CN113586239A - Engine fault diagnosis method, engine fault diagnosis device, controller and storage medium - Google Patents
Engine fault diagnosis method, engine fault diagnosis device, controller and storage medium Download PDFInfo
- Publication number
- CN113586239A CN113586239A CN202110997645.7A CN202110997645A CN113586239A CN 113586239 A CN113586239 A CN 113586239A CN 202110997645 A CN202110997645 A CN 202110997645A CN 113586239 A CN113586239 A CN 113586239A
- Authority
- CN
- China
- Prior art keywords
- engine
- value
- signal
- analysis
- processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004458 analytical method Methods 0.000 claims abstract description 247
- 238000012545 processing Methods 0.000 claims abstract description 158
- 238000005192 partition Methods 0.000 claims abstract description 119
- 238000001914 filtration Methods 0.000 claims description 49
- 238000007619 statistical method Methods 0.000 claims description 45
- 238000004590 computer program Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 14
- 238000001514 detection method Methods 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002405 diagnostic procedure Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000010705 motor oil Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
- F02B77/00—Component parts, details or accessories, not otherwise provided for
- F02B77/08—Safety, indicating, or supervising devices
- F02B77/083—Safety, indicating, or supervising devices relating to maintenance, e.g. diagnostic device
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The application relates to an engine fault diagnosis method, an engine fault diagnosis device, a controller and a storage medium. The method comprises the following steps: acquiring running signals generated by an engine of a vehicle in different running working conditions; the operation condition is determined according to the rotating speed and the torque of the engine, and the operation signal represents the real-time operation state of the engine; determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value; acquiring an operation actual value of the operation signal, and determining the deviation between the operation actual value and a real-time operation analysis value; and carrying out engine fault diagnosis according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result. By adopting the method, the engine fault detection efficiency can be improved.
Description
Technical Field
The present disclosure relates to the field of vehicle control technologies, and in particular, to a method, an apparatus, a controller, and a storage medium for diagnosing engine faults.
Background
The traditional commercial vehicle power system has increasingly complex engine electronic control system due to the requirements of energy conservation, environmental protection and intellectualization. From the development point of view, the change further causes the increase of the calibration workload of the electronic control data of the diagnosis part; this change further increases the difficulty of subsequent maintenance from an after-market point of view. In the prior art, in order to ensure effective fault diagnosis of an engine, planned maintenance is performed on the engine according to the running time or mileage of a vehicle through post-fault maintenance. Nevertheless, the above-described method enables troubleshooting to be performed periodically. However, it needs a manual maintenance scheme with fixed time and fixed quantity, and it lacks the capability of automatic fault diagnosis, and has the problem of low fault detection efficiency.
Disclosure of Invention
Accordingly, it is desirable to provide an engine fault diagnosis method, apparatus, controller, and storage medium capable of efficiently detecting an engine fault in response to the above-described technical problems.
An engine fault diagnostic method, the method comprising:
acquiring running signals generated by an engine of a vehicle in different running working conditions; the operation condition is determined according to the rotating speed and the torque of the engine, and the operation signal represents the real-time operation state of the engine;
determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value;
acquiring an operation actual value of the operation signal, and determining a deviation between the operation actual value and the real-time operation analysis value;
and diagnosing the engine fault according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
An engine fault diagnosis apparatus comprising an acquisition module, a first processing module, a second processing module, and an output module, wherein:
the acquisition module is used for acquiring running signals generated by an engine of a vehicle in different running working conditions; the operation condition is determined according to the rotating speed and the torque of the engine, and the operation signal represents the real-time operation state of the engine;
the first processing module is used for determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value;
the second processing module is used for acquiring an operation actual value of the operation signal and determining a deviation between the operation actual value and the real-time operation analysis value;
and the output module is used for carrying out engine fault diagnosis according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
A controller comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring running signals generated by an engine of a vehicle in different running working conditions; the operation condition is determined according to the rotating speed and the torque of the engine, and the operation signal represents the real-time operation state of the engine;
determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value;
acquiring an operation actual value of the operation signal, and determining a deviation between the operation actual value and the real-time operation analysis value;
and diagnosing the engine fault according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring running signals generated by an engine of a vehicle in different running working conditions; the operation condition is determined according to the rotating speed and the torque of the engine, and the operation signal represents the real-time operation state of the engine;
determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value;
acquiring an operation actual value of the operation signal, and determining a deviation between the operation actual value and the real-time operation analysis value;
and diagnosing the engine fault according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
According to the engine fault diagnosis method, the engine fault diagnosis device, the controller and the storage medium, based on the target analysis model, the operation signals generated by the engine of the vehicle under different operation conditions are subjected to the partition statistical analysis, so that the problem that the calibration workload of the electronic control data is large in a diagnosis part in the prior art is solved, and the analysis efficiency of the electronic control data can be improved. And the real-time operation analysis value calculated by the target analysis model is used as a standard value by combining the data processing experience of the target analysis model in the historical processing time period, and the engine fault diagnosis is carried out on the basis of the deviation between the operation actual value of the operation signal and the standard value, so that the accuracy of the fault diagnosis result can be guaranteed, and the engine fault detection efficiency can be improved.
Drawings
FIG. 1 is a diagram of an exemplary engine fault diagnostic method;
FIG. 2 is a schematic flow chart diagram of a method for engine fault diagnosis in one embodiment;
FIG. 3 is a schematic flow chart illustrating the steps for calculating a real-time operating analysis value according to one embodiment;
FIG. 4 is a schematic flow chart diagram illustrating an overall engine fault diagnosis method according to an embodiment;
FIG. 5 is a block diagram showing the construction of an engine failure diagnosis apparatus according to an embodiment;
FIG. 6 is an internal block diagram of a controller in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The engine fault diagnosis method is suitable for an application scene of diagnosing the engine fault of the vehicle. The current application scenario is provided with a vehicle 100, a controller 102, a plurality of sensors 104 and an engine 106; among other things, the controller 102, the sensor 104, and the engine 106 are components in the vehicle 100. The controller 102 is coupled to each of the sensors 104 and the engine 106, and receives operating signals collected via each of the sensors 104 that are generated by the engine 106 during different operating conditions. The controller 102 acquires operation signals generated by an engine 106 arranged in the vehicle 100 in different operation conditions; the operating conditions are determined according to the engine speed and the engine torque, and the operating signals represent the real-time operating state of the engine 106; the controller 102 determines an input signal of a target analysis model based on the operation signal, and performs statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value; the controller 102 acquires an actual value of the operation signal and determines a deviation between the actual value and the real-time operation analysis value; the controller 102 performs engine fault diagnosis based on the deviation between the actual operating value and the real-time operating analysis value to obtain a corresponding fault diagnosis result.
The controller 102 may be, but is not limited to, a vehicle controller or an engine controller, which is not limited in the embodiments of the present application. The sensors 104 may be, but are not limited to, various pressure sensors, flow sensors, temperature sensors, rotational speed sensors, and the like. An engine is a device capable of converting other forms of energy into mechanical energy, including, for example, internal combustion engines, external combustion engines, jet engines, and electric motors. It should be noted that the engine is applicable to both the power generation device and the whole equipment including the power generation device, such as a gasoline engine and an aircraft engine.
In one embodiment, as shown in fig. 2, an engine fault diagnosis method is provided, which is described by taking an example of the method applied to an engine controller, and comprises the following steps:
step S202, acquiring running signals generated by an engine of a vehicle in different running working conditions; the operating condition is determined based on engine speed and engine torque, and the operating signal characterizes a real-time operating state of the engine.
Specifically, a sensor is arranged on the engine controller, and the engine controller acquires a sensor signal acquired by the sensor, wherein the sensor signal comprises operation signals generated by the engine in different operation conditions. It should be noted that the type of the operation signal includes at least one of pressure, temperature, rotation speed, and flow rate. The real-time operating condition of the engine includes at least one of normal operation, risk of operating failure, and severe operating failure.
In one embodiment, the engine Controller may be connected to the sensors via a Controller Area Network (CAN) bus to enable information interaction with the sensors. Of course, the engine controller may also directly acquire the operating signals generated by the engine of the vehicle in different operating conditions without being connected to the sensor through the CAN bus, which is not limited in the embodiment of the present application.
Step S204, determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value.
Specifically, the operation signal is acquired by a sensor arranged on the controller, and the input signal of the target analysis model is determined based on the operation signal, and the method comprises the following steps: when the operation signal is determined to be obtained by transmitting through a CAN bus connected with the sensor, the operation signal is directly used as an input signal of a target analysis model; otherwise, when the operation signal is determined to be the analog quantity signal, performing high-frequency filtering processing on the operation signal to obtain a corresponding high-frequency filtering signal; carrying out effectiveness analysis on the high-frequency filtering signal to obtain a corresponding analysis result; and when the analysis result represents that the high-frequency filtering signal is an effective signal, performing low-pass filtering processing on the high-frequency filtering signal, and taking the processed low-pass filtering signal as an input signal of the target analysis model.
In one embodiment, when the engine controller determines that the operation signal is collected via a sensor provided on the engine controller, high frequency filtering, validity analysis, and low pass filtering are performed due to sensor data transmitted via the CAN bus (for example, as shown in fig. 4, the current sensor data may be at least one of intake air flow rate, after-cold intake air pressure, after-cold intake air temperature, common rail fuel pressure, metering valve average current, low pressure fuel pressure, and engine oil pressure). Therefore, in the present embodiment, when receiving the operation signal transmitted via the CAN bus, the engine controller directly uses the operation signal as an input signal of the target analysis model, so that the target analysis model performs statistical analysis processing on the input signal and obtains a corresponding analysis result.
In one embodiment, when the engine controller is not connected to the sensor through the CAN bus, and when it is determined that the received operating signal is an analog signal, first, the collected operating signal is subjected to high-frequency filtering (for example, the engine controller may perform high-frequency filtering through a built-in hardware input circuit, and of course, the engine controller may also perform high-pass filtering in other processing manners, which is not limited in the embodiments of the present application), so as to obtain a corresponding high-frequency filtered signal. Then, validity analysis is performed on the obtained high-frequency filtering signal (for example, whether the collected voltage is too high or too low is determined through rationality check of the collected voltage, and of course, the engine controller may also perform validity analysis in other processing manners, which is not limited in this embodiment of the application), so as to ensure accuracy of the collected signal. Finally, the low-pass filtering process is performed on the analyzed effective high-frequency filtered signal (for example, the engine controller may perform the low-pass filtering through a low-pass filter, and certainly, the engine controller may also perform the low-pass filtering in other processing manners, which is not limited in this embodiment of the application), and the processed low-pass filtered signal is used as an input signal of the target analysis model.
Therefore, before the running signal is input into the target analysis model for statistical processing, the running signal is subjected to reasonability check of voltage acquisition and high-frequency and low-frequency filtering processing, so that the validity of the running signal is ensured under the condition of avoiding high-frequency interference, and the accuracy of engine fault diagnosis is improved.
Step S206, acquiring the operation actual value of the operation signal, and determining the deviation between the operation actual value and the real-time operation analysis value.
Specifically, determining the deviation between the actual operating value and the real-time operating analysis value includes: determining a deviation between the operational actual value and the operational analytical value according to the following formula:
wherein, In _ model is a real-time operation analysis value, In _ sensor is an operation actual value, and Ratio is a deviation between the operation actual value and the real-time operation analysis value.
And step S208, performing engine fault diagnosis according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
Specifically, the engine fault diagnosis is performed according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result, and the method comprises the following steps: when the absolute value of the deviation is smaller than or equal to a preset normal judgment threshold value, outputting a first diagnosis result representing that the engine operates normally; when the absolute value of the deviation is larger than a preset normal judgment threshold value and is smaller than or equal to a preset risk judgment threshold value, outputting a second diagnosis result representing that the engine has an operation fault risk; when the absolute value of the deviation is larger than a preset risk judgment threshold value and is smaller than or equal to a preset fault judgment threshold value, outputting a third diagnosis result representing that the engine is in an operation fault state; and outputting a fourth diagnosis result representing that the engine is in a serious operation fault state when the absolute value of the deviation is greater than a preset fault judgment threshold value.
In one embodiment, the engine controller ranks the fault condition of the engine into four ranks, a normal condition, an early warning alert condition, a fault condition, and a critical fault condition. Based on the formula (1), when the engine controller determines that the Ratio is in the value range of | Ratio | ≦ 10%, the engine is considered to be in the normal state level; at this time, a first diagnostic result indicating that the engine is operating normally will be output. When the engine controller determines that the Ratio is in a value range of 10% < | Ratio | ≦ 25%, the engine is considered to be in an early warning prompting state grade; at this time, a second diagnostic result indicating that the engine is at risk of an operational failure will be output. When the engine controller determines that the Ratio is in the value range of 25% < | Ratio | ≦ 50%, the engine is considered to be in the fault state level; at this time, a third diagnostic result indicating that the engine is in an operation failure state will be output. When the engine controller determines that the Ratio is in a value range of | Ratio | > 50%, the engine is considered to be in a serious fault state grade; at this time, a fourth diagnostic result indicating that the engine is in a severe operating fault state will be output.
In the engine fault diagnosis, the running signals generated by the engine of the vehicle under different running working conditions are subjected to the partition statistical analysis based on the target analysis model, so that the problem that the calibration workload of the electronic control data is large in a diagnosis part in the prior art is solved, and the analysis efficiency of the electronic control data can be improved. And the real-time operation analysis value calculated by the target analysis model is used as a standard value by combining the data processing experience of the target analysis model in the historical processing time period, and the engine fault diagnosis is carried out on the basis of the deviation between the operation actual value of the operation signal and the standard value, so that the accuracy of the fault diagnosis result can be guaranteed, and the engine fault detection efficiency can be improved.
In one embodiment, referring to fig. 3, the statistical processing is performed on the current input signal in the established target data partition by the target analysis model to obtain the corresponding real-time operation analysis value, which includes the following steps:
step S302, searching a target data partition in each established data partition when a current input signal is determined through a target analysis model, the operation condition corresponding to the input signal is associated with, and a preset partition establishing condition is met; the partition establishing conditions include that the output of the operation signal is normal, the deviation value of the engine torque in the preset time meets a preset first deviation condition, the deviation value of the engine speed in the preset time meets a preset second deviation condition, and the engine speed and the engine torque are included in a preset point selection range.
Specifically, the engine controller establishes a RAM data partition in a built-in single chip microcomputer RAM (Random Access Memory) with the engine speed and the engine torque as basic coordinate axes and with the operation signal to be counted as an output, wherein the RAM data partition can be used for storing data to be statistically analyzed and can also be used for storing statistically analyzed data after the statistical analysis. It should be noted that, before the power failure of the engine controller, the statistical analysis data and the data to be statistically analyzed stored in each RAM data partition need to be copied to a preset backup partition for backup processing.
In one embodiment, the backup partition may be an engine controller EEPROM (Electrically Erasable Programmable read Only memory) partition. It should be noted that the EEPROM is a memory chip whose data is not lost after power failure, and it can erase existing information on a computer or a dedicated device, and be reprogrammed, and is generally plug and play. The engine controller will perform signal partition statistics when it is determined that the following conditions are satisfied:
(1) and outputting normal running signals to be counted.
(2) And determining that the engine speed and the engine torque are within a preset point selection range (for example, the deviation of the point selection range of the engine speed from the reference point is ± 20rpm, and the deviation of the point selection range of the engine torque from the reference point is ± 20Nm, it should be noted that the above point selection range may be modified by pre-calibration, which is not limited in the embodiment of the present application) based on the established RAM data partition.
(3) And determining that the engine is in a stable operating condition (for example, when the difference between the maximum value and the minimum value of the engine speed is determined to be less than 40rpm and the difference between the maximum value and the minimum value of the engine torque is determined to be less than 40Nm within 3 seconds, the engine is considered to be in the stable operating condition, and of course, the point selection time and the difference can be modified through pre-calibration, which is not limited by the embodiment of the present application).
And step S304, when the searching is determined to be successful, processing the current input signal in the searched target data partition through the target analysis model to obtain a corresponding real-time operation analysis value.
Specifically, the processing of the current input signal in the searched target data partition by the target analysis model to obtain a corresponding real-time operation analysis value includes: taking the running signal as an input signal of a target analysis model, and processing the current input signal in the searched target data partition through the target analysis model according to the following formula to obtain a corresponding weighted processing signal:
wherein Num is a weighting parameter, In is an operation signal, and Out is a weighted processing signal obtained by processing; when the weighted processing signal is determined to be in the historical processing time period and is taken as the input signal of the target analysis model for statistical processing, taking the target historical operation analysis value obtained by historical processing as the real-time operation analysis value; and when the weighted processing signal is determined not to be taken as the input signal of the target analysis model for statistical processing in the historical processing time period, calculating the real-time operation analysis value according to the value trend among the historical operation analysis values obtained by processing the target analysis model.
In one embodiment, the engine controller is used for establishing a query chart based on the engine speed, the engine torque and the RAM data partition, and performing table lookup operation based on the query chart by adopting a conventional binary interpolation method, taking a weighted processing signal as a lookup condition and a target historical operation analysis value obtained by corresponding historical processing as a lookup target in the process of using a target analysis model. Wherein:
(1) when the engine controller determines that the corresponding target historical operation analysis value can be inquired from the inquiry chart, the weighted processing signal is considered to be used as an input signal of the target analysis model in the historical processing time period and is subjected to statistical processing. At this time, the engine controller directly takes the corresponding target historical operation analysis value as the real-time operation analysis value.
(2) When the engine controller determines that the corresponding target historical operation analysis value cannot be inquired from the inquiry chart, the weighted processing signal is not regarded as the input signal of the target analysis model in the historical processing time period. At this time, the engine controller calculates the real-time operation analysis values based on the value trend between the corresponding historical operation analysis values.
Therefore, compared with the prior art that a calculation mode of real-time operation analysis values is carried out based on a large number of calibrations, the method carries out partition statistics according to the operation condition of the engine, and the problem that the workload of diagnosis part calibration is large in the prior art is solved.
And S306, when the search is determined to fail, establishing a target data partition according to the engine speed, the engine torque and the operation signal, and processing the current input signal in the currently established target data partition through a target analysis model to obtain a corresponding real-time operation analysis value.
Specifically, when the search is determined to be failed, the target data partition is established by taking the engine speed and the engine torque as basic coordinate axes and taking the operation signal to be counted as output. The target data partition may store the operation signals to be counted, or may store the real-time operation analysis value data after the statistical analysis. In order to avoid the loss of the data stored in the target data partition after the engine controller is powered off, the stored running signals to be counted and the real-time running analysis value data after statistical analysis are copied to a preset backup partition for backup processing before the engine controller is powered off, and the backed-up real-time running analysis value data after statistical analysis is restored to the corresponding target data partition for continuous statistical learning when the engine controller is powered back.
In this embodiment, before the running signal to be counted is input to the target analysis model for statistical analysis, weighting is performed on the running signal to be counted, so that the accuracy of processing different types of signals can be ensured. And by carrying out partition statistics based on the operation condition of the engine, the problem of large calibration workload of a diagnosis part in the development process is avoided, and the data analysis efficiency can be improved. And before the power failure of the engine controller, carrying out statistical analysis and backup of data to be statistically analyzed in advance, avoiding loss of stored data in the data partition and avoiding the problem of low fault diagnosis accuracy caused by incomplete data.
In one embodiment, the method further comprises: taking the operation signal as data to be subjected to statistical analysis, taking the operation analysis value determined according to the operation signal as statistical analysis data, and respectively storing the operation analysis value into corresponding data partitions; before the controller is determined to be in a power-down state, copying data to be subjected to statistical analysis and stored in the data partition and the statistical analysis data to a preset backup partition respectively for backup processing; and when the controller is determined to be in a power-on state, restoring the statistical analysis data pre-stored in the backup partition to the corresponding data partition so as to ensure the smooth execution of the statistical processing process.
Specifically, the operation signals to be counted may be stored in the data partition as the data to be counted and analyzed, or the real-time operation analysis value data after the statistical analysis may be stored as the statistical analysis data. The data to be counted and analyzed stored in the data partition and the loss of the data to be counted and analyzed are avoided after the engine controller is powered off. In one embodiment, before it is determined that the engine controller is in a power-down state, the data to be analyzed and the statistical analysis data stored in each data partition are respectively copied to a preset backup partition for backup processing. And when the engine controller is determined to be in a power-on state, recovering the successfully backed-up statistical analysis data in the backup partition into the data partition, and ensuring the smooth execution of the statistical processing process.
In this embodiment, before the engine controller is powered off, the statistical analysis data and the data to be statistically analyzed are backed up in advance, so that loss of stored data in the data partition due to power failure of the engine controller is avoided, and the problem of low fault diagnosis accuracy due to incomplete stored data in the data partition is avoided.
In an embodiment, please refer to fig. 4, which is a schematic overall flow chart of the engine fault diagnosis method, in the current embodiment, when performing the engine fault diagnosis, the method specifically includes the following steps:
1. and a signal acquisition processing stage: the engine controller processes the received collected signals, which include sensor signals directly collected by the engine controller, or communicates with the sensor when connected to the sensor through a CAN bus, so as to obtain the signals. The method comprises the steps of firstly carrying out high-frequency filtering processing on directly acquired acquisition signals, then carrying out effectiveness analysis on the processed high-frequency filtering signals, and finally carrying out low-pass filtering processing on the analyzed effective high-frequency filtering signals. It should be noted that, since the above processing is already completed by the data communicated on the CAN bus, the signal processing does not need to be repeated.
2. And a signal partition counting stage: and establishing a data partition by taking the rotating speed and the torque of the engine as basic coordinate axes and taking the signals to be counted as output according to the acquired and processed signals to be counted without faults. Before determining that the engine controller is powered down, data to be subjected to statistical analysis and statistical analysis data stored in the data partition are backed up in the EEPROM partition. It should be noted that, in order to ensure the accuracy of the different types of signal processing, the engine controller further needs to perform the following weighted average calculation on the corresponding types of signal data:
where Num is a weighting parameter, In is a running signal, and Out is a weighted processing signal obtained by processing. The calculation result is continuously updated and filled in the data partition, and the weighting parameters Num corresponding to the different types of signals can be respectively set.
3. Updating an adaptive model stage: when the engine controller is powered on again, the statistical data backed up in the EEPROM subarea is restored to the data subarea for continuous statistical learning. Wherein, during the use of the target analysis model, a corresponding query graph can be established based on the engine speed, the engine torque and the established data partition. And then, calculating the model output value of the corresponding signal under the current engine operation condition by adopting a conventional binary interpolation method and through table lookup operation.
4. And (3) a basic model processing stage: because the statistical learning of the target analysis model needs a certain period process, after the data partition learning is primarily completed, a corresponding state mark is output to represent the statistical completion state. In order to avoid accidental loss of statistical data and data to be statistical before data partition learning is completed or an engine controller is powered down, backup redundancy needs to be performed through a basic model. It should be noted that the basic model is stored in the engine controller FLASH, and the basic model is refreshed and updated by an off-line device, a diagnostic instrument or an OTA.
5. And (3) a model arbitration output stage: and finally determining the calculation result of the current working condition standard value of the output basic model or the target analysis model according to the actual condition of data statistics learning. For example, the engine controller may output the calculated values of the basic model before the data statistics learning is completed; of course, the engine controller may also use the target analysis model calculation value output after the learning is completed, and in this case, the data matrix information in the target analysis model should also be continuously updated.
6. And a fault level threshold calculation stage: according to the signal fault grade division (normal, early warning prompt, fault and serious fault) condition, on the basis of the current working condition model calculation reference value output by the target analysis model, the judgment threshold value under the states of normal, early warning prompt, fault, serious fault and the like is calculated based on the formula (1): and outputting a first diagnosis result that the engine is in a normal operation state when it is determined that the deviation is in a range of | Ratio | ≦ 10%: when the deviation is determined to be within the range of 10% < | Ratio | ≦ 25%, outputting a second diagnosis result that the engine is in an early warning prompting state; outputting a third diagnosis result that the engine is in a running fault state when the deviation is determined to be in the range of 25% < | Ratio | ≦ 50%; when it is determined that the deviation is in the range of | Ratio | > 50%, a fourth diagnosis that the engine is in a severe operation failure state is output. It should be noted that the above-mentioned discrimination threshold may be modified by calibrating the correspondence.
7. And fault grade judging and outputting stage: the engine controller judges the current actual fault state in real time according to the data processed by the current sensor and in combination with the judgment threshold value of the fault level, and the fault state can be formally output only by ensuring the continuous output of the fault state for a period of time in consideration of the change of the vehicle operation condition so as to ensure the accuracy of the fault state and output the relevant diagnosis state information through the communication and diagnosis interface.
The engine fault diagnosis method is not only suitable for the transmitter controller, but also suitable for the vehicle controller, can realize the establishment of a calibration-free self-adaptive digital model (namely a target analysis model) based on the analysis and statistics of the existing sensor signals of the vehicle and the engine, provides an effective data base for the subsequent signal fault grade diagnosis and output based on the calculated value output by the self-adaptive digital model, realizes the effective fault diagnosis of the engine through the strong calculation capability and storage capability of the controller, enhances the driving safety and maintenance, and reduces the workload of electronic control calibration.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 5, an engine fault diagnosis apparatus 500 is provided, the apparatus 500 including an acquisition module 501, a first processing module 502, a second processing module 503, and an output module 504, wherein:
the acquiring module 501 is used for acquiring running signals generated by an engine of a vehicle in different running working conditions; the operating condition is determined based on engine speed and engine torque, and the operating signal characterizes a real-time operating state of the engine.
The first processing module 502 is configured to determine an input signal of a target analysis model based on the operation signal, and perform statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value.
A second processing module 503 is configured to obtain an actual operation value of the operation signal and determine a deviation between the actual operation value and the real-time operation analysis value.
And the output module 504 is used for performing fault diagnosis on the engine according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
In one embodiment, the operation signal is acquired by a sensor arranged on the controller; the first processing module 502 is further configured to directly take the operation signal as an input signal of the target analysis model when it is determined that the operation signal is transmitted via the CAN bus to which the sensor is connected; otherwise, when the operation signal is determined to be the analog quantity signal, performing high-frequency filtering processing on the operation signal to obtain a corresponding high-frequency filtering signal; carrying out effectiveness analysis on the high-frequency filtering signal to obtain a corresponding analysis result; and when the analysis result represents that the high-frequency filtering signal is an effective signal, performing low-pass filtering processing on the high-frequency filtering signal, and taking the processed low-pass filtering signal as an input signal of the target analysis model.
In one embodiment, the first processing module 502 is further configured to search a target data partition in each established data partition when determining, by the target analysis model, that a current input signal corresponds to an associated operating condition and meets a preset partition establishment condition; the partition establishing conditions comprise that the output of the running signal is normal, the deviation value of the engine torque in the preset time meets a preset first deviation condition, the deviation value of the engine rotating speed in the preset time meets a preset second deviation condition, and the engine rotating speed and the engine torque are included in a preset point selection range; when the searching is determined to be successful, processing the current input signal in the searched target data partition through the target analysis model to obtain a corresponding real-time operation analysis value; when the search is determined to be failed, establishing a target data partition according to the engine speed, the engine torque and the operation signal, and processing the current input signal in the currently established target data partition through a target analysis model to obtain a corresponding real-time operation analysis value.
In one embodiment, the first processing module 502 is further configured to use the operation signal as an input signal of a target analysis model, and process the current input signal in a searched target data partition through the target analysis model according to the following formula to obtain a corresponding weighted processing signal:
wherein Num is a weighting parameter, In is an operation signal, and Out is a weighted processing signal obtained by processing; when the weighted processing signal is determined to be in the historical processing time period and is taken as the input signal of the target analysis model for statistical processing, taking the target historical operation analysis value obtained by historical processing as the real-time operation analysis value; and when the weighted processing signal is determined not to be taken as the input signal of the target analysis model for statistical processing in the historical processing time period, calculating the real-time operation analysis value according to the value trend among the historical operation analysis values obtained by processing the target analysis model.
In one embodiment, the second processing module 503 is further configured to determine a deviation between the operation actual value and the operation analyzed value according to the following formula:
wherein, In _ model is a real-time operation analysis value, In _ sensor is an operation actual value, and Ratio is a deviation between the operation actual value and the real-time operation analysis value.
In one embodiment, the output module 504 is further configured to output a first diagnosis result indicating that the engine is operating normally when the absolute value of the deviation is smaller than or equal to a preset normal judgment threshold; when the absolute value of the deviation is larger than a preset normal judgment threshold value and is smaller than or equal to a preset risk judgment threshold value, outputting a second diagnosis result representing that the engine has an operation fault risk; when the absolute value of the deviation is larger than a preset risk judgment threshold value and is smaller than or equal to a preset fault judgment threshold value, outputting a third diagnosis result representing that the engine is in an operation fault state; and outputting a fourth diagnosis result representing that the engine is in a serious operation fault state when the absolute value of the deviation is greater than a preset fault judgment threshold value.
In one embodiment, the apparatus further comprises a backup module, wherein: the backup module is used for taking the operation signals as data to be subjected to statistical analysis, taking the operation analysis values determined according to the operation signals as statistical analysis data, and respectively storing the operation analysis values into corresponding data partitions; before the controller is determined to be in a power-down state, copying data to be subjected to statistical analysis and stored in the data partition and the statistical analysis data to a preset backup partition respectively for backup processing; and when the controller is determined to be in a power-on state, restoring the statistical analysis data pre-stored in the backup partition to the corresponding data partition so as to ensure the smooth execution of the statistical processing process.
The engine fault diagnosis device carries out the partition statistical analysis on the running signals generated by the engine of the vehicle in different running working conditions based on the target analysis model, avoids the problem that the calibration workload of the electronic control data is large in the diagnosis part in the prior art, and can improve the analysis efficiency of the electronic control data. And the real-time operation analysis value calculated by the target analysis model is used as a standard value by combining the data processing experience of the target analysis model in the historical processing time period, and the engine fault diagnosis is carried out on the basis of the deviation between the operation actual value of the operation signal and the standard value, so that the accuracy of the fault diagnosis result can be guaranteed, and the engine fault detection efficiency can be improved.
For specific limitations of the engine fault diagnosis device, reference may be made to the above limitations of the engine fault diagnosis method, which are not described herein again. The respective modules in the engine failure diagnosis apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a controller is provided, the internal structure of which may be as shown in fig. 6. It should be noted that the controller may be a vehicle controller or an engine controller, which is not limited in the embodiments of the present application. Wherein the controller comprises a processor and a memory connected by a system bus. The memory stores a computer program, and the processor executes the computer program to realize the following steps: acquiring running signals generated by an engine of a vehicle in different running working conditions; the operation condition is determined according to the rotating speed and the torque of the engine, and the operation signal represents the real-time operation state of the engine; determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value; acquiring an operation actual value of the operation signal, and determining the deviation between the operation actual value and a real-time operation analysis value; and carrying out engine fault diagnosis according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
In one embodiment, the operation signal is collected by a sensor arranged on the controller, and the processor executes the computer program to further realize the following steps: when the operation signal is determined to be obtained by transmitting through a CAN bus connected with the sensor, the operation signal is directly used as an input signal of a target analysis model; otherwise, when the operation signal is determined to be the analog quantity signal, performing high-frequency filtering processing on the operation signal to obtain a corresponding high-frequency filtering signal; carrying out effectiveness analysis on the high-frequency filtering signal to obtain a corresponding analysis result; and when the analysis result represents that the high-frequency filtering signal is an effective signal, performing low-pass filtering processing on the high-frequency filtering signal, and taking the processed low-pass filtering signal as an input signal of the target analysis model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: searching a target data partition in each established data partition when a current input signal is determined through a target analysis model, and the operation condition corresponding to the current input signal meets a preset partition establishing condition; the partition establishing conditions comprise that the output of the running signal is normal, the deviation value of the engine torque in the preset time meets a preset first deviation condition, the deviation value of the engine rotating speed in the preset time meets a preset second deviation condition, and the engine rotating speed and the engine torque are included in a preset point selection range; when the searching is determined to be successful, processing the current input signal in the searched target data partition through the target analysis model to obtain a corresponding real-time operation analysis value; when the search is determined to be failed, establishing a target data partition according to the engine speed, the engine torque and the operation signal, and processing the current input signal in the currently established target data partition through a target analysis model to obtain a corresponding real-time operation analysis value.
In one embodiment, the processor, when executing the computer program, further performs the steps of: taking the running signal as an input signal of a target analysis model, and processing the current input signal in the searched target data partition through the target analysis model according to the following formula to obtain a corresponding weighted processing signal:
wherein Num is a weighting parameter, In is an operation signal, and Out is a weighted processing signal obtained by processing; when the weighted processing signal is determined to be in the historical processing time period and is taken as the input signal of the target analysis model for statistical processing, taking the target historical operation analysis value obtained by historical processing as the real-time operation analysis value; and when the weighted processing signal is determined not to be taken as the input signal of the target analysis model for statistical processing in the historical processing time period, calculating the real-time operation analysis value according to the value trend among the historical operation analysis values obtained by processing the target analysis model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: determining a deviation between the operational actual value and the operational analytical value according to the following formula:
wherein, In _ model is a real-time operation analysis value, In _ sensor is an operation actual value, and Ratio is a deviation between the operation actual value and the real-time operation analysis value.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when the absolute value of the deviation is smaller than or equal to a preset normal judgment threshold value, outputting a first diagnosis result representing that the engine operates normally; when the absolute value of the deviation is larger than a preset normal judgment threshold value and is smaller than or equal to a preset risk judgment threshold value, outputting a second diagnosis result representing that the engine has an operation fault risk; when the absolute value of the deviation is larger than a preset risk judgment threshold value and is smaller than or equal to a preset fault judgment threshold value, outputting a third diagnosis result representing that the engine is in an operation fault state; and outputting a fourth diagnosis result representing that the engine is in a serious operation fault state when the absolute value of the deviation is greater than a preset fault judgment threshold value.
In one embodiment, the processor, when executing the computer program, further performs the steps of: taking the operation signal as data to be subjected to statistical analysis, taking the operation analysis value determined according to the operation signal as statistical analysis data, and respectively storing the operation analysis value into corresponding data partitions; before the controller is determined to be in a power-down state, copying data to be subjected to statistical analysis and stored in the data partition and the statistical analysis data to a preset backup partition respectively for backup processing; and when the controller is determined to be in a power-on state, restoring the statistical analysis data pre-stored in the backup partition to the corresponding data partition so as to ensure the smooth execution of the statistical processing process.
The controller carries out partition statistical analysis on the running signals generated by the engine of the vehicle in different running working conditions based on the target analysis model, avoids the problem of large workload of calibration of the electronic control data in a diagnosis part in the prior art, and can improve the analysis efficiency of the electronic control data. And the real-time operation analysis value calculated by the target analysis model is used as a standard value by combining the data processing experience of the target analysis model in the historical processing time period, and the engine fault diagnosis is carried out on the basis of the deviation between the operation actual value of the operation signal and the standard value, so that the accuracy of the fault diagnosis result can be guaranteed, and the engine fault detection efficiency can be improved.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring running signals generated by an engine of a vehicle in different running working conditions; the operation condition is determined according to the rotating speed and the torque of the engine, and the operation signal represents the real-time operation state of the engine; determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value; acquiring an operation actual value of the operation signal, and determining the deviation between the operation actual value and a real-time operation analysis value; and carrying out engine fault diagnosis according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
In one embodiment, the operation signal is collected by a sensor arranged on the controller, and the computer program is used for realizing the following steps when being executed by the processor: when the operation signal is determined to be obtained by transmitting through a CAN bus connected with the sensor, the operation signal is directly used as an input signal of a target analysis model; otherwise, when the operation signal is determined to be the analog quantity signal, performing high-frequency filtering processing on the operation signal to obtain a corresponding high-frequency filtering signal; carrying out effectiveness analysis on the high-frequency filtering signal to obtain a corresponding analysis result; and when the analysis result represents that the high-frequency filtering signal is an effective signal, performing low-pass filtering processing on the high-frequency filtering signal, and taking the processed low-pass filtering signal as an input signal of the target analysis model.
In one embodiment, the computer program when executed by the processor further performs the steps of: searching a target data partition in each established data partition when a current input signal is determined through a target analysis model, and the operation condition corresponding to the current input signal meets a preset partition establishing condition; the partition establishing conditions comprise that the output of the running signal is normal, the deviation value of the engine torque in the preset time meets a preset first deviation condition, the deviation value of the engine rotating speed in the preset time meets a preset second deviation condition, and the engine rotating speed and the engine torque are included in a preset point selection range; when the searching is determined to be successful, processing the current input signal in the searched target data partition through the target analysis model to obtain a corresponding real-time operation analysis value; when the search is determined to be failed, establishing a target data partition according to the engine speed, the engine torque and the operation signal, and processing the current input signal in the currently established target data partition through a target analysis model to obtain a corresponding real-time operation analysis value.
In one embodiment, the computer program when executed by the processor further performs the steps of: taking the running signal as an input signal of a target analysis model, and processing the current input signal in the searched target data partition through the target analysis model according to the following formula to obtain a corresponding weighted processing signal:
wherein Num is a weighting parameter, In is an operation signal, and Out is a weighted processing signal obtained by processing; when the weighted processing signal is determined to be in the historical processing time period and is taken as the input signal of the target analysis model for statistical processing, taking the target historical operation analysis value obtained by historical processing as the real-time operation analysis value; and when the weighted processing signal is determined not to be taken as the input signal of the target analysis model for statistical processing in the historical processing time period, calculating the real-time operation analysis value according to the value trend among the historical operation analysis values obtained by processing the target analysis model.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining a deviation between the operational actual value and the operational analytical value according to the following formula:
wherein, In _ model is a real-time operation analysis value, In _ sensor is an operation actual value, and Ratio is a deviation between the operation actual value and the real-time operation analysis value.
In one embodiment, the computer program when executed by the processor further performs the steps of: when the absolute value of the deviation is smaller than or equal to a preset normal judgment threshold value, outputting a first diagnosis result representing that the engine operates normally; when the absolute value of the deviation is larger than a preset normal judgment threshold value and is smaller than or equal to a preset risk judgment threshold value, outputting a second diagnosis result representing that the engine has an operation fault risk; when the absolute value of the deviation is larger than a preset risk judgment threshold value and is smaller than or equal to a preset fault judgment threshold value, outputting a third diagnosis result representing that the engine is in an operation fault state; and outputting a fourth diagnosis result representing that the engine is in a serious operation fault state when the absolute value of the deviation is greater than a preset fault judgment threshold value.
In one embodiment, the computer program when executed by the processor further performs the steps of: taking the operation signal as data to be subjected to statistical analysis, taking the operation analysis value determined according to the operation signal as statistical analysis data, and respectively storing the operation analysis value into corresponding data partitions; before the controller is determined to be in a power-down state, copying data to be subjected to statistical analysis and stored in the data partition and the statistical analysis data to a preset backup partition respectively for backup processing; and when the controller is determined to be in a power-on state, restoring the statistical analysis data pre-stored in the backup partition to the corresponding data partition so as to ensure the smooth execution of the statistical processing process.
The storage medium carries out partition statistical analysis on the running signals generated by the engine of the vehicle in different running working conditions based on the target analysis model, avoids the problem of large workload of calibration of the electronic control data in a diagnosis part in the prior art, and can improve the analysis efficiency of the electronic control data. And the real-time operation analysis value calculated by the target analysis model is used as a standard value by combining the data processing experience of the target analysis model in the historical processing time period, and the engine fault diagnosis is carried out on the basis of the deviation between the operation actual value of the operation signal and the standard value, so that the accuracy of the fault diagnosis result can be guaranteed, and the engine fault detection efficiency can be improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An engine fault diagnosis method, characterized by comprising:
acquiring running signals generated by an engine of a vehicle in different running working conditions; the operation condition is determined according to the rotating speed and the torque of the engine, and the operation signal represents the real-time operation state of the engine;
determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value;
acquiring an operation actual value of the operation signal, and determining a deviation between the operation actual value and the real-time operation analysis value;
and diagnosing the engine fault according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
2. The method of claim 1, wherein the operating signals are collected via sensors provided on a controller, and wherein determining the input signals for the target analytical model based on the operating signals comprises:
when the operating signal is determined to be transmitted through a CAN bus connected with the sensor, the operating signal is directly used as an input signal of a target analysis model;
otherwise, when the operation signal is determined to be an analog quantity signal, performing high-frequency filtering processing on the operation signal to obtain a corresponding high-frequency filtering signal;
carrying out effectiveness analysis on the high-frequency filtering signal to obtain a corresponding analysis result;
and when the analysis result represents that the high-frequency filtering signal is an effective signal, performing low-pass filtering processing on the high-frequency filtering signal, and taking the processed low-pass filtering signal as an input signal of a target analysis model.
3. The method of claim 1, wherein said statistically processing the current input signal in the established target data partition by the target analysis model to obtain the corresponding real-time operation analysis value comprises:
searching a target data partition in each established data partition when the current input signal is determined by the target analysis model, the operation condition corresponding to the current input signal meets the preset partition establishment condition; the partition establishing conditions comprise that the output of the running signal is normal, the deviation value of the engine torque in a preset time meets a preset first deviation condition, the deviation value of the engine rotating speed in a preset time meets a preset second deviation condition, and the engine rotating speed and the engine torque are included in a preset point selection range;
when the searching is determined to be successful, processing the current input signal in the searched target data partition through the target analysis model to obtain a corresponding real-time operation analysis value;
and when the search is determined to be failed, establishing a target data partition according to the engine rotating speed, the engine torque and the operation signal, and processing the current input signal in the currently established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value.
4. The method of claim 3, wherein the processing of the current input signal by the target analysis model in the searched target data partition to obtain the corresponding real-time operation analysis value comprises:
taking the running signal as an input signal of a target analysis model, and processing the current input signal in the searched target data partition through the target analysis model according to the following formula to obtain a corresponding weighted processing signal:
wherein Num is a weighting parameter, In is the operating signal, and Out is a weighted processing signal obtained by processing;
when the weighted processing signal is determined to be used as the input signal of the target analysis model for statistical processing in a historical processing time period, taking a target historical operation analysis value obtained by historical processing as a real-time operation analysis value;
and when the weighted processing signal is determined not to be taken as the input signal of the target analysis model for statistical processing in the historical processing time period, calculating the real-time operation analysis value according to the value trend among the historical operation analysis values obtained by the processing of the target analysis model.
5. The method of claim 1, wherein said determining a deviation between said operational actual value and said real-time operational analysis value comprises:
determining a deviation between the operational actual value and the operational analytical value according to the following formula:
wherein In _ model is the real-time operation analysis value, In _ sensor is the operation actual value, and Ratio is a deviation between the operation actual value and the real-time operation analysis value.
6. The method of claim 1, wherein said performing an engine fault diagnosis based on a deviation between said actual operating value and said real-time operating analysis value to obtain a corresponding fault diagnosis result comprises:
when the absolute value of the deviation is smaller than or equal to a preset normal judgment threshold value, outputting a first diagnosis result representing that the engine operates normally;
when the absolute value of the deviation is larger than the preset normal judgment threshold and is smaller than or equal to the preset risk judgment threshold, outputting a second diagnosis result representing that the engine has an operation fault risk;
when the absolute value of the deviation is larger than the preset risk judgment threshold and is smaller than or equal to the preset fault judgment threshold, outputting a third diagnosis result representing that the engine is in an operation fault state;
and outputting a fourth diagnosis result representing that the engine is in a serious operation fault state when the absolute value of the deviation is greater than the preset fault discrimination threshold.
7. The method according to any one of claims 1 to 6, further comprising:
taking the operation signals as data to be subjected to statistical analysis, taking operation analysis values determined according to the operation signals as statistical analysis data, and respectively storing the operation analysis values into corresponding data partitions;
before the controller is determined to be in a power-down state, copying data to be subjected to statistical analysis and stored in the data partition and the statistical analysis data to a preset backup partition respectively for backup processing;
and when the controller is determined to be in a power-on state, restoring the statistical analysis data pre-stored in the backup partition to the corresponding data partition so as to ensure the smooth execution of the statistical processing process.
8. An engine fault diagnosis apparatus comprising an acquisition module, a first processing module, a second processing module, and an output module, wherein:
the acquisition module is used for acquiring running signals generated by an engine of a vehicle in different running working conditions; the operation condition is determined according to the rotating speed and the torque of the engine, and the operation signal represents the real-time operation state of the engine;
the first processing module is used for determining an input signal of a target analysis model based on the operation signal, and performing statistical processing on the current input signal in the established target data partition through the target analysis model to obtain a corresponding real-time operation analysis value;
the second processing module is used for acquiring an operation actual value of the operation signal and determining a deviation between the operation actual value and the real-time operation analysis value;
and the output module is used for carrying out engine fault diagnosis according to the deviation between the actual operation value and the real-time operation analysis value to obtain a corresponding fault diagnosis result.
9. A controller comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110997645.7A CN113586239B (en) | 2021-08-27 | 2021-08-27 | Engine fault diagnosis method, engine fault diagnosis device, controller and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110997645.7A CN113586239B (en) | 2021-08-27 | 2021-08-27 | Engine fault diagnosis method, engine fault diagnosis device, controller and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113586239A true CN113586239A (en) | 2021-11-02 |
| CN113586239B CN113586239B (en) | 2022-09-16 |
Family
ID=78239935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110997645.7A Active CN113586239B (en) | 2021-08-27 | 2021-08-27 | Engine fault diagnosis method, engine fault diagnosis device, controller and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113586239B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114104224A (en) * | 2021-11-15 | 2022-03-01 | 中国船舶重工集团公司第七一一研究所 | Device management method, device, electronic device and computer-readable storage medium |
| CN114861323A (en) * | 2022-05-31 | 2022-08-05 | 东风汽车集团股份有限公司 | Vehicle running deviation analysis method, device and equipment and readable storage medium |
| CN114995346A (en) * | 2022-06-13 | 2022-09-02 | 中国第一汽车股份有限公司 | Engine electrical diagnosis calibration method, device, equipment and medium |
| CN115111078A (en) * | 2022-07-22 | 2022-09-27 | 浙江吉利控股集团有限公司 | Engine torque monitoring method, equipment and storage medium |
| CN116360390A (en) * | 2023-03-09 | 2023-06-30 | 深圳市拓普泰克技术股份有限公司 | Central control system for hybrid electric vehicle diagnosis |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105264211A (en) * | 2013-06-11 | 2016-01-20 | 日产自动车株式会社 | Internal combustion engine control device, and control method |
| CN105814294A (en) * | 2014-03-19 | 2016-07-27 | 马自达汽车株式会社 | Failure detection device for engine with turbocharger |
| CN111120097A (en) * | 2019-12-30 | 2020-05-08 | 中国船舶重工集团公司第七一一研究所 | Indicator diagram-based online early warning method, system and medium for diesel under all working conditions |
| US20200182180A1 (en) * | 2017-08-30 | 2020-06-11 | Denso Corporation | Internal combustion engine control system |
| CN111795824A (en) * | 2019-04-09 | 2020-10-20 | 中国航发商用航空发动机有限责任公司 | Fault diagnosis method and system for mechanical power system |
| CN111927640A (en) * | 2020-08-19 | 2020-11-13 | 潍柴动力股份有限公司 | Engine fault detection method, device, equipment and computer readable storage medium |
| CN112666925A (en) * | 2020-12-21 | 2021-04-16 | 中国北方发动机研究所(天津) | Diesel engine vehicle-mounted diagnosis system and diagnosis method thereof |
-
2021
- 2021-08-27 CN CN202110997645.7A patent/CN113586239B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105264211A (en) * | 2013-06-11 | 2016-01-20 | 日产自动车株式会社 | Internal combustion engine control device, and control method |
| CN105814294A (en) * | 2014-03-19 | 2016-07-27 | 马自达汽车株式会社 | Failure detection device for engine with turbocharger |
| US20200182180A1 (en) * | 2017-08-30 | 2020-06-11 | Denso Corporation | Internal combustion engine control system |
| CN111795824A (en) * | 2019-04-09 | 2020-10-20 | 中国航发商用航空发动机有限责任公司 | Fault diagnosis method and system for mechanical power system |
| CN111120097A (en) * | 2019-12-30 | 2020-05-08 | 中国船舶重工集团公司第七一一研究所 | Indicator diagram-based online early warning method, system and medium for diesel under all working conditions |
| CN111927640A (en) * | 2020-08-19 | 2020-11-13 | 潍柴动力股份有限公司 | Engine fault detection method, device, equipment and computer readable storage medium |
| CN112666925A (en) * | 2020-12-21 | 2021-04-16 | 中国北方发动机研究所(天津) | Diesel engine vehicle-mounted diagnosis system and diagnosis method thereof |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114104224A (en) * | 2021-11-15 | 2022-03-01 | 中国船舶重工集团公司第七一一研究所 | Device management method, device, electronic device and computer-readable storage medium |
| CN114861323A (en) * | 2022-05-31 | 2022-08-05 | 东风汽车集团股份有限公司 | Vehicle running deviation analysis method, device and equipment and readable storage medium |
| CN114995346A (en) * | 2022-06-13 | 2022-09-02 | 中国第一汽车股份有限公司 | Engine electrical diagnosis calibration method, device, equipment and medium |
| CN115111078A (en) * | 2022-07-22 | 2022-09-27 | 浙江吉利控股集团有限公司 | Engine torque monitoring method, equipment and storage medium |
| CN115111078B (en) * | 2022-07-22 | 2024-03-19 | 浙江吉利控股集团有限公司 | Engine torque monitoring method, equipment and storage medium |
| CN116360390A (en) * | 2023-03-09 | 2023-06-30 | 深圳市拓普泰克技术股份有限公司 | Central control system for hybrid electric vehicle diagnosis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113586239B (en) | 2022-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113586239B (en) | Engine fault diagnosis method, engine fault diagnosis device, controller and storage medium | |
| CN109163913A (en) | A kind of Diagnosis method of automobile faults and relevant device | |
| CN112255552B (en) | Fault diagnosis method and device for temperature acquisition device of fuel cell and vehicle | |
| CN104471238B (en) | For starting the diagnosis of motor | |
| CN111103072A (en) | Urea tank fault diagnosis method and device, vehicle and storage medium | |
| CN108536122B (en) | Hybrid electric vehicle diagnostic system and method | |
| CN111140391A (en) | Air intake sensor fault processing method, device and system, vehicle and medium | |
| CN111982522A (en) | Engine performance monitoring method, device and system and storage medium | |
| US20110153035A1 (en) | Sensor Failure Detection System And Method | |
| CN118228373A (en) | New energy automobile power consumption analysis method and device, electronic equipment and storage medium | |
| CN110410222B (en) | Method and equipment for judging throttle opening fault | |
| CN115079663A (en) | Vehicle power system monitoring method and device based on digital twin technology | |
| CN113187592A (en) | Secondary air system monitoring method, device, equipment and storage medium | |
| US11100732B2 (en) | Enhanced system failure diagnosis | |
| CN108803581B (en) | Fault remote diagnosis method based on expert template | |
| CN114083987B (en) | Correction method and device for battery monitoring parameters and computer equipment | |
| CN113312758B (en) | Health state evaluation method and device for wind generating set | |
| CN114523918A (en) | Vehicle speed signal detection method and device, mobile terminal and storage medium | |
| CN114837776A (en) | SCR system control method, electronic device, and storage medium | |
| CN114088408A (en) | Cooling liquid temperature diagnosis method and device, vehicle and storage medium | |
| DE102005007324B4 (en) | Monitoring engine coolant temperature sensors | |
| JP5126538B2 (en) | Vehicle control device | |
| CN112360639B (en) | Fault monitoring method and device for throttle valve actuator | |
| CN116088485B (en) | Vehicle fault data acquisition system and method and vehicle | |
| CN114252195B (en) | Rail pressure credibility detection method, device, storage medium and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |