Hybrid loader heat management method, device, equipment, medium and product

Abstract

The application relates to the technical field of heat management of hybrid engineering machinery, and discloses a heat management method, device, equipment, medium and product of a hybrid loader. The heat management method of the hybrid loader provided by the application acquires a heat load grade and a temperature change amount by collecting current operation parameters and inputting a temperature prediction model, and heat management is performed based on the heat load grade and the temperature change amount, so that the self-adaptability and efficiency of heat management are improved.

Description

Technical Field

[0001] This application relates to the field of thermal management technology for hybrid engineering machinery, specifically to a thermal management method, device, equipment, medium, and product for a hybrid loader. Background Technology

[0002] In related technologies, the thermal management mode of loaders cannot effectively cope with the complex and ever-changing working conditions in actual operation and the different driving habits of different drivers. For example, the characteristics of loader operation such as rapid acceleration, rapid deceleration and sudden load changes cause frequent and large changes in the flow rate of water pump coolant, which accelerates the aging of key components and reduces their service life. Summary of the Invention

[0003] This application provides a thermal management method, apparatus, equipment, medium, and product for a hybrid loader.

[0004] In a first aspect, this application provides a thermal management method for a hybrid loader, the method comprising: collecting current operating parameters of the hybrid loader, wherein the current operating parameters include at least one of the current operating power, current power change rate, and current operating duration of each motor in the hybrid loader; inputting the current operating parameters into a temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period, wherein the temperature prediction model is trained using historical operating parameters; and performing thermal management on the hybrid loader based on the heat load level and temperature change.

[0005] Based on the aforementioned technical means, by collecting the current operating parameters of the hybrid loader in real time and inputting them into a temperature prediction model trained with historical data, it is possible to dynamically obtain the heat load level and temperature change of the motor within a preset time period.

[0006] In one optional implementation, the step of training the temperature prediction model includes: obtaining historical operating parameters of each motor in the hybrid loader and corresponding historical cooling device parameters, wherein the historical operating parameters include the historical power, historical power change rate and historical running time of each motor at different times, and the historical cooling device parameters include the historical coolant temperature; and training the model of the data to be trained based on the historical operating parameters and corresponding historical cooling device parameters to obtain the temperature prediction model.

[0007] Based on the above technical means, the obtained temperature prediction model can more accurately reflect the actual thermal behavior of each motor in the hybrid loader, and improve the prediction accuracy of heat load level and temperature change.

[0008] In one optional implementation, a temperature prediction model is trained based on historical operating parameters and corresponding historical cooling device parameters. This includes: storing the historical operating parameters and corresponding historical cooling device parameters to obtain stored operating data, wherein the stored operating data is periodically updated according to a time series; and adjusting the weights of the parameters in the temperature prediction model based on the stored operating data and applying the adjusted parameters to the temperature prediction model.

[0009] Based on the above technical means, not only is the accuracy of heat load prediction significantly improved, but the robustness and adaptability of the model are also enhanced. This enables the thermal management system of the hybrid loader to accurately and effectively control heat dissipation or heat preservation, avoiding over-cooling or under-cooling caused by inaccurate prediction, extending the service life of key components such as motors, and improving the overall operating efficiency and reliability of the machine.

[0010] In one optional implementation, the temperature prediction model includes one of a neural network model and a linear regression algorithm. The current operating parameters are input into the temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period. This includes: inputting the current operating parameters into a trained neural network to obtain the heat load level; inputting the current operating parameters into a trained linear regression algorithm to obtain the heat load; and calculating the temperature change based on the heat load.

[0011] Based on the aforementioned technical means, by applying the neural network model to the task of classifying heat load levels, it is possible to utilize its ability to capture nonlinear relationships to identify the heat load levels of motors under different operating conditions.

[0012] In one alternative implementation, thermal management of the hybrid loader is performed based on the heat load level and the amount of temperature change, including: determining the basic strength of thermal management according to the heat load level, and determining the additional strength of thermal management according to the amount of temperature change.

[0013] Based on the above technical means, the thermal management system can maintain overall stability while taking into account the dynamic changes in an instant, thereby improving the adaptability, response accuracy and overall efficiency of thermal management, effectively extending the service life of the motor and ensuring the stable operation of the hybrid loader.

[0014] In one optional implementation, the method further includes: determining the ratio of the power of each motor to the total power in the power allocation information, and prioritizing the heat dissipation of each motor according to the ratio; and performing heat dissipation control and / or heat preservation control on each motor according to the priority ranking.

[0015] Based on the above technical means, the overall thermal management efficiency of the hybrid loader has been improved, the service life of each motor has been extended, and the system energy consumption has been optimized.

[0016] Secondly, this application provides a thermal management device for a hybrid loader, the device comprising: a data acquisition module for acquiring the current operating parameters of the hybrid loader, wherein the current operating parameters include at least one of the current operating power, current power change rate, and current operating duration of each motor in the hybrid loader; a prediction module for inputting the current operating parameters into a temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period, wherein the temperature prediction model is trained using historical operating parameters; and a management module for performing thermal management on the hybrid loader based on the heat load level and temperature change.

[0017] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the thermal management method of the hybrid loader described in the first aspect or any corresponding embodiment.

[0018] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the thermal management method for a hybrid loader according to the first aspect or any corresponding embodiment described above.

[0019] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the thermal management method for a hybrid loader described in the first aspect or any corresponding embodiment. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is a schematic flowchart of a first method for thermal management of a hybrid loader according to an embodiment of this application; Figure 2 This is a second flowchart illustrating the thermal management method for a hybrid loader according to an embodiment of this application; Figure 3 This is a schematic diagram of a third process for a thermal management method for a hybrid loader according to an embodiment of this application; Figure 4 This is a structural block diagram of the thermal management device of a hybrid loader according to an embodiment of this application; Figure 5 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0024] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0025] In related technologies, loader thermal management systems primarily rely on fixed parameter thresholds and predefined rules for control. This makes them unable to adapt to diverse working conditions and driving habits, and difficult to accurately cover all complex scenarios. Furthermore, they fail to adequately consider the characteristics of sudden acceleration, deceleration, and load changes that may occur during loader operation, potentially accelerating the aging of critical components. Existing systems lack mechanisms for real-time perception of operating status, dynamic prediction of thermal load changes, and adaptive adjustment; instead, they rely on static, pre-set rules for passive responses.

[0026] In response, this application proposes a thermal management method for hybrid loaders, such as... Figure 1 As shown, the method includes: Step S101: Collect the current operating parameters of the hybrid loader.

[0027] The current operating parameters include at least one of the following: the current operating power, the current power change rate, and the current operating time of each motor in the hybrid loader.

[0028] A hybrid loader is a loader equipped with at least two power sources. Its power system can mix and distribute energy according to working conditions to improve fuel efficiency and operational performance.

[0029] Current operating parameters refer to data collected in real-time or near real-time during the operation of a hybrid loader, reflecting its working status, such as the current operating power, current power change rate, and current operating time of each motor. These parameters are used to characterize the load and operating intensity of the loader at a specific moment.

[0030] Specifically, this can be achieved by deploying appropriate sensors or data interfaces, such as power sensors, speed sensors, and timing modules, on the hybrid loader to periodically acquire operational data. For example, the motor's current operating power can be measured in real time using current and voltage sensors; the current power change rate can be obtained by differential calculation of continuously collected power data; and the current operating duration can be recorded by an internal timer. The acquisition of these parameters aims to reflect the actual operating status and load conditions of the hybrid loader and its motor in real time.

[0031] Step S102: Input the current operating parameters into the temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period.

[0032] The temperature prediction model was trained using historical operating parameters.

[0033] A temperature prediction model is a mathematical or algorithmic model that is built by learning and training on historical operating data. It can predict the heat load level and temperature change trend of key components in a hybrid loader, such as the motor, within a preset time period based on the input current operating parameters.

[0034] The heat load level refers to the result of a graded assessment of the heat load borne by each motor in a hybrid loader within a preset time period. For example, it can be divided into low, medium, high or more detailed levels to indicate the degree of heat generation of the motor.

[0035] Temperature change refers to the expected increase or decrease in the temperature of each motor in a hybrid loader relative to the current temperature within a preset time period. This value reflects the dynamic trend of motor temperature change.

[0036] Specifically, the model can be a pre-built lookup table based on historical data statistical patterns, or a mathematical model fitted using empirical formulas. When current operating parameters are input into the model, it outputs the heat load level and temperature change of each motor in the hybrid loader over a preset future time period, based on its internal logic or stored mapping relationships. For example, the model can consult a preset table based on the current power, power change rate, and operating time to directly provide the corresponding heat load level, such as "low," "medium," or "high," and the expected temperature rise.

[0037] Step S103: Perform thermal management on the hybrid loader based on the heat load level and temperature change.

[0038] Thermal management refers to regulating and maintaining the temperature of key components in a hybrid loader, such as the motor, by controlling the cooling system, heating system, or other related actuators to ensure that they operate within a suitable temperature range, thereby guaranteeing their performance, efficiency, and service life.

[0039] Specifically, based on the predicted heat load level, for example, when the heat load level is "high," the cooling fan can be directly started or the coolant pump flow rate increased. Simultaneously, considering the predicted temperature change, such as when the expected temperature rise exceeds a certain threshold, the operating intensity of the cooling system can be further adjusted, for example, by switching the cooling fan speed from low to medium. Thus, by controlling the actuators such as the cooling or heating systems, the motor temperature in the hybrid loader is maintained within a suitable operating range, thereby preventing overheating or overcooling from affecting motor performance and lifespan.

[0040] It is understood that the thermal management method proposed in this application, by collecting the current operating parameters of the hybrid loader in real time and inputting them into a temperature prediction model trained with historical data, can dynamically obtain the thermal load level and temperature change of the motor within a preset time period. Therefore, the system can perform adaptive thermal management of the hybrid loader based on this predictive information. This overcomes the limitations of traditional systems that rely on fixed thresholds and predefined rules, achieving precise responses to diverse working conditions, driving habits, and operational characteristics, effectively avoiding component aging caused by sudden load changes, thereby improving the reliability and efficiency of the hybrid loader's operation. In some of the solutions described above in this application, a temperature prediction model is proposed to predict the heat load level and temperature change. However, in the process of its implementation, the training of the model may lack effective integration of historical operating parameters and cooling device parameters, resulting in insufficient prediction accuracy and failure to fully reflect the actual operating conditions and the impact of the cooling system.

[0041] In this regard, this application further proposes the following steps for training the temperature prediction model: Step a1: Obtain the historical operating parameters of each motor in the hybrid loader and the corresponding historical cooling device parameters. The historical operating parameters include the historical power, historical power change rate and historical running time of each motor at different times. The historical cooling device parameters include the historical coolant temperature.

[0042] Step a2: Train the model of the data to be trained based on historical operating parameters and corresponding historical cooling device parameters to obtain a temperature prediction model.

[0043] Specifically, acquiring historical operating parameters of each motor and corresponding historical cooling system parameters in the hybrid loader aims to provide comprehensive, multi-dimensional input data for training the temperature prediction model. Historical operating parameters reflect the heat generation of the motors under different operating conditions, while historical cooling system parameters reflect the cooling system's heat dissipation capability. This step can be achieved by deploying a sensor network on the hybrid loader to collect real-time data such as the power, power change rate, operating time, and coolant temperature of each motor, storing this data in an onboard data logger or cloud server to form a historical database. Alternatively, data can be interfaced with the hybrid loader's vehicle control unit (VCU) or motor control unit (MCU) to obtain the necessary historical operating data and cooling system data from their internal buses and store them periodically.

[0044] Historical operating parameters include the historical power, historical power change rate, and historical running time of each motor at different times. These parameters are key indicators for assessing the motor's thermal load. Historical power directly reflects the heat generated by the motor's work; the historical power change rate captures the thermal shock caused by transient load changes in the motor, such as rapid acceleration or deceleration; historical running time accumulates the heat generated by the motor's continuous operation, which is crucial for assessing thermal inertia effects. Historical power can be measured and calculated in real time using current and voltage sensors; the historical power change rate can be calculated by differential or derivative calculations of the historical power data; and the historical running time can be obtained through a timer or system running time recording module. Furthermore, these parameters can also be directly output by the motor controller, which typically records the motor's real-time operating status and can provide historical data as needed.

[0045] Historical cooling system parameters include historical coolant temperature. Historical coolant temperature is a key parameter for measuring the cooling system's heat dissipation efficiency and the motor's heat dissipation environment. It reflects the cooling system's ability to remove heat from the motor and is crucial for accurately predicting motor temperature. Historical coolant temperature can be measured in real time by installing temperature sensors in the coolant circulation lines and recording the values. Alternatively, it can be obtained from the coolant temperature data recorded internally by the cooling system controller (such as an electronic water pump controller).

[0046] A temperature prediction model is obtained by training a data model based on historical operating parameters and corresponding historical cooling device parameters. By inputting multi-dimensional historical data into the data model, the model can learn the complex nonlinear relationship between motor operating state, cooling system state, and motor temperature changes, thereby establishing a temperature prediction model with high prediction accuracy. Machine learning algorithms, such as neural networks (e.g., Long Short-Term Memory Network (LSTM), Convolutional Neural Network (CNN), fully connected neural networks, Support Vector Machines (SVM), or decision trees), can be used, with historical operating parameters and historical cooling device parameters as input features and the actual measured motor temperature as the output label for supervised learning training. Alternatively, a combination of physical model and data-driven approach can be used. First, a thermodynamic physical model of the motor is established, and then historical data is used to identify and calibrate the unknown parameters in the model, resulting in a hybrid model.

[0047] It is understandable that by integrating historical operating parameters—namely, historical power, historical power change rate, historical operating time, and historical cooling device parameters—namely, historical coolant temperature—the above technical solution provides a comprehensive and accurate data foundation for training the temperature prediction model. The introduction of historical operating parameters allows the model to capture the dynamic changes in the motor's thermal load under different operating conditions, including transient load impacts and heat accumulated during continuous operation, avoiding prediction biases caused by relying on only a single parameter. The introduction of historical coolant temperature directly reflects the cooling system's heat dissipation capacity, enabling the model to fully consider the actual operating state of the cooling system when predicting motor temperature, thus more accurately assessing the motor's heat dissipation environment. This allows the resulting temperature prediction model to more accurately reflect the actual thermal behavior of each motor in the hybrid loader, improving the prediction accuracy of thermal load levels and temperature changes. This provides a basis for subsequent thermal management strategies, enabling the thermal management system to respond promptly and accurately to changes in the motor's thermal state, avoiding overcooling or overheating, thereby optimizing motor operating efficiency, extending motor life, and improving the reliability of the entire vehicle. In some of the solutions mentioned above in this application, a method for training a temperature prediction model based on historical operating parameters and historical cooling device parameters is proposed. However, in this process, since historical data may become outdated over time and cannot reflect the dynamic changes of actual operating conditions in a timely manner, the model parameters become fixed and difficult to adapt to new operating scenarios, thereby reducing the accuracy and adaptability of heat load prediction.

[0048] In response, this application further proposes a method for dynamically optimizing the temperature prediction model, specifically including: Step b1 involves storing historical operating parameters and corresponding historical cooling device parameters to obtain stored operating data, which is periodically updated according to a time series.

[0049] Step b2: Based on the stored running data, adjust the weights of the parameters in the temperature prediction model and apply the adjusted parameters to the temperature prediction model.

[0050] Specifically, historical operating parameters and corresponding historical cooling device parameters are stored to obtain stored operating data. Stored operating data refers to the systematically collected and persistently saved information on the hybrid loader's operating status and cooling system response at different points in time. Its purpose is to provide a stable, comprehensive, and traceable data foundation for the training and continuous optimization of the temperature prediction model, ensuring that the model can learn from historical experience. In practical applications, various methods can be used to implement data storage. For example, this data can be stored in a relational database, such as MySQL or PostgreSQL, by defining appropriate table structures to record information such as the historical power, historical power change rate, historical running time, and historical coolant temperature of each motor; alternatively, the data can be stored in a distributed file system such as HDFS, organized in file form, and managed using data lake technology to facilitate the storage and processing of large-scale data.

[0051] The stored operational data is periodically updated according to a time series. The purpose of this periodic update is to ensure that the stored data remains timely and relevant, preventing a decline in model predictive ability due to outdated data. By periodically adding the latest operational data and cooling device parameters to the stored dataset, the model can promptly capture dynamic changes in the hybrid loader's operating conditions, environmental factors, or component aging. For example, a scheduled task can be set to collect the latest operational data and cooling device parameters from the hybrid loader's control system at preset intervals, such as hourly or daily, and append them to the existing stored operational data; alternatively, streaming data processing technology can be used to inject newly generated data into the storage system in real time, achieving near real-time data updates.

[0052] Based on stored operational data, the parameters in the temperature prediction model are weighted and adjusted. Weight adjustment refers to adjusting the internal parameters of the temperature prediction model, such as the connection weights and biases in a neural network, or the coefficients in a linear regression model, according to the latest, periodically updated stored operational data. This allows the model to adjust its internal logic according to new data patterns, thereby improving the accuracy of predicting future heat load and temperature changes. For example, for a neural network-based temperature prediction model, online learning or incremental learning methods can be used to update the model's weights in small batches using newly acquired data, without retraining the entire model from scratch; alternatively, the model can be retrained periodically, such as weekly or monthly, using all or part of the latest stored operational data to ensure that the model parameters fully reflect the latest operational characteristics.

[0053] The weighted parameters are then applied to the temperature prediction model. This means deploying the optimized model parameters to the actual operating temperature prediction module, making them effective immediately. This ensures that the hybrid loader's thermal management system always makes decisions based on the latest and most accurate prediction model. For example, parameter files or memory values ​​in the current operating model can be directly replaced to achieve real-time model updates; alternatively, in more complex systems, model version management and A / B testing strategies can be employed. The corrected model can be used as a candidate model for small-scale testing to verify its performance improvements and stability before gradually switching to the official operating model.

[0054] It is understood that, through the above-described technical solution in this embodiment, this application solves the problem of decreased prediction accuracy and insufficient adaptability of temperature prediction models due to outdated historical data. By storing historical operating parameters and historical cooling device parameters and periodically updating them according to time series, the timeliness and comprehensiveness of the model training data are ensured. Based on this, the parameters in the temperature prediction model are weighted and corrected according to the latest stored operating data, and the corrected parameters are promptly applied to the model. This allows the temperature prediction model to dynamically learn and adapt to the thermal load characteristics of the hybrid loader under different working conditions, environments, and usage habits. This not only significantly improves the accuracy of thermal load prediction but also enhances the robustness and adaptability of the model. This enables the thermal management system of the hybrid loader to accurately and effectively control heat dissipation or insulation, avoiding over-cooling or under-cooling due to inaccurate predictions, extending the service life of key components such as the motor, and improving the overall operating efficiency and reliability of the machine. In some of the embodiments described above in this application, a temperature prediction model is proposed to predict the heat load level and temperature change. However, in its implementation, the model selection may not be accurate enough and may not be able to effectively handle the collaborative needs of classification and regression tasks under complex operating conditions, resulting in insufficient prediction accuracy and low efficiency of thermal management decision-making.

[0055] In response, this application further proposes a thermal management method for hybrid loaders, wherein the temperature prediction model includes one of a neural network model and a linear regression algorithm, such as... Figure 2 As shown, the method includes: Step S201: Collect the current operating parameters of the hybrid loader. See details... Figure 1 Step S101 in the embodiment will not be described again here.

[0056] Step S202 involves inputting the current operating parameters into the temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period. The temperature prediction model is trained using historical operating parameters. Specifically, this includes: Step S2021: Input the current operating parameters into the trained neural network to obtain the heat load level.

[0057] Step S2022: Input the current operating parameters into the trained linear regression algorithm to obtain the heat load.

[0058] Step S2023: Calculate the temperature change based on the heat load.

[0059] Specifically, temperature prediction models can include either neural network models or linear regression algorithms. Neural network models are mathematical models that mimic the structure and function of biological neural networks, performing tasks such as classification and regression by learning patterns in input data. Their implementation can include, but is not limited to: Multilayer Perceptron (MLP), which includes an input layer, hidden layers, and an output layer, trained using backpropagation to recognize complex patterns; or Recurrent Neural Networks (RNNs), suitable for processing time-series data, capable of capturing time dependencies in the data and accurately predicting dynamic changes. Linear regression algorithms are statistical methods that predict numerical outputs by fitting a linear relationship between independent and dependent variables. Their implementation can include, but is not limited to: Least Squares, which determines the best-fit line by minimizing the sum of squared residuals to achieve accurate estimation of heat load; or Gradient Descent, which optimizes the predictive performance of the linear model by iteratively adjusting model parameters to minimize the loss function.

[0060] In acquiring the heat load level and temperature change of each motor in a hybrid loader over a preset time period, the current operating parameters are first input into a trained neural network to obtain the heat load level. Utilizing the neural network's pattern recognition and classification capabilities, the heat load state of the motor is determined based on real-time operating data, such as the motor's current operating power, current power change rate, and current operating time. For example, the neural network can receive these parameters and output a discrete value or probability distribution representing different heat load levels, such as "low," "medium," and "high," or output a continuous value, which is then mapped to the corresponding heat load level using a preset threshold.

[0061] Simultaneously, the current operating parameters are input into a trained linear regression algorithm to obtain the heat load. Utilizing the efficient numerical prediction capabilities of the linear regression algorithm, the heat load of the motor is quantified based on the current operating parameters. For example, the linear regression model can directly output a numerical value representing the heat load, such as watts or joules, or output an intermediate variable related to the heat load, which is then transformed through a transformation function to obtain the final heat load.

[0062] Based on this, the temperature change is calculated from the heat load. The predicted heat load is then converted into a perceptible temperature change, providing a more intuitive and accurate basis for subsequent thermal management decisions. For example, the temperature change over a preset time period can be calculated using thermodynamic formulas based on physical parameters such as heat load, motor heat capacity, and heat dissipation coefficient; alternatively, a simplified empirical formula or lookup table can be established to directly map the heat load to the corresponding temperature change.

[0063] Step S203: Perform thermal management on the hybrid loader based on the heat load level and temperature change.

[0064] It is understood that, through the above-described technical solution in this embodiment, this application solves the problems of insufficient accuracy and low efficiency of traditional temperature prediction models when dealing with the collaborative needs of classification and regression tasks under complex working conditions. Specifically, by applying a neural network model to the classification task of heat load levels, its ability to capture nonlinear relationships can be utilized to identify the heat load levels of the motor under different operating conditions. Simultaneously, the use of a linear regression algorithm for numerical prediction of heat load ensures the speed and efficiency of prediction. This avoids the limitations of a single model in handling multiple tasks, improving the accuracy and robustness of temperature prediction. Furthermore, converting the predicted heat load into temperature change provides a more intuitive and quantitative decision-making basis for the thermal management of the hybrid loader, enabling the thermal management system to accurately and adaptively respond to changes in the motor's heat load, thus optimizing the overall thermal management efficiency and performance of the hybrid loader. In some of the embodiments described above in this application, thermal management based on heat load level and temperature change is proposed to optimize thermal control. However, in its implementation, the lack of fine division of thermal management intensity may lead to low management efficiency or inaccurate response, and it may be unable to efficiently adapt to dynamic changes in heat load and instantaneous demand.

[0065] In response, this application further proposes a thermal management method for hybrid loaders, such as... Figure 3 As shown, the method includes: Step S301: Collect the current operating parameters of the hybrid loader. See details... Figure 1 Step S101 in the embodiment will not be described again here.

[0066] Step S302 involves inputting the current operating parameters into the temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period. The temperature prediction model is trained using historical operating parameters. Specifically, this includes: Step S3021: Input the current operating parameters into the trained neural network to obtain the heat load level. See details... Figure 2 Step S2021 in the embodiment will not be repeated here.

[0067] Step S3022: Input the current operating parameters into the trained linear regression algorithm to obtain the heat load. See details... Figure 2 Step S2022 in the embodiment will not be repeated here.

[0068] Step S3023: Calculate the temperature change based on the heat load. See details in [reference needed]. Figure 2 Step S2023 in the embodiment will not be repeated here.

[0069] Step S303: Perform thermal management on the hybrid loader based on the heat load level and temperature change. Specifically, this includes: Step S3031: Determine the basic strength of the thermal management based on the heat load level, and determine the additional strength of the thermal management based on the temperature change.

[0070] The basic strength of thermal management is determined based on the heat load level. The heat load level refers to the accumulated heat state of each motor in the hybrid loader over a period of time or its heat load range. For example, it can be divided into three levels: low, medium, and high, or a more detailed five-level division. Determining the basic strength of thermal management means presetting or dynamically adjusting a benchmark cooling or heat dissipation intensity according to different heat load levels. Specifically, this can be achieved by pre-establishing a mapping table between heat load levels and basic strength. For example, when the heat load level is "medium," the system sets the basic strength to medium coolant flow rate and fan speed. Alternatively, it can be achieved through fuzzy control or expert systems, inferring the corresponding basic strength based on the input heat load level through a series of rules or fuzzy logic. For example, when the heat load level is within a specific range, the basic strength increases linearly proportionally.

[0071] Simultaneously, the additional intensity of thermal management is determined based on the temperature change. Temperature change refers to the trend or rate of change of motor temperature over a short period, reflecting the instantaneous fluctuation of the heat load. For example, it could be the difference between the current temperature and the previous temperature, or the rate of temperature change over a period of time. Determining the additional intensity of thermal management involves dynamically and temporarily adding intensity based on the temperature change, building upon the base intensity. Specifically, this can be achieved using a PID controller, taking the temperature change as input to calculate the required additional cooling intensity. For example, when the temperature change exceeds a preset threshold, the additional intensity increases proportionally. Alternatively, it can be achieved using a preset response curve, finding the corresponding additional intensity value from the preset curve based on the magnitude of the temperature change. For example, the larger the temperature change, the greater the increase in additional intensity.

[0072] It is understood that, through the above-described technical solution in this embodiment, this application achieves a refined division of thermal management intensity, solving the problems of low efficiency and inaccurate response of traditional thermal management strategies when dealing with dynamic thermal load changes in hybrid loaders. Specifically, by determining the basic intensity of thermal management based on the thermal load level, a stable and continuous heat dissipation benchmark can be provided for the hybrid loader, ensuring reliable long-term thermal management support under different load levels. Simultaneously, determining the additional intensity of thermal management based on the temperature change enables the system to respond quickly and flexibly to sudden or rapid changes in the instantaneous thermal load of the motor, avoiding insufficient or excessive cooling due to excessive thermal load fluctuations. This allows the thermal management system to maintain overall stability while also considering the dynamic nature of instantaneous changes, thereby improving the adaptability, response accuracy, and overall efficiency of thermal management, effectively extending the service life of the motor and ensuring the stable operation of the hybrid loader. In some of the solutions mentioned above in this application, thermal management methods are proposed to manage thermal power based on heat load level and temperature change. However, in this process, the priority ranking is not based on the power contribution ratio of each motor, which may lead to an uneven distribution of thermal management resources, affecting overall efficiency and component life.

[0073] In this regard, this application further proposes a thermal management method for a hybrid loader, the method further including: Step c1: Determine the ratio of the power of each motor to the total power in the power allocation information, and sort the heat dissipation priority of each motor according to the ratio; perform heat dissipation control and / or heat preservation control on each motor according to the priority sort.

[0074] Specifically, when determining the ratio of each motor's power to the total power in the power allocation information, this step aims to quantify the actual load contribution of each motor in the hybrid loader under the current operating conditions. The power allocation information can be obtained from the hybrid loader's energy management system (EMS). This can be achieved by collecting the instantaneous output power of each motor in real time and summing the total instantaneous output power of the hybrid loader, thus calculating the ratio of each motor's power to the total power. Alternatively, this ratio can be obtained by predicting the power allocation ratio of each motor under specific operating conditions using a preset power allocation strategy or a model trained based on historical operating data. This ratio directly reflects the contribution of each motor to the total system load, providing an objective and quantitative basis for subsequent thermal management decisions.

[0075] Based on this, the heat dissipation priorities of each motor are ranked according to this ratio. This step dynamically determines the thermal management priority of each motor in the hybrid loader based on the power ratio calculated above. Generally, motors with higher power ratios generate more heat and have a more urgent need for cooling, thus they should be given a higher heat dissipation priority. For example, one or more thresholds can be set to classify motors into high, medium, and low priorities; or, they can be directly sorted linearly from high to low according to their power ratios. This ensures that thermal management resources are preferentially allocated to critical motors with larger heat loads and a higher risk of overheating, thereby effectively preventing the risk of localized overheating.

[0076] Furthermore, heat dissipation and / or heat preservation control are implemented for each motor according to priority. Differentiated thermal management strategies are applied to each motor in the hybrid loader. Heat dissipation control may include, but is not limited to, adjusting the coolant pump flow rate, adjusting the cooling fan speed, and turning auxiliary cooling devices on or off to increase or decrease the cooling intensity for specific motors. Heat preservation control may involve reducing coolant circulation, lowering fan speed, or activating heating devices in extreme low-temperature environments to maintain the motor within a suitable operating temperature range.

[0077] In one example, heat dissipation / insulation priorities are differentiated according to the motor power allocation ratio to ensure the thermal safety of high-power output components while also taking into account the energy consumption optimization of low-power components.

[0078] Power allocation pattern recognition is based on the power ratio of the two motors, λ = Pwalking / Ptotal, λ∈[0,1], dividing the power allocation into 5 categories, corresponding to differentiated thermal management priorities, for example: Hydraulic-dominated mode: λ < 0.3 hydraulic motor > engine > travel motor > battery; Balanced mode: 0.3≤λ≤0.7 Hydraulic motor = Walking motor > Engine > Battery; Walking-dominant mode: λ > 0.7 walking motor > battery > engine > hydraulic motor.

[0079] It is understood that, through the above-described technical solution in this embodiment, this application, based on thermal management based on heat load level and temperature change, further introduces a dynamic priority ranking mechanism. Specifically, by determining the ratio of the power of each motor in the hybrid loader to the total power, the actual load contribution of each motor can be objectively and quantitatively assessed, avoiding deviations caused by subjective judgment or fixed rules. Based on this ratio, the motors are prioritized for heat dissipation, enabling the thermal management system to identify key motors with higher heat loads and greater susceptibility to overheating under current operating conditions. Thus, with limited cooling resources, priority is given to cooling these high-priority motors. Simultaneously, for motors with lower power contributions, the cooling intensity can be appropriately reduced, or even insulation control can be implemented, avoiding unnecessary energy consumption and overcooling. This solves the problem of uneven resource allocation in traditional thermal management, improves the overall thermal management efficiency of the hybrid loader, extends the service life of each motor, and optimizes system energy consumption.

[0080] In one example, the following provides a more detailed explanation of the above technical solution through a more specific example: In a scenario where a hybrid-powered loader is operating, such as during earthmoving at a construction site, the loader needs to adapt to various working conditions, including light-load driving, heavy-load digging, rapid loading and unloading, and prolonged idling. Simultaneously, different operators may have different driving habits; for example, operator A might be accustomed to frequent rapid acceleration and deceleration. Traditional thermal management systems based on fixed thresholds struggle to effectively handle these diverse working conditions and driving habits, potentially leading to lag or overcooling in the cooling system, thereby impacting component lifespan and energy efficiency.

[0081] This method achieves intelligent thermal management of hybrid loaders through the following steps: First, the loader's control system continuously collects its current operating parameters in real time. These parameters include at least the current operating power, current power change rate, and current running time of each motor. For example, for the drive motor and hydraulic pump motor, the system collects their instantaneous power, the magnitude of power change over a short period of time, and the cumulative running time since startup at a high frequency (e.g., 10 times per second).

[0082] Next, these collected current operating parameters are input into a pre-trained temperature prediction model. This temperature prediction model can be a neural network model. When the loader enters the heavy-load excavation phase, the system inputs the real-time collected motor power, power change rate, and runtime into the trained neural network model. The model immediately outputs the heat load level of each motor within a preset future time period, such as the next 5 minutes. Simultaneously, these parameters are also input into a trained linear regression algorithm to obtain the heat load within the preset future time period, and calculate the temperature change of each motor based on this heat load. This temperature prediction model is trained by acquiring historical operating parameters of each motor in the loader, including the historical power, historical power change rate, and historical runtime of each motor at different times, and corresponding historical cooling device parameters, such as historical coolant temperature. During training, these historical operating parameters and historical cooling device parameters are stored to form stored operating data, which is periodically updated according to a time series. Based on this stored operating data, the parameters in the temperature prediction model are weighted and adjusted, and the weighted parameters are applied to the model to ensure that the model can continuously adapt to new operating modes and environmental changes.

[0083] Finally, thermal management of the hybrid loader is implemented based on the predicted heat load level and temperature change. For example, when it is predicted that the drive motor and hydraulic pump motor will be at a high heat load level within the next 5 minutes, and a rapid temperature rise is expected: The system will determine the basic intensity of thermal management based on the predicted high heat load level. For example, it will increase the speed of the cooling water pump to a medium level and turn on some of the cooling fans.

[0084] Simultaneously, based on the predicted large temperature changes, the system further determines the additional intensity of thermal management. For example, if a rapid temperature rise is predicted, the system will further increase the speed of the cooling water pump and adjust the operating mode of the cooling fan to intervene in cooling in advance and avoid temperature overshoot.

[0085] Unlike existing technologies that passively wait for the motor temperature to reach a threshold before initiating cooling, this method proactively manages the system based on predictions of future heat load and temperature changes. This allows the cooling system to smoothly adjust its output, avoiding frequent and significant fluctuations in cooling water pump flow, thereby reducing component wear and extending service life.

[0086] Furthermore, the system determines the ratio of each motor's power to the total power in the power allocation information and prioritizes the heat dissipation of each motor based on this ratio. For example, during heavy-duty excavation, the hydraulic pump motor may bear most of the load, thus its heat dissipation priority will be increased. The system will prioritize and apply more aggressive heat dissipation control to high-priority motors to ensure that the temperature of critical components remains within a safe range. Under certain low-temperature or light-load conditions, the system can even implement heat preservation control based on prediction results to maintain the motor within its optimal operating temperature range.

[0087] Using the above methods, the loader can perceive its operating status in real time, dynamically predict changes in heat load, and adaptively learn and adjust according to the actual situation. This solves the problems of traditional thermal management systems, such as their inability to adapt to diverse working conditions and driving habits, the difficulty and limitations in setting thresholds, and the failure to fully consider the operating characteristics of the loader. As a result, more efficient and reliable thermal management is achieved.

[0088] This embodiment also provides a thermal management device for a hybrid loader, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0089] This embodiment provides a thermal management device for a hybrid loader, such as... Figure 4 As shown, it includes: The acquisition module 401 is used to acquire the current operating parameters of the hybrid loader, wherein the current operating parameters include at least one of the following: the current operating power of each motor in the hybrid loader, the current power change rate, and the current running time. Prediction module 402 is used to input the current operating parameters into the temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period. The temperature prediction model is trained by historical operating parameters. Management module 403 is used to perform thermal management on the hybrid loader based on heat load level and temperature change.

[0090] In some alternative implementations, the prediction module 402 includes: The first unit is used to input the current operating parameters into the trained neural network to obtain the heat load level.

[0091] The second unit is used to input the current operating parameters into the trained linear regression algorithm to obtain the heat load.

[0092] The third unit is used to calculate the temperature change based on the heat load.

[0093] In some alternative implementations, management module 403 includes: The fourth unit is used to determine the basic strength of thermal management based on the heat load level, and to determine the additional strength of thermal management based on the amount of temperature change.

[0094] The thermal management device for the hybrid loader provided in this application embodiment can execute the thermal management method for the hybrid loader provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0095] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0096] The following is a detailed reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from memory 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0097] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0098] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a memory 508, or installed from a ROM 502. When the computer program is executed by the processor 501, it performs the functions defined in the thermal management method for a hybrid loader according to embodiments of this application.

[0099] Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0100] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the thermal management method for the hybrid loader shown in the above embodiments is implemented.

[0101] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0102] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A thermal management method for a hybrid loader, characterized in that, The method includes: Collect the current operating parameters of the hybrid loader, wherein the current operating parameters include at least one of the following: the current operating power, the current power change rate, and the current operating time of each motor in the hybrid loader; The current operating parameters are input into the temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period. The temperature prediction model is obtained by training with historical operating parameters. Thermal management is performed on the hybrid loader based on the heat load level and the temperature change.

2. The method according to claim 1, characterized in that, The steps for training the temperature prediction model include: The historical operating parameters of each motor in the hybrid loader and the corresponding historical cooling device parameters are obtained. The historical operating parameters include the historical power, historical power change rate and historical running time of each motor at different times. The historical cooling device parameters include the historical coolant temperature. The temperature prediction model is obtained by training the model based on the historical operating parameters and the corresponding historical cooling device parameters.

3. The method according to claim 2, characterized in that, The step of training the model based on the historical operating parameters and the corresponding historical cooling device parameters to obtain the temperature prediction model includes: The historical operating parameters and the corresponding historical cooling device parameters are stored to obtain stored operating data, wherein the stored operating data is periodically updated according to a time series. Based on the stored running data, the parameters in the temperature prediction model are weighted and adjusted, and the weighted parameters are applied to the temperature prediction model.

4. The method according to claim 1, characterized in that, The temperature prediction model includes one of a neural network model and a linear regression algorithm. The step of inputting the current operating parameters into the temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period includes: The current operating parameters are input into the trained neural network to obtain the heat load level; The current operating parameters are input into the trained linear regression algorithm to obtain the heat load. The temperature change is calculated based on the heat load.

5. The method according to claim 1, characterized in that, The thermal management of the hybrid loader based on the heat load level and the temperature change includes: The basic strength of the thermal management is determined based on the heat load level, and the additional strength of the thermal management is determined based on the temperature change.

6. The method according to claim 1, characterized in that, The method further includes: Determine the ratio of the power of each motor to the total power in the power allocation information, and sort the heat dissipation priority of each motor according to the ratio; Heat dissipation control and / or heat preservation control are performed on each motor according to the priority order.

7. A thermal management device for a hybrid loader, characterized in that, The device includes: The data acquisition module is used to acquire the current operating parameters of the hybrid loader, wherein the current operating parameters include at least one of the following: the current operating power of each motor in the hybrid loader, the current power change rate, and the current operating time. The prediction module is used to input the current operating parameters into the temperature prediction model to obtain the heat load level and temperature change of each motor in the hybrid loader within a preset time period. The temperature prediction model is obtained by training with historical operating parameters. The management module is used to perform thermal management on the hybrid loader based on the heat load level and the temperature change.

8. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform the thermal management method for the hybrid loader as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the thermal management method of the hybrid loader according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the thermal management method for the hybrid loader as described in any one of claims 1 to 6.

Images