Thermal management method and equipment for light truck cab and medium

Abstract

The invention discloses a thermal management method and device for a light truck cab and a medium, and the method comprises the steps: obtaining key part data and driver data of the cab, determining an equation set corresponding to a key part according to the key part data and the driver data, and determining a plurality of layered thermal resistance network models according to the equation set; and acquiring internal and external environment parameters of the cab, training and integrating a preset neural network model according to the internal and external environment parameters and the plurality of layered thermal resistance network models to obtain a thermal resistance network model, and predicting the heat flow of the cab through the thermal resistance network model. The hierarchical thermal resistance network model is constructed in combination with key components and driver data, and the neural network is trained and integrated by using internal and external environmental parameters, so that the thermal characteristics of the cab can be accurately reflected, the thermal flow prediction accuracy is improved, a reliable basis is provided for thermal management, and optimization design and improvement of energy efficiency and comfort are facilitated.

Description

Technical Field

[0001] The present application relates to the field of new energy vehicle technology, and in particular to a thermal management method, equipment, and medium for a light truck cab. Background Art

[0002] The thermal management of the electric light truck cab has a direct impact on driver comfort and vehicle energy consumption. Currently, the cabs of light trucks on the market are composed of multiple components, including glass, exterior sheet metal, air conditioning and felt layers, and interior trim. These components exhibit significant thermal characteristics under different operating conditions. Traditional cab thermal management modeling fails to fully account for the dynamic interactions between these components, leaving significant room for optimization in temperature, humidity, and energy consumption control. Furthermore, complex factors such as varying driving speeds, ambient temperature fluctuations, varying vehicle loads, solar radiation interference, the nonlinear response of the air conditioning system, and the utilization of waste heat from the electric light truck battery further complicate modeling. In practical applications, these factors lead to poor control accuracy of the thermal management system, making it difficult to meet the driver's demand for a comfortable driving environment and potentially resulting in energy waste. Existing technical approaches based on purely physical equations require extensive experimentation to calibrate parameters and struggle to adapt to dynamic environmental changes. Purely data-driven AI models, lacking constraints on physical mechanisms, are prone to overfitting. Summary of the Invention

[0003] In order to solve the above problems, the present application proposes a thermal management method for a light truck cab, including: obtaining key component data and driver data of the cab, the key components including glass, outer sheet metal, air layer, felt layer, and interior material, determining a set of equations corresponding to the key components based on the key component data and driver data, and determining multiple hierarchical thermal resistance network models based on the set of equations; obtaining internal and external environmental parameters of the cab, training and integrating a pre-set neural network model based on the internal and external environmental parameters and the multiple hierarchical thermal resistance network models to obtain a thermal resistance network model, and predicting the heat flow of the cab through the thermal resistance network model.

[0004] In one example, key component data and driver data of the cab are obtained, specifically including: collecting the transmittance, thermal conductivity, specific heat capacity, geometric shape and area data of the glass components; recording the thickness, thermal conductivity, specific heat capacity, geometric shape and coverage area data of the outer sheet metal; measuring the thickness, air flow rate and heat exchange coefficient of the air layer; obtaining the thermal insulation performance, moisture absorption characteristics and heat capacity data of the felt layer; collecting the surface emissivity, thermal resistance and geometric shape data of the interior material; determining the thermal physiological model corresponding to the driver, and obtaining node heat data based on multiple nodes of the thermal physiological model.

[0005] In one example, a group of equations corresponding to key components is determined based on the key component data and the driver data, specifically including: determining a non-steady-state heat conduction equation based on the data of the glass component, the non-steady-state heat conduction equation including transmittance, solar radiation absorption rate and convective heat transfer between the inner and outer surfaces; determining a thermal resistance network model based on the data of the outer sheet metal, and determining a thermal balance equation based on each node of the thermal resistance network model; determining an equivalent thermal resistance and heat capacity model based on the data of the air layer and the felt layer, and determining a heat transfer equation based on the equivalent thermal resistance and heat capacity model; determining a dynamic thermal response equation and a contact heat transfer equation based on the data of the interior material and the node heat data; integrating the thermal physiological model, the non-steady-state heat conduction equation, the thermal balance equation, the heat transfer equation, the dynamic thermal response equation and the contact heat transfer equation to determine the group of equations.

[0006] In one example, the internal and external environmental parameters of the cab are obtained, specifically including: real-time monitoring of the ambient temperature, relative humidity, and solar radiation intensity of the environment outside the cab; recording the vehicle speed to determine the air convection coefficient based on the vehicle speed, collecting temperature and humidity data at multiple locations inside the cab, and obtaining the operating status of the air-conditioning system, which includes the set temperature, wind speed level, and outlet temperature.

[0007] In one example, a preset neural network model is trained and integrated based on the internal and external environmental parameters and the multiple hierarchical thermal resistance network models, specifically including: preprocessing the internal and external environmental parameters to determine key features, which include ambient temperature, ambient humidity, solar radiation intensity, vehicle speed, temperature difference between the inside and outside of the glass, sheet metal temperature gradient, air layer heat flux density, and interior surface temperature; determining a preset multi-layer perceptron and determining the network structure of the multi-layer perceptron, which includes an input layer, multiple hidden layers, and an output layer; the number of nodes in the input layer is equal to the number of key features; the number of neurons in each layer of the hidden layer is set to a predetermined initial range, and ReLU is used as the activation function; the output layer is designed to be the temperature and humidity values ​​of multiple areas inside the cab.

[0008] In one example, the heat flow of the cab is predicted using the thermal resistance network model, specifically including: dividing the cab into multiple node systems, the node systems including thermal resistances in series and thermal resistances in parallel, calculating heat transfer through a preset set of formulas to obtain a preliminary prediction result; inputting the input parameters of the current working conditions into the thermal resistance network model to output a prediction residual, adjusting the key parameters of the thermal resistance network model according to the prediction residual, the key parameters including equivalent thermal conductivity, convection heat transfer coefficient, and radiation heat transfer parameters; and recalculating using the adjusted thermal resistance network model to obtain a corrected temperature prediction result.

[0009] In one example, after predicting the heat flow of the cab using the thermal resistance network model, the method further includes: verifying the prediction results of the thermal resistance network model, deploying the verified thermal resistance network model into a thermal management control system of a light truck, so as to predict the temperature and humidity values ​​of the cab through the thermal management control system, and coordinately control thermal management components according to the temperature and humidity values, wherein the thermal management components include an air conditioning subsystem, a ventilation subsystem, and a battery cooling subsystem.

[0010] In one example, the method further includes: regularly collecting new data of light trucks during actual operation, the new data including thermal management-related data under different seasons, different regional climates, multiple driving conditions, and different load conditions; and updating and training a thermal resistance network model deployed in a thermal management control system based on the new data so that the thermal resistance network model adapts to the actual operating conditions of the vehicle.

[0011] On the other hand, the present application also proposes a thermal management device for a light truck cab, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the thermal management device for the light truck cab to execute: a method as described in any one of the above examples.

[0012] On the other hand, the present application also proposes a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to perform the method described in any one of the above examples.

[0013] This application conducts comprehensive multi-dimensional data collection, covering key components, the driver, and internal and external environmental parameters, providing a rich basis for accurate modeling. Secondly, when constructing a hierarchical thermal resistance network model, corresponding equations are determined for different component characteristics, which can accurately reflect the thermal characteristics of each component and improve model accuracy. Using internal and external environmental parameters and the hierarchical thermal resistance network model to train and integrate a neural network, the neural network's powerful learning and prediction capabilities are fully utilized, resulting in a more reliable thermal resistance network model. Regarding heat flow prediction, the cab is transformed into a node system for calculation. Key parameters are adjusted based on the model output prediction residuals to obtain corrected and accurate prediction results. After verification, the prediction results are deployed to the thermal management control system, enabling real-time temperature and humidity predictions to guide the coordinated control of thermal management components such as air conditioning, ventilation, and battery cooling, achieving precise thermal comfort regulation and reducing energy consumption. Furthermore, regularly collecting new data to update and train the model ensures that the model remains adapted to the actual vehicle operating conditions, maintaining excellent prediction performance and effectively responding to changes in seasons, regions, operating conditions, and load conditions. This provides a scientific, efficient, and dynamic solution for light truck cab thermal management, improving overall vehicle performance and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0015] Figure 1 This is a flow chart of a thermal management method for a light truck cab in an embodiment of the present application;

[0016] Figure 2 This is a schematic diagram of a thermal management device for a light truck cab in an embodiment of the present application. DETAILED DESCRIPTION

[0017] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0019] like Figure 1 As shown, in order to solve the above problems, an embodiment of the present application provides a thermal management method for a light truck cab, the method comprising:

[0020] S101. Acquire key component data and driver data of the cab, wherein the key components include glass, outer sheet metal, air layer, felt layer, and interior material; determine a set of equations corresponding to the key components based on the key component data and driver data; and determine multiple layered thermal resistance network models based on the set of equations.

[0021] The parameters of the key components of the cab are collected, including the geometric shape, material properties and relative position relationship of the key components such as glass, outer sheet metal, air and felt layer, and interior, as shown in Table 1.

[0022] Table 1

[0023]

[0024]

[0025] In addition, it is necessary to collect parameters such as the transmittance and thermal conductivity of different types of glass, such as windshields and side windows; the thickness, thermal conductivity, and specific heat capacity of the outer sheet metal; the thickness, air flow rate, and heat exchange coefficient of the air layer; the thermal insulation performance, moisture absorption characteristics, and heat capacity of the felt layer; and the surface emissivity and thermal resistance of the interior materials, as shown in Table 2.

[0026] Table 2

[0027]

[0028]

[0029] In one embodiment, during the cab modeling process, the first step is to model the glass layer in the cab main body. Factors such as the glass's light transmittance, solar radiation absorption rate, and convection heat transfer between the inner and outer surfaces need to be considered to establish a non-steady-state heat conduction equation. According to the law of conservation of energy, the rate of heat change per unit volume in the glass layer is equal to the net rate of heat input into that volume. Specifically, when considering heat conduction, according to Fourier's law, the heat flux density Where k is the thermal conductivity of glass, is the temperature gradient; for solar radiation, let the solar radiation absorption rate be α and the solar radiation intensity be I, then the amount of solar radiation absorbed per unit volume is αI; for the convective heat transfer between the inner and outer surfaces, let the inner surface convective heat transfer coefficient be h1, the outer surface convective heat transfer coefficient be h2, the indoor temperature be T1, and the outdoor temperature be T2, then the heat transfer per unit area of ​​the inner surface is h1(T-T1), and the heat transfer per unit area of ​​the outer surface is h2(T2-T). Let the thickness of the glass layer be L and the transmittance be τ. When establishing the heat conduction equation, the transmittance mainly affects the amount of solar radiation reaching the glass because the radiation passing through the glass will be reduced. Combining the above factors, we can obtain the one-dimensional unsteady-state heat conduction equation:

[0030]

[0031] Where ρ is the density of the glass, c is the specific heat capacity of the glass, t is time, and x is the coordinate along the thickness of the glass. Parameters required for modeling include the glass's thermophysical properties ρ, c, and k; solar radiation parameters I, α, and τ; convective heat transfer coefficients h1 and h2; boundary temperatures T1 and T2; geometric parameters (glass layer thickness L); and the initial temperature distribution of the glass layer (T(x, 0)). Solving the above equations reveals the distribution of the temperature T(x, t) within the glass layer as a function of time t and position x. This information, along with the temporal variations of the temperatures on the inner and outer surfaces of the glass layer and the temporal variations of the heat flux through the glass layer, allows analysis of the heat transfer characteristics and thermal insulation performance of the glass layer.

[0032] In one embodiment, sheet metal layer modeling aims to calculate the temperature of thermal resistance network nodes based on the material's thermal conductivity and thickness. First, a geometric model is constructed. Based on the actual size and shape of the cab, a precise geometric model of the sheet metal layer is constructed using 3D modeling software. The dimensions, shapes, and spatial relationships of its components are clearly defined, with particular attention paid to details such as thickness variations in different locations. Next, a material model is determined to clarify the thermophysical properties of the sheet metal material, primarily its thermal conductivity, as sheet metal materials vary in thermal conductivity. A thermal resistance network model is then established, discretizing the sheet metal layer into a large number of nodes. Each node represents a tiny region within the sheet metal layer, and adjacent nodes are connected by thermal resistances to simulate the heat conduction process within the sheet metal layer. In this model, nodes are basic units, distributed in a certain pattern within the sheet metal layer space. Their temperature state reflects the thermal conditions at that location. The node distribution density is determined by the structural complexity of the sheet metal layer and the required computational accuracy. Nodes are denser in areas with large structural variations or drastic heat flux changes. Thermal resistances connect adjacent nodes, and their magnitude is determined by the material's thermal conductivity and the distance between nodes, i.e., the sheet metal layer thickness. The calculation formula is R = d / kA. It is usually assumed that the heat transfer area A is a unit area, so R = d / k. Thermal resistance reflects the difficulty of heat transfer between nodes. The greater the thermal resistance, the more difficult the heat transfer. The calculation process of the node temperature of the thermal resistance network is: first determine the boundary conditions and clarify the boundary temperature or heat flux density of the sheet metal layer. For example, it is known that one side of the sheet metal layer is in contact with the high temperature environment and the temperature is T h , the other side is in contact with the low temperature environment, the temperature is T c The temperatures on both sides can be used as the known temperature conditions of the boundary nodes; then the thermal resistance network equation is established. According to the principle of thermal balance, for each internal node, the heat flowing into the node is equal to the heat flowing out of the node.

[0033] Taking a one-dimensional thermal resistance network as an example, let the temperature of node i be T i , the temperatures of the left and right adjacent nodes are T i-1 and Ti+1 , then Based on this, the thermal balance equations for all nodes can be listed to form a system of equations. Finally, the system of equations can be solved using numerical methods such as Gaussian elimination and iterative methods to obtain the temperature value of each node. Using the above thermal resistance network model and calculation process, the temperature of each node in the thermal resistance network can be accurately calculated based on the thermal conductivity and thickness of the sheet metal layer, thereby understanding the temperature distribution within the sheet metal layer.

[0034] In one embodiment, in the modeling of the air and felt layers, the air gap and the felt are regarded as a composite thermal insulation layer, and equivalent thermal resistance and thermal capacitance are introduced to construct the model. The model structure consists of three parts: thermal resistance, heat capacity, and heat flow path. In terms of thermal resistance, the air gap and felt each have thermal resistance and are in a series relationship. The equivalent thermal resistance of the composite insulation layer is equal to the sum of the two thermal resistances. Air has low thermal conductivity and high thermal resistance, which can effectively hinder heat transfer. Felt, as a porous material, also has a certain thermal insulation capacity and thermal resistance value. In terms of thermal capacity, air and felt have their own heat capacity, which can be equivalent to the heat capacity of the composite insulation layer. The heat capacity reflects the ability of the material to store heat. The heat capacity of air is related to mass and specific heat capacity, while the heat capacity of felt is related to factors such as material and quality. The equivalent heat capacity affects the rate of temperature change during heat transfer. In the heat flow path, it is assumed that heat is transferred from one side through the composite insulation layer to the other side, and the heat flow first passes through the air gap and then through the felt, or vice versa. When establishing the model, the heat flow direction and boundary conditions are determined according to the actual situation. For example, given the temperature on both sides of the insulation layer or the heat flux density on one side, the temperature distribution and heat flow in the insulation layer are calculated by solving the heat conduction equation.

[0035] Taking one-dimensional heat conduction as an example, the composite insulation layer is divided into multiple micro-segments. Each micro-segment has a corresponding equivalent thermal resistance and heat capacity, similar to the RC network in the circuit. By establishing a thermal balance equation to describe the heat transfer and storage process in each micro-segment, the thermal performance of the entire composite insulation layer under different thermal boundary conditions is analyzed. Specifically, in the thermal resistance network, the air gap thermal resistance R air Depends on its thickness L air , air thermal conductivity λ air And the heat transfer area A can be expressed as Felt thermal resistance R felt Similarly, the felt thickness L felt , thermal conductivity λ felt and area A, that is, Equivalent thermal resistance R of composite insulation layer eq =R air +R felt In the heat capacity system, the heat capacity of air C air and air quality m air and specific heat capacity c air Related, namely Cair =m air c air , felt heat capacity C felt =m felt c felt , equivalent heat capacity of composite insulation layer C eq =C air +C felt In the heat transfer process, it is assumed that the heat is transferred from the high temperature side T h Transferred to the low temperature side through the composite insulation layer T c , the heat flux q obeys Fourier's law, that is The calculation process includes temperature change calculation and heat flow calculation. When calculating temperature change, according to the principle of heat balance, for a small time interval Δt, the heat flowing into the composite insulation layer is equal to the increase in the internal energy of the insulation layer, that is, qAΔt=C eq ΔT, where ΔT is the change in the temperature of the insulation layer. Substituting the heat flux density q into the equation yields The temperature distribution of the insulation layer at different times can be obtained through iterative calculation. When calculating the heat flow, the equivalent thermal resistance and the temperature difference on both sides are known. The heat flux through the composite insulation layer can be calculated. In practical applications, numerical calculations or analytical solutions are performed based on specific boundary and initial conditions, combining the above formula to analyze the insulation performance and temperature variation of the composite insulation layer. Actual conditions may be more complex, requiring model modifications to account for factors such as convective and radiative heat transfer.

[0036] In one embodiment, the interior layer modeling needs to establish a dynamic thermal response equation and an interior-driver contact heat transfer equation based on the heat capacity and surface radiation characteristics of the interior material. The dynamic thermal response equation is established based on the law of conservation of energy, that is, the heat accumulation of the interior material is equal to the heat absorbed minus the heat lost. This process must take into account the heat capacity characteristics of the material, which reflects the material's ability to absorb or release heat; and the surface radiation characteristics, which determine the rate at which the material exchanges heat with the surrounding environment through radiation. Its expression is: Where m is the mass of the interior material, C is the specific heat capacity of the material, T is the temperature of the material, t is the time, and q in is the heat flux density entering the material through conduction, etc., q out is the heat flux leaving the material by conduction, etc. is the radiative heat flux density, ∈ is the emissivity of the material, σ is the Stefan-Boltzmann constant, A is the surface area of ​​the material, T sur is the ambient temperature. This equation takes as input the material's mass, specific heat capacity, emissivity, surface area, ambient temperature, and heat flux, and outputs the temperature of the interior material over time.

[0037] The interior-driver contact heat transfer equation is based on Fourier's law, which states that heat transfers from a high-temperature object to a low-temperature object at a rate proportional to the temperature gradient. Considering the heat transfer between the driver and the interior, the contact area, contact thermal resistance, and the temperature difference between the two are key factors. Its expression is q c =hA(T d -T i ), where q c is the contact heat transfer heat flux density, h is the contact heat transfer coefficient, A{c} is the contact area, T d is the driver's skin temperature, T i is the interior material temperature. This equation takes as input the contact heat transfer coefficient, contact area, driver skin temperature, and interior material temperature. It outputs the heat flux density between the driver and the interior. This heat flux density can be used to further analyze factors such as the driver's perceived thermal comfort.

[0038] In one embodiment, the driver model is a driver thermophysiological model used to simulate the heat generation, transfer, and exchange processes in different parts of the driver's body, focusing on key nodes such as the head, chest, and feet. Specifically, the model sets the driver's head as a node, taking into account brain metabolic heat production, which produces approximately 20W of heat. This node mainly exchanges heat with the roof through radiation, transferring heat to the surrounding environment. The chest is used as another node, combining cardiopulmonary activity heat production, producing approximately 40W of heat. Due to contact with the seat, this node transfers heat to the seat through conduction, thereby simulating heat exchange between the chest and the seat. At the same time, the feet are set as nodes to quantify foot heat production, with a heat production of approximately 15W. On the one hand, this node exchanges heat with the floor through heat conduction, and on the other hand, there is a convection coupling effect with the air conditioning outlet, that is, heat is exchanged with the air in the air conditioning outlet through convection, thereby simulating heat transfer between the feet and the surrounding environment. By simulating the heat generation of these three nodes and their heat exchange with the surrounding environment, we can more comprehensively describe the thermal physiological state of the driver's body in the vehicle environment, providing a theoretical basis and model support for further research on driver thermal comfort and vehicle environment control.

[0039] S102. Obtaining internal and external environmental parameters of the cab, training and integrating a pre-set neural network model based on the internal and external environmental parameters and the multiple hierarchical thermal resistance network models to obtain a thermal resistance network model, and predicting the heat flow of the cab using the thermal resistance network model.

[0040] In one embodiment, the neural network auxiliary modeling plays an important role in the field of cab thermal management. The model external influence input parameters cover various temperature gradients, environmental temperature and humidity, solar radiation intensity, vehicle driving speed affecting the convection coefficient, glass inside and outside temperature difference, sheet metal temperature gradient, air layer heat flux density, interior surface temperature, and air conditioning operating state, etc. The model parameter output correction term is the residual error of the neural network prediction physical model and the actual temperature, and the thermal resistance network parameters such as the equivalent thermal conductivity are dynamically adjusted accordingly. In combination with the electric vehicle cab scene in the high temperature environment in summer, first, the external influence input parameters are defined. In a certain summer noon test scene, the environmental parameters are collected in real time, for example, the environmental temperature is 40℃, the relative humidity is 50%, the solar radiation intensity is 900W / m 2 ; the vehicle operating parameters are collected, for example, the vehicle speed is 80km / h, the air conditioning refrigeration mode is set to 22℃, the wind speed is 3 gears; and the structure parameters are collected, for example, the glass outside temperature is 65℃, the inside temperature is 30℃, the glass inside and outside temperature difference is 35℃; the roof sheet metal temperature is 60℃, the interior layer temperature is 32℃, the sheet metal-interior temperature gradient is 28℃; the air layer heat flux density near the air conditioning air outlet is -50W / m 2 , and the vehicle window is 15W / m 2; The seat surface temperature is 35°C, and the instrument panel surface temperature is 38°C. Then, a preliminary calculation of the physical model is performed based on the thermal resistance network. The traditional thermal resistance network model is used to simplify the cab into a node system consisting of glass, sheet metal, interior, air and other nodes in series / parallel. The heat transfer is calculated according to Fourier's law of heat conduction and Newton's cooling formula. Based on the above input parameters, the model preliminarily predicts that the average temperature in the cab is 28°C; then the neural network prediction residual is performed, and historical operating conditions data such as input parameters and actual temperature under different seasons, vehicle speeds, and air-conditioning conditions are collected in advance to construct a data set and train the neural network. For example, LSTM or multi-layer perceptron inputs the 12 input parameters of the current working conditions into the trained neural network in real time. The model output prediction residual is -3°C, that is, the physical model prediction value is 3°C higher than the actual temperature; then the thermal resistance network parameters are dynamically adjusted according to the residual predicted by the neural network. The thermal conductivity of glass and sheet metal was adjusted from 1.2W / (m·K) to 1.0W / (m·K) to reduce the amount of heat transferred into the cab. The convective heat transfer coefficient between the air-conditioning outlet and the air was fine-tuned to enhance the cooling effect. The radiation emissivity of the interior surface was reduced to reduce the temperature rise caused by solar radiation. After the adjustment, the thermal resistance network model was recalculated and the corrected temperature was 25°C. Verification and iteration were then carried out. The average temperature in the cab was measured to be 25.5°C by the in-vehicle temperature sensor. The error of the corrected model was reduced to 0.5°C, which was significantly improved compared to the initial model. At the same time, the input parameters of the current working conditions, the prediction residuals, the corrected parameters and the actual temperature were fed back to the neural network, and the model was continuously updated to improve the long-term prediction accuracy. This model dynamically corrects the thermal resistance network parameters through neural networks, and can adapt to complex and changeable driving environments such as sudden rainstorms causing a sudden drop in solar radiation and changes in wind speed when driving at high speeds. Compared with traditional static models, it can more accurately predict temperature and assist the air-conditioning system in intelligently adjusting the cooling capacity to achieve a balance between energy saving and comfort.

[0041] In one embodiment, to comprehensively and accurately collect data related to thermal management in the light truck cab, a large number of high-precision sensors are deployed at key locations inside and outside the cab. Specifically, temperature sensors with an accuracy of ±0.1°C are installed on the inner and outer surfaces of the glass, the inner and outer sheet metal, different sections of the air layer, key points within the felt layer, interior surfaces, instrument panel air vents, and around the driver's head, chest, and feet. Humidity sensors are installed in the cab to monitor internal humidity changes in real time. Flow rate sensors are installed at the air conditioning vents and air inlets to accurately capture airflow velocity. Furthermore, light intensity sensors and vehicle speed sensors are installed to comprehensively collect environmental and operational data relevant to thermal management. All sensors are connected to the onboard computer via a data acquisition module, with a data acquisition frequency set between 2Hz and 5Hz to ensure real-time and accurate capture of dynamic changes in the thermal environment. The collected data covers a wide range of conditions, including different seasons, climates, driving conditions, and loads. Driving conditions include urban congestion, highway cruising, slow driving on rural roads, and idling parking. Load conditions include unladen, half-loaded, and fully loaded. Simulation is also combined with the generation of diverse CAN bus integrated data to obtain relevant data on air conditioning, batteries, etc. In terms of software systems, the embedded AI chip can run the thermal management model in real time and output optimal control instructions through a PID controller or reinforcement learning agent.

[0042] In one embodiment, preprocessing is required for the massive amount of collected data. First, data cleaning is performed, using statistical methods to identify and remove outliers. For example, for temperature data, if the temperature at a particular point in time deviates from the mean temperature of the same region by more than three standard deviations, it is considered an outlier and removed. For flow rate data, any negative value or a value that exceeds the sensor's range by several times is also considered an outlier and removed. Next, missing data is processed using an appropriate filling method. For continuous data, such as a small number of missing values ​​in a temperature series, linear interpolation is used to fill in the missing values ​​based on the trends of adjacent data points. For discrete data, such as occasionally missing records of vehicle load conditions, the mode is selected based on the frequency of occurrence of the corresponding operating condition in the historical data. Finally, key features are carefully screened and extracted from the preprocessed data and used as input to the neural network. These features include ambient temperature, humidity, solar radiation intensity, vehicle speed, temperature difference between the inside and outside of the glass, sheet metal temperature gradient, air layer heat flux density, and interior surface temperature. They comprehensively reflect the internal and external factors affecting the cab thermal environment and the thermal state of each component.

[0043] In one embodiment, considering the complexity of the thermal management system and the input-output relationship, a multi-layer perceptron (MLP) is selected as the basic neural network architecture to construct a network structure consisting of an input layer, multiple hidden layers, and an output layer. The number of nodes in the input layer corresponds to the number of key features extracted to ensure that all influencing factors can be fully received. The hidden layer is set to 2-4 layers, and the number of neurons in each layer is optimized and determined through experiments. The initial range is set to 30-100 neurons. ReLU is used as the activation function to introduce nonlinear factors and enhance the model's ability to express complex heat transfer relationships. The output layer is designed to predict the temperature and humidity values ​​of multiple key areas inside the cab, such as the temperature of the driver's head, chest, and feet, as well as the average humidity in the cab, so as to intuitively evaluate thermal comfort and air quality.

[0044] In one embodiment, the preprocessed data set is divided into a training set, a validation set, and a test set in a ratio of 70%, 15%, and 15%. Then, the constructed neural network model is trained using the training set, and the stochastic gradient descent (SGD) and its variant optimization algorithms, such as the Adam optimization algorithm, are used in combination with the mean square error (MSE) as the loss function. The network weights are continuously adjusted through the back-propagation algorithm to gradually reduce the loss value of the model on the training set. In the early stage of training, a larger learning rate, such as 0.01, is set to speed up the convergence speed; as the training progresses, when it is observed that the loss value of the validation set no longer decreases after 3-5 consecutive iterations, the learning rate decay strategy is used to reduce the learning rate by 50% to prevent the model from falling into a local optimal solution, thereby ensuring that the model has good generalization ability.

[0045] In one embodiment, after a validated model is deployed to a light truck's thermal management control system, it can receive real-time sensor data as input. The model's output, predicted cabin temperature and humidity, can guide the coordinated control of thermal management components such as the air conditioning system, ventilation system, and battery cooling system. For example, based on the predicted temperature increase trend, the air conditioning cooling power can be adjusted in advance; based on the predicted humidity value, the dehumidification function can be turned on or off at the appropriate time, thereby achieving precise thermal comfort adjustment and effectively reducing energy consumption. Furthermore, as light trucks continue to be used, new data needs to be collected regularly. The update cycle, typically one to two months, is determined based on the frequency of vehicle use and the degree of change in operating conditions. The deployed model is then updated and trained using this new data. When incorporating new data into the training set, it must be processed according to the data preprocessing steps described previously to ensure that the model always adapts to the actual vehicle operating conditions and maintains excellent predictive performance.

[0046] like Figure 2 As shown, the embodiment of the present application also provides a thermal management device for a light truck cab, comprising:

[0047] at least one processor; and,

[0048] a memory communicatively connected to at least one processor; wherein,

[0049] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor to enable a thermal management device for a light truck cab to perform: the method described in any one of the above embodiments.

[0050] An embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to perform the method described in any one of the above embodiments.

[0051] In the 1990s, it was relatively easy to distinguish whether an improvement in a technology was a hardware improvement (e.g., an improvement in the circuit structure of a diode, transistor, switch, etc.) or a software improvement (an improvement in a method flow). However, as technology has evolved, many improvements in method flows today can be considered as direct improvements in hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structures by programming the improved method flows into hardware circuits. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using hardware entity modules. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is an integrated circuit whose logic function is determined by user programming of the device. A digital system is "integrated" on a PLD by the designer programming the PLD, rather than by ordering a chip manufacturer to design and fabricate a custom integrated circuit chip. Moreover, instead of manually fabricating integrated circuit chips, this programming is now mostly implemented using "logic compiler" software, which is similar to software compilers used in program development, and the original code to be compiled is written in a specific programming language, which is called a hardware description language (HDL), and there are many such languages, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., and the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should be aware that, as long as the method flow is logically programmed in the above-mentioned hardware description languages and programmed into an integrated circuit, a hardware circuit implementing the logical method flow can be easily obtained.

[0052] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to implementing the controller in a purely computer-readable program code format, the controller can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules that implement the method and structures within the hardware component.

[0053] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0054] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0055] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device and medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0056] The device and medium provided by the embodiments of the present application are one-to-one corresponding, and therefore, the device and medium also have similar beneficial technical effects to the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device and medium will not be described here again.

[0057] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. In addition, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0058] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowcharts and / or block diagrams.

[0059] These computer program instructions can also be stored in a computer-readable memory capable of directing the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowcharts and / or block diagrams.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowcharts and / or block diagrams.

[0061] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memories.

[0062] Memory can include non-persistent memory, Random Access Memory (RAM), and / or non-volatile memory, such as Read Only Memory (ROM) or flash memory, in computer readable media. Memory is an example of computer readable media.

[0063] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0064] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not include only those elements in the list, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without further limitation, an element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0065] The above merely provides an example of the present application and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for thermal management of a light truck cab, characterized in that: include: Acquiring key component data of the cab and driver data, the key components including glass, outer sheet metal, air layer, felt layer, and interior material, and determining a set of equations corresponding to the key components based on the key component data and the driver data, thereby determining multiple hierarchical thermal resistance network models based on the set of equations; The internal and external environmental parameters of the cab are obtained, and a pre-set neural network model is trained and integrated according to the internal and external environmental parameters and the multiple hierarchical thermal resistance network models to obtain a thermal resistance network model, and the heat flow of the cab is predicted by the thermal resistance network model.

2. The method according to claim 1, characterized in that Obtain key cab component data and driver data, including: Collect data on light transmittance, thermal conductivity, specific heat capacity, geometry, and area of ​​glass components; Record the thickness, thermal conductivity, specific heat capacity, geometry and coverage area data of the outer sheet metal; Measure the thickness of the air layer, air velocity and heat exchange coefficient; Obtain data on the thermal insulation performance, moisture absorption characteristics and heat capacity of the felt layer; Collect surface emissivity, thermal resistance, and geometry data for interior materials; A thermophysiological model corresponding to the driver is determined, and node heat data is obtained according to a plurality of nodes of the thermophysiological model.

3. The method according to claim 2, characterized in that Determine the equation group corresponding to the key component according to the key component data and the driver data, specifically including: Determining a non-steady-state heat conduction equation based on the data of the glass component, wherein the non-steady-state heat conduction equation includes light transmittance, solar radiation absorptivity, and convection heat transfer between the inner and outer surfaces; Determining a thermal resistance network model according to the data of the outer sheet metal, and determining a thermal balance equation according to each node of the thermal resistance network model; Determining an equivalent thermal resistance and heat capacity model based on the data of the air layer and the felt layer, and determining a heat transfer equation based on the equivalent thermal resistance and heat capacity model; Determining a dynamic thermal response equation and a contact heat transfer equation based on the interior material data and the node heat data; The thermophysiological model, the unsteady-state heat conduction equation, the heat balance equation, the heat transfer equation, the dynamic thermal response equation and the contact heat transfer equation are integrated to determine the set of equations.

4. The method according to claim 1, wherein Obtain the internal and external environmental parameters of the cab, including: Real-time monitoring of the ambient temperature, relative humidity, and solar radiation intensity of the cab's external environment; The vehicle's driving speed is recorded to determine the air convection coefficient based on the vehicle's driving speed, and temperature and humidity data at multiple locations inside the cab are collected to obtain the operating status of the air conditioning system, which includes the set temperature, wind speed level, and outlet temperature.

5. The method according to claim 1, wherein Training and integrating a preset neural network model according to the internal and external environmental parameters and the multiple hierarchical thermal resistance network models specifically includes: Preprocessing the internal and external environmental parameters to determine key features, including ambient temperature, ambient humidity, solar radiation intensity, vehicle speed, temperature difference between the inside and outside of the glass, sheet metal temperature gradient, air layer heat flux density, and interior surface temperature; Determining a pre-set multi-layer perceptron and determining a network structure of the multi-layer perceptron, wherein the network structure includes an input layer, multiple hidden layers, and an output layer; The number of input layer nodes is equal to the number of key features; The number of neurons in each layer of the hidden layer is set to a predetermined initial range, and ReLU is used as the activation function; The output layer is designed to be the temperature and humidity values ​​of multiple areas inside the cab.

6. The method according to claim 1, characterized in that Predicting the heat flow of the cab by using the thermal resistance network model specifically includes: The cab is divided into multiple node systems, including thermal resistances in series and in parallel, and heat transfer is calculated using a pre-set set of formulas to obtain preliminary prediction results. Inputting the input parameters of the current working condition into the thermal resistance network model to output a prediction residual, and adjusting the key parameters of the thermal resistance network model according to the prediction residual, the key parameters including equivalent thermal conductivity, convection heat transfer coefficient, and radiation heat transfer parameter; Recalculation is performed using the adjusted thermal resistance network model to obtain a revised temperature prediction result.

7. The method according to claim 1, characterized in that After predicting the heat flow of the cab using the thermal resistance network model, the method further includes: The prediction results of the thermal resistance network model are verified, and the verified thermal resistance network model is deployed in a thermal management control system of a light truck to predict the temperature and humidity values ​​of the cab through the thermal management control system, so as to coordinate and control thermal management components according to the temperature and humidity values, and the thermal management components include an air conditioning subsystem, a ventilation subsystem, and a battery cooling subsystem.

8. The method according to claim 1, characterized in that The method further comprises: Regularly collect new data from actual light truck operation, including thermal management data for different seasons, climates, driving conditions, and loads. The thermal resistance network model deployed in the thermal management control system is updated and trained according to the new data, so that the thermal resistance network model adapts to the actual operating conditions of the vehicle.

9. A thermal management device for a light truck cab, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the thermal management device of the light truck cab to perform: the method according to any one of claims 1 to 8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to: perform the method according to any one of claims 1 to 8.

Images