Engine cooling system control method and device based on multi-source information fusion

Abstract

The invention discloses an engine cooling system control method and device based on multi-source information fusion, and the method comprises the steps: obtaining front road feature data and real-time sensor data, and fusing the road feature data and the real-time sensor data through a pre-established model, generating an engine load prediction sequence and environmental conditions; determining a cooling demand according to the load prediction sequence and the real-time sensor data, and determining a flow distribution ratio of a mechanical water pump to an electronic water pump by adopting a flow distribution mechanism; and according to the flow distribution proportion and the environment condition, the operation state of the water pump is adjusted, and a cooperative cooling control signal is generated. Therefore, according to the engine cooling system control method based on multi-source information fusion, the response speed and stability of the cooling system are improved, the flow distribution efficiency is optimized, energy consumption is reduced, and the service life of the engine is prolonged.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of engine thermal management technology, and in particular to an engine cooling system control method and device based on multi-source information fusion. Background Technology

[0002] The engine thermal management system plays a crucial role in ensuring engine performance, reducing fuel consumption, extending service life, and improving the economy and reliability of the entire vehicle. Its core objective is to maintain stable engine operation within its optimal operating temperature range. In this system, the water pump, as the core power component driving coolant circulation, directly affects the overall engine performance. The water pump drives the coolant to circulate among key components such as the engine water jacket, radiator, and oil cooler, promptly removing heat from high-temperature areas such as the combustion chamber, cylinder block, and cylinder head. During cold starts, the flow rate needs to be reduced to accelerate warm-up; under high-temperature conditions, the flow rate needs to be increased to prevent serious malfunctions such as cylinder scoring and knocking caused by overheating.

[0003] Currently, the mainstream solution in the commercial vehicle diesel engine field still relies on traditional mechanical water pumps. However, this technology has significant bottlenecks: the mechanical water pump is rigidly connected to the engine crankshaft via a belt, and its speed strictly follows the crankshaft speed, making it impossible to independently and dynamically adjust the coolant flow according to the engine's real-time cooling needs. This results in relatively excessive flow under low-speed / low-load conditions, causing unnecessary heat loss, prolonging warm-up time, and increasing the power consumption of accessories driving the water pump; under high-speed / high-load conditions, the flow may be insufficient, leading to untimely heat dissipation, increased water temperature, and forcing the engine to reduce power as a self-protection measure, affecting power and efficiency.

[0004] While electronic water pumps theoretically offer the flexibility to adjust flow rate on demand, existing systems are limited by the voltage and power constraints of traditional commercial vehicle power systems, making it difficult to meet the high-flow-rate coolant circulation requirements of large-displacement diesel engines in commercial vehicles. Single mechanical water pumps or power-constrained electronic water pump systems struggle to effectively handle the frequent and rapidly changing complex operating conditions of vehicles. The lack of predictive capability for future driving conditions forces the system to rely solely on delayed real-time temperature feedback for response. For example, before a vehicle enters a steep incline, the system cannot anticipate and increase cooling capacity, potentially causing the coolant temperature to rise rapidly to dangerous levels. In idling scenarios, sudden changes in operating conditions can easily cause coolant temperature fluctuations, affecting stable engine operation.

[0005] To overcome the limitations of a single water pump, a hybrid system combining mechanical and electronic pumps is a potential solution. However, achieving seamless switching and precise flow coordination control between the two is technically complex. Existing methods are prone to coolant flow fluctuations during switching, leading to engine coolant temperature oscillations and threatening operational stability. Therefore, the core challenge currently facing commercial vehicle engine thermal management lies in: overcoming the limitations imposed by the vehicle's power supply on high-power electronic water pumps, how to effectively integrate road information ahead to predict future heat load demands, and on this basis, achieve efficient and stable coordinated control of the mechanical and electronic water pumps. Summary of the Invention

[0006] This invention provides an engine cooling system control method and device based on multi-source information fusion, which improves the cooling system response speed and stability, optimizes flow distribution efficiency, reduces energy consumption, and extends engine service life.

[0007] To achieve the above objectives, in a first aspect, the present invention provides an engine cooling system control method based on multi-source information fusion, comprising: acquiring road feature data and real-time sensor data ahead; fusing the road feature data and real-time sensor data through a pre-established model to generate an engine load prediction sequence and environmental conditions; determining cooling requirements based on the load prediction sequence and the real-time sensor data; determining the flow allocation ratio between mechanical water pumps and electronic water pumps using a flow allocation mechanism; adjusting the water pump operating state based on the flow allocation ratio and the environmental conditions; and generating a coordinated cooling control signal.

[0008] Secondly, this invention provides an engine cooling system control device based on multi-source information fusion, comprising: a first generation module, a determination module, and a second generation module. The first generation module acquires road feature data and real-time sensor data, and fuses the road feature data and real-time sensor data through a pre-established model to generate an engine load prediction sequence and environmental conditions. The determination module determines the cooling demand based on the load prediction sequence and the real-time sensor data, and uses a flow allocation mechanism to determine the flow allocation ratio between the mechanical water pump and the electric water pump. The second generation module adjusts the water pump operating state based on the flow allocation ratio and the environmental conditions to generate a coordinated cooling control signal.

[0009] Thirdly, the present invention provides an electronic device, comprising: at least one processor; and

[0010] A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute the engine cooling system control method based on multi-source information fusion as described above.

[0011] Fourthly, the present invention provides a computer-readable storage medium including a computer program and instructions, which, when the computer program or the instructions are executed on a computer, cause the computer to perform the engine cooling system control method based on multi-source information fusion as described above.

[0012] Compared with the prior art, the engine cooling system control method and device based on multi-source information fusion according to the present invention predicts the engine load by fusing the characteristics of the road ahead and real-time sensor data, dynamically allocates the flow ratio of mechanical water pump and electronic water pump, and optimizes the control signal by combining a closed-loop correction mechanism. This solves the problems of insufficient cooling efficiency caused by the inability of traditional mechanical water pump to adjust the flow on demand and the limited power of electronic water pump. It has the advantages of improving the response speed and stability of the cooling system, optimizing the flow distribution efficiency, reducing energy consumption and extending the service life of the engine. Attached Figure Description

[0013] Figure 1 This is a flowchart illustrating an engine cooling system control method based on multi-source information fusion according to Embodiment 1 of the present invention.

[0014] Figure 2 This is a schematic diagram of the structure of an engine cooling system control device based on multi-source information fusion in Embodiment 2 of the present invention;

[0015] Figure 3 This is a schematic diagram of the structure of an electronic device according to Embodiment 3 of the present invention;

[0016] Figure 4 This is a schematic diagram of the structure of a dual-pump cooling system in a specific embodiment of the present invention;

[0017] Figure 5 This is a schematic diagram of the cooling system flow path in a specific embodiment of the present invention. Detailed Implementation

[0018] The embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and not intended to limit the scope of the invention. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the embodiments of the present invention, and not all structures.

[0019] To facilitate understanding, the main implementation concepts of the various embodiments of the present invention will be briefly described first.

[0020] In existing technologies, commercial vehicle engine cooling systems generally use mechanical water pumps to drive coolant circulation. The pump's rotation speed is rigidly coupled to the engine crankshaft, leading to an inherent contradiction between flow regulation and heat dissipation requirements. Excessive flow at low loads prolongs warm-up time, while insufficient flow at high loads poses an overheating risk. While electronic water pumps have independent adjustment capabilities, their power supply is limited and cannot meet the demands of large-displacement diesel engines. Mixed water pump systems, lacking precise coordinated control, are prone to flow fluctuations and temperature oscillations during switching, failing to achieve stable operation under dynamic conditions. For example, when a vehicle enters a long uphill section, traditional systems can only rely on delayed temperature feedback for adjustment, unable to anticipate changes in heat load.

[0021] To address these issues, researchers noticed a strong correlation between road information and engine load; for example, changes in slope directly affect engine torque output. By incorporating elevation data from navigation maps and real-time road condition information, a heat load prediction model can be established. They also discovered the complementary flow characteristics of mechanical and electronic pumps, enabling precise control through the fine-tuning capabilities of the electronic pump while maintaining a basic flow rate. Based on this, a technical approach was developed that integrates multi-source information to predict heat load and dynamically allocates flow rates between the two pumps.

[0022] Example 1, Figure 1 This is a flowchart illustrating an engine cooling system control method based on multi-source information fusion according to Embodiment 1 of the present invention, as shown below. Figure 1 As shown, Embodiment 1 provides a control method for an engine cooling system based on multi-source information fusion, including:

[0023] S1, acquire road feature data and real-time sensor data ahead, and fuse the road feature data and real-time sensor data through a pre-established model to generate an engine load prediction sequence and environmental conditions;

[0024] Specifically, the road ahead feature data refers to geographical and road condition information including slope, altitude, and traffic flow. This information can be acquired through the vehicle navigation system and vehicle-to-everything (V2X) communication module to predict future trends in engine workload. Real-time sensor data includes parameters such as crankshaft speed, coolant temperature, and vehicle speed, collected by a sensor array located in the engine compartment to reflect the current thermal state. Model fusion refers to the process of feature extraction and correlation analysis of multi-dimensional data. Specifically, machine learning algorithms can be used to establish a mapping relationship between road features and thermal load.

[0025] S2, determine the cooling demand based on the load prediction sequence and the real-time sensor data, and determine the flow allocation ratio between the mechanical water pump and the electronic water pump using a flow allocation mechanism;

[0026] Specifically, the engine load prediction sequence refers to the curve of engine torque demand change over a future period, generated based on historical data and real-time information, and can be generated using time series prediction algorithms. The flow allocation mechanism refers to the control strategy that dynamically allocates the flow contribution of mechanical pumps and electric pumps according to cooling demand, and can be achieved in real-time optimization of flow ratio using a proportional-integral controller.

[0027] S3, adjust the water pump operating status according to the flow distribution ratio and the environmental conditions, and generate a coordinated cooling control signal.

[0028] Specifically, during vehicle operation, the navigation system continuously provides data on the gradient and elevation changes of the road ahead. Combined with real-time collected engine coolant temperature and RPM information, it generates a load change curve for the next five minutes using a trained predictive model. When it predicts entering a continuous uphill section, the system pre-calculates the required increase in coolant flow. The basic flow is provided by the mechanical pump, and any excess is supplemented by adjusting the speed of the electric pump. During cruising on flat roads, the electric pump can independently maintain a small flow circulation, while the mechanical pump is disconnected via a clutch to reduce energy consumption. Through the coordinated operation of the two pumps, both heat dissipation capacity under high loads and energy waste under low loads are ensured.

[0029] Compared to existing technologies, traditional solutions adjust pump speed solely based on current water temperature, while this method achieves proactive control by integrating navigation data. Existing mixed-pump systems use fixed switching thresholds, while this invention achieves smooth transitions through dynamic flow distribution. Existing electronic pump control relies on a single temperature signal, while this invention incorporates multiple factors such as ambient temperature and altitude for compensatory adjustment.

[0030] Based on the above analysis, it can be seen that this invention achieves predictive control and precise flow regulation of the engine cooling system. During long-distance uphill driving, it can enhance heat dissipation capacity in advance, preventing abnormal temperature rise; in congested areas, it can quickly switch to a low-flow mode, reducing unnecessary energy consumption. The coordinated operation of the dual pumps eliminates the flow abrupt changes problem of traditional systems, ensuring that the engine is always within its optimal operating temperature range.

[0031] In this embodiment, the engine cooling system control method based on multi-source information fusion further includes: S4, acquiring real-time feedback data to compare the predicted load with the actual load; if the deviation exceeds a preset threshold, adjusting the flow distribution ratio through a closed-loop correction mechanism, and updating the water pump operating status based on the adjusted flow distribution ratio to generate a corrected collaborative cooling output.

[0032] Real-time feedback data refers to the actual engine operating parameters collected by crankshaft torque sensors, coolant temperature sensors, and vehicle speed sensors. This can be implemented using a dynamic data acquisition module to verify the accuracy of the predicted load. The closed-loop correction mechanism is a feedback adjustment algorithm based on the deviation value, which can be implemented using a proportional-integral-derivative (PID) control algorithm to dynamically compensate for errors in the prediction model. Flow distribution ratio adjustment refers to the reallocation of flow output between the mechanical and electronic water pumps based on the updated prediction sequence. This can be implemented using a multi-objective optimization algorithm to eliminate deviations between actual operating conditions and the predicted scenario.

[0033] Specifically, during the cooling control process, the deviation between real-time sensor data and the predicted load sequence is continuously calculated. When the deviation exceeds a preset threshold, such as when the vehicle suddenly enters an unpredictable steep slope scenario, the prediction model parameters are dynamically adjusted through an iterative feedback loop. The adjusted model regenerates the engine load prediction sequence and recalculates the cooling demand based on the latest sensor data. Based on the updated cooling demand, the flow distribution mechanism redetermines the flow ratio between the mechanical and electric water pumps, for example, increasing the mechanical water pump flow from 60% to 75% while reducing the compensation flow of the electric water pump. The adjusted flow distribution command is sent to the water pump controller to update the coolant circulation state and finally output a corrected cooperative control signal.

[0034] Existing methods rely solely on real-time temperature feedback for passive adjustment, failing to proactively correct prediction errors before sudden changes in operating conditions. For example, during the transition from a long downhill slope to a steep slope, existing technologies require waiting for the water temperature to rise to a threshold before increasing the flow rate. In contrast, this invention identifies deviations and corrects flow distribution in advance by comparing predictions with actual loads in real time, thus avoiding drastic fluctuations in water temperature.

[0035] Through the above technical solution, this invention solves the problem of cooling control lag caused by prediction model errors, maintaining stable engine coolant temperature under complex road condition changes. For example, when a vehicle encounters sudden congestion or rapid acceleration, the closed-loop correction mechanism can complete the flow ratio adjustment within 3 seconds, controlling the coolant temperature fluctuation within ±2℃, thus preventing the engine from reducing power due to overheating or decreasing efficiency at low temperatures.

[0036] In this embodiment, S1 includes: S11, obtaining slope information, altitude data, dynamic road conditions and ambient temperature from navigation maps and vehicle networks, and obtaining real-time sensor data from vehicle sensors; S12, fusing the slope information, altitude data, dynamic road conditions, ambient temperature and real-time sensor data using a pre-established road scene analysis model to generate a fused feature vector; S13, obtaining historical engine data from a pre-stored database based on the fused feature vector, determining the load change trend, and generating the engine load prediction sequence and environmental conditions.

[0037] Among these, navigation maps and vehicle-to-everything (V2X) refer to digital platforms used to acquire road information ahead, specifically implemented through in-vehicle navigation terminals or cloud data interfaces, used to extract road gradient, altitude, and real-time traffic conditions. The road scene analysis model refers to a multimodal data processing module based on machine learning algorithms, specifically implemented using an architecture combining convolutional neural networks and long short-term memory networks, used to model the spatiotemporal correlation between road features and environmental parameters. The fused feature vector refers to the standardized expression of multidimensional data after dimensionality reduction and feature extraction, specifically generated using principal component analysis or autoencoders, used to characterize the thermal load influencing factors under the current driving scenario. The pre-stored database refers to a storage unit storing historical operating conditions and engine operating parameters, specifically implemented using in-vehicle storage or a cloud database, used to match load change patterns under similar scenarios. Historical engine data refers to the engine's operating records under different road and environmental conditions, specifically including parameters such as engine speed, torque, coolant temperature, and fuel consumption, used to establish a benchmark reference for load prediction.

[0038] Specifically, during vehicle operation, the navigation map and vehicle-to-everything (V2X) platform continuously acquire information on the road's slope, altitude changes, traffic congestion, and external temperature. Simultaneously, vehicle sensors collect engine speed, coolant temperature, and vehicle speed signals. The road scene analysis model fuses this multi-source data, generating a fused feature vector that includes road characteristics, environmental conditions, and real-time operating status through time-series alignment and spatial correlation analysis. This vector is input into a pre-stored database, and a similarity matching algorithm retrieves records with the same or similar feature vectors from historical operating conditions, extracting the corresponding engine load change trend data. Based on a weighted calculation of historical trends and current real-time data, a predicted engine load sequence for the future is generated, and environmental condition parameters are output as auxiliary inputs for cooling system adjustment.

[0039] Compared to existing technologies, current methods rely solely on real-time sensor data to determine cooling demand, lacking the ability to predict changes in road conditions and the environment ahead, resulting in a delayed response from the cooling system. This invention, by integrating navigation maps and vehicle network data with historical engine operating patterns, enables advance prediction of the engine's future thermal load. This allows the cooling system to proactively adjust based on the prediction results, effectively avoiding insufficient or redundant heat dissipation due to sudden changes in operating conditions.

[0040] Based on the above analysis, this invention can identify upcoming high-load or low-load scenarios in advance, such as long-distance uphill climbs or sections with frequent start-stop cycles, thereby adjusting the cooling strategy before the actual engine load changes. This predictive mechanism based on multi-source information fusion significantly improves the response speed and control accuracy of the cooling system, ensuring that the engine maintains its optimal operating temperature under different road conditions and environmental factors.

[0041] In this embodiment, S2 includes: S21, acquiring real-time data from the crankshaft torque sensor, water temperature sensor, and vehicle speed sensor; S22, fusing the load prediction sequence, the real-time data, and the environmental conditions, and calculating the cooling demand assessment value using a linear regression algorithm; S23, determining the flow distribution ratio of the mechanical water pump and the electronic water pump based on the cooling demand assessment value using a proportional-integral control allocation mechanism.

[0042] Specifically, a crankshaft torque sensor is a device used to measure the torque of the engine output shaft. It can be implemented using strain gauges or magnetoelastic sensors, providing dynamic input for cooling demand calculations by monitoring real-time engine load changes. A coolant temperature sensor is a device used to detect the coolant temperature. It can be implemented using thermistors or thermocouples, continuously collecting cooling circuit temperature data to reflect the current heat dissipation status. A vehicle speed sensor is a device used to acquire vehicle speed. It can be implemented using Hall effect sensors or magnetoresistive sensors, combining vehicle motion status to help predict future heat load trends. A linear regression algorithm is a mathematical method that establishes a linear relationship model based on multivariate data. Specifically, it can use the least squares method to fit the weighted relationship between each input variable and cooling demand, achieving accurate assessment by quantifying the influence of different factors on heat dissipation demand. A proportional-integral control distribution mechanism is a control strategy that combines rapid response with integral control to eliminate steady-state errors. Specifically, it can be implemented by setting a cumulative compensation coefficient for flow deviation, ensuring the stability of flow distribution by dynamically adjusting the cooperative working ratio of the mechanical pump and the electric pump.

[0043] Specifically, during the cooling demand determination phase, real-time monitoring data of crankshaft torque, coolant temperature, and vehicle speed are collected simultaneously. These data represent the engine's current output power, cooling system status, and driving conditions, respectively. Subsequently, the real-time data is fused with a pre-generated load prediction sequence and environmental conditions. The load prediction sequence includes the engine's expected workload over future periods, while environmental conditions include external parameters such as temperature and altitude. A mapping model between the fused data and cooling demand is established using a linear regression algorithm. This model obtains the weight coefficients of each input variable through training on historical operating data, accurately quantifying the intensity of cooling demand under different combinations of operating conditions. Based on the calculated cooling demand assessment, a proportional-integral control mechanism dynamically allocates the flow ratio between the mechanical and electronic water pumps. This mechanism continuously corrects for deviations between the assessment and actual cooling conditions, ensuring rapid response in flow adjustment while avoiding system oscillations caused by frequent adjustments.

[0044] Existing methods typically rely solely on feedback data from a single water temperature sensor for cooling control, failing to effectively incorporate engine load variations and driving conditions, resulting in flow distribution lagging behind actual needs. This invention, however, integrates multi-source real-time monitoring data and predictive information, combines a linear regression model to accurately quantify cooling requirements, and employs a proportional-integral control mechanism to dynamically optimize flow distribution, significantly improving the system's adaptability to complex operating conditions.

[0045] Based on the above analysis, it can be seen that this invention can accurately identify the cooling demand intensity under different operating conditions. By dynamically adjusting the cooperative working ratio of the mechanical pump and the electronic pump, it effectively solves the problems of insufficient heat dissipation or energy waste caused by the mismatch of flow regulation of traditional mechanical water pumps and the limited power of electronic water pumps. Under high engine load scenarios, it can quickly increase the coolant circulation flow to prevent overheating; under low load conditions, it can reduce the flow output to reduce energy loss, thereby optimizing overall energy efficiency while ensuring stable engine operation.

[0046] In this embodiment, S3 includes: when the load prediction sequence shows a high load scenario, starting the mechanical water pump flow path and setting a basic flow value based on the flow allocation ratio, adjusting the heat dissipation efficiency by multiplying the temperature data in the environmental conditions by a preset correction factor, determining the electronic water pump speed parameter by combining the flow allocation ratio and coolant monitoring data, adjusting the electronic water pump speed, integrating thermal balance optimization, and generating a collaborative cooling control signal.

[0047] Among them, the high-load scenario refers to the engine being in a condition that requires high-intensity heat dissipation, such as climbing, heavy load, or continuous high-speed operation. Specifically, it can be predicted and identified by the slope information in the road feature data and the vehicle load data, which is used to trigger the coordinated control mechanism of the mechanical water pump and the electronic water pump.

[0048] The flow distribution ratio refers to the weighted relationship between the flow output of mechanical water pumps and electronic water pumps. Specifically, it can be dynamically calculated by combining the proportional-integral control algorithm with the cooling demand assessment value to balance the basic cooling demand and the dynamic adjustment demand.

[0049] The preset correction factor is a coefficient that dynamically adjusts heat dissipation efficiency based on ambient temperature. It can be generated using a piecewise temperature function or a lookup table. For example, the correction factor is set to 1.2 when the ambient temperature is above 35℃ and 0.8 when it is below 10℃, to compensate for the impact of extreme environments on heat dissipation capacity. Thermal balance optimization involves establishing a heat exchange model using coolant temperature and flow rate monitoring data. This can be achieved through finite element simulation or iterative calculations using empirical formulas, and is used to adjust water pump speed parameters in real time to maintain stable engine temperature.

[0050] Specifically, when a steep incline or increased vehicle load leading to high-load scenarios is predicted, the mechanical water pump flow path is activated and a base flow rate value is set, which can be determined based on engine displacement and current speed. Ambient temperature data is adjusted using a preset correction factor, for example, increasing heat dissipation efficiency by 20% to cope with high-temperature environments. Combined with real-time data monitored by the coolant flow sensor, a PID control algorithm dynamically calculates the target speed of the electronic water pump. The flow distribution ratio between the mechanical and electronic water pumps is updated in real time; for example, when heat dissipation demand surges, the electronic water pump speed is increased to 80% of the preset maximum value to supplement the flow. Finally, the rationality of the flow distribution is verified through a thermal balance optimization model, generating a coordinated control signal that includes the mechanical pump's start / stop status and the electronic pump's speed parameters.

[0051] Compared to existing technologies, traditional mechanical water pumps suffer from insufficient flow and delayed heat dissipation under high-load conditions, while hybrid water pump systems are prone to flow fluctuations during switching. This solution compensates for the impact of ambient temperature in advance by pre-setting a correction factor and dynamically adjusts the electric pump speed based on real-time coolant data. This allows the flow distribution ratio to respond quickly to changes in thermal load, preventing engine overheating due to delayed heat dissipation. Simultaneously, a thermal balance optimization model ensures that the coordinated output of the mechanical and electric pumps conforms to thermodynamic equilibrium conditions, reducing water temperature fluctuations during flow switching.

[0052] Through the above technical solution, this application can achieve precise coordinated control of the mechanical water pump and the electronic water pump under high-load scenarios. For example, before the vehicle enters a steep slope, the system increases the speed of the electronic water pump in advance based on predictive data, and combined with the basic flow output of the mechanical water pump, effectively avoids a sudden rise in water temperature due to insufficient heat dissipation capacity. At the same time, through ambient temperature correction and thermal balance optimization, it ensures stable heat dissipation efficiency under different climatic conditions, prevents the engine from triggering power reduction protection due to overheating, and ensures continuous power output.

[0053] In this embodiment, S3 further includes: when the load prediction sequence shows a low load scenario, shutting down the mechanical water pump flow path based on the flow distribution ratio, using the electronic water pump to operate independently, correcting the speed value according to the flow distribution ratio, dynamic road condition data in the environment, and water temperature fluctuation data, integrating water temperature fluctuation monitoring data to adjust the output, determining a low flow control scheme, adjusting the electronic water pump speed to maintain a small circulation mode, and generating a collaborative cooling control signal.

[0054] The low-load scenario refers to the operating condition where the torque demand of the engine is lower than the preset threshold and the coolant temperature is within the safe range. Specifically, it can be determined by the real-time data from the crankshaft torque sensor and the water temperature sensor, and is used to trigger the low-flow control mode to reduce energy consumption.

[0055] The flow distribution ratio refers to the weighted relationship of flow output between the mechanical water pump and the electronic water pump. Specifically, it can be dynamically calculated based on the cooling demand assessment value using a proportional-integral control algorithm. This is used to completely shut down the mechanical water pump in low-load scenarios to reduce parasitic power loss.

[0056] Dynamic road condition data refers to information on changes in the slope, congestion status, and expected driving speed of the road ahead of the vehicle. This information can be obtained and analyzed in real time through vehicle-to-everything (V2X) or navigation maps to predict short-term heat load fluctuations and optimize the response of the electronic water pump.

[0057] Among them, water temperature fluctuation data refers to the amplitude and frequency of changes in coolant temperature within a preset time window. Specifically, it can be achieved by continuously sampling with a water temperature sensor and calculating the standard deviation, which is used to evaluate the matching degree between the current heat dissipation demand and the water pump adjustment effect.

[0058] Among them, the low flow control scheme refers to the regulation strategy of maintaining the minimum necessary coolant circulation only through an electronic water pump. Specifically, it can generate control commands based on the comparison of the flow rate monitoring data in the engine water jacket with a preset threshold, in order to balance heat dissipation demand and energy consumption in low load scenarios.

[0059] Specifically, when the load prediction sequence indicates a low-load scenario, the mechanical water pump flow path is shut off to eliminate parasitic power losses caused by its rigid coupling with the crankshaft. At this time, the electric water pump enters an independent operation mode, and its speed value is initially corrected based on the flow distribution ratio and dynamic road condition data in the environment. For example, if there is a congested section of road ahead with frequent starts and stops, the speed reference value is increased in advance based on the predicted engine load fluctuation trend. At the same time, water temperature fluctuation data is integrated into the control loop, and the output parameters of the electric water pump are dynamically adjusted by monitoring the amplitude and frequency of temperature changes in real time. During this process, the low-flow control scheme reduces the radiator's involvement by limiting the coolant circulation path to the small internal circulation of the engine, thereby reducing system energy consumption while maintaining the necessary cooling capacity. The final generated coordinated cooling control signal stabilizes the electric water pump speed within a preset range, ensuring that the water temperature fluctuation amplitude is controlled within the allowable threshold.

[0060] Compared to existing technologies, current solutions still rely on mechanical water pumps under low-load conditions, leading to excessive coolant flow that cannot be actively adjusted, resulting in energy waste and water temperature fluctuations. This solution, however, completely shuts down the mechanical water pump and uses independent electronic pump control. It dynamically adjusts the flow output based on real-time traffic predictions and water temperature monitoring data, avoiding the ineffective power consumption of the mechanical water pump and reducing the thermal inertia of the heat dissipation path through a small-circulation mode, significantly improving temperature stability under low-load conditions.

[0061] Based on the above analysis, it can be seen that this invention solves the energy waste problem caused by excessive flow of traditional mechanical water pumps in low-load scenarios, while overcoming the deficiency of a single electronic water pump being unable to independently maintain stable heat dissipation due to power limitations. By integrating dynamic road condition prediction and water temperature fluctuation monitoring data, precise control of the electronic water pump speed is achieved, effectively suppressing water temperature fluctuations even when the mechanical water pump is turned off, ensuring the engine's thermal balance under low-load conditions.

[0062] In this embodiment, S4 includes: S41, comparing the predicted load with the actual load through real-time feedback, calculating the deviation value and comparing it with a preset threshold; S42, if the deviation exceeds the preset threshold, adjusting the prediction model parameters through iterative feedback loop, and re-executing S1 based on the adjusted model parameters to generate an updated engine load prediction sequence and environmental conditions; S43, redetermining the cooling demand based on the updated engine load prediction sequence and real-time sensor data, and calculating the adjusted flow allocation ratio using a flow allocation mechanism; S44, updating the water pump operating status based on the adjusted flow allocation ratio and environmental conditions, and generating a corrected collaborative cooling output.

[0063] The closed-loop correction mechanism refers to the control logic that dynamically adjusts based on the difference between real-time feedback data and the output of the prediction model. Specifically, it can use a proportional-integral-derivative (PID) algorithm combined with historical deviation data for parameter correction to eliminate control lag caused by the accumulation of prediction errors. The iterative feedback loop refers to the parameter optimization process of retraining the prediction model using the current deviation as input. Specifically, it can use a gradient descent algorithm to update the model weight coefficients, making the prediction sequence closer to the actual operating conditions. Dynamic road condition data refers to the real-time changes in road slope, curve curvature, and traffic flow ahead of the vehicle. This data can be obtained through the fusion of vehicle-to-everything (V2X) networks and navigation maps, and is used to correct the predicted parameters for heat dissipation demand in environmental conditions.

[0064] Specifically, during vehicle operation, when the deviation between the actual engine load and the predicted sequence exceeds a set threshold, the prediction model parameters are recalibrated. For example, in a long-distance uphill scenario, if the initial prediction does not fully consider the cumulative effect of the gradient, resulting in an actual load higher than expected, the system will trigger an iterative update of the model parameters. The updated prediction sequence will recalculate the cooling demand based on the latest road condition data and adjust the collaborative working mode of the mechanical and electronic water pumps through a flow distribution mechanism. The resulting corrective control signal can adjust the heat dissipation capacity in advance, avoiding water temperature overshoot caused by prediction deviations. This process can optimize the control strategy before the vehicle enters complex road conditions, ensuring that the cooling system's response speed remains synchronized with changes in operating conditions.

[0065] Compared to existing technologies, traditional methods rely solely on current coolant temperature feedback for passive adjustment, failing to proactively correct control strategies when prediction deviations occur. For example, in existing technologies, when a vehicle suddenly encounters an unforeseen, continuous uphill section, the cooling system only begins to increase flow after the engine coolant temperature rises, posing a risk of response lag. This solution, however, through real-time comparison and model iteration, can adjust control parameters at the initial stage of prediction deviations, allowing the flow distribution ratio to adapt to changes in actual demand earlier and effectively shortening the control system's response delay time.

[0066] Through the above technical solution, this invention can quickly correct the control strategy when the prediction model deviates, especially when the vehicle encounters sudden operating conditions or complex road conditions, significantly reducing the risk of engine overheating. For example, on a continuous uphill curve, the system can increase the flow compensation ratio of the electronic water pump in advance by correcting the prediction model in real time, avoiding a sudden rise in water temperature due to insufficient flow from the mechanical water pump. Simultaneously, when a sudden load change occurs under idling conditions, this solution can adjust the flow distribution in a timely manner, controlling the water temperature fluctuation within a smaller range and ensuring that the engine always operates within its optimal temperature range.

[0067] In one specific embodiment, such as Figures 4 to 5 As shown, the engine cooling system control method based on multi-source information fusion of the present invention predicts the future operating conditions and heat dissipation requirements of the engine using a predictive algorithm, and then performs predictive control of the water pump. Under low load conditions, the electronic water pump operates independently; under high load conditions, the mechanical water pump takes over, while the electronic water pump dynamically adjusts according to demand.

[0068] The system obtains road features through multi-source information fusion. Key inputs include:

[0069] 1) Static road attributes: Obtain the slope (±5%~±20%), altitude (affecting intake air density and combustion efficiency), curve curvature (related to deceleration / acceleration requirements), and speed limit signs (predict vehicle speed range) 3-5 kilometers ahead through the navigation map.

[0070] 2) Dynamic traffic information: Obtain the status of traffic congestion ahead (such as stop-and-go traffic), traffic light sequence (predict idling waiting), and road surface type (such as unpaved roads that may restrict vehicle speed) through vehicle-to-everything (V2X) or real-time traffic data.

[0071] 3) Environmental information: Combine real-time weather (temperature, precipitation) at the road location to adjust heat dissipation efficiency (e.g., radiator heat dissipation capacity is increased by 30% in rainy weather).

[0072] After being analyzed, this information is transformed into an "engine load curve for the next 5-10 seconds"—for example: a 15% gradient 2 kilometers ahead → predicts that the engine load will increase from the current 40% to 70%; a traffic light 1 kilometer ahead → predicts that the engine will enter idle mode (load < 10%) in 30 seconds.

[0073] Mapping Logic Between Road Characteristics and Cooling Requirements

[0074]

[0075] Implementation of scenario-based control

[0076] 1) Anticipate the uphill climb (200-500 meters in advance):

[0077] When the navigation system detects a steep slope ahead, it pre-calculates the load increment corresponding to the slope (e.g., a +15% slope corresponds to a 30% load increase) and predicts that the water temperature may rise to 98℃ in 5 seconds based on the current water temperature (e.g., 90℃). At this time: if the current mode is independent electronic water pump, the mechanical water pump flow path is activated 1-2 seconds in advance, and the electronic water pump speed gradually increases from 500rpm to 1500rpm, forming a synergy of "mechanical pump base flow + electronic pump pre-fill flow" to prevent a sudden rise in water temperature when going uphill. Simultaneously, the radiator fan starts earlier (adjusting its speed based on ambient temperature) to enhance heat dissipation redundancy.

[0078] 2) Adjustments before going downhill (300 meters in advance):

[0079] When a long downhill slope is detected, the system anticipates that the engine load will drop from 60% to 20%, drastically reducing cooling demand. The system proactively shuts off the mechanical water pump flow path (with a 1-second delay to ensure a smooth flow transition), and the electric water pump speed gradually decreases from 1200 rpm to 300 rpm, switching to a small circulation mode to reduce heat loss—especially in low-temperature environments, preventing excessive engine temperature drop (e.g., from 90°C to below 75°C) and maintaining optimal operating temperature.

[0080] 3) Traffic light idling prediction (50-100 meters in advance):

[0081] Based on the traffic light timings, it is predicted that the vehicle will enter a 30-second idling period. If the current mode is a dual-pump collaboration mode, the reliance on the mechanical water pump is reduced 5 seconds in advance: the electronic water pump speed is increased from 800 rpm to 1000 rpm, while the mechanical water pump flow path is gradually closed. During idling, the system completely switches to independent operation of the electronic water pump (500 rpm), reducing idling energy consumption (approximately 60% lower than the mechanical water pump idling power consumption).

[0082] 4) High-speed curve adaptive (100-200 meters in advance):

[0083] Before a sharp bend, the vehicle slows down (from 120 km / h to 80 km / h), and the engine load is predicted to decrease from 50% to 35%. The system compensates for the reduction in mechanical water pump flow (due to the decrease in engine speed) by finely adjusting the electronic water pump speed (from 1000 rpm to 800 rpm), ensuring that the water temperature fluctuation during the bend is ≤±1℃, thus avoiding temperature oscillations caused by load fluctuations.

[0084] Road information may contain errors (such as discrepancies between navigation gradient and actual gradient). The system implements closed-loop correction through real-time feedback: comparing the "load based on road prediction" with the "actual engine load" (obtained via a crankshaft torque sensor), if the deviation is >10%, the prediction model is immediately corrected (e.g., if the actual gradient is 5% greater than the navigation gradient, the subsequent load prediction value is increased by 15%). Combining the deviation between the actual and predicted water temperature (e.g., predicted 95℃ but actual 97℃), the electronic water pump speed is dynamically increased (e.g., an additional 300 rpm increase) to compensate for the uncertainty in road information prediction.

[0085] When the engine load fluctuates between "low-high" or "high-low" ranges (such as during acceleration and deceleration), the controller uses a smooth switching algorithm to avoid frequent start-stop of the water pump: when the load increases from 25% to 35%, the mechanical water pump flow path is opened 0.5 seconds in advance, and the electric water pump speed gradually decreases from 800 rpm to 500 rpm (assistive transition); when the load decreases from 40% to 20%, the mechanical water pump flow path is closed 1 second late, and the electric water pump speed gradually increases from 500 rpm to 1000 rpm (ensuring continuous flow).

[0086] When the prediction algorithm fails or the sensor malfunctions, it automatically switches to "temperature feedback control". Basic cooling function is guaranteed by coolant temperature thresholds (e.g., the electric water pump runs at full speed when ≥100℃, and the electric water pump operates independently when ≤70℃).

[0087] In summary, the engine cooling system control method based on multi-source information fusion of the present invention has the following beneficial effects:

[0088] 1. High efficiency and energy saving: The electronic water pump operates independently under low load, reducing energy consumption by 30%-50% compared to traditional mechanical water pumps; under high load, it adjusts as needed, reducing ineffective flow loss.

[0089] 2. Rapid warm-up: The low-load, small-circulation design reduces engine cold start warm-up time by 20%-30%, reducing cold start wear and emissions.

[0090] 3. Precise temperature control: Predictive control responds to changes in operating conditions in advance, avoiding temperature overshoot (±5℃→±2℃) of traditional feedback control, and extending engine life.

[0091] 4. Adaptable to all working conditions: It takes into account both low-load (urban commuting) and high-load (high-speed / uphill) scenarios.

[0092] Example 2, Figure 2 This is a schematic diagram of the structure of an engine cooling system control device based on multi-source information fusion in Embodiment 2 of the present invention, as shown below. Figure 2 As shown in Embodiment 2, an engine cooling system control device based on multi-source information fusion is provided, including: a first generation module 201, a determination module 202, and a second generation module 203. The first generation module 201 is used to acquire road feature data and real-time sensor data, and fuse the road feature data and real-time sensor data through a pre-established model to generate an engine load prediction sequence and environmental conditions. The determination module 202 is used to determine the cooling demand based on the load prediction sequence and the real-time sensor data, and uses a flow allocation mechanism to determine the flow allocation ratio between the mechanical water pump and the electric water pump. The second generation module 203 is used to adjust the water pump operating state based on the flow allocation ratio and the environmental conditions to generate a coordinated cooling control signal.

[0093] In this embodiment, the engine cooling system control device based on multi-source information fusion further includes: a third generation module, used to acquire real-time feedback data to compare the predicted load with the actual load. If the deviation exceeds a preset threshold, the flow distribution ratio is adjusted through a closed-loop correction mechanism, and the water pump operating status is updated based on the adjusted flow distribution ratio to generate a corrected collaborative cooling output.

[0094] In this embodiment, the first generation module 201 includes a first acquisition unit, a first generation unit, and a second generation unit. The first acquisition unit acquires slope information, altitude data, dynamic road conditions, and ambient temperature from navigation maps and vehicle networks, and acquires real-time sensor data from vehicle sensors. The first generation unit uses a pre-established road scene analysis model to fuse the slope information, altitude data, dynamic road conditions, ambient temperature, and real-time sensor data to generate a fused feature vector. The second generation unit acquires historical engine data from a pre-stored database based on the fused feature vector, determines the load change trend, and generates the engine load prediction sequence and environmental conditions.

[0095] In this embodiment, the determining module 202 includes a second acquisition unit, a first calculation unit, and a determining unit. The second acquisition unit is used to acquire real-time data from a crankshaft torque sensor, a water temperature sensor, and a vehicle speed sensor. The first calculation unit is used to fuse the load prediction sequence, the real-time data, and the environmental conditions to calculate a cooling demand assessment value using a linear regression algorithm. The determining unit is used to determine the flow distribution ratio of the mechanical water pump and the electric water pump based on the cooling demand assessment value using a proportional-integral control allocation mechanism.

[0096] In this embodiment, the second generation module 203 includes: a third generation unit, used to, when the load prediction sequence shows a high load scenario, activate the mechanical water pump flow path based on the flow distribution ratio and set a basic flow value, adjust the heat dissipation efficiency by multiplying the temperature data in the environmental conditions by a preset correction factor, determine the electronic water pump speed parameters by combining the flow distribution ratio and coolant monitoring data, adjust the electronic water pump speed, integrate thermal balance optimization, and generate a collaborative cooling control signal.

[0097] In this embodiment, the second generation module 203 further includes: a fourth generation unit, used to, when the load prediction sequence shows a low load scenario, shut down the mechanical water pump flow path based on the flow distribution ratio, use the electronic water pump to operate independently, correct the speed value according to the flow distribution ratio, dynamic road condition data and water temperature fluctuation data in the environment, integrate water temperature fluctuation monitoring data to adjust the output, determine a low flow control scheme, adjust the speed of the electronic water pump to maintain a small circulation mode, and generate a collaborative cooling control signal.

[0098] In this embodiment, the third generation module includes a second calculation unit, a fifth generation unit, a third calculation unit, and a sixth generation unit. The second calculation unit is used to compare the predicted load with the actual load through real-time feedback, and calculate the deviation value and compare it with a preset threshold. The fifth generation unit is used to iteratively adjust the prediction model parameters through feedback loops if the deviation exceeds the preset threshold, and re-execute S1 based on the adjusted model parameters to generate an updated engine load prediction sequence and environmental conditions. The third calculation unit is used to redetermine the cooling demand based on the updated engine load prediction sequence and real-time sensor data, and calculate the adjusted flow allocation ratio using a flow allocation mechanism. The sixth generation unit is used to update the water pump operating status based on the adjusted flow allocation ratio and environmental conditions, and generate a corrected coordinated cooling output.

[0099] The various variations and specific examples of the engine cooling system control method based on multi-source information fusion provided in Embodiment 1 are also applicable to the engine cooling system control device based on multi-source information fusion provided in this embodiment. Through the foregoing detailed description of an engine cooling system control method based on multi-source information fusion, those skilled in the art can clearly understand the implementation method of an engine cooling system control device based on multi-source information fusion in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0100] Example 3, Figure 3 This is a schematic diagram of the structure of an electronic device according to Embodiment 3 of the present invention, as shown below. Figure 3 As shown, Embodiment 3 also provides an electronic device 300, which may include a processor 301 and a memory 302.

[0101] Memory 302 is used to store programs. Memory 302 may include volatile memory, such as random-access memory (RAM), such as static random-access memory (SRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM), etc.; memory may also include non-volatile memory, such as flash memory. Memory 302 is used to store computer programs (such as application programs, functional modules, etc. that implement the above methods), computer instructions, etc. The computer programs, computer instructions, etc., can be partitioned and stored in one or more memories 302. Furthermore, the computer programs, computer instructions, data, etc., can be accessed by processor 301.

[0102] The aforementioned computer programs and instructions can be stored in one or more partitions of memory 302. Furthermore, the aforementioned computer programs and instructions can be invoked by processor 301.

[0103] The processor 301 is configured to execute the computer program stored in the memory 302 to implement the various steps of the methods described in the above embodiments. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0104] The processor 301 and the memory 302 can be independent structures or integrated structures. When the processor 301 and the memory 302 are independent structures, the memory 302 and the processor 301 can be coupled together via bus 303.

[0105] The electronic device in this embodiment can execute the technical solution in the above method. Its specific implementation process and technical principle are the same, and will not be repeated here.

[0106] Example 4: Example 4 also provides a computer-readable storage medium including a computer program and instructions, which, when executed on a computer, cause the computer to perform the engine cooling system control method based on multi-source information fusion according to any embodiment of the present invention.

[0107] Computer-readable storage media include various media that can store program code, such as USB flash drives, external hard drives, ROM, RAM, magnetic disks, or optical disks.

[0108] This embodiment also provides a computer program product, which includes: a computer program stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the solution provided in any of the above embodiments.

[0109] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this invention disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0110] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A control method for an engine cooling system based on multi-source information fusion, characterized in that, include: S1, acquire road feature data and real-time sensor data ahead, and fuse the road feature data and real-time sensor data through a pre-established model to generate an engine load prediction sequence and environmental conditions; S2, determine the cooling demand based on the load prediction sequence and the real-time sensor data, and determine the flow allocation ratio between the mechanical water pump and the electronic water pump using a flow allocation mechanism; S3, adjust the water pump operating status according to the flow distribution ratio and the environmental conditions, and generate a coordinated cooling control signal.

2. The engine cooling system control method based on multi-source information fusion as described in claim 1, characterized in that, Also includes: S4. Obtain real-time feedback data to compare the predicted load with the actual load. If the deviation exceeds a preset threshold, adjust the flow distribution ratio through a closed-loop correction mechanism, update the pump operating status based on the adjusted flow distribution ratio, and generate a corrected collaborative cooling output.

3. The engine cooling system control method based on multi-source information fusion as described in claim 1, characterized in that, S1 includes: S11 obtains slope information, altitude data, dynamic road conditions and ambient temperature from navigation maps and vehicle networking, and obtains real-time sensor data from vehicle sensors; S12, using a pre-established road scene analysis model to fuse the slope information, the altitude data, the dynamic road conditions, the ambient temperature, and the real-time sensor data to generate a fused feature vector; S13, based on the fused feature vector, retrieve historical engine data from the pre-stored database, determine the load change trend, and generate the engine load prediction sequence and environmental conditions.

4. The engine cooling system control method based on multi-source information fusion as described in claim 1, characterized in that, S2 includes: S21 acquires real-time data from the crankshaft torque sensor, water temperature sensor, and vehicle speed sensor; S22, integrate the load forecast sequence, the real-time data, and the environmental conditions, and calculate the cooling demand assessment value using a linear regression algorithm; S23, based on the cooling demand assessment value, a proportional-integral control allocation mechanism is used to determine the flow distribution ratio of the mechanical water pump and the electronic water pump.

5. The engine cooling system control method based on multi-source information fusion as described in claim 1, characterized in that, S3 includes: When the load prediction sequence shows a high load scenario, the mechanical water pump flow path is activated based on the flow distribution ratio and a basic flow value is set. The heat dissipation efficiency is adjusted by multiplying the temperature data in the environmental conditions by a preset correction factor. The electronic water pump speed parameter is determined by combining the flow distribution ratio and coolant monitoring data. The electronic water pump speed is adjusted, and thermal balance optimization is integrated to generate a collaborative cooling control signal.

6. The engine cooling system control method based on multi-source information fusion as described in claim 1, characterized in that, S3 further includes: When the load prediction sequence shows a low load scenario, the mechanical water pump flow path is shut down based on the flow distribution ratio, and the electronic water pump operates independently. The speed value is corrected according to the flow distribution ratio, dynamic road condition data in the environment, and water temperature fluctuation data. The output is adjusted by integrating water temperature fluctuation monitoring data to determine a low flow control scheme. The speed of the electronic water pump is adjusted to maintain a small circulation mode, and a collaborative cooling control signal is generated.

7. The engine cooling system control method based on multi-source information fusion as described in claim 2, characterized in that, S4 includes: S41, By comparing the predicted load with the actual load in real time, the deviation value is calculated and compared with a preset threshold. S42, if the deviation exceeds the preset threshold, the prediction model parameters are adjusted through iterative feedback loop, and S1 is re-executed based on the adjusted model parameters to generate an updated engine load prediction sequence and environmental conditions. S43, based on the updated engine load prediction sequence and real-time sensor data, redetermine the cooling requirements and calculate the adjusted flow distribution ratio using a flow distribution mechanism; S44, based on the adjusted flow distribution ratio and environmental conditions, update the water pump operating status and generate the corrected collaborative cooling output.

8. A control device for an engine cooling system based on multi-source information fusion, characterized in that, include: The first generation module is used to acquire road feature data and real-time sensor data ahead, and fuse the road feature data and real-time sensor data through a pre-established model to generate an engine load prediction sequence and environmental conditions. The determination module is used to determine the cooling demand based on the load prediction sequence and the real-time sensor data, and to determine the flow allocation ratio between the mechanical water pump and the electronic water pump using a flow allocation mechanism. as well as The second generation module is used to adjust the water pump operating status according to the flow distribution ratio and the environmental conditions, and generate a coordinated cooling control signal.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the engine cooling system control method based on multi-source information fusion as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It includes computer programs and instructions, which, when run on a computer, cause the computer to perform the engine cooling system control method based on multi-source information fusion as described in any one of claims 1-7.

Images