Interconnection system for monitoring air conditioning pressure sensors in new energy vehicles

By designing an air conditioning pressure sensor monitoring interconnection system in new energy vehicles, using frequency domain and time domain analysis combined with cross-modal fusion coding of MetaNet model, the problem that traditional systems cannot accurately adjust the air pressure in the car is solved, and passenger comfort and Energy efficiency.

CN118464277BActive Publication Date: 2024-11-01WENZHOU WEILI CAR FITTINGS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410631980.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-21
Publication Date
2024-11-01
Estimated Expiration
2044-05-21

AI Technical Summary

Technical Problem

Traditional car air conditioning systems cannot accurately adapt to passengers’ personalized needs and dynamic environmental changes, resulting in insufficient passenger comfort and energy efficiency, especially in the car’s air pressure regulation is not intelligent and precise enough.

Method used

Design an interconnected air conditioning pressure sensor monitoring system for new energy vehicles. By collecting air pressure data in the vehicle, performing frequency and time domain analysis, and using the MetaNet model for cross-modal fusion encoding, generating fan speed control instructions to adjust air pressure .

Benefits of technology

More precise temperature regulation and air pressure control are achieved, improving passenger comfort and energy efficiency, providing additional information to indirectly regulate air flow speed and improve the interior environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118464277B_ABST
    Figure CN118464277B_ABST
Patent Text Reader

Abstract

Disclosed is an interconnection system for monitoring air conditioning pressure sensors of new energy vehicles. First, the time series of air pressure in the vehicle collected by the air conditioning pressure sensor of the new energy vehicle is transmitted to the vehicle control center through the Internet of Vehicles. Then, in the vehicle control center, the time series of air pressure in the vehicle is converted into frequency domain and analyzed in frequency domain and time domain. Then, in the vehicle control center, the obtained time-frequency mode feature map of air pressure in the vehicle and the implicit representation vector of time-space mode of air pressure in the vehicle are passed through the time-frequency domain cross-modal fusion encoder based on the MetaNet model to obtain the time-frequency domain fusion representation feature map of air pressure in the vehicle. Finally, in the vehicle control center, the control instruction of the fan speed is determined based on the time-frequency domain fusion representation feature map of air pressure in the vehicle.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of new energy vehicles, and in particular to an interconnection system for monitoring air-conditioning pressure sensors of new energy vehicles. Background Art

[0002] As the global demand for sustainable transportation solutions continues to grow, the new energy vehicle industry has ushered in rapid development. New energy vehicles not only need to provide clean energy solutions, but also need to ensure the comfort and safety of passengers. In-vehicle environment control, especially temperature regulation, is one of the key factors affecting passenger experience.

[0003] In traditional automotive air conditioning systems, temperature regulation mainly relies on manual adjustment by the user, with a few using temperature sensors and simple control systems. However, this approach may not be able to accurately adapt to the personalized needs of passengers or dynamically changing environmental conditions. In order to provide a higher level of comfort and more efficient energy use, a smarter and more precise control strategy is needed.

[0004] Air pressure inside a vehicle is another important factor that affects passenger comfort. Changes in air pressure reflect air flow and distribution, which in turn affects the perception and distribution of temperature and can even affect passengers’ moods. For example, a decrease in air pressure may make passengers feel oppressive, while an increase in air pressure may make them feel stuffy.

[0005] Therefore, an interconnected system for monitoring air-conditioning pressure sensors in new energy vehicles is expected. Summary of the invention

[0006] The present disclosure is made in view of the above problems. One object of the present disclosure is to provide an interconnection system for monitoring pressure sensors of air conditioners of new energy vehicles.

[0007] The embodiment of the present disclosure provides an interconnection system for monitoring pressure sensors of air conditioners of new energy vehicles, which includes:

[0008] Automobile air-conditioning pressure sensor acquisition module, used to obtain the time series of the air pressure inside the car collected by the air-conditioning pressure sensor of the new energy automobile;

[0009] A transmission module, used for transmitting the time series of the air pressure inside the vehicle to a vehicle control center through the Internet of Vehicles;

[0010] An air pressure frequency domain analysis module is used to perform frequency domain conversion and frequency domain analysis on the time series of the air pressure inside the vehicle in the vehicle control center to obtain a time-frequency mode characteristic diagram of the air pressure inside the vehicle;

[0011] An air pressure time domain analysis module is used to perform time domain analysis on the time series of the air pressure inside the vehicle at the vehicle control center to obtain an implicit representation vector of the spatiotemporal pattern of the air pressure inside the vehicle;

[0012] The air pressure data cross-modal fusion module is used to obtain the time-domain-frequency domain fusion representation feature map of the in-vehicle air pressure at the in-vehicle control center by using a time-domain-frequency domain cross-modal fusion encoder based on the MetaNet model to obtain the time-domain-frequency domain fusion representation feature map of the in-vehicle air pressure;

[0013] The fan speed control module is used to determine the fan speed control instruction in the vehicle computer control center based on the time domain-frequency domain fusion representation feature map of the vehicle interior air pressure.

[0014] For example, according to an interconnected system for monitoring air-conditioning pressure sensors of new energy vehicles according to an embodiment of the present disclosure, the air pressure frequency domain analysis module includes:

[0015] A wavelet transform unit, used for performing wavelet transform processing on the time series of the air pressure inside the vehicle to obtain a two-dimensional time-frequency diagram of the air pressure inside the vehicle;

[0016] The time-frequency pattern extraction unit is used to pass the two-dimensional time-frequency diagram of the in-vehicle air pressure through the time-frequency pattern feature extractor of the in-vehicle air pressure to obtain the time-frequency pattern feature diagram of the in-vehicle air pressure.

[0017] For example, according to an interconnected system for monitoring air-conditioning pressure sensors of new energy vehicles according to an embodiment of the present disclosure, the time-frequency pattern extraction unit is used to:

[0018] The two-dimensional time-frequency diagram of the in-vehicle air pressure is passed through an in-vehicle air pressure time-frequency pattern feature extractor based on a DenseNet model to obtain the in-vehicle air pressure time-frequency pattern feature diagram.

[0019] For example, according to an interconnected system for monitoring air-conditioning pressure sensors of new energy vehicles according to an embodiment of the present disclosure, the air pressure time domain analysis module includes:

[0020] A sequence structuring unit, used for arranging the time series of the air pressure inside the vehicle according to the time dimension to obtain a time series input vector of the air pressure inside the vehicle;

[0021] A segmentation unit, used for performing vector segmentation on the vehicle interior air pressure time series input vector to obtain a sequence of local vehicle interior air pressure time series input vectors;

[0022] The time series pattern extraction unit is used to pass the sequence of the local in-vehicle air pressure time series input vectors through the in-vehicle air pressure spatiotemporal pattern feature extractor to obtain the in-vehicle air pressure spatiotemporal pattern implicit representation vector.

[0023] For example, according to an interconnection system for monitoring air-conditioning pressure sensors of new energy vehicles according to an embodiment of the present disclosure, the timing pattern extraction unit is used to:

[0024] The sequence of the local in-vehicle air pressure time series input vectors is passed through an in-vehicle air pressure spatiotemporal pattern feature extractor based on a bidirectional long short-term memory neural network model to obtain an in-vehicle air pressure spatiotemporal pattern implicit representation vector.

[0025] For example, according to an interconnected system for monitoring air-conditioning pressure sensors of new energy vehicles according to an embodiment of the present disclosure, the air pressure data cross-modal fusion module includes:

[0026] A dimension correction unit, used for performing channel dimension correction on the implicit representation vector of the in-vehicle air pressure spatiotemporal pattern to obtain a corrected convolution feature vector of the in-vehicle air pressure spatiotemporal pattern;

[0027] A fusion representation unit is used to fuse the modified convolution feature vector of the in-vehicle air pressure spatiotemporal pattern with the in-vehicle air pressure time-frequency pattern feature map to obtain the in-vehicle air pressure time-domain-frequency domain fusion representation feature map.

[0028] For example, according to an interconnected system for monitoring air-conditioning pressure sensors of new energy vehicles according to an embodiment of the present disclosure, the dimension correction unit is used to:

[0029] Passing the implicit representation vector of the spatiotemporal pattern of the air pressure inside the vehicle through a point convolution layer to obtain a first convolution feature vector;

[0030] Passing the first convolution feature vector through a first rectified linear unit to obtain a first rectified convolution feature vector;

[0031] Passing the first modified convolutional feature vector through the point convolution layer to obtain a second convolutional feature vector;

[0032] The second convolution feature vector is passed through a second corrected linear unit to obtain the corrected convolution feature vector of the spatiotemporal pattern of the air pressure inside the vehicle.

[0033] For example, according to an interconnected system for monitoring air-conditioning pressure sensors of new energy vehicles according to an embodiment of the present disclosure, the first corrected linear unit uses a ReLU function, and the second corrected linear unit uses a Sigmoid function.

[0034] For example, according to an interconnection system for monitoring pressure sensors of air conditioners in new energy vehicles according to an embodiment of the present disclosure, the fan speed control module is used to:

[0035] The time-domain-frequency-domain fusion representation feature map of the vehicle interior air pressure is passed through a classifier-based fan speed controller to obtain the control instruction, where the control instruction is used to indicate whether the fan speed at the current time point should increase, decrease, or remain unchanged.

[0036] For example, according to an embodiment of the present disclosure, an interconnected system for monitoring air conditioning pressure sensors of new energy vehicles further includes a training module for training the in-vehicle air pressure time-frequency pattern feature extractor based on the DenseNet model, the in-vehicle air pressure time-space pattern feature extractor based on the bidirectional long short-term memory neural network model, the time-domain-frequency domain cross-modal fusion encoder based on the MetaNet model, and the fan speed controller based on the classifier; wherein the training module includes:

[0037] A training data acquisition unit, used to acquire training data, wherein the training data includes a time series of air pressure inside a training vehicle and a real value at a current time point at which the fan speed should increase, decrease, or remain unchanged;

[0038] A training wavelet transform processing unit, used for performing wavelet transform processing on the time series of the air pressure inside the training vehicle in the vehicle control center to obtain a two-dimensional time-frequency diagram of the air pressure inside the training vehicle;

[0039] A training vehicle interior air pressure time-frequency pattern feature extraction unit is used to obtain a training vehicle interior air pressure time-frequency pattern feature map by passing the training vehicle interior air pressure two-dimensional time-frequency map through the vehicle interior air pressure time-frequency pattern feature extractor based on the DenseNet model in the vehicle computer control center;

[0040] A training vehicle interior air pressure spatiotemporal pattern feature extraction unit is used to, in the vehicle control center, pass the time series of the training vehicle interior air pressure through the vehicle interior air pressure spatiotemporal pattern feature extractor based on the bidirectional long short-term memory neural network model to obtain an implicit representation vector of the training vehicle interior air pressure spatiotemporal pattern;

[0041] A training cross-modal fusion encoding unit is used to obtain a training vehicle interior air pressure time-domain-frequency domain fusion representation feature map in the vehicle control center by passing the training vehicle interior air pressure time-frequency mode feature map and the training vehicle interior air pressure time-space mode implicit representation vector through the MetaNet model-based time-domain-frequency domain cross-modal fusion encoder;

[0042] A classification loss calculation unit is used to pass the training vehicle interior air pressure time domain-frequency domain fusion representation feature map through the classifier-based fan speed controller in the vehicle control center to obtain a control instruction probability value and a classification loss function value;

[0043] A correlation loss calculation unit, configured to calculate a probability correlation loss function value based on the control instruction probability value in the vehicle control center;

[0044] A loss training unit is used to train the in-vehicle air pressure time-frequency pattern feature extractor based on the DenseNet model, the in-vehicle air pressure time-space pattern feature extractor based on the bidirectional long short-term memory neural network model, the time domain-frequency domain cross-modal fusion encoder based on the MetaNet model, and the classifier-based fan speed controller in the vehicle control center using the weighted sum between the classification loss function value and the probability-related loss function value as the loss function value.

[0045] According to the interconnection system for monitoring the air-conditioning pressure sensor of new energy vehicles in the embodiment of the present disclosure, it uses the air-conditioning pressure sensor of new energy vehicles to collect the air pressure data in the vehicle, introduces the interconnection technology and intelligent algorithm, and performs in-depth analysis on the data forms in each domain in the form of dual-pipeline parallel analysis after domain conversion of the air pressure data in the vehicle, and then organically integrates and interacts the two through cross-modal fusion coding to form a comprehensive fluctuation characteristic pattern expression of the air pressure in the vehicle, thereby guiding the control and adjustment of the fan speed. In this way, the air pressure data in the vehicle can provide additional information for temperature adjustment, and the air flow speed in the vehicle can be indirectly adjusted by controlling the fan speed, so as to achieve air pressure adjustment and improve user comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings of the embodiments of the present disclosure. Obviously, the drawings described below only relate to some embodiments of the present disclosure, and are not intended to limit the present disclosure.

[0047] Figure 1 A schematic diagram of the application architecture of an interconnection system for monitoring air-conditioning pressure sensors of new energy vehicles in an embodiment of the present disclosure is shown;

[0048] Figure 2 A schematic diagram of the structure of an interconnection system for monitoring air-conditioning pressure sensors for new energy vehicles in an embodiment of the present disclosure is shown;

[0049] Figure 3 A schematic diagram of the structure of an air pressure frequency domain analysis module of an interconnected system for monitoring air conditioning pressure sensors of new energy vehicles in an embodiment of the present disclosure is shown;

[0050] Figure 4 A schematic diagram of the structure of an air pressure time domain analysis module of an interconnected system for monitoring air conditioning pressure sensors of new energy vehicles in an embodiment of the present disclosure is shown;

[0051] Figure 5A schematic diagram of the structure of a cross-modal fusion module of air pressure data of an interconnected system for monitoring air-conditioning pressure sensors of new energy vehicles in an embodiment of the present disclosure is shown;

[0052] Figure 6 A flow chart of an interconnection method for monitoring air conditioning pressure sensors of new energy vehicles in an embodiment of the present disclosure is shown;

[0053] Figure 7 An application scenario diagram of an interconnection system for monitoring air-conditioning pressure sensors of new energy vehicles in an embodiment of the present disclosure is shown; and

[0054] Figure 8 A schematic diagram of a storage medium according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present disclosure, rather than all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present disclosure.

[0056] The terms used in this specification are those general terms currently widely used in the art in consideration of the functions of the present disclosure, but these terms may vary according to the intention of a person of ordinary skill in the art, precedents, or new technologies in the art. In addition, specific terms may be selected by the applicant, and in this case, their detailed meanings will be described in the detailed description of the present disclosure. Therefore, the terms used in the specification should not be understood as simple names, but rather as an overall description based on the meaning of the terms and the present disclosure.

[0057] Although the present disclosure makes various references to certain modules in the system according to embodiments of the present disclosure, any number of different modules can be used and run on a user terminal and / or server. The modules are illustrative only, and different aspects of the systems and methods can use different modules.

[0058] Flowcharts are used in this disclosure to illustrate the operations performed by the system according to the embodiments of the present disclosure. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0059] Figure 1 A schematic diagram of the application architecture of an interconnected system for monitoring air-conditioning pressure sensors of new energy vehicles in an embodiment of the present disclosure is shown, including a server 100 and a terminal device 200.

[0060] The terminal device 200 and the server 100 can be connected via the Internet to achieve mutual communication. Optionally, the above-mentioned Internet uses standard communication technology and / or protocol. The Internet is usually the Internet, but it can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or a virtual private network. In some embodiments, the data exchanged through the network can be represented by technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0061] The server 100 can provide various network services for the terminal device 200, wherein the server 100 can be a single server, a server cluster consisting of several servers, or a cloud computing center. Specifically, the server 100 may include a processor 110 (Center Processing Unit, CPU), a memory 120, an input device 130, and an output device 140, etc. The input device 130 may include a keyboard, a mouse, a touch screen, etc., and the output device 140 may include a display device, such as a liquid crystal display (Liquid Crystal Display, LCD), a cathode ray tube (Cathode Ray Tube, CRT), etc.

[0062] The memory 120 may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor 110 with program instructions and data stored in the memory 120. In the embodiment of the present disclosure, the memory 120 may be used to store the corresponding method of the interconnection system for monitoring the air conditioning pressure sensor of a new energy vehicle in the embodiment of the present disclosure.

[0063] The processor 110 calls the program instructions stored in the memory 120, and the processor 110 is used to execute the steps of any interconnection method for monitoring the air-conditioning pressure sensor of a new energy vehicle in the embodiments of the present disclosure according to the obtained program instructions.

[0064] In addition, the application architecture diagram in the embodiment of the present disclosure is intended to more clearly illustrate the technical solution in the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided in the embodiment of the present disclosure. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present disclosure is also applicable to similar problems.

[0065] The following is a non-restrictive description of an interconnected system for monitoring air-conditioning pressure sensors for new energy vehicles provided according to at least one embodiment of the present disclosure through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of the present disclosure.

[0066] In response to the above technical problems, the technical concept of the present disclosure is: using the air-conditioning pressure sensor of new energy vehicles to collect the air pressure data in the car, introducing interconnection technology and intelligent algorithms, performing domain conversion on the air pressure data in the car, and then conducting in-depth analysis of the data forms in each domain in the form of dual-pipeline parallel analysis, and then organically integrating and interacting the two through cross-modal fusion coding to form a comprehensive fluctuation characteristic pattern expression of the air pressure in the car, thereby guiding the control and adjustment of the fan speed. In this way, the air pressure data in the car can provide additional information for temperature adjustment, and the air flow speed in the car can be indirectly adjusted by controlling the fan speed, so as to achieve air pressure adjustment and improve user comfort.

[0067] Based on this, Figure 2The schematic diagram of the structure of the interconnection system 800 for monitoring the air-conditioning pressure sensor of a new energy vehicle in the embodiment of the present disclosure is shown. The interconnection system 800 for monitoring the air-conditioning pressure sensor of a new energy vehicle includes: an automobile air-conditioning pressure sensor acquisition module 810, which is used to obtain the time series of the air pressure in the vehicle collected by the air-conditioning pressure sensor of the new energy vehicle; a transmission module 820, which is used to transmit the time series of the air pressure in the vehicle to the vehicle control center through the Internet of Vehicles; an air pressure frequency domain analysis module 830, which is used to perform frequency domain conversion and frequency domain analysis on the time series of the air pressure in the vehicle at the vehicle control center to obtain a time-frequency mode characteristic diagram of the air pressure in the vehicle; an air pressure time domain analysis module 840, which is used to transmit the time series of the air pressure in the vehicle to the vehicle control center through the Internet of Vehicles. , performing time domain analysis on the time series of the in-vehicle air pressure to obtain an implicit representation vector of the in-vehicle air pressure spatiotemporal pattern; an air pressure data cross-modal fusion module 850, used in the in-vehicle control center, to obtain a time-domain-frequency domain fusion representation feature map of the in-vehicle air pressure time-frequency pattern and the implicit representation vector of the in-vehicle air pressure spatiotemporal pattern through a time-domain-frequency domain cross-modal fusion encoder based on the MetaNet model; a fan speed control module 860, used in the in-vehicle control center, to determine a control instruction for the fan speed based on the time-domain-frequency domain fusion representation feature map of the in-vehicle air pressure.

[0068] Specifically, in the technical solution disclosed in the present invention, first, the time series of the air pressure inside the car collected by the air conditioning pressure sensor of the new energy vehicle is obtained. In this way, the time series of the air pressure inside the car provides a continuous record of the change of the air pressure inside the car over time. By analyzing it, the law of air pressure change can be learned and the characteristic patterns of time series fluctuations, such as periodic fluctuations or abnormal changes, can be identified. These characteristic patterns of air pressure time series fluctuations may be associated with specific environmental conditions or vehicle behaviors, and can provide important data support for the control of fan speed. Then, the time series of the air pressure inside the car is transmitted to the vehicle control center through the Internet of Vehicles. It should be understood that the vehicle control center is usually equipped with more powerful computing resources, which can centrally process and analyze large amounts of data from sensors, so that it has the ability to run complex algorithms.

[0069] Considering that the time series of the air pressure in the vehicle often shows a trend of slow change or is accompanied by transient fluctuations and oscillations. In actual application scenarios, these mutations are usually the most interesting part of the data. In traditional data processing methods, Fourier transform is a powerful tool for data analysis, but it cannot effectively represent mutations. Therefore, in the technical solution of the present disclosure, it is expected that the time series of the air pressure in the vehicle is subjected to wavelet transform processing in the vehicle control center to obtain a two-dimensional time-frequency diagram of the air pressure in the vehicle. Among them, the wavelet transform processing uses a wavelet function with good localization characteristics in time and frequency to process the time series of the air pressure in the vehicle to convert it into the two-dimensional time-frequency diagram of the air pressure in the vehicle. Specifically, the wavelet transform decomposes the signal (the time series of the air pressure in the vehicle in the technical solution of the present disclosure) into the wavelet functions that constitute it, and these wavelet functions are localized waveforms in the time-frequency domain. Compared with the Fourier transform, the wavelet transform provides localization information in the time-frequency domain, which makes it very useful in analyzing non-stationary signals (signal characteristics change over time). Since the air pressure inside the car may show non-uniform changes over time, wavelet transform can adapt to this non-stationarity and provide more accurate analysis.

[0070] Considering that the two-dimensional time-frequency diagram of the in-vehicle air pressure provides time domain and frequency domain information about the air pressure change. However, since the two-dimensional time-frequency diagram of the in-vehicle air pressure contains a large number of data points, it may be difficult to directly extract useful features from the two-dimensional time-frequency diagram of the in-vehicle air pressure, and the useful information may be obscured by noise or unimportant details. In the technical solution disclosed in the present invention, in the vehicle control center, the two-dimensional time-frequency diagram of the in-vehicle air pressure is passed through an in-vehicle air pressure time-frequency pattern feature extractor based on the DenseNet model to utilize the deep learning architecture of DenseNet (densely connected convolutional network) to learn the rich feature representation in the two-dimensional time-frequency diagram of the in-vehicle air pressure.

[0071] Accordingly, if Figure 3 As shown, the air pressure frequency domain analysis module 830 includes: a wavelet transform unit 831, which is used to perform wavelet transform processing on the time series of the in-vehicle air pressure to obtain a two-dimensional time-frequency diagram of the in-vehicle air pressure; a time-frequency pattern extraction unit 832, which is used to pass the two-dimensional time-frequency diagram of the in-vehicle air pressure through a time-frequency pattern feature extractor of the in-vehicle air pressure to obtain the time-frequency pattern feature diagram of the in-vehicle air pressure.

[0072] Specifically, the time-frequency pattern extraction unit 832 is used to: pass the two-dimensional time-frequency diagram of the in-vehicle air pressure through an in-vehicle air pressure time-frequency pattern feature extractor based on a DenseNet model to obtain the in-vehicle air pressure time-frequency pattern feature diagram.

[0073] At the same time, in the vehicle control center, the time series of the air pressure in the vehicle is passed through the air pressure spatiotemporal pattern feature extractor based on the bidirectional long short-term memory neural network model to obtain the implicit representation vector of the air pressure spatiotemporal pattern in the vehicle. Among them, the bidirectional long short-term memory neural network (Bi-directional Long Short-Term Memory, Bi-LSTM) is a special recurrent neural network (RNN) that can process sequence data and capture long-term dependencies in time series. In the actual application scenario of the present disclosure, the air pressure data in the time series of the air pressure in the vehicle contain complex time-dependent associations, and the bidirectional long short-term memory neural network is naturally suitable for capturing such long-term temporal interweaving patterns of the air pressure in the vehicle. More importantly, the bidirectional long short-term memory neural network can process past and future information at the same time, which means that the model can simultaneously consider the contextual information before and after the current point in the time series of the air pressure in the vehicle, so as to more comprehensively understand the contextual temporal association pattern of the air pressure.

[0074] Accordingly, if Figure 4 As shown, the air pressure time domain analysis module 840 includes: a sequence structuring unit 841, which is used to arrange the time series of the in-vehicle air pressure according to the time dimension to obtain the in-vehicle air pressure time series input vector; a segmentation unit 842, which is used to perform vector segmentation on the in-vehicle air pressure time series input vector to obtain a sequence of local in-vehicle air pressure time series input vectors; and a time series pattern extraction unit 843, which is used to pass the sequence of local in-vehicle air pressure time series input vectors through an in-vehicle air pressure spatiotemporal pattern feature extractor to obtain the in-vehicle air pressure spatiotemporal pattern implicit representation vector.

[0075] Among them, the time series pattern extraction unit 843 is used to: pass the sequence of the local in-vehicle air pressure time series input vector through the in-vehicle air pressure spatiotemporal pattern feature extractor based on the bidirectional long short-term memory neural network model to obtain the in-vehicle air pressure spatiotemporal pattern implicit representation vector.

[0076] Next, in the vehicle control center, the time-frequency mode feature map of the in-vehicle air pressure and the implicit representation vector of the time-space mode of the in-vehicle air pressure are passed through a time-domain-frequency domain cross-modal fusion encoder based on the MetaNet model to obtain a time-domain-frequency domain fusion representation feature map of the in-vehicle air pressure. Here, the time-frequency mode feature map of the in-vehicle air pressure contains the time-frequency feature pattern of the in-vehicle air pressure data, which to a certain extent focuses on revealing the periodic law of the in-vehicle air pressure, while the implicit representation vector of the time-space mode of the in-vehicle air pressure contains the dynamic characteristics of the time series of the in-vehicle air pressure in the time dimension, which may focus more on characterizing and describing the long-term temporal dependence of the in-vehicle air pressure. The two respectively express the characteristics of the in-vehicle air pressure in different aspects and may contain complementary information. In this way, by integrating the two through the time-domain-frequency domain cross-modal fusion encoder based on the MetaNet model, the characteristic representation of the in-vehicle air pressure can be enriched.

[0077] Accordingly, if Figure 5 As shown, the air pressure data cross-modal fusion module 850 includes: a dimension correction unit 851, which is used to perform channel dimension correction on the implicit representation vector of the in-vehicle air pressure spatiotemporal pattern to obtain a corrected convolution feature vector of the in-vehicle air pressure spatiotemporal pattern; and a fusion representation unit 852, which is used to fuse the corrected convolution feature vector of the in-vehicle air pressure spatiotemporal pattern with the in-vehicle air pressure time-frequency pattern feature map to obtain the in-vehicle air pressure time-domain-frequency domain fusion representation feature map.

[0078] The dimension correction unit 851 is used to: pass the implicit representation vector of the temporal and spatial pattern of the air pressure in the vehicle through a point convolution layer to obtain a first convolution feature vector; pass the first convolution feature vector through a first correction linear unit to obtain a first correction convolution feature vector; pass the first correction convolution feature vector through the point convolution layer to obtain a second convolution feature vector; pass the second convolution feature vector through a second correction linear unit to obtain a correction convolution feature vector of the temporal and spatial pattern of the air pressure in the vehicle. Specifically, the first correction linear unit uses a ReLU function, and the second correction linear unit uses a Sigmoid function.

[0079] Furthermore, in the vehicle control center, the time-domain-frequency-domain fusion representation feature map of the air pressure in the vehicle is passed through a classifier-based fan speed controller to obtain a control instruction, and the control instruction is used to indicate whether the fan speed at the current time point should be increased, decreased, or kept unchanged. In this way, the control and adjustment of the fan speed are guided to provide additional information for temperature adjustment with the help of the air pressure data in the vehicle, and the air flow speed in the vehicle is indirectly adjusted to achieve air pressure adjustment and improve user comfort.

[0080] Correspondingly, the fan speed control module 860 is used to: pass the time domain-frequency domain fusion representation feature map of the vehicle interior air pressure through a classifier-based fan speed controller to obtain the control instruction, and the control instruction is used to indicate whether the fan speed at the current time point should increase, decrease or remain unchanged.

[0081] It should be understood that the role of the classifier is to use the given categories and known training data to learn classification rules and classifiers, and then classify (or predict) unknown data. Logistic regression, SVM, etc. are often used to solve binary classification problems. For multi-class classification problems, logistic regression or SVM can also be used, but multiple binary classifications are required to form a multi-classification, but this is prone to errors and inefficient. Commonly used multi-classification methods include the Softmax classification function.

[0082] Furthermore, in the technical solution of the present invention, the interconnected system for monitoring the air-conditioning pressure sensor of new energy vehicles also includes a training module for training the in-vehicle air pressure time-frequency pattern feature extractor based on the DenseNet model, the in-vehicle air pressure time-space pattern feature extractor based on the bidirectional long short-term memory neural network model, the time domain-frequency domain cross-modal fusion encoder based on the MetaNet model, and the classifier-based fan speed controller.

[0083] Among them, the training module includes: a training data acquisition unit, which is used to acquire training data, and the training data includes a time series of the training vehicle interior air pressure and a real value at the current time point that the fan speed should increase, decrease or remain unchanged; a training wavelet transform processing unit, which is used to perform wavelet transform processing on the time series of the training vehicle interior air pressure in the vehicle control center to obtain a two-dimensional time-frequency diagram of the training vehicle interior air pressure; a training vehicle interior air pressure time-frequency pattern feature extraction unit, which is used to pass the two-dimensional time-frequency diagram of the training vehicle interior air pressure through the vehicle interior air pressure time-frequency pattern feature extractor based on the DenseNet model in the vehicle control center to obtain a training vehicle interior air pressure time-frequency pattern feature diagram; a training vehicle interior air pressure spatiotemporal pattern feature extraction unit, which is used to pass the time series of the training vehicle interior air pressure through the vehicle interior air pressure spatiotemporal pattern feature extractor based on the bidirectional long short-term memory neural network model in the vehicle control center to obtain a training vehicle interior air pressure spatiotemporal pattern implicit representation vector; a training cross-modal fusion encoding unit, which is used to pass the training vehicle interior air pressure time-frequency pattern feature extractor based on the bidirectional long short-term memory neural network model in the vehicle control center to obtain a training vehicle interior air pressure spatiotemporal pattern implicit representation vector; The pattern feature map and the implicit representation vector of the training in-vehicle air pressure spatiotemporal pattern are passed through the time-domain-frequency-domain cross-modal fusion encoder based on the MetaNet model to obtain the training in-vehicle air pressure time-domain-frequency-domain fusion representation feature map; a classification loss calculation unit is used to pass the training in-vehicle air pressure time-domain-frequency-domain fusion representation feature map through the fan speed controller based on the classifier in the vehicle control center to obtain a control instruction probability value and a classification loss function value; a correlation loss calculation unit is used to calculate the probability correlation loss function value based on the control instruction probability value in the vehicle control center; a loss training unit is used to train the in-vehicle air pressure time-frequency pattern feature extractor based on the DenseNet model, the in-vehicle air pressure spatiotemporal pattern feature extractor based on the bidirectional long short-term memory neural network model, the time-domain-frequency-domain cross-modal fusion encoder based on the MetaNet model, and the fan speed controller based on the classifier in the vehicle control center using the weighted sum between the classification loss function value and the probability correlation loss function value as the loss function value.

[0084] In an optimization example, during the model training process, the control instruction probability value obtained by the fan speed controller based on the classifier for the time-frequency domain fusion representation feature map of the vehicle interior air pressure is, for example, expressed as , respectively representing the probability values ​​of the fan speed at the current time point whether it should increase, decrease or remain unchanged, and calculating the probability-related loss function value. The calculation process of the probability-related loss function value is specifically as follows: obtaining the control instruction probability value Then, subtract the control instruction probability value from one Get the score difference ; Determine the characteristic mean of all characteristic values ​​of the vehicle interior air pressure time domain-frequency domain fusion representation characteristic map as the characteristic set and characteristic variance ; Calculate each eigenvalue of the vehicle interior air pressure time domain-frequency domain fusion representation feature map in the form of cross entropy With each control quality probability value The product of the fractions minus each of the fractional differences With the feature mean The product of the class cross entropy difference is obtained; for each eigenvalue in the vehicle interior air pressure time domain-frequency domain fusion representation feature map and each control quality probability value The squares of the corresponding class cross entropy differences are summed and divided by the scale of the time-domain-frequency-domain fusion representation feature map of the interior air pressure to obtain a first loss term, wherein the scale of the time-domain-frequency-domain fusion representation feature map of the interior air pressure is the product of the width and height of the feature matrix of the time-domain-frequency-domain fusion representation feature map of the interior air pressure multiplied by the number of channels of the time-domain-frequency-domain fusion representation feature map of the interior air pressure; the control instruction probability value and the score difference The square of the bi-norm of the probability distribution vector and the characteristic variance Multiply them to obtain a second loss term; subtract the second loss term from the first loss term to obtain the probability-related loss function value.

[0085] Here, for the image semantic features of the two-dimensional time-frequency graph of the training vehicle interior air pressure expressed by the time-frequency pattern feature graph of the training vehicle interior air pressure, when the short-range-long-range bidirectional temporal correlation features of the training vehicle interior air pressure expressed by the implicit spatiotemporal pattern representation vector of the training vehicle interior air pressure are channel-constrained, the mixed distribution of different dimensional features of cross-modal data causes the out-of-distribution noise of the feature representation set, which causes the overall distribution noise of the training vehicle interior air pressure time-frequency domain fusion representation feature graph, thereby affecting the accuracy of the classification result. The above-mentioned probability-related loss function sets the approximate expected variance characteristics of the out-of-distribution noise of the feature set of the training vehicle interior air pressure time-frequency domain fusion representation feature graph relative to the Bernoulli sampling instance of the feature set based on the probability distribution characteristics expressed by the probability value and score difference of the training vehicle interior air pressure time-frequency domain fusion representation feature graph through the classifier.

[0086] Therefore, the distribution feature noise measurement is performed using statistical noise distribution based on the probability distribution characteristics expressed by the probability value and the fractional difference of the training vehicle interior air pressure time-domain-frequency domain fusion representation feature map through the training probability-related loss function. Based on the probability distribution of each feature value of the training vehicle interior air pressure time-domain-frequency domain fusion representation feature map in the classification process, the possible sampling noise features can be degraded according to the probabilistic cross-random selection characteristics of the expected variance of the training vehicle interior air pressure time-domain-frequency domain fusion representation feature map, which includes the class cross-entropy compound difference calculation. In this way, the class distribution noise reduction of self-supervised learning is realized in the process of updating the model parameters based on the training vehicle interior air pressure time-domain-frequency domain fusion representation feature map, so as to improve the accuracy of the control instructions obtained by the fan speed controller based on the classifier for the training vehicle interior air pressure time-domain-frequency domain fusion representation feature map.

[0087] Based on the above embodiments, see Figure 6 FIG. 1 is a flow chart of an interconnection method for monitoring air conditioning pressure sensors of new energy vehicles in an embodiment of the present disclosure. For example, the interconnection method for monitoring air conditioning pressure sensors of new energy vehicles can be executed by a server, which can be Figure 1 The server 100 shown in FIG. Figure 6 As shown, according to an embodiment of the present disclosure, the interconnection method for monitoring the air-conditioning pressure sensor of a new energy vehicle includes the following steps: S510, acquiring the time series of the air pressure inside the vehicle collected by the air-conditioning pressure sensor of the new energy vehicle; S520, transmitting the time series of the air pressure inside the vehicle to the vehicle control center through the vehicle network; S530, at the vehicle control center, performing frequency domain conversion and frequency domain analysis on the time series of the air pressure inside the vehicle to obtain a time-frequency mode characteristic diagram of the air pressure inside the vehicle; S540, at the vehicle control center, performing frequency domain conversion and frequency domain analysis on the time series of the air pressure inside the vehicle The column is subjected to time domain analysis to obtain an implicit representation vector of the spatiotemporal pattern of the in-vehicle air pressure; S550, an air pressure data cross-modal fusion module 850 is used to obtain a time-domain-frequency domain fusion representation feature map of the in-vehicle air pressure time-frequency pattern and the implicit representation vector of the spatiotemporal pattern of the in-vehicle air pressure through a time-domain-frequency domain cross-modal fusion encoder based on a MetaNet model in the in-vehicle control center; S560, in the in-vehicle control center, a control instruction for the fan speed is determined based on the time-domain-frequency domain fusion representation feature map of the in-vehicle air pressure.

[0088] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned interconnection method for monitoring the air conditioning pressure sensor of a new energy vehicle have been described in the above reference. Figures 2 to 5 The description of the interconnected system 800 for monitoring the air-conditioning pressure sensor of a new energy vehicle has been described in detail, and therefore, its repeated description will be omitted.

[0089] Figure 7 FIG. 1 is an application scenario diagram of an interconnection system for monitoring air conditioning pressure sensors of new energy vehicles according to an embodiment of the present disclosure. Figure 7 As shown, in this application scenario, first, the time series of the air pressure inside the vehicle collected by the air conditioning pressure sensor of the new energy vehicle is obtained (for example, Figure 7 D), and then, the time series of the air pressure inside the vehicle is input to a server (for example, Figure 7 In S) shown in , the server can use the interconnection algorithm for monitoring the air-conditioning pressure sensor of a new energy vehicle to process the time series of the air pressure in the vehicle to determine the control instruction of the fan speed.

[0090] Based on the above embodiments, another exemplary embodiment of an electronic device is also provided in the embodiments of the present disclosure. In some possible implementations, the electronic device in the embodiments of the present disclosure may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the interconnection method for monitoring the air conditioning pressure sensor of a new energy vehicle in the above embodiments when executing the program.

[0091] For example, the electronic device is disclosed in the present invention Figure 1 Taking the server 100 in the example as an example, the processor in the electronic device is the processor 110 in the server 100, and the memory in the electronic device is the memory 120 in the server 100.

[0092] An embodiment of the present disclosure also provides a computer-readable storage medium. Figure 8 FIG. 1 is a schematic diagram of a computer-readable storage medium 1000 according to an embodiment of the present disclosure. Figure 8 As shown, the computer-readable storage medium 1000 stores computer-executable instructions 1001. When the computer-executable instructions 1001 are executed by the processor, the interconnection method for monitoring the air-conditioning pressure sensor of a new energy vehicle according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc.

[0093] The embodiment of the present disclosure also provides a computer program product or computer program, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the interconnection method for monitoring the air-conditioning pressure sensor of a new energy vehicle according to the embodiment of the present disclosure.

[0094] Those skilled in the art will appreciate that the contents disclosed in this disclosure may be subject to various modifications and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0095] In addition, although the present disclosure makes various references to certain units in the system according to embodiments of the present disclosure, any number of different units may be used and run on the client and / or server. The units are illustrative only, and different aspects of the systems and methods may use different units.

[0096] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of a software functional module. The present disclosure is not limited to any particular form of combination of hardware and software.

[0097] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

[0098] The above is an explanation of the present disclosure and should not be considered as a limitation thereof. Although several exemplary embodiments of the present disclosure have been described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present disclosure. Therefore, all such modifications are intended to be included within the scope of the present disclosure as defined in the claims. It should be understood that the above is an explanation of the present disclosure and should not be considered as being limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present disclosure is defined by the claims and their equivalents.

Claims

1. An interconnection system for monitoring air conditioning pressure sensors in new energy vehicles. It is characterized in that include: Automobile air-conditioning pressure sensor acquisition module, used to obtain the time series of the air pressure inside the car collected by the air-conditioning pressure sensor of the new energy automobile; A transmission module, used for transmitting the time series of the air pressure inside the vehicle to a vehicle control center through the Internet of Vehicles; An air pressure frequency domain analysis module is used to perform frequency domain conversion and frequency domain analysis on the time series of the air pressure inside the vehicle in the vehicle control center to obtain a time-frequency mode characteristic diagram of the air pressure inside the vehicle; An air pressure time domain analysis module is used to perform time domain analysis on the time series of the air pressure inside the vehicle at the vehicle control center to obtain an implicit representation vector of the spatiotemporal pattern of the air pressure inside the vehicle; The air pressure data cross-modal fusion module is used to obtain the time-domain-frequency domain fusion representation feature map of the in-vehicle air pressure at the in-vehicle control center by using a time-domain-frequency domain cross-modal fusion encoder based on the MetaNet model to obtain the time-domain-frequency domain fusion representation feature map of the in-vehicle air pressure; A fan speed control module is used to determine a fan speed control instruction in the vehicle computer control center based on the time-domain-frequency-domain fusion representation characteristic diagram of the air pressure inside the vehicle; Wherein, the fan speed control module is used to: Passing the time-domain-frequency-domain fusion representation feature map of the air pressure inside the vehicle through a fan speed controller based on a classifier to obtain the control instruction, wherein the control instruction is used to indicate whether the fan speed at the current time point should increase, decrease, or remain unchanged; Among them, it also includes a training module for training a vehicle interior air pressure time-frequency pattern feature extractor based on a DenseNet model, a vehicle interior air pressure time-space pattern feature extractor based on a bidirectional long short-term memory neural network model, a time domain-frequency domain cross-modal fusion encoder based on a MetaNet model, and a fan speed controller based on a classifier; wherein the training module includes: A training data acquisition unit, used to acquire training data, wherein the training data includes a time series of air pressure inside a training vehicle and a real value at a current time point at which the fan speed should increase, decrease, or remain unchanged; A training wavelet transform processing unit, used for performing wavelet transform processing on the time series of the air pressure inside the training vehicle in the vehicle control center to obtain a two-dimensional time-frequency diagram of the air pressure inside the training vehicle; A training vehicle interior air pressure time-frequency pattern feature extraction unit is used to obtain a training vehicle interior air pressure time-frequency pattern feature map by passing the training vehicle interior air pressure two-dimensional time-frequency map through the vehicle interior air pressure time-frequency pattern feature extractor based on the DenseNet model in the vehicle computer control center; A training vehicle interior air pressure spatiotemporal pattern feature extraction unit is used to, in the vehicle control center, pass the time series of the training vehicle interior air pressure through the vehicle interior air pressure spatiotemporal pattern feature extractor based on the bidirectional long short-term memory neural network model to obtain an implicit representation vector of the training vehicle interior air pressure spatiotemporal pattern; A training cross-modal fusion encoding unit is used to obtain a training vehicle interior air pressure time-domain-frequency domain fusion representation feature map in the vehicle control center by passing the training vehicle interior air pressure time-frequency mode feature map and the training vehicle interior air pressure time-space mode implicit representation vector through the MetaNet model-based time-domain-frequency domain cross-modal fusion encoder; A classification loss calculation unit is used to pass the training vehicle interior air pressure time domain-frequency domain fusion representation feature map through the classifier-based fan speed controller in the vehicle control center to obtain a control instruction probability value and a classification loss function value; A correlation loss calculation unit, configured to calculate a probability correlation loss function value based on the control instruction probability value in the vehicle control center; A loss training unit is used to train the in-vehicle air pressure time-frequency pattern feature extractor based on the DenseNet model, the in-vehicle air pressure time-space pattern feature extractor based on the bidirectional long short-term memory neural network model, the time domain-frequency domain cross-modal fusion encoder based on the MetaNet model, and the classifier-based fan speed controller in the vehicle control center using the weighted sum between the classification loss function value and the probability-related loss function value as the loss function value.

2. The interconnection system for monitoring pressure sensors of air conditioners in new energy vehicles according to claim 1, It is characterized in that The air pressure frequency domain analysis module comprises: A wavelet transform unit, used for performing wavelet transform processing on the time series of the air pressure inside the vehicle to obtain a two-dimensional time-frequency diagram of the air pressure inside the vehicle; The time-frequency pattern extraction unit is used to pass the two-dimensional time-frequency diagram of the in-vehicle air pressure through the time-frequency pattern feature extractor of the in-vehicle air pressure to obtain the time-frequency pattern feature diagram of the in-vehicle air pressure.

3. The interconnection system for monitoring pressure sensors of air conditioners in new energy vehicles according to claim 2, It is characterized in that The time-frequency pattern extraction unit is used to: The two-dimensional time-frequency diagram of the in-vehicle air pressure is passed through an in-vehicle air pressure time-frequency pattern feature extractor based on a DenseNet model to obtain the in-vehicle air pressure time-frequency pattern feature diagram.

4. The interconnection system for monitoring pressure sensors of air conditioners in new energy vehicles according to claim 3, It is characterized in that The air pressure time domain analysis module comprises: A sequence structuring unit, used for arranging the time series of the air pressure inside the vehicle according to the time dimension to obtain a time series input vector of the air pressure inside the vehicle; A segmentation unit, used for performing vector segmentation on the vehicle interior air pressure time series input vector to obtain a sequence of local vehicle interior air pressure time series input vectors; The time series pattern extraction unit is used to pass the sequence of the local in-vehicle air pressure time series input vectors through the in-vehicle air pressure spatiotemporal pattern feature extractor to obtain the in-vehicle air pressure spatiotemporal pattern implicit representation vector.

5. The interconnection system for monitoring pressure sensors of air conditioners in new energy vehicles according to claim 4, It is characterized in that The timing pattern extraction unit is used to: The sequence of the local in-vehicle air pressure time series input vectors is passed through an in-vehicle air pressure spatiotemporal pattern feature extractor based on a bidirectional long short-term memory neural network model to obtain an in-vehicle air pressure spatiotemporal pattern implicit representation vector.

6. The interconnection system for monitoring pressure sensors of air conditioners in new energy vehicles according to claim 5, It is characterized in that The air pressure data cross-modal fusion module includes: A dimension correction unit, used for performing channel dimension correction on the implicit representation vector of the in-vehicle air pressure spatiotemporal pattern to obtain a corrected convolution feature vector of the in-vehicle air pressure spatiotemporal pattern; A fusion representation unit is used to fuse the modified convolution feature vector of the in-vehicle air pressure spatiotemporal pattern with the in-vehicle air pressure time-frequency pattern feature map to obtain the in-vehicle air pressure time-domain-frequency domain fusion representation feature map.

7. The interconnection system for monitoring pressure sensors of air conditioners in new energy vehicles according to claim 6, It is characterized in that The dimension correction unit is used to: Passing the implicit representation vector of the spatiotemporal pattern of the air pressure inside the vehicle through a point convolution layer to obtain a first convolution feature vector; Passing the first convolution feature vector through a first rectified linear unit to obtain a first rectified convolution feature vector; Passing the first modified convolutional feature vector through the point convolution layer to obtain a second convolutional feature vector; The second convolution feature vector is passed through a second corrected linear unit to obtain the corrected convolution feature vector of the spatiotemporal pattern of the air pressure inside the vehicle.

8. The interconnection system for monitoring pressure sensors of air conditioners in new energy vehicles according to claim 7, It is characterized in that The first rectified linear unit uses a ReLU function, and the second rectified linear unit uses a Sigmoid function.