric vehicle to monitor the temperature and pressure distribution of the battery in real time. The sensor array of the distributed sensing unit closely adheres to the battery surface, fully covering the key areas of the battery and collecting temperature and pressure data in real time. The signal processing unit transmits the processed data to the data analysis unit after filtering, amplifying, and digitizing the collected raw signals. The data analysis unit generates a three-dimensional distribution map and extracts key features through the spatial distribution modeling module. The abnormal detection module classifies the features based on the support vector machine algorithm to determine whether there is an abnormal state. When an abnormality is detected, the intelligent decision-making unit selects the appropriate response strategy according to the pre-set rule engine and transmits the monitoring data and warning information to the remote monitoring platform through the wireless communication module. The human-computer interaction terminal displays monitoring data and warning information through a graphical interface, allowing the operator to take timely measures to ensure the safe operation of the battery based on the displayed content.

[0028] The implementation of the system can effectively overcome the problem of incomplete battery internal state monitoring and difficulty in capturing local abnormalities due to insufficient sensor arrangement density in existing technologies. By constructing a high-density distributed sensing network and a multi-dimensional data fusion analysis mechanism, the system realizes fine perception of the global temperature and pressure distribution of the battery, and improves the identification ability of potential abnormal states by combining intelligent data processing algorithms.

[0029] In order to better enable those skilled in the art to fully understand and implement the present application, the specific implementation principles of the present application are further described below in conjunction with a specific application scenario.

[0030] In the actual operation scenario of electric vehicle power battery pack, a battery full-domain temperature and pressure distribution monitoring system is deployed to monitor the health status of the battery in real time. First, the thin film sensor array in the distributed sensing unit is closely attached to the surface of the battery, and the flexible substrate material is selected to be a polyimide film with a thickness of not more than 0.2 millimeters, ensuring that the sensor array can uniformly cover the surface of the battery and will not cause additional stress to the battery structure. The sensor array is composed of multiple miniature thermistors and piezoelectric films, and each sensor node has an independent address code for precise positioning of the data collection location. These sensors are fixed to the surface of the battery shell by conductive adhesive or embedded, and the raw signals collected are transmitted to the signal processing unit through a flexible circuit board.

[0031] After receiving the raw signals from the distributed sensing unit, the signal processing unit first adjusts the gain of the weak analog signals through a low-noise amplifier, with a gain range of 10 to 100 adjustable to adapt to different intensity of input signal requirements. Subsequently, a band-pass filter is used to filter the signals, with a cutoff frequency of 10 Hz to 1 kHz to filter out high-frequency noise and DC offset, thereby improving the signal quality. The filtered and amplified signals are sent to an analog-to-digital conversion module, which uses a 24-bit resolution Sigma-Delta type ADC chip to convert the analog signals to digital signals at a sampling frequency of 1 kHz, and transmits them to the data analysis unit through a high-speed data bus.

[0032] After receiving the digitized signals, the data analysis unit performs three-dimensional modeling based on the spatial distribution modeling module. Specifically, the battery surface is first divided into several 1mm x 1mm grid cells, each of which corresponds to a temperature and pressure value. For areas where sensor nodes are not arranged, an interpolation algorithm is used to fill in the data to generate a complete three-dimensional distribution map. The feature extraction module extracts key features from the modeling results, such as temperature gradient, pressure change rate, and local extreme values, which provide basic data support for subsequent anomaly detection. The anomaly detection module classifies the extracted features using a support vector machine algorithm to determine whether there is an abnormal state. The training process of the support vector machine algorithm includes collecting historical data under normal and abnormal states to construct a training data set, and normalizing the data set so that the value range of each feature is [0, 1]. The radial basis function is selected as the kernel function, and the values of the penalty parameter C and the kernel parameter γ are optimized through cross-validation until the classification accuracy rate reaches more than 95%. When an anomaly is detected, the anomaly detection module generates a report containing the abnormal location, type, and severity, and sends it to the intelligent decision-making unit.

[0033] The intelligent decision unit parses the abnormal type and severity information according to the received abnormal detection report, and filters all candidate strategies that meet the conditions based on the rule engine. The rule engine has multiple abnormal response strategies preset, such as triggering an alarm, adjusting the charging and discharging parameters, or cutting off external loads, etc. Through a priority sorting algorithm, the intelligent decision unit selects the strategy with the highest priority as the final response strategy. For example, when detecting a local temperature that is too high, the intelligent decision unit may trigger an alarm and transmit the warning information to the remote monitoring platform through the wireless communication module, while adjusting the charging and discharging parameters of the battery to reduce the load. The intelligent decision unit also has a self-learning function, which continuously optimizes the accuracy of abnormality discrimination through online updating of the rule library.

[0034] The wireless communication module uses a dual-band RF transceiver chip, supporting wireless communication protocols at 2.4 GHz and 5 GHz frequency bands. The wireless communication module achieves data transmission through an antenna array composed of four directional antennas, each with a gain of 5dBi and a coverage range of 30 meters. During data transmission, the wireless communication module uses the AES-256 encryption algorithm to encrypt data packets, ensuring the security of data transmission. The monitoring data and warning information are transmitted to the human-computer interaction terminal through a secure communication link.

[0035] The human-computer interaction terminal displays monitoring data and warning information through a graphical interface. The operator can dynamically view the temperature and pressure distribution map of the battery surface and interior through the real-time data display module, and intuitively understand the current running state of the battery. The historical data query module allows the operator to retrieve and replay historical monitoring data, facilitating the analysis of the long-term running trend of the battery. The abnormal alarm module displays the abnormal detection report and the response strategy execution result, and the operator can take appropriate measures according to the alarm content. The system setting module is used to configure the wireless communication parameters and the rule engine parameters, ensuring that the system can be flexibly adjusted according to actual needs.

[0036] Through the above steps, the system realizes fine perception of the global temperature and pressure distribution of the battery. The high-density distributed sensing network comprehensively covers the key areas of the battery, and real-time collects temperature and pressure data; the multi-dimensional data fusion analysis mechanism combined with intelligent data processing algorithms effectively improves the identification ability of potential abnormal states. For example, during high-rate charging and discharging, the system can timely capture local overheating or pressure abnormal phenomena in the battery, avoiding the situation that potential risks are ignored due to sparse monitoring points. In addition, by dynamically perceiving the differences between single batteries in a large-scale battery pack, the system can further amplify the impact of local abnormalities, thereby ensuring the safe operation of the entire system.

[0037] In summary, the application overcomes the problem of incomplete monitoring of the internal state of the battery caused by insufficient density of the sensor arrangement in the prior art by the cooperative work of the distributed sensing unit, the signal processing unit, the data analysis unit, the intelligent decision unit, the wireless communication module and the human-computer interaction terminal, and realizes real-time monitoring of the global temperature and pressure distribution of the battery and intelligent response to abnormal states.

[0038] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary and that certain changes and modifications can be made thereto without departing from the principles and spirit of the application. The scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A battery global temperature and pressure distribution monitoring system, characterized in that, include: Distributed sensing units are used to collect temperature and pressure data of the battery surface and interior in real time; The signal processing unit, connected to the distributed sensing unit, is used to perform low-noise amplification, bandpass filtering, and analog-to-digital conversion on the received raw signal. The data analysis unit, connected to the signal processing unit, is used to perform three-dimensional modeling on the processed data based on the spatial distribution modeling module, and to extract key features through the feature extraction module. The anomaly detection module classifies the extracted features to determine whether there is an abnormal state. The intelligent decision-making unit, connected to the data analysis unit, is used to generate early warning information and trigger response instructions based on anomaly detection results; The wireless communication module, connected to the intelligent decision-making unit, is used to transmit monitoring data and early warning information to the remote monitoring platform; The human-computer interaction terminal is connected to the wireless communication module via a secure communication link and is used to display battery operating status, historical data trends, and abnormal alarm information.

2. The system according to claim 1, characterized in that, The distributed sensing unit uses a thin-film sensor array made of flexible substrate material. The sensor array consists of multiple miniature thermistors and piezoelectric films. Each sensor node has an independent address code. The sensor array is fixed to the surface of the battery casing by adhesive bonding or embedding and is connected to the signal processing unit through a flexible circuit board. The flexible substrate material is a polyimide film with a thickness of no more than 0.2 mm.

3. The system according to claim 1, characterized in that, The signal processing unit is equipped with a low-noise amplifier, a bandpass filter, and an analog-to-digital converter module. The gain range of the low-noise amplifier is adjustable from 10 to 100 times, the cutoff frequency of the bandpass filter is set from 10 Hz to 1 kHz, and the analog-to-digital converter module uses a 24-bit resolution Σ-Δ ADC chip with a sampling frequency of 1 kHz.

4. The system according to claim 1, characterized in that, The data analysis unit integrates a spatial distribution modeling module, a feature extraction module, and an anomaly detection module. The spatial distribution modeling module performs three-dimensional modeling of the temperature and pressure fields on and inside the battery surface based on the finite element analysis method. The model mesh size is 1mm×1mm×1mm. The feature extraction module extracts key features such as temperature gradient, pressure change rate, and local extrema from the modeling results. The anomaly detection module classifies the extracted features using the support vector machine algorithm.

5. The system according to claim 4, characterized in that, The training process of the Support Vector Machine (SVM) algorithm includes the following steps: collecting historical data under normal and abnormal states to construct a training dataset; normalizing the training dataset so that the value range of each feature is [0,1]; selecting the radial basis function as the kernel function and setting the initial values ​​of the penalty parameter C and the kernel parameter γ; and optimizing the values ​​of parameters C and γ through cross-validation until the classification accuracy reaches more than 95%.

6. The system according to claim 1, characterized in that, The intelligent decision-making unit adopts a rule engine-based logical control architecture. The rule engine has multiple pre-set exception response strategies. The intelligent decision-making unit selects the corresponding response strategy according to the exception type and severity, and updates the rule base online through self-learning function.

7. The system according to claim 1, characterized in that, The wireless communication module uses a dual-band RF transceiver chip, supporting wireless communication protocols in the 2.4GHz and 5GHz bands. The wireless communication module achieves data transmission through an antenna array, which consists of four directional antennas, each with a gain of 5dBi and a coverage range of 30 meters. The wireless communication module uses the AES-256 encryption algorithm to encrypt data packets during data transmission.

8. A method for monitoring the global temperature and pressure distribution of a battery, characterized in that, Includes the following steps: S1: The distributed sensing unit continuously collects temperature and pressure data of the battery surface and interior in real time, and transmits the raw signals to the signal processing unit through the flexible circuit board; S2: The signal processing unit sequentially performs low-noise amplification, bandpass filtering, and analog-to-digital conversion on the received raw signal, and then transmits the processed digital signal to the data analysis unit. S3: The data analysis unit performs three-dimensional modeling on the processed data based on the spatial distribution modeling module, and extracts key features through the feature extraction module; S4: The anomaly detection module classifies the extracted features and determines whether there is an abnormal state. If an anomaly is detected, an anomaly detection report is generated. S5: The intelligent decision-making unit receives the anomaly detection report, selects the corresponding response strategy according to the preset rule engine, and transmits the monitoring data and early warning information to the remote monitoring platform through the wireless communication module; S6: The human-computer interaction terminal receives and displays monitoring data and early warning information.

9. The method according to claim 8, characterized in that, In step S3, the spatial distribution modeling module uses the finite element analysis method to perform three-dimensional modeling of the temperature and pressure fields on and inside the battery surface. The modeling process includes the following sub-steps: dividing the battery surface into several uniformly distributed grid units, each grid unit having a size of 1mm×1mm; calculating the temperature and pressure values ​​of each grid unit based on the data collected by the sensor array; and using an interpolation algorithm to fill in the data in areas where no sensor nodes are arranged, thereby generating a complete three-dimensional distribution map.

10. The method according to claim 8, characterized in that, In step S5, the intelligent decision-making unit selects the corresponding response strategy based on the anomaly type and severity. The response strategy selection process includes the following sub-steps: parsing the anomaly detection report to extract anomaly type and severity information, matching the preset strategies in the rule engine to filter out all candidate strategies that meet the conditions, selecting the strategy with the highest priority as the final response strategy according to the priority ranking algorithm, executing the selected response strategy and recording the execution results.

Images