Vehicle liquid level alarm method and device, vehicle and medium

Abstract

The invention provides a vehicle liquid level alarm method and device, a vehicle and a medium. The vehicle comprises an engine and an electronic water pump, and the method comprises the steps that multiple pieces of cooling liquid temperature information of the engine and multiple pieces of torque current information of the electronic water pump are collected, temperature change characteristic information is determined according to the multiple pieces of cooling liquid temperature information, and current mean value characteristic information and current fluctuation characteristic information are determined according to the multiple pieces of torque current information; target liquid level probability information is determined according to the temperature change characteristic information, the current mean value characteristic information and the current fluctuation characteristic information, and liquid level early warning counting information is determined according to the engine rotating speed information, the cooling liquid temperature information and the target liquid level probability information; if yes, liquid level alarm information is generated, and vehicle liquid level alarm is conducted. Non-contact type liquid level monitoring can be achieved, vehicle liquid level alarming can be achieved according to various parameters, and the false alarm rate is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of liquid level detection, in particular to a vehicle liquid level alarm method and device, vehicle and medium. BACKGROUND

[0002] With the rapid development of the new energy vehicle industry, the requirements for vehicle quality are increasing. Among them, the engine liquid level monitoring technology as a key link to ensure the safe operation of the cooling system, its core goal is to detect the liquid level height in the engine overflow jug in real time and accurately, so as to ensure the safe and efficient operation of the vehicle.

[0003] The liquid level monitoring technology is mainly divided into contact type and non-contact type. At present, the automobile industry generally uses contact type sensors, among which the float type mechanical switch is mainly used. This technology triggers the alarm circuit through the lifting of the float, but when the engine runs for a long time under high load, the float type, capacitive type and other contact type liquid level sensors are easily affected by high temperature, vibration and liquid pollution and other factors, resulting in a high failure rate. In addition, the liquid level sensor needs to be calibrated and replaced regularly, increasing the maintenance cost. At the same time, a single liquid level sensor is easily disturbed by the outside world, resulting in a high false alarm rate of liquid level alarm. SUMMARY

[0004] In view of the above problems, the embodiments of the present application provide a vehicle liquid level alarm method, device, vehicle and medium.

[0005] In the first aspect of the present application, a vehicle liquid level alarm method is first provided, the vehicle includes an engine and an electronic water pump, and the method comprises: Collecting a plurality of cooling liquid temperature information of the engine and a plurality of torque current information of the electronic water pump according to a preset frequency; Determining temperature change characteristic information according to the plurality of cooling liquid temperature information; Determining current mean characteristic information and current fluctuation characteristic information according to the plurality of torque current information; Determining target liquid level probability information according to the temperature change characteristic information, the current mean characteristic information and the current fluctuation characteristic information; Obtaining engine speed information, and determining liquid level early warning count information according to the engine speed information, the cooling liquid temperature information and the target liquid level probability information; If the liquid level early warning count information is greater than or equal to a preset early warning count threshold, generating liquid level alarm information and performing vehicle liquid level alarm.

[0006] Optionally, the determining temperature change characteristic information according to the plurality of cooling liquid temperature information comprises: For any preset time period, obtain the coolant temperature information collected at the starting time of the preset time period and the coolant temperature information collected at the ending time of the preset time period; wherein the length of the preset time period is greater than the period corresponding to the preset frequency; According to the length of the preset time period, the coolant temperature information collected at the starting time of the preset time period and the coolant temperature information collected at the ending time of the preset time period, determine the temperature change characteristic information.

[0007] Optionally, the determining the current mean value characteristic information and the current fluctuation characteristic information according to the plurality of torque current information comprises: According to the preset frequency and the length of the preset time period, determine the collection times information; Obtain the plurality of torque current information collected in the preset time period; According to the plurality of torque current information and the collection times information, determine the current mean value characteristic information; According to the collection times information, the plurality of torque current information and the current mean value characteristic information, determine the current fluctuation characteristic information.

[0008] Optionally, the obtaining the engine speed information, and determining the liquid level early warning count information according to the engine speed information, the coolant temperature information and the target liquid level probability information comprises: Obtain the engine speed information at the starting time of the preset time period; According to the engine speed information, the coolant temperature information and the target liquid level probability information, generate the liquid level early warning count information.

[0009] Optionally, the generating the liquid level early warning count information according to the engine speed information, the coolant temperature information and the target liquid level probability information comprises: In the case that the engine speed information is less than a preset first speed, if the target liquid level probability information is greater than a preset first probability threshold value, and the coolant temperature information collected at the starting time of the preset time period is greater than a preset temperature threshold value, generate the liquid level early warning count information; In the case that the engine speed information is greater than or equal to a preset first speed, and the engine speed information is less than or equal to a preset second speed, determine a dynamic probability threshold value according to the engine speed information, the preset first speed, the preset second speed, the preset first probability threshold value and a preset second probability threshold value; if the target liquid level probability information is greater than the dynamic probability threshold value, and the coolant temperature information collected at the starting time of the preset time period is greater than a preset temperature threshold value, generate the liquid level early warning count information; In a case that the engine speed information is greater than a preset second speed, if the target liquid level probability information is greater than a preset second probability threshold, and cooling liquid temperature information collected at a starting moment of the preset time period is greater than a preset temperature threshold, the liquid level early warning count information is generated; wherein the preset second probability threshold is greater than the preset first probability threshold.

[0010] Optionally, the target liquid level probability information is determined according to the temperature change characteristic information, the current mean value characteristic information and the current fluctuation characteristic information, comprising: The temperature change characteristic information, the current mean value characteristic information and the current fluctuation characteristic information are input into a pre-trained liquid level probability prediction model for processing to obtain target liquid level probability information output by the liquid level probability prediction model.

[0011] Optionally, the liquid level probability prediction model is trained in the following manner: Sample characteristic information and verification characteristic information are obtained; wherein the sample characteristic information comprises sample temperature change characteristic information, sample current mean value characteristic information and sample current fluctuation characteristic information; the verification characteristic information comprises verification temperature change characteristic information, verification current mean value characteristic information and verification current fluctuation characteristic information; Sample target liquid level probability is determined according to the sample characteristic information; The sample characteristic information and the sample target liquid level probability are taken as liquid level probability prediction model training samples; The sample characteristic information is taken as input of the liquid level probability prediction model, the sample target liquid level probability is taken as output of the liquid level probability prediction model, the liquid level probability prediction model training samples are used to train the liquid level probability prediction model, and a liquid level probability prediction model to be verified is obtained; The verification characteristic information is input into the liquid level probability prediction model to be verified to obtain verification target liquid level probability output by the liquid level probability prediction model to be verified; A loss function corresponding to the liquid level probability prediction model is calculated according to the sample target liquid level probability and the verification target liquid level probability; The liquid level probability prediction model corresponding to the loss function is used to adjust model parameters of the liquid level probability prediction model to be verified, and the step of taking the sample characteristic information as input of the liquid level probability prediction model, taking the sample target liquid level probability as output of the liquid level probability prediction model, and using the liquid level probability prediction model training samples to train the liquid level probability prediction model is re-executed until a preset training stop condition is reached, and a trained liquid level probability prediction model is obtained.

[0012] In a second aspect, the application provides a vehicle liquid level alarm device, the vehicle comprising an engine and an electronic water pump, the device comprising: an information collection module configured to collect a plurality of cooling liquid temperature information of the engine and a plurality of torque current information of the electronic water pump at a preset frequency; a temperature change feature acquisition module configured to determine temperature change feature information according to the plurality of cooling liquid temperature information; a current feature acquisition module configured to determine current mean value feature information and current fluctuation feature information according to the plurality of torque current information; a liquid level probability determination module configured to determine target liquid level probability information according to the temperature change feature information, the current mean value feature information and the current fluctuation feature information; a liquid level early warning count module configured to obtain engine speed information, and determine liquid level early warning count information according to the engine speed information, the cooling liquid temperature information and the target liquid level probability information; a liquid level alarm module configured to generate liquid level alarm information and perform vehicle liquid level alarm if the liquid level early warning count information is greater than or equal to a preset early warning count threshold.

[0013] In a third aspect, the application provides a vehicle comprising a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program is executed by the processor to implement the method described above.

[0014] In a fourth aspect, the application provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and the computer program is executed by a processor to implement the method described above.

[0015] The embodiments of the application have the following advantages: In the embodiment of the present application, the engine cooling liquid temperature information and the electronic water pump torque current information are collected according to the preset frequency. The present application uses the existing electronic water pump and cooling liquid temperature sensor data to realize liquid level monitoring, without the need for additional liquid level sensors, thereby significantly reducing the maintenance cost and wire harness complexity. The temperature change characteristic information is determined according to the cooling liquid temperature information, the current mean characteristic information and the current fluctuation characteristic information are determined according to the torque current information, and the target liquid level probability information is determined according to the temperature change characteristic information, the current mean characteristic information and the current fluctuation characteristic information. The present application can determine the target liquid level probability information according to the cooling liquid temperature information and the torque current information, can realize non-contact liquid level monitoring, avoids relying on the vulnerable liquid level sensor, and reduces the failure risk caused by the mechanical or environment. The engine speed information is obtained, the liquid level warning count information is determined according to the engine speed information, the cooling liquid temperature information and the target liquid level probability information, and if the liquid level warning count information is greater than or equal to the preset warning count threshold, the liquid level alarm information is generated and the vehicle liquid level alarm is performed. The present application uses multiple parameters to determine the liquid level warning count information to realize the vehicle liquid level alarm, is not easily affected by external interference, and effectively reduces the false positive rate of the liquid level alarm. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced as follows.

[0017] Figure 1 is a step flow chart of a vehicle liquid level alarm method provided by an embodiment of the present application; Figure 2 is a logic flow chart of a vehicle liquid level alarm provided by an embodiment of the present application; Figure 3 is a structural schematic diagram of a vehicle liquid level alarm device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purposes, technical solutions and advantages of the embodiments of the present application more clear, the embodiments of the present application will be described in detail below with reference to the drawings. However, those skilled in the art can understand that in the embodiments of the present application, many technical details are proposed in order to make the readers better understand the present application. However, even without these technical details and various changes and updates based on the following embodiments, the technical solutions claimed by the present application can be implemented. The division of the following embodiments is for the convenience of description, and should not constitute any limitation on the specific implementation of the present application. The embodiments can be combined and referenced with each other without contradiction.

[0019] The liquid level monitoring technology is mainly divided into contact type and non-contact type. At present, the contact type sensor is generally used in the automobile industry, among which the float type mechanical switch is mainly used. The technology triggers the alarm circuit through the float rising and falling with the liquid level, but has problems such as mechanical jam, high temperature expansion failure and the like. The non-contact monitoring technology is based on the principles of ultrasonic wave, radar, laser ranging and the like, has high precision requirement, but the cost is also relatively high.

[0020] For the traditional contact type monitoring method, the sensor material has very high requirements for high temperature, high pressure and corrosive liquid (such as concentrated sulfuric acid), and the contact type sensor needs regular maintenance. The non-contact monitoring method may cause error increase when facing steam or turbulent flow, and the cost is also high. In addition, different host factories have poor compatibility of interface protocol of different sensors, and it is difficult to realize sharing.

[0021] At present, the liquid level monitoring technology is developing towards high precision, intelligence and wireless. The industry pain points mainly concentrate on environmental adaptability, cost control and standardization.

[0022] Therefore, the application provides a vehicle liquid level alarm method, device, vehicle and medium, which can realize liquid level monitoring by using the existing electronic water pump and coolant temperature sensor data of the vehicle, without the need for additional liquid level sensor, thereby significantly reducing the maintenance cost and wire harness complexity. Moreover, the target liquid level probability information can be determined according to the coolant temperature information and torque current information, non-contact liquid level monitoring can be realized, the dependence on the vulnerable liquid level sensor is avoided, and the failure risk caused by the mechanical or environment is reduced. In addition, the liquid level warning count information is determined by using multiple parameters, and then the vehicle liquid level alarm is realized, which is not easily affected by external interference, and the false positive rate of the liquid level alarm is effectively reduced.

[0023] Reference Figure 1 Fig. 1 shows a step flowchart of a vehicle liquid level alarm method provided by an embodiment of the application.

[0024] In the embodiment of the application, the vehicle includes an engine and an electronic water pump. The engine and the electronic water pump are two key components in the automobile cooling system. The engine generates heat, and the electronic water pump removes the heat by circulating coolant to prevent the engine from overheating. The two components work together to ensure that the engine operates efficiently and reliably at the optimal temperature.

[0025] The engine is the power source of the automobile, which can generate power by burning fuel to drive the vehicle to travel. A large amount of heat is generated during the operation of the engine, which will cause the engine to overheat if not dissipated in time, thereby causing failure or even damage. Therefore, in the embodiment of the application, the liquid level of the coolant of the engine can be detected and alarmed to ensure that the engine can dissipate heat normally.

[0026] The electric water pump is a core component of the cooling system, responsible for circulating coolant between the engine and radiator. As the coolant flows through the engine, it absorbs heat, then flows through the radiator, where the fan dissipates the heat into the air, thus lowering the coolant temperature. The electric water pump is driven by an electric motor, and its speed and flow rate can be adjusted according to the engine's temperature requirements for more precise temperature control. In this embodiment, the operating status of the electric water pump also affects the coolant level.

[0027] The method may specifically include the following steps: Step 101: Collect several coolant temperature information of the engine and several torque current information of the electronic water pump at a preset frequency.

[0028] In this embodiment, several coolant temperature data of the engine and several torque current data of the electric water pump can be collected at a preset frequency. The coolant temperature data can be collected by an engine coolant temperature sensor, and the torque current data can be collected by the electric water pump.

[0029] The coolant temperature information can be collected by an engine coolant temperature sensor, which can be installed in the engine coolant circuit to monitor coolant temperature changes in real time. Coolant temperature information reflects the engine's operating temperature status and is an important basis for determining whether the engine is overheating and whether the cooling system is operating normally.

[0030] Torque current information can be collected by the electric water pump itself. The electric water pump integrates a current detection device that can monitor current changes in real time when the motor drives the pump. Torque current information reflects the operating load status of the electric water pump. When the coolant level in the engine overflow tank is at the normal or high level, the electric water pump needs to overcome greater resistance to maintain coolant circulation, resulting in increased torque current. When the coolant level in the engine overflow tank is low, the resistance the electric water pump needs to overcome is relatively smaller, resulting in decreased torque current.

[0031] Step 102: Determine temperature change characteristic information based on the aforementioned coolant temperature information.

[0032] In this embodiment, temperature change characteristic information can be determined based on several coolant temperature information. The temperature change characteristic information can refer to parameters or indicators extracted from engine coolant temperature information through analysis and processing, which reflect the trend and characteristics of coolant temperature changes.

[0033] The temperature change characteristic information may include one or more of the following: Temperature change rate: the rate of change of coolant temperature over time, which can reflect the thermal load change of the engine.

[0034] Temperature fluctuation range: the fluctuation amplitude of coolant temperature, which can reflect the stability of the cooling system.

[0035] Temperature peak and valley: the highest and lowest values of coolant temperature, which can reflect the working temperature range of the engine.

[0036] Temperature change trend: the change direction of coolant temperature (rising, falling or stable), which can reflect the heat dissipation capacity of the cooling system.

[0037] Step 103, determining current mean characteristic information and current fluctuation characteristic information according to the plurality of torque current information.

[0038] In the embodiments of the present application, current mean characteristic information and current fluctuation characteristic information can be determined according to the plurality of torque current information. The current mean characteristic information can refer to the average value of the electronic water pump torque current within a certain time range, which can reflect the average load of the electronic water pump in the normal working state. The current fluctuation characteristic information can refer to the fluctuation of the electronic water pump torque current within a certain time range, which can be represented by calculating the standard deviation or fluctuation amplitude of the current.

[0039] Step 104, determining target liquid level probability information according to the temperature change characteristic information, the current mean characteristic information and the current fluctuation characteristic information.

[0040] In the embodiments of the present application, target liquid level probability information can be determined according to temperature change characteristic information, current mean characteristic information and current fluctuation characteristic information. The target liquid level probability information is used to represent the probability of the liquid level state of the coolant in the engine overflow pot being in a low liquid level state.

[0041] The engine overflow pot has a lower limit scale line and an upper limit scale line of liquid level. When the liquid level of the coolant in the engine overflow pot is lower than the lower limit scale line of liquid level, it is considered that the liquid level state of the coolant in the engine overflow pot is in a low liquid level. When the liquid level of the coolant in the engine overflow pot is higher than the lower limit scale line of liquid level and lower than the upper limit scale line of liquid level, it is considered that the liquid level state of the coolant in the engine overflow pot is in a normal liquid level. When the liquid level of the coolant in the engine overflow pot is higher than the upper limit scale line of liquid level, it is considered that the liquid level state of the coolant in the engine overflow pot is in a high liquid level.

[0042] Step 105, obtaining engine speed information, and determining liquid level early warning count information according to the engine speed information, the coolant temperature information and the target liquid level probability information.

[0043] In the embodiments of the present application, engine speed information can be acquired, and liquid level early warning count information can be determined according to the engine speed information, coolant temperature information and target liquid level probability information. The liquid level early warning count information can be a numerical index determined according to the engine speed information, coolant temperature information and target liquid level probability information. The numerical index can reflect the cumulative degree of coolant liquid level abnormality, and the higher the numerical value, the greater the possibility of liquid level abnormality.

[0044] The engine speed information can be a speed signal collected by a speed sensor (such as a crankshaft position sensor or a camshaft position sensor) provided in the engine, and the real-time speed of the engine can be calculated by a vehicle control system according to the speed signal of the sensor. The vehicle control system can include an ECU (Electronic Control Unit).

[0045] In step 106, if the liquid level early warning count information is greater than or equal to a preset early warning count threshold, liquid level alarm information is generated and vehicle liquid level alarm is performed.

[0046] In the embodiments of the present application, if the liquid level early warning count information is greater than or equal to a preset early warning count threshold, liquid level alarm information is generated and vehicle liquid level alarm is performed. The preset early warning count threshold can be a critical point, and when the liquid level early warning count information reaches or exceeds the preset early warning count threshold, it indicates that the liquid level abnormality has reached a degree that needs to be handled immediately.

[0047] When the liquid level alarm information is generated, an alarm signal can be sent by the vehicle control system to remind the driver or relevant personnel that the liquid level state of the coolant in the engine overflow jug is low.

[0048] The specific alarm signal sending mode can refer to the following modes: Dashboard alarm: On the instrument panel of the vehicle, a special indicator light (such as a red or yellow coolant liquid level alarm light) can be set. When the liquid level alarm information is generated, the indicator light will light up to prompt the driver that the coolant liquid level is too low. The instrument panel of some vehicle models can also display text or symbol prompts, such as "LOW COOLANT LEVEL" (low coolant level), to further clarify the alarm information.

[0049] Buzzer alarm: When the liquid level alarm information is generated, the vehicle control system can trigger the buzzer to send a sound alarm signal (such as a short "tick-tock" sound) to attract the attention of the driver. In addition, the buzzer alarm can be set to a high priority to ensure that the driver can promptly perceive the liquid level abnormality.

[0050] ECU alarm: When the liquid level early warning count information reaches or exceeds the preset early warning count threshold, the ECU generates a liquid level alarm information and triggers the above-mentioned alarm mechanism. Moreover, the ECU also records the relevant data of the liquid level alarm information for subsequent fault diagnosis or maintenance analysis.

[0051] Vehicle information system (such as center control screen): The liquid level alarm information can be displayed through the vehicle information system to provide more intuitive visual prompts.

[0052] Mobile phone APP or remote notification: For vehicles supporting Internet of Vehicles functions, the liquid level alarm information can also be sent to the vehicle owner through the mobile phone APP or remote notification, such as the way supported by the vehicle communication module (T-Box), to remind him / her to handle it in time.

[0053] In the embodiments of the present application, the engine cooling liquid temperature information and the electronic water pump torque current information are collected at a preset frequency. The present application uses the existing electronic water pump and cooling liquid temperature sensor data of the vehicle to realize liquid level monitoring, without the need for additional liquid level sensors, thereby significantly reducing maintenance costs and wire harness complexity. The temperature change characteristic information is determined according to the cooling liquid temperature information, the current mean characteristic information and the current fluctuation characteristic information are determined according to the torque current information, and the target liquid level probability information is determined according to the temperature change characteristic information, the current mean characteristic information and the current fluctuation characteristic information. The present application can determine the target liquid level probability information according to the cooling liquid temperature information and the torque current information, can realize non-contact liquid level monitoring, avoids relying on the easily damaged liquid level sensor, and reduces the failure risk caused by machinery or environment. The engine speed information is obtained, the liquid level early warning count information is determined according to the engine speed information, the cooling liquid temperature information and the target liquid level probability information, and if the liquid level early warning count information is greater than or equal to the preset early warning count threshold, a liquid level alarm information is generated and the vehicle liquid level alarm is performed. The present application uses multiple parameters to determine the liquid level early warning count information to realize the vehicle liquid level alarm, is not easily affected by external interference, and effectively reduces the false positive rate of liquid level alarm.

[0054] In an optional embodiment of the present application, step 102 further includes the following steps: S111, for any preset time period, obtaining the cooling liquid temperature information collected at the starting time of the preset time period and the cooling liquid temperature information collected at the ending time of the preset time period; wherein the length of the preset time period is greater than the period corresponding to the preset frequency; S112, determining the temperature change characteristic information according to the length of the preset time period, the cooling liquid temperature information collected at the starting time of the preset time period and the cooling liquid temperature information collected at the ending time of the preset time period.

[0055] In the embodiment of the present application, for any preset time period, cooling liquid temperature information collected at the starting time of the preset time period and cooling liquid temperature information collected at the ending time of the preset time period can be obtained. The length of the preset time period is greater than the period corresponding to the preset frequency, and the preset time period can be set as a sliding window. The sliding window is dynamic, and as time goes by, the window slides with time (i.e., the preset time period is updated), and the expired data is discarded and new data is added.

[0056] Then, the temperature change characteristic information is determined according to the length of the preset time period, the cooling liquid temperature information collected at the starting time of the preset time period, and the cooling liquid temperature information collected at the ending time of the preset time period. The temperature change characteristic information can also include a water temperature rise slope.

[0057] In a specific implementation, the water temperature rise slope can be calculated from the cooling liquid temperature information collected in the preset time period, and the water temperature rise slope can reflect the heat dissipation failure trend. The specific water temperature rise slope calculation formula is as follows:

[0058] The water temperature rise slope, that is, the temperature change characteristic information in the present application. The cooling liquid temperature information collected at the ending time of the preset time period is represented by T2. The cooling liquid temperature information collected at the starting time of the preset time period is represented by T1. The length of the preset time period is represented by t. It can be understood that if the length of the preset time period is set to 5s, the value of t at this time is 5.

[0059] The present application dynamically obtains the cooling liquid temperature information in the preset time period, and calculates the temperature change characteristic information such as the water temperature rise slope according to the temperature information at the starting time and the ending time, thereby realizing real-time monitoring and analysis of the cooling liquid temperature change. By calculating the water temperature rise slope, the change trend of the cooling liquid temperature can be more accurately reflected, and a reliable basis is provided for subsequent liquid level early warning and alarm, thereby improving the safety and reliability of the vehicle cooling system.

[0060] In an optional embodiment of the present application, step 103 further includes the following steps: S121, determining the collection times information according to the preset frequency and the length of the preset time period; S122, obtaining the plurality of torque current information collected in the preset time period; S123, determining the current mean value characteristic information according to the plurality of torque current information and the collection times information; S124, determining the current fluctuation characteristic information according to the collection times information, the plurality of torque current information, and the current mean value characteristic information.​

[0061] In the embodiment of the present application, the acquisition frequency information can be determined according to the preset frequency and the length of the preset time period. The acquisition frequency information represents the number of times of acquiring the torque current information in the preset time period. The acquisition frequency information can be obtained by dividing the length of the preset time period by the period corresponding to the preset frequency.

[0062] Then, the several torque current information acquired in the preset time period can be obtained, and the current mean characteristic information can be determined according to the several torque current information and the acquisition frequency information. The current mean characteristic information can include the current mean.

[0063] The current fluctuation characteristic information can be determined according to the acquisition frequency information, the several torque current information and the current mean characteristic information. The current fluctuation characteristic information can include the current fluctuation variance.

[0064] In the embodiment of the present application, when the liquid level state of the cooling liquid in the engine water overflow pot is a low liquid level, the current mean decreases, the current fluctuation variance increases, and the water temperature rise slope increases. When the liquid level state of the cooling liquid in the engine water overflow pot is a normal liquid level or a high liquid level, the current mean increases, the current fluctuation variance decreases, and the water temperature rise slope decreases.

[0065] In the specific implementation, the current mean can be calculated by the torque current information acquired in the preset time period and the acquisition frequency information. The current mean can reflect the electronic water pump load reference value. The specific current mean calculation formula is as follows:

[0066] wherein, represents the current mean, N represents the acquisition frequency information, and I represents the torque current information acquired at different times in the preset time period.

[0067] In the specific implementation, the current fluctuation variance can be calculated by the acquisition frequency information, the several torque current information and the current mean characteristic information. The current fluctuation variance can be used to detect the electronic water pump cavitation / idling abnormality. The specific current fluctuation variance calculation formula is as follows:

[0068] wherein, represents the current fluctuation variance, represents the current mean, N represents the acquisition frequency information, and I represents the torque current information acquired at different times in the preset time period.

[0069] The application determines the acquisition times information in combination with the preset frequency and the length of the preset period, and acquires a plurality of torque current information in the preset period by using a sliding window mechanism. The current mean value is used as a load reference value to help evaluate the normal working state of the electronic water pump, and the current fluctuation variance is used to detect cavitation or abnormal idling to improve the fault detection capability of the system. By calculating the current mean value and the current fluctuation variance, the system can accurately reflect the load reference value and the running state of the electronic water pump, not only improving the real-time and accuracy of data acquisition, but also providing reliable feature information for the running state monitoring and abnormal detection of the electronic water pump, thereby effectively guaranteeing the performance and safety of the cooling system of the vehicle.

[0070] In an optional embodiment of the application, step 105 further comprises the following steps: S131, obtaining the engine speed information at the starting time of the preset period; S132, generating the liquid level early warning count information according to the engine speed information, the coolant temperature information and the target liquid level probability information.

[0071] In the embodiment of the application, the engine speed information at the starting time of the preset period can be obtained, and the liquid level early warning count information is generated according to the engine speed information, the coolant temperature information and the target liquid level probability information.

[0072] In a specific implementation, for any preset period, that is, a sliding window, the liquid level early warning count information can be generated according to the engine speed information at the starting time of the preset period, the coolant temperature information at the starting time of the preset period and the target liquid level probability information corresponding to the preset period.

[0073] The application can comprehensively analyze these key parameters by obtaining the engine speed information, the coolant temperature information and the target liquid level probability information at the starting time of the preset period, and generate the liquid level early warning count information. The application performs real-time monitoring and data processing for each preset period, ensuring the timeliness and accuracy of the early warning information. By dynamically generating the early warning count information, the early warning strategy can be continuously optimized to provide more comprehensive protection for engine operation.

[0074] In an optional embodiment of the application, step S132 further comprises the following steps: S141, in the case that the engine speed information is less than a preset first speed, if the target liquid level probability information is greater than a preset first probability threshold value, and the coolant temperature information collected at the starting time of the preset period is greater than a preset temperature threshold value, the liquid level early warning count information is generated; S142, in the case that the engine speed information is greater than or equal to a preset first speed and the engine speed information is less than or equal to a preset second speed, determining a dynamic probability threshold according to the engine speed information, the preset first speed, the preset second speed, a preset first probability threshold and a preset second probability threshold; if the target liquid level probability information is greater than the dynamic probability threshold and cooling liquid temperature information collected at a starting time of the preset time period is greater than a preset temperature threshold, generating the liquid level early warning count information; S143, in the case that the engine speed information is greater than the preset second speed, if the target liquid level probability information is greater than the preset second probability threshold and the cooling liquid temperature information collected at the starting time of the preset time period is greater than the preset temperature threshold, generating the liquid level early warning count information; wherein the preset second probability threshold is greater than the preset first probability threshold.

[0075] In the embodiments of the present application, in the case that the engine speed information is less than the preset first speed, if the target liquid level probability information is greater than the preset first probability threshold and the cooling liquid temperature information collected at the starting time of the preset time period is greater than the preset temperature threshold, the liquid level early warning count information is generated.

[0076] In specific implementation, the engine speed information can be represented by engspeed, the target liquid level probability information can be represented by P(low), the preset temperature threshold is a temperature upper limit, which can be represented by T MAX ℃, and the liquid level early warning count information can be represented by a flag bit count Q. A1 represents the preset first probability threshold. As described above, T i represents the cooling liquid temperature information collected at the starting time of the preset time period, and the preset first speed is set to 2500 rpm.

[0077] When engspeed < 2500 rpm, if P(low) > A1 and T i > T MAX ℃, the value of the flag bit count Q is increased by 1.

[0078] In the case that the engine speed information is greater than or equal to the preset first speed and the engine speed information is less than or equal to the preset second speed, a dynamic probability threshold is determined according to the engine speed information, the preset first speed, the preset second speed, the preset first probability threshold and the preset second probability threshold; if the target liquid level probability information is greater than the dynamic probability threshold and the cooling liquid temperature information collected at the starting time of the preset time period is greater than the preset temperature threshold, the liquid level early warning count information is generated.

[0079] In specific implementation, A2 represents the preset second probability threshold, and the preset second speed can be set to 3500 rpm.

[0080] When 2500rpm < engspeed < 3500rpm, if P(low) > A1 + (A2-A1) x (engspeed-2500) / (3500-2500), and T i > T MAX ℃, the value of the flag bit count Q is added by 1.

[0081] It can be understood that the dynamic probability threshold is determined according to the engine speed information, the preset first speed, the preset second speed, the preset first probability threshold and the preset second probability threshold, and the specific calculation manner is that the dynamic probability threshold is equal to A1 + (A2-A1) x (engspeed-2500) / (3500-2500).

[0082] In the case that the engine speed information is greater than the preset second speed, if the target liquid level probability information is greater than the preset second probability threshold, and the cooling liquid temperature information collected at the starting moment of the preset period is greater than the preset temperature threshold, the liquid level early warning count information is generated; wherein the preset second probability threshold is greater than the preset first probability threshold.

[0083] In the specific implementation, the preset second probability threshold A2 is greater than the preset first probability threshold A1.

[0084] When engspeed > 3500rpm, if P(low) > A2, and T i > T MAX ℃, the value of the flag bit count Q is added by 1.

[0085] In the embodiments of the present application, after the liquid level early warning count information, that is, the value of the flag bit count Q is generated, it can be judged whether the flag bit count Q is greater than a preset early warning count threshold. The preset early warning count threshold can be a critical point, when the liquid level early warning count information reaches or exceeds the preset early warning count threshold, it indicates that the liquid level abnormality has reached a degree that needs to be handled immediately. The preset early warning count threshold can be set according to actual conditions.

[0086] Taking the preset early warning count threshold as 3 as an example, when the flag bit count Q > 3, it indicates that at this time not only the liquid level state is low liquid level, but also the cooling liquid temperature is high, the liquid level alarm information is generated and the vehicle liquid level alarm is performed. When the flag bit count Q < 3, the judgment of the liquid level early warning count information is continuously performed, and when the above judgment conditions of the liquid level early warning count information are not met, the flag bit count Q is reset.

[0087] The application generates liquid level early warning count information through multi-condition comprehensive judgment, which significantly improves the accuracy and reliability of liquid level early warning. First, according to different intervals of engine speed information, the judgment conditions of liquid level early warning count information are dynamically adjusted, so that the early warning strategy can adapt to the liquid level monitoring needs under different working conditions. Second, combined with the cooling liquid temperature information, the rigor of the early warning is further strengthened to ensure that the early warning is triggered only when the liquid level is abnormal and the cooling liquid temperature is too high, avoiding false positives. Through the accumulation and reset mechanism of the flag bit count, the continuous liquid level abnormal state can be effectively identified, and the liquid level alarm information can be generated when the conditions are met, so as to timely remind the user to take measures and ensure the safe operation of the engine.

[0088] In an optional embodiment of the application, step S104 further comprises the following steps: S151, input the temperature change characteristic information, the current mean characteristic information and the current fluctuation characteristic information into a pre-trained liquid level probability prediction model for processing to obtain target liquid level probability information output by the liquid level probability prediction model.

[0089] In the embodiment of the application, the temperature change characteristic information, the current mean characteristic information and the current fluctuation characteristic information can be input into a pre-trained liquid level probability prediction model for processing to obtain target liquid level probability information output by the liquid level probability prediction model. The liquid level probability prediction model can be an algorithm model based on machine learning or deep learning, which can be used to predict or evaluate the probability of the liquid level state of the cooling liquid in the engine overflow jug being a low liquid level.

[0090] By inputting the temperature change characteristic information, the current mean characteristic information and the current fluctuation characteristic information into a pre-trained liquid level probability prediction model, the application can accurately predict the target liquid level probability information. The complementarity of multi-dimensional feature data is fully utilized, and the powerful processing capability of the machine learning model is combined to effectively capture the complex relationship between the liquid level change and the engine operating state, analyze and output the target liquid level probability information, and provide reliable data support for subsequent liquid level early warning and alarm.

[0091] In an optional embodiment of the application, the liquid level probability prediction model is trained in the following manner: S161, obtain sample characteristic information and verification characteristic information; wherein the sample characteristic information includes sample temperature change characteristic information, sample current mean characteristic information and sample current fluctuation characteristic information; the verification characteristic information includes verification temperature change characteristic information, verification current mean characteristic information and verification current fluctuation characteristic information; S162, determine a sample target liquid level probability according to the sample characteristic information; S163, use the sample characteristic information and the sample target liquid level probability as liquid level probability prediction model training samples; S164, the sample feature information is used as the input of the liquid level probability prediction model, the sample target liquid level probability is used as the output of the liquid level probability prediction model, and the liquid level probability prediction model is trained using the training samples of the liquid level probability prediction model to obtain the liquid level probability prediction model to be verified. S165, input the verification feature information into the liquid level probability prediction model to be verified, and obtain the verification target liquid level probability output by the liquid level probability prediction model to be verified. S166, Calculate the loss function corresponding to the liquid level probability prediction model based on the sample target liquid level probability and the verification target liquid level probability; S167, the loss function corresponding to the liquid level probability prediction model is used to adjust the model parameters of the liquid level probability prediction model to be verified, and the steps of using the sample feature information as the input of the liquid level probability prediction model, using the sample target liquid level probability as the output of the liquid level probability prediction model, and using the training samples of the liquid level probability prediction model to train the liquid level probability prediction model are executed again until the preset training stop condition is reached, so as to obtain the trained liquid level probability prediction model.

[0092] In this embodiment, sample feature information and verification feature information can be obtained. The sample feature information includes sample temperature change feature information, sample average current feature information, and sample current fluctuation feature information. The verification feature information includes verification temperature change feature information, verification average current feature information, and verification current fluctuation feature information. It is understood that the sample temperature change feature information, the sample average current feature information, and the sample current fluctuation feature information are all used as training samples. Similarly, the verification temperature change feature information, the verification average current feature information, and the verification current fluctuation feature information are all used as training and verification current fluctuation feature information.

[0093] In this embodiment, the target liquid level probability of a sample can be determined based on sample feature information. The target liquid level probability is the target liquid level probability information corresponding to the sample feature information and used as a training sample. In other words, the target liquid level probability represents the probability that the coolant level in the engine overflow tank, used as a training sample, is at a low level. In specific implementations, a random forest algorithm can be used to determine the target liquid level probability based on the sample feature information. Alternatively, other machine learning algorithms or statistical methods can be selected to determine the target liquid level probability of the sample, depending on actual needs.

[0094] Then, the sample feature information and the sample target liquid level probability can be taken as liquid level probability prediction model training samples, the sample feature information can be taken as the input of the liquid level probability prediction model, the sample target liquid level probability can be taken as the output of the liquid level probability prediction model, the liquid level probability prediction model is trained by using the liquid level probability prediction model training samples, and a liquid level probability prediction model to be verified is obtained.

[0095] In the embodiment of the application, the verification feature information can be input into the liquid level probability prediction model to be verified, and a verification target liquid level probability output by the liquid level probability prediction model to be verified is obtained. The verification target liquid level probability is target liquid level probability information corresponding to the verification feature information as a verification sample, that is, the verification target liquid level probability is used to represent the probability that the liquid level state of the cooling liquid in the engine overflow jug as a verification sample is in a low liquid level state.

[0096] According to the sample target liquid level probability and the verification target liquid level probability, a loss function corresponding to the liquid level probability prediction model is calculated.

[0097] Finally, the liquid level probability prediction model is trained by using the liquid level probability prediction model corresponding to the loss function, and the step of taking the sample feature information as the input of the liquid level probability prediction model, taking the sample target liquid level probability as the output of the liquid level probability prediction model, and training the liquid level probability prediction model by using the liquid level probability prediction model training samples is re-executed until a preset training stop condition is reached, and a trained liquid level probability prediction model is obtained.

[0098] In a specific implementation, the sample feature information and the verification feature information can be generated according to the torque current information and the engine coolant temperature information of the electronic water pump extracted on the engine test bench and / or the whole vehicle. The torque current information and the engine coolant temperature information extracted on the engine test bench can be taken as bench data, and the torque current information and the engine coolant temperature information extracted on the whole vehicle can be taken as whole vehicle data. Ten thousand pieces of bench data and whole vehicle data can be extracted, the sample feature information and the verification feature information are calculated in the foregoing manner, and the sample feature information is labeled to obtain the sample target liquid level probability. The liquid level probability prediction model is trained, and the trained liquid level probability prediction model is deployed to the engine controller. In addition, the bench data and the whole vehicle data can be updated regularly every 6 months, effectively considering the performance changes of the water pump and the pipeline caused by wear, aging or other factors in the use process, so as to ensure that the prediction result of the model is always consistent with the actual situation.

[0099] The application obtains sample feature information and verification feature information, generates sample target liquid level probability in combination with multi-dimensional features such as temperature change feature, current mean value and current fluctuation, and uses the sample target liquid level probability as a training sample. The model is trained in an iterative optimization manner, the model parameters are adjusted by calculating a loss function until a preset training stop condition is reached, and a trained liquid level probability prediction model is obtained. The trained model is deployed to an engine controller, and the liquid level probability can be predicted in real time.

[0100] Referring to Figure 2 , a logic flow chart of vehicle liquid level alarm provided by an embodiment of the application is shown. In the specific implementation, the vehicle liquid level alarm can be performed with reference to Figure 2 .

[0101] First, data collection is performed. In the embodiment of the application, the cooling liquid temperature information of the engine and the torque current information of the electronic water pump can be collected at a preset frequency. In the specific implementation, the preset frequency can be set to 100 ms.

[0102] Then, feature extraction is performed. In the embodiment of the application, the temperature change feature information can be determined according to the cooling liquid temperature information, and the current mean value feature information and the current fluctuation feature information can be determined according to the torque current information.

[0103] Target liquid level probability information is obtained. In the embodiment of the application, the target liquid level probability information can be determined according to the temperature change feature information, the current mean value feature information and the current fluctuation feature information.

[0104] It is determined whether the liquid level is low. If the liquid level is not low, it is considered that the liquid level is normal, and if the liquid level is low, the liquid level warning count information is determined according to the engine speed information, the cooling liquid temperature information and the target liquid level probability information.

[0105] It is determined whether the liquid level warning count information is greater than or equal to a threshold value. In the embodiment of the application, if the liquid level warning count information is less than a preset warning count threshold value, it is continuously determined whether the liquid level is low.

[0106] If the liquid level warning count information is greater than or equal to the preset warning count threshold value, the vehicle liquid level alarm is performed.

[0107] Referring to Figure 3 , a structural schematic diagram of a vehicle liquid level alarm device provided by an embodiment of the application is shown. The vehicle includes an engine and an electronic water pump, and the device includes: An information collection module 301 is configured to collect the cooling liquid temperature information of the engine and the torque current information of the electronic water pump at a preset frequency. A temperature change feature acquisition module 302 is configured to determine temperature change feature information according to the cooling liquid temperature information. The current feature acquisition module 303 is configured to determine current mean value feature information and current fluctuation feature information according to the torque current information. The liquid level probability determination module 304 is configured to determine target liquid level probability information according to the temperature variation feature information, the current mean value feature information, and the current fluctuation feature information. The liquid level early warning count module 305 is configured to acquire engine speed information, and determine liquid level early warning count information according to the engine speed information, the cooling liquid temperature information, and the target liquid level probability information. The liquid level alarm module 306 is configured to generate liquid level alarm information and perform vehicle liquid level alarm if the liquid level early warning count information is greater than or equal to a preset early warning count threshold.

[0108] In an optional embodiment of the present application, the temperature variation feature acquisition module 302 comprises: The cooling liquid temperature acquisition submodule is configured to acquire cooling liquid temperature information collected at a starting time of a preset time period and cooling liquid temperature information collected at an ending time of the preset time period for any preset time period, where the length of the preset time period is greater than a period corresponding to the preset frequency. The temperature variation feature determination submodule is configured to determine the temperature variation feature information according to the length of the preset time period, the cooling liquid temperature information collected at the starting time of the preset time period, and the cooling liquid temperature information collected at the ending time of the preset time period.

[0109] In an optional embodiment of the present application, the current feature acquisition module 303 comprises: The acquisition times determination submodule is configured to determine acquisition times information according to the preset frequency and the length of the preset time period. The torque current acquisition submodule is configured to acquire the torque current information collected in the preset time period. The current mean value determination submodule is configured to determine the current mean value feature information according to the torque current information and the acquisition times information. The current fluctuation determination submodule is configured to determine the current fluctuation feature information according to the acquisition times information, the torque current information, and the current mean value feature information.

[0110] In an optional embodiment of the present application, the liquid level early warning count module 305 comprises: The engine speed acquisition submodule is configured to acquire the engine speed information at a starting time of a preset time period. The early warning count generation submodule is configured to generate the liquid level early warning count information according to the engine speed information, the cooling liquid temperature information, and the target liquid level probability information.

[0111] In an optional embodiment of the present application, the early warning count generation submodule comprises: The first early warning count generation unit is configured to, in the case that the engine speed information is less than the preset first speed, generate the liquid level early warning count information if the target liquid level probability information is greater than a preset first probability threshold and the cooling liquid temperature information collected at the start of the preset time period is greater than a preset temperature threshold. The second early warning count generation unit is configured to, in the case that the engine speed information is greater than or equal to the preset first speed and less than or equal to a preset second speed, determine a dynamic probability threshold according to the engine speed information, the preset first speed, the preset second speed, the preset first probability threshold and a preset second probability threshold; generate the liquid level early warning count information if the target liquid level probability information is greater than the dynamic probability threshold and the cooling liquid temperature information collected at the start of the preset time period is greater than a preset temperature threshold. The third early warning count generation unit is configured to, in the case that the engine speed information is greater than the preset second speed, generate the liquid level early warning count information if the target liquid level probability information is greater than a preset second probability threshold and the cooling liquid temperature information collected at the start of the preset time period is greater than a preset temperature threshold; wherein the preset second probability threshold is greater than the preset first probability threshold.

[0112] In an optional embodiment of the present application, the liquid level probability determination module 304 comprises: The liquid level probability determination submodule is configured to input the temperature change feature information, the current mean value feature information and the current fluctuation feature information into a pre-trained liquid level probability prediction model for processing to obtain target liquid level probability information output by the liquid level probability prediction model.

[0113] In an optional embodiment of the present application, the liquid level probability prediction model is trained in the following manner: The sample feature acquisition module is configured to acquire sample feature information and verification feature information; wherein the sample feature information comprises sample temperature change feature information, sample current mean value feature information and sample current fluctuation feature information; and the verification feature information comprises verification temperature change feature information, verification current mean value feature information and verification current fluctuation feature information. The sample target liquid level probability determination module is configured to determine sample target liquid level probability according to the sample feature information. The training sample acquisition module is configured to use the sample feature information and the sample target liquid level probability as liquid level probability prediction model training samples. a model training module, configured to input the sample feature information into the liquid level probability prediction model as input, and input the sample target liquid level probability into the liquid level probability prediction model as output, and train the liquid level probability prediction model by using the liquid level probability prediction model training sample, to obtain a liquid level probability prediction model to be verified; a model verification module, configured to input the verification feature information into the liquid level probability prediction model to be verified, to obtain a verification target liquid level probability output by the liquid level probability prediction model to be verified; a loss function determination module, configured to calculate a loss function corresponding to the liquid level probability prediction model according to the sample target liquid level probability and the verification target liquid level probability; an iterative training module, configured to adjust model parameters of the liquid level probability prediction model to be verified by using the loss function corresponding to the liquid level probability prediction model, and re-perform the steps of inputting the sample feature information into the liquid level probability prediction model as input, and inputting the sample target liquid level probability into the liquid level probability prediction model as output, and training the liquid level probability prediction model by using the liquid level probability prediction model training sample, until a preset training stop condition is reached, to obtain a trained liquid level probability prediction model.

[0114] For the device embodiment, since it is basically similar to the method embodiment, it is described more simply, and the related parts refer to the part of the method embodiment.

[0115] An embodiment of the present application further provides a vehicle, which can include a processor, a memory, and a computer program stored on the memory and capable of running on the processor, and the computer program is executed by the processor to implement the method described above.

[0116] An embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method described above.

[0117] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of countries and regions, and provide corresponding operation entrances for users to choose authorization or refusal.

[0118] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same and similar parts of each embodiment can be referred to each other.

[0119] Those skilled in the art will understand that embodiments of the present application can be provided as methods, apparatus, or computer program products. Accordingly, embodiments of the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, and the like) embodying computer readable program code.

[0120] Embodiments of the present application are described herein with reference to the drawings, in which are shown flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and / or block of the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device, or other programmable data processing terminal apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal apparatus, create means for implementing the functions specified in the flowcharts and / or block diagrams block or blocks. Figure 1 one or more functions specified by one or more blocks Figure 1 one or more functions specified by one or more blocks

[0121] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing terminal apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowcharts and / or block diagrams block or blocks. Figure 1 one or more functions specified by one or more blocks Figure 1 one or more functions specified by one or more blocks

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal apparatus to cause a series of operational steps to be performed on the computer or other programmable terminal apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable terminal apparatus provide steps for implementing the flowcharts and / or block diagrams block or blocks. Figure 1 one or more functions specified by one or more blocks Figure 1 one or more functions specified by one or more blocks

[0123] While preferred embodiments of the present application have been described, additional modifications and changes can occur to those skilled in the art once they gain a working knowledge of the basic inventive concepts. Therefore, the appended claims are intended to cover all such modifications and changes as fall within the true spirit and scope of the present application.

[0124] Finally, it is to be understood that the phraseology or terminology such as "first" and "second" etc. used herein is merely intended to differentiate one entity or operation from another entity or operation, without necessarily requiring or implying any actual such relationship or order between such entities or operations. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the aforesaid element.

[0125] The above provides a vehicle liquid level alarm method, device, vehicle and medium, and the principles and implementation modes of the present application are described by applying specific examples in the present article. The above example is only used to help understand the method and core idea of the present application. Meanwhile, for those skilled in the art, the specific implementation modes and application ranges will be changed according to the idea of the present application. In summary, the content of the present article should not be understood as a limitation of the present application.

Claims

1. A vehicle liquid level alarm method, characterized in that, The vehicle includes an engine and an electric water pump, and the method includes: The engine's coolant temperature information and the electronic water pump's torque current information are collected at a preset frequency. Temperature change characteristic information is determined based on the aforementioned coolant temperature information; Based on the aforementioned torque and current information, determine the average current characteristic information and the current fluctuation characteristic information; The target liquid level probability information is determined based on the temperature change characteristic information, the average current characteristic information, and the current fluctuation characteristic information; Obtain engine speed information, and determine liquid level warning count information based on the engine speed information, coolant temperature information, and target liquid level probability information; If the liquid level warning count information is greater than or equal to the preset warning count threshold, then liquid level alarm information is generated and a vehicle liquid level alarm is triggered.

2. The method according to claim 1, characterized in that, The step of determining temperature change characteristic information based on the plurality of coolant temperature information includes: For any preset time period, acquire the coolant temperature information collected at the start time of the preset time period and the coolant temperature information collected at the end time of the preset time period; wherein, the duration of the preset time period is greater than the period corresponding to the preset frequency; The temperature change characteristic information is determined based on the duration of the preset time period, the coolant temperature information collected at the start time of the preset time period, and the coolant temperature information collected at the end time of the preset time period.

3. The method according to claim 2, characterized in that, The step of determining the average current characteristic information and the current fluctuation characteristic information based on the plurality of torque current information includes: The number of data collections is determined based on the preset frequency and the duration of the preset time period; Acquire the several torque current information collected during the preset time period; The average current characteristic information is determined based on several torque current information and the number of data collections. The current fluctuation characteristic information is determined based on the number of data collections, the torque current information, and the average current characteristic information.

4. The method according to claim 2, characterized in that, The step of acquiring engine speed information and determining liquid level warning count information based on the engine speed information, the coolant temperature information, and the target liquid level probability information includes: Obtain the engine speed information at the start time of the preset time period; The liquid level warning count information is generated based on the engine speed information, the coolant temperature information, and the target liquid level probability information.

5. The method according to claim 4, characterized in that, The step of generating the liquid level warning count information based on the engine speed information, the coolant temperature information, and the target liquid level probability information includes: If the engine speed information is less than a preset first speed, and the target liquid level probability information is greater than a preset first probability threshold, and the coolant temperature information collected at the start of the preset time period is greater than a preset temperature threshold, then the liquid level warning count information is generated. When the engine speed information is greater than or equal to a preset first speed and less than or equal to a preset second speed, a dynamic probability threshold is determined based on the engine speed information, the preset first speed, the preset second speed, the preset first probability threshold, and the preset second probability threshold; if the target liquid level probability information is greater than the dynamic probability threshold and the coolant temperature information collected at the start time of the preset time period is greater than a preset temperature threshold, then the liquid level warning count information is generated. If the engine speed information is greater than a preset second speed, and the target liquid level probability information is greater than the preset second probability threshold, and the coolant temperature information collected at the start of the preset time period is greater than a preset temperature threshold, then the liquid level warning count information is generated; wherein, the preset second probability threshold is greater than the preset first probability threshold.

6. The method according to claim 1, characterized in that, The step of determining the target liquid level probability information based on the temperature change characteristic information, the average current characteristic information, and the current fluctuation characteristic information includes: The temperature change characteristic information, the average current characteristic information, and the current fluctuation characteristic information are input into a pre-trained liquid level probability prediction model for processing to obtain the target liquid level probability information output by the liquid level probability prediction model.

7. The method according to claim 6, characterized in that, The liquid level probability prediction model is trained in the following manner: Acquire sample feature information and verification feature information; wherein, the sample feature information includes sample temperature change feature information, sample current mean feature information, and sample current fluctuation feature information; the verification feature information includes verification temperature change feature information, verification current mean feature information, and verification current fluctuation feature information; The probability of the target liquid level in the sample is determined based on the sample feature information; The sample feature information and the sample target liquid level probability are used as training samples for the liquid level probability prediction model. The sample feature information is used as the input of the liquid level probability prediction model, the sample target liquid level probability is used as the output of the liquid level probability prediction model, and the liquid level probability prediction model is trained using the training samples of the liquid level probability prediction model to obtain the liquid level probability prediction model to be verified. The verification feature information is input into the liquid level probability prediction model to be verified to obtain the verification target liquid level probability output by the liquid level probability prediction model to be verified. Calculate the loss function corresponding to the liquid level probability prediction model based on the sample target liquid level probability and the verification target liquid level probability; The loss function corresponding to the liquid level probability prediction model is used to adjust the model parameters of the liquid level probability prediction model to be verified. Then, the steps of using the sample feature information as the input of the liquid level probability prediction model, using the sample target liquid level probability as the output of the liquid level probability prediction model, and using the training samples of the liquid level probability prediction model to train the liquid level probability prediction model are repeated until the preset training stopping condition is reached, so as to obtain the trained liquid level probability prediction model.

8. A vehicle liquid level alarm device, characterized in that, The vehicle includes an engine and an electric water pump, and the device includes: The information acquisition module is used to acquire several coolant temperature information of the engine and several torque current information of the electronic water pump at a preset frequency. A temperature change feature acquisition module is used to determine temperature change feature information based on the aforementioned coolant temperature information. The current feature acquisition module is used to determine the average current feature information and the current fluctuation feature information based on the aforementioned torque current information. The liquid level probability determination module is used to determine the target liquid level probability information based on the temperature change characteristic information, the average current characteristic information, and the current fluctuation characteristic information; The liquid level warning counting module is used to acquire engine speed information and determine liquid level warning counting information based on the engine speed information, the coolant temperature information and the target liquid level probability information. The liquid level alarm module is used to generate liquid level alarm information and trigger a vehicle liquid level alarm if the liquid level warning count information is greater than or equal to a preset warning count threshold.

9. A vehicle, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method as described in any one of claims 1-7.

Images