Method and device for detecting state of intake and exhaust system of engine

Abstract

The invention provides a method for detecting the state of an intake and exhaust system of an engine. The method comprises the steps that intake parameters associated with the engine, exhaust parameters associated with the engine and the rotating speed value of the engine are obtained; and providing the air inlet parameter, the exhaust parameter and the rotating speed value as characteristic data to a machine learning model so as to determine the state of the air inlet and exhaust system.

Description

Technical Field

[0001] The present disclosure generally relates to an intake and exhaust system of an engine, and more particularly to a method and apparatus for detecting a state of an intake and exhaust system of an engine. Background Art

[0002] The intake and exhaust systems of an engine include an intake system that provides air to the engine and an exhaust system that discharges the exhaust gas from the engine. For example, for vehicles using diesel engines, in order to ensure the quality of air supply, the intake system is usually equipped with air filters, intercoolers and other components, while the exhaust system is equipped with exhaust gas treatment components such as diesel particulate matter filters. In addition, in order to improve power, some vehicles are equipped with superchargers in the intake and exhaust systems to provide more fresh air to the engine.

[0003] However, as the use time increases, the components of the intake and exhaust systems will leak, become clogged, and wear out, leading to problems such as insufficient intake and abnormal exhaust back pressure, which will affect the vehicle's power, economy, and emission standards. Users often need to drive the vehicle to a repair station for professional testing to discover these problems, which increases the hidden dangers of vehicle use.

[0004] Therefore, it is desirable to provide an efficient method and device for determining the status of an intake and exhaust system in real time, so as to promptly and accurately remind the user of the corresponding faulty component when a fault occurs, thereby ensuring the normal operation of the vehicle. Summary of the invention

[0005] According to one aspect of the present disclosure, a method for performing status detection on an intake and exhaust system of an engine is provided, comprising: obtaining intake parameters associated with the engine, exhaust parameters associated with the engine, and a speed value of the engine; providing the intake parameters, the exhaust parameters, and the speed value as feature data to a machine learning model to determine the status of the intake and exhaust system.

[0006] According to another aspect of the present disclosure, a device for detecting the state of an intake and exhaust system of an engine is provided, comprising: a memory; and a control unit coupled to the memory, wherein the control unit is configured to execute the method according to the present disclosure.

[0007] According to yet another aspect of the present disclosure, a computer readable medium is provided, which stores a computer program including instructions, which, when executed by a control unit, cause the control unit to be configured to perform the method according to the present disclosure.

[0008] According to yet another aspect of the present disclosure, a device for detecting a state of an intake and exhaust system of an engine is provided, comprising a unit for executing the method according to the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Various embodiments of the claimed subject matter will now be described by way of example with reference to the accompanying drawings. In the different drawings, the same reference numerals are used to denote the same or similar components.

[0010] Figure 1 A schematic diagram of an intake and exhaust system 100 of an engine according to an embodiment of the present disclosure is shown.

[0011] Figure 2 A schematic diagram of a system 200 for detecting a state of an intake and exhaust system of an engine according to an embodiment of the present disclosure is shown.

[0012] Figure 3 A flow chart of a method 300 for detecting a state of an intake and exhaust system of an engine according to an embodiment of the present disclosure is shown.

[0013] Figure 4 A block diagram of a device 400 for detecting a state of an intake and exhaust system of an engine according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0014] In the following description, many specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure. However, those skilled in the relevant art will recognize that the present disclosure can be practiced without one or more of the specific details, or alternative methods, components, etc. can be used to practice the present disclosure. In some instances, well-known structures and operations are not shown or described in detail to avoid unnecessarily obscuring the present disclosure.

[0015] Figure 1 A schematic diagram of an intake and exhaust system 100 of an engine according to an embodiment of the present disclosure is shown. In this embodiment, the system 100 includes a diesel engine.

[0016] like Figure 1 As shown, the system 100 includes a cylinder 118 of the engine, an intake conduit from the intake port 102 to the cylinder 118, and an exhaust conduit from the cylinder 118 to the exhaust port 130. Figure 1 Fresh air enters the cylinder 118 through the intake duct in the direction indicated by the arrow with diagonal hatching in FIG. 1 , and is mixed with the fuel injected through the injector (not shown) and burns to generate power. Exhaust gas generated by the combustion is discharged from the system 100 through the exhaust duct.

[0017] An air filter 104 , a supercharger 106 , an intercooler 112 and a throttle valve 114 are respectively arranged on the air intake pipe along the direction of gas flow. Figure 1The supercharger 106 shown in the figure is a mechanical supercharger composed of a coaxially mounted turbine 110 and a compressor 108, which is used to increase the intake density. Failure of the above components can cause abnormal engine intake. For example, when a component is blocked, or when the rubber hose between the components is damaged or the joints are loose, resulting in gas leakage, the actual engine intake will be insufficient, and the engine's power, economy and particulate matter emissions will deteriorate to varying degrees. On the other hand, the failure of the supercharger 106 can also cause abnormal intake. For example, if the bypass valve of the supercharger 106 cannot be opened normally, the supercharger 106 may be over-pressurized, causing excessive nitrogen oxides in the exhaust gas, and the impeller may be worn due to excessive rotation speed. The supercharger 106 with impeller wear may also cause insufficient intake in subsequent work.

[0018] Although some solutions can continuously detect air flow to determine whether there is an abnormal intake volume, this solution is often only applicable to vehicles that are in a steady-state condition during the detection period. It cannot promptly reflect the real-time situation of the vehicle and cannot accurately determine the type of fault.

[0019] The supercharger 106, the diesel oxidation catalyst 126, and the diesel particulate filter 128 are respectively arranged on the exhaust pipe along the direction of gas flow. When these components are blocked or the bypass valve of the supercharger 106 cannot be opened normally, the exhaust back pressure of the engine will increase, which will also cause the power and economy of the engine to decrease.

[0020] It should be understood that Figure 1 The intake and exhaust system 100 of the present disclosure shown is only schematic and is not intended to limit the structure of the intake and exhaust system. The intake and exhaust system 100 according to the embodiment of the present disclosure may also include an exhaust gas recirculation system composed of an exhaust gas recirculation cooler 120, an exhaust gas recirculation valve 122 and other components, an air flow meter (not shown) arranged in the intake pipe, a selective catalytic reduction system (not shown) in the exhaust pipe and other components related to the intake and exhaust of the engine. In addition, Figure 1 The components shown may take many forms, for example, the supercharger 106 may be an electric supercharger device.

[0021] In order to detect the state of the intake and exhaust system 100 in real time, accurately and efficiently. The embodiment of the present disclosure provides a system for determining whether a fault occurs in the intake and exhaust system 100 and the type of fault that occurs based on a machine learning model. Figure 2 The system according to the embodiment of the present disclosure is further described.

[0022] Figure 2A schematic diagram of a system 200 for detecting the state of an intake and exhaust system of an engine according to an embodiment of the present disclosure is shown. The system 200 is composed of a data acquisition unit 210 and a judgment unit 220 .

[0023] The data acquisition unit 210 is used to obtain feature data to be input into the machine learning model. The feature data includes intake parameters associated with the engine, exhaust parameters associated with the engine, and the engine speed value. The intake parameters may include air pressure and temperature values ​​at any suitable location in the intake duct. In one embodiment, the intake parameters include: Figure 1 The air pressure value P2 at the air outlet of the throttle valve 114 is shown. Accordingly, the exhaust parameters may include the air pressure and temperature values ​​at any suitable position in the exhaust pipe. For example, in one embodiment, the exhaust parameters include: Figure 1 The air pressure value P3 at the supercharger air inlet in the exhaust pipe of the engine is shown. In addition to the above parameters, the data acquisition unit 210 can also obtain the fuel consumption per stroke of the engine as additional characteristic data.

[0024] It should be understood that the data acquisition unit 210 can obtain each characteristic data in any appropriate manner. For example, the data acquisition unit 210 can obtain the corresponding air pressure and temperature values ​​through physical sensors or virtual sensors arranged at appropriate positions in the intake and exhaust systems. The data acquisition unit 210 can also obtain parameters such as the engine speed value and fuel consumption per stroke by communicating with a processing unit module (such as an electronic control unit (ECU)). The way in which the data acquisition unit 210 obtains characteristic data is not limited to the examples disclosed in the present invention. It should be understood that if the corresponding parameters are optional, then the corresponding sensor device or processing unit module is also optional to reduce costs.

[0025] The judgment unit 220 is used to process the feature data collected by the data collection unit 210 to determine the state of the intake and exhaust system. Specifically, the judgment unit 220 is used to generate a detection result of the state of the intake and exhaust system based on the input feature data and with the help of a machine learning model using a classification algorithm. The machine learning model is obtained through training, wherein the training process is based on multiple samples, each sample including the above-mentioned feature data. The classification algorithm used by the machine learning model may include logistic regression, convex hull, K-means clustering (K-means), support vector machine (Support Vector Machine, SVM), random forest, naive Bayes, multilayer perceptron (Multilayer Perceptron, MLP), etc. The generated detection result of the state of the intake and exhaust system may indicate whether there is a fault in the intake and exhaust system and / or indicate the type of fault that has occurred, including, for example, air filter blockage, intake pipe leakage, supercharger bypass valve failure to open, supercharger impeller wear, exhaust pipe leakage, and diesel particulate filter blockage, etc.

[0026] Figure 2 The system 200 shown for detecting the state of the intake and exhaust system of the engine using a machine learning model can be configured in the ECU of the vehicle, or a part thereof (such as the judgment unit 220) can be arranged in the cloud. Since the input feature data of the system 200 is a real-time parameter, real-time monitoring of the intake and exhaust system can be achieved. In addition, by adopting a machine learning model constructed based on various normal operating conditions and sample data reflecting different types of fault conditions, the system 200 can accurately determine the occurrence of a fault and the type of fault, which is convenient for users to find the fault in the first place and take corresponding measures.

[0027] Figure 3 A flow chart of a method 300 for detecting a state of an intake and exhaust system of an engine according to an embodiment of the present disclosure is shown.

[0028] At step S310, method 300 includes obtaining intake parameters associated with the engine, exhaust parameters associated with the engine, and a speed value of the engine. In one embodiment, the intake parameters include an air pressure value at a throttle valve outlet in an intake duct of the engine, and the exhaust parameters include an air pressure value at a supercharger intake port in an exhaust duct of the engine. In one embodiment, method 300 also includes obtaining a fuel consumption per stroke of the engine.

[0029] At step S320, method 300 includes providing intake parameters, exhaust parameters, and speed values ​​as feature data to a machine learning model to determine the state of the intake and exhaust system. In one embodiment, determining the state of the intake and exhaust system includes determining whether there is a fault in the intake and exhaust system. In one embodiment, determining the state of the intake and exhaust system includes determining the type of fault that occurs, and the type of fault includes: air filter fault, intake pipe leakage fault, supercharger bypass valve fault, supercharger impeller fault, exhaust pipe leakage fault, and diesel particulate filter fault. In one embodiment, the machine learning model uses a classification algorithm, and the classification algorithm includes logistic regression, convex hull, K-means clustering, support vector machine, random forest, naive Bayes, and multi-layer perceptron. In one embodiment, method 300 also includes providing fuel consumption per stroke, intake parameters, exhaust parameters, and speed values ​​as feature data to a machine learning model to determine the state of the intake and exhaust system.

[0030] Figure 4 A block diagram of a device 400 for detecting the state of an intake and exhaust system of an engine according to an embodiment of the present disclosure is shown. In one embodiment, the device 400 may include a control unit of a vehicle, such as an electronic control unit (ECU).

[0031] The device 400 includes a processor 402 connected to an internal communication bus 408, and the processor 402 is used to execute instructions in a memory 404 to implement the method for state detection of the intake and exhaust system of the engine described in detail above. Examples of the processor 402 may include a central processing unit (CPU), a microcontroller, and the like. The memory 404 suitable for tangibly embodying computer program instructions and data includes various forms of memory, such as EPROM, EEPROM, and flash memory devices, and the like. The device 400 may also include an input interface 410 and an output interface 412. The input interface 410 is used to receive input signals and data, including, for example, sensing signals of sensors coupled to a control unit. The output interface 412 is used to send output signals and data, for example, for displaying fault information to a user via a display. In addition, the device 400 may also include an analog-to-digital converter 406 for converting analog signals from various sensors into digital signals.

[0032] The various methods, steps, operations, units, modules, components, models, and networks described in conjunction with the present disclosure may be implemented as hardware, software executed by a processor, firmware, or any combination thereof. According to one or more aspects of the present disclosure, a computer program product for detecting a state of an intake and exhaust system of an engine may include a computer program for implementing the above-mentioned reference Figure 3A processor may execute computer code for one or more of the methods or steps described. According to other aspects of the present disclosure, a computer readable medium may store computer code for detecting the state of an intake and exhaust system of an engine, and when the code is executed by a processor, the processor may execute the above-mentioned reference Figure 3 One or more of the methods or steps described. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. Any connection can be properly referred to as a computer-readable medium.

[0033] The various embodiments of the present invention are described above with reference to a diesel engine, but this is not restrictive. The method of the present invention for detecting the state of an intake and exhaust system of an engine is also applicable to a gasoline engine and can be applied to various types of aircraft and / or ships.

[0034] In addition to what is described herein, various modifications may be made to the embodiments and implementations of the present disclosure without departing from the scope of the embodiments and implementations of the present disclosure. Therefore, the descriptions and examples herein should be interpreted as illustrative rather than limiting. The scope of the present disclosure should be measured only by reference to the claims.

Claims

1. A method for detecting the state of an intake and exhaust system of an engine, comprising: Obtaining an intake parameter associated with the engine, an exhaust parameter associated with the engine, and a rotation speed value of the engine; The intake parameter, the exhaust parameter, and the rotational speed value are provided as feature data to a machine learning model to determine the state of the intake and exhaust system.

2. The method according to claim 1, wherein: The intake parameter includes an air pressure value at a throttle valve outlet in an intake duct of the engine, and the exhaust parameter includes an air pressure value at a supercharger inlet in an exhaust duct of the engine.

3. The method according to claim 1, wherein: Determining the state of the intake and exhaust system includes determining whether there is a fault in the intake and exhaust system.

4. The method according to claim 1, wherein: Determining the state of the intake and exhaust system includes determining the type of fault that occurs, and the type of fault includes: air filter fault, intake pipe leakage fault, supercharger bypass valve fault, supercharger impeller fault, exhaust pipe leakage fault, and diesel particulate filter fault.

5. The method according to claim 1, wherein: The machine learning model adopts a classification algorithm, which includes logistic regression, convex hull, K-means clustering, support vector machine, random forest, naive Bayes, and multi-layer perceptron.

6. The method according to claim 1, further comprising: Obtaining fuel consumption per stroke of the engine; The fuel consumption per stroke, the intake parameters, the exhaust parameters, and the speed value are provided as feature data to a machine learning model to determine the state of the intake and exhaust system.

7. A device for detecting the state of an intake and exhaust system of an engine, comprising: R.406547 Memory; A control unit is coupled to the memory, wherein the control unit is configured to execute the method according to any one of claims 1-6.

8. A computer readable medium storing a computer program comprising instructions which, when executed by a control unit, cause the control unit to be configured to perform the method according to any one of claims 1 to 6.

9. A device for detecting the state of an intake and exhaust system of an engine, comprising a unit for executing the method according to any one of claims 1 to 6.

Images