Automobile engine temperature regulation and control method based on real-time data monitoring

Abstract

The invention relates to the technical field of automobile engines, in particular to an automobile engine temperature regulation and control method based on real-time data monitoring, which comprises the following steps: S1, collecting multi-source data in real time; s2, data feature extraction and fusion; s3, temperature regulation and control strategy intelligent decision making; s4, performing hierarchical regulation and control; according to the method, through multi-source data fusion and an intelligent algorithm, the limitation of traditional threshold control is broken through, millisecond-level response and dynamic adjustment of the engine temperature are achieved, and the temperature control precision is improved; according to the optimal strategy decision based on reinforcement learning, excessive work of the cooling system is avoided, and energy consumption is reduced; meanwhile, the engine is maintained to operate in the optimal temperature interval, and the fuel economy and the power output efficiency are improved; the real-time monitoring and closed-loop feedback mechanism can recognize the abnormal temperature trend in advance, high-temperature faults are avoided through hierarchical regulation and control, the service life of an engine and parts is prolonged, and the reliability of a vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile engines, and in particular to a method for controlling automobile engine temperature based on real-time data monitoring. Background Art

[0002] Engine temperature is a key factor affecting vehicle performance and reliability. Currently, automotive engine temperature control often relies on simple control strategies based on preset thresholds, such as activating the cooling fan or water pump when the temperature reaches a fixed value. However, this approach has significant drawbacks: Firstly, it cannot adapt to complex and variable operating conditions (such as the dynamic changes in engine thermal load during rapid acceleration and hill climbing); secondly, single threshold control lacks comprehensive consideration of the engine's thermal balance system, which can easily lead to delayed or over-regulated temperature control, impacting engine efficiency and component life, and even causing failures. Therefore, a method for automotive engine temperature control based on real-time data monitoring is proposed. Summary of the Invention

[0003] In view of this, the present invention provides a method for controlling automobile engine temperature based on real-time data monitoring to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0004] The technical solution of the present invention is implemented as follows: a method for controlling the temperature of an automobile engine based on real-time data monitoring comprises the following steps:

[0005] S1, real-time collection of multi-source data;

[0006] S2, data feature extraction and fusion;

[0007] S3, intelligent decision-making of temperature control strategy;

[0008] S4. Implementation of hierarchical regulation;

[0009] S5. Real-time evaluation and feedback of regulatory effects.

[0010] Further preferably, in S1, a sensor network is deployed in key parts of the engine and the entire vehicle system to collect multi-dimensional data in real time, including:

[0011] Engine data: Cylinder head temperature, cylinder block temperature, oil temperature, and coolant temperature are collected through temperature sensors; coolant pressure is obtained using pressure sensors; and coolant flow is monitored using flow sensors.

[0012] Operating condition data: obtain engine speed, torque, load rate, vehicle speed, gear position and other data from the vehicle CAN bus;

[0013] Environmental data: Ambient temperature and humidity are collected through ambient temperature sensors and humidity sensors; atmospheric pressure is obtained using a pressure sensor. All sensor data is transmitted to the central control unit (ECU) in real time at a millisecond frequency.

[0014] Further preferably, in the S2, the data processing module built into the ECU preprocesses the raw data, removes noise through sliding average filtering, and uses the principal component analysis (PCA) algorithm to reduce the dimensionality of high-dimensional data and extract key features. At the same time, the long short-term memory network (LSTM) is used to perform feature mining on the time series data to capture the temperature change trend. Finally, the features of multi-source data are fused to construct a comprehensive feature vector including the engine thermal state, operating conditions, and environmental factors.

[0015] Further preferably, in said S3, based on the fused feature vector, a temperature control decision model is constructed by a reinforcement learning algorithm. The model takes the optimal operating temperature range of the engine (such as 85-95°C) as the target, and takes the deviation between the current temperature and the target temperature, the temperature change rate, the complexity of the working condition, etc. as the state input, and takes the cooling fan speed adjustment, water pump flow adjustment, thermostat opening adjustment, intake cooling valve opening and closing and other control actions as outputs. The model dynamically learns the optimal control strategy by continuously interacting with the engine system, with minimizing temperature deviation and optimizing energy consumption as the reward function.

[0016] Further preferably, in said S4, a hierarchical control mechanism is adopted according to the control strategy output by the decision model: primary control: when the temperature approaches the warning threshold (such as 90°C), the cooling fan speed and water pump flow are fine-tuned first to achieve smooth temperature regulation with lower energy consumption;

[0017] Intermediate control: If the temperature continues to rise to the warning threshold (95°C), the thermostat opening is adjusted synchronously to increase the coolant circulation path and accelerate heat dissipation;

[0018] Advanced control: When the temperature exceeds the dangerous threshold (100°C), in addition to maximizing the cooling system power, the engine control unit also limits the engine torque output to reduce the thermal load.

[0019] Further preferably, in said S5, after the control action is executed, the engine temperature and related parameter changes are continuously monitored, and the dynamic time warping (DTW) algorithm is used to compare the actual temperature curve with the predicted temperature curve to evaluate the control effect. If the temperature does not drop as expected or fluctuates, the new monitoring data is fed back to the decision model to trigger strategy correction, forming a closed-loop control of "data collection-analysis decision-control execution-effect evaluation".

[0020] The embodiment of the present invention adopts the above technical solution, which has the following advantages:

[0021] 1. The present invention breaks the limitations of traditional threshold control through multi-source data fusion and intelligent algorithms, achieves millisecond-level response and dynamic adjustment of engine temperature, and improves temperature control accuracy.

[0022] 2. The present invention makes optimal strategy decisions based on reinforcement learning, which avoids excessive operation of the cooling system and reduces energy consumption; at the same time, it maintains the engine operating in the optimal temperature range, improving fuel economy and power output efficiency.

[0023] 3. The real-time monitoring and closed-loop feedback mechanism of the present invention can identify abnormal temperature trends in advance, avoid high-temperature failures through graded control, extend the service life of the engine and components, and improve vehicle reliability.

[0024] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0026] Figure 1 Flow chart of the method of the present invention. DETAILED DESCRIPTION

[0027] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0028] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0029] like Figure 1 As shown, an embodiment of the present invention provides a method for controlling automobile engine temperature based on real-time data monitoring, comprising the following steps:

[0030] S1, real-time collection of multi-source data;

[0031] S2, data feature extraction and fusion;

[0032] S3, intelligent decision-making of temperature control strategy;

[0033] S4. Implementation of hierarchical regulation;

[0034] S5. Real-time evaluation and feedback of regulatory effects.

[0035] In one embodiment, in S1, a sensor network is deployed in key engine parts and vehicle systems to collect multi-dimensional data in real time, including:

[0036] Engine data: Cylinder head temperature, cylinder block temperature, oil temperature, and coolant temperature are collected through temperature sensors; coolant pressure is obtained using pressure sensors; and coolant flow is monitored using flow sensors.

[0037] Operating condition data: obtain engine speed, torque, load rate, vehicle speed, gear position and other data from the vehicle CAN bus;

[0038] Environmental data: Ambient temperature and humidity are collected through ambient temperature sensors and humidity sensors; atmospheric pressure is obtained using a pressure sensor. All sensor data is transmitted to the central control unit (ECU) in real time at a millisecond frequency.

[0039] In one embodiment, in S2, the data processing module built into the ECU preprocesses the raw data, removes noise through sliding average filtering, and uses the principal component analysis (PCA) algorithm to reduce the dimensionality of high-dimensional data and extract key features. At the same time, the long short-term memory network (LSTM) is used to perform feature mining on time series data to capture temperature change trends. Finally, the features of multi-source data are fused to construct a comprehensive feature vector that includes the engine thermal state, operating conditions, and environmental factors.

[0040] In one embodiment, in S3, based on the fused feature vector, a temperature control decision model is constructed through a reinforcement learning algorithm. The model takes the optimal operating temperature range of the engine (such as 85-95°C) as the target, and takes the deviation between the current temperature and the target temperature, the temperature change rate, the complexity of the operating conditions, etc. as state inputs, and takes control actions such as cooling fan speed adjustment, water pump flow adjustment, thermostat opening adjustment, and intake cooling valve opening and closing as outputs. The model dynamically learns the optimal control strategy by continuously interacting with the engine system, with minimizing temperature deviation and optimizing energy consumption as reward functions.

[0041] In one embodiment, in S4, a hierarchical control mechanism is adopted based on the control strategy output by the decision model: Primary control: When the temperature approaches the warning threshold (e.g., 90°C), the cooling fan speed and water pump flow are fine-tuned to achieve smooth temperature regulation with less energy consumption;

[0042] Intermediate control: If the temperature continues to rise to the warning threshold (95°C), the thermostat opening is adjusted synchronously to increase the coolant circulation path and accelerate heat dissipation;

[0043] Advanced control: When the temperature exceeds the dangerous threshold (100°C), in addition to maximizing the cooling system power, the engine control unit also limits the engine torque output to reduce the thermal load.

[0044] In one embodiment, in S5, after the control action is executed, the engine temperature and related parameter changes are continuously monitored, and the dynamic time warping (DTW) algorithm is used to compare the actual temperature curve with the predicted temperature curve to evaluate the control effect. If the temperature does not drop as expected or fluctuates, the new monitoring data is fed back to the decision model to trigger strategy correction, forming a closed-loop control of "data collection-analysis decision-control execution-effect evaluation".

[0045] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various modifications and substitutions within the technical scope disclosed in the present invention, and such modifications and substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for controlling automobile engine temperature based on real-time data monitoring, characterized in that: The following steps are involved: S1, real-time collection of multi-source data; S2, data feature extraction and fusion; S3, intelligent decision-making of temperature control strategy; S4. Implementation of hierarchical regulation; S5. Real-time evaluation and feedback of regulatory effects.

2. The automobile engine temperature control method based on real-time data monitoring according to claim 1 is characterized in that: In S1, a sensor network is deployed in key engine parts and vehicle systems to collect multi-dimensional data in real time, including: Engine data: Cylinder head temperature, cylinder block temperature, oil temperature, and coolant temperature are collected through temperature sensors; coolant pressure is obtained using pressure sensors; and coolant flow is monitored using flow sensors. Operating condition data: obtain engine speed, torque, load rate, vehicle speed, gear position and other data from the vehicle CAN bus; Environmental data: Ambient temperature and humidity are collected through ambient temperature sensors and humidity sensors; atmospheric pressure is obtained using a pressure sensor. All sensor data is transmitted to the central control unit (ECU) in real time at a millisecond frequency.

3. The automobile engine temperature control method based on real-time data monitoring according to claim 1 is characterized in that: In S2, the data processing module built into the ECU preprocesses the raw data, removes noise through sliding average filtering, and uses the principal component analysis (PCA) algorithm to reduce the dimensionality of high-dimensional data and extract key features. At the same time, the long short-term memory network (LSTM) is used to perform feature mining on time series data to capture temperature change trends. Finally, the features of multi-source data are fused to construct a comprehensive feature vector that includes the engine thermal state, operating conditions, and environmental factors.

4. The automobile engine temperature control method based on real-time data monitoring according to claim 1, characterized in that: In the S3, based on the fused feature vector, a temperature control decision model is constructed through a reinforcement learning algorithm. The model takes the optimal operating temperature range of the engine (such as 85-95°C) as the target, and takes the deviation between the current temperature and the target temperature, the temperature change rate, the complexity of the operating conditions, etc. as state inputs, and takes control actions such as cooling fan speed adjustment, water pump flow adjustment, thermostat opening adjustment, and intake cooling valve opening and closing as outputs. The model dynamically learns the optimal control strategy by continuously interacting with the engine system, with minimizing temperature deviation and optimizing energy consumption as reward functions.

5. The automobile engine temperature control method based on real-time data monitoring according to claim 1 is characterized in that: In S4, a hierarchical control mechanism is adopted according to the control strategy output by the decision model: Primary control: When the temperature approaches the warning threshold (such as 90°C), the cooling fan speed and water pump flow rate are fine-tuned to achieve smooth temperature regulation with minimal energy consumption. Intermediate control: If the temperature continues to rise to the warning threshold (95°C), the thermostat opening is adjusted synchronously to increase the coolant circulation path and accelerate heat dissipation; Advanced control: When the temperature exceeds the dangerous threshold (100°C), in addition to maximizing the cooling system power, the engine control unit also limits the engine torque output to reduce the thermal load.

6. The automobile engine temperature control method based on real-time data monitoring according to claim 1, characterized in that: In S5, after the control action is executed, the engine temperature and related parameter changes are continuously monitored, and the dynamic time warping (DTW) algorithm is used to compare the actual temperature curve with the predicted temperature curve to evaluate the control effect. If the temperature does not drop as expected or fluctuates, the new monitoring data is fed back to the decision model to trigger strategy correction, forming a closed-loop control of "data collection-analysis decision-making-control execution-effect evaluation".

Images