CN115169385A - Method and system for fitting target sensor for vehicle, and storage medium - Google Patents
Method and system for fitting target sensor for vehicle, and storage medium Download PDFInfo
- Publication number
- CN115169385A CN115169385A CN202210679611.8A CN202210679611A CN115169385A CN 115169385 A CN115169385 A CN 115169385A CN 202210679611 A CN202210679611 A CN 202210679611A CN 115169385 A CN115169385 A CN 115169385A
- Authority
- CN
- China
- Prior art keywords
- signal
- target
- fitting
- sensing signal
- sensing
- 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.)
- Pending
Links
Images
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present application relates to a method and system, storage medium, of fitting an object sensor for a vehicle for generating an object sensing signal, the method comprising: determining a characteristic of the target sense signal generated by the target sensor with respect to vehicle fault diagnosis; receiving a plurality of sensing signals from the in-vehicle sensor; screening out similar sensing signals from the plurality of sensing signals according to the similarity degree with the target sensing signal; fitting the similar sensing signals based on a fitting algorithm to generate a fitted signal for fitting the target sensing signal; verifying the application performance of the fitted signal according to the characteristic of the fitted signal about the vehicle fault diagnosis; and determining whether to adjust the fitting algorithm and/or the screening rule of the similar sensing signals according to the application performance.
Description
Technical Field
The present application relates to the field of vehicle sensors, and more particularly, to a method and system for fitting a target sensor for a vehicle, and a storage medium.
Background
In the development stage of a new vehicle, it may be necessary to add a sensor (referred to herein as a target sensor) to collect specific information and send the collected information in the form of a signal (referred to herein as a target sensing signal) to a processing system of the vehicle for fault diagnosis and the like. However, the addition of sensors means additional cost in mass production of vehicle models, and more signals also occupy valuable processing resources of the vehicle. On the other hand, there may be some known or potential correlation or redundancy in the information collected between sensors, so that the target sensing signal of some sensors may be fitted with the signals of other sensors.
In view of the above, the present application provides a method of fitting a target sensor for a vehicle.
Disclosure of Invention
Embodiments of the present application provide a method and system for fitting a target sensor for a vehicle, and a storage medium, for implementing efficient fitting of a target sensor.
According to an aspect of the present application, a method of fitting an object sensor for a vehicle for generating an object sensing signal is provided. The method comprises the following steps: determining a characteristic of the target sense signal generated by the target sensor with respect to vehicle fault diagnosis; receiving a plurality of sensing signals from the in-vehicle sensor; screening out similar sensing signals from the plurality of sensing signals according to the similarity degree with the target sensing signal; fitting the similar sensing signals based on a fitting algorithm to generate a fitted signal for fitting the target sensing signal; verifying the application performance of the fitted signal according to the characteristic of the fitted signal about the vehicle fault diagnosis; and determining whether to adjust the fitting algorithm and/or the screening rule of the similar sensing signals according to the application performance.
In some embodiments of the present application, optionally, determining a characteristic of the target sense signal generated by the target sensor with respect to vehicle fault diagnosis comprises: acquiring a first sensing signal in a fault state and a second sensing signal in a non-fault state through the target sensor; extracting time domain and/or frequency domain features of the first sensing signal and the second sensing signal; and determining the time domain and/or frequency domain characteristics of the target sensing signal with respect to the vehicle fault diagnosis according to the difference of the time domain and/or frequency domain characteristics of the first sensing signal and the second sensing signal.
In some embodiments of the application, optionally, the target sensing signal has the same sampling frequency as a first signal of the plurality of sensing signals, and whether the first signal is the similar sensing signal is determined according to a similarity degree of the first signal and the target sensing signal, wherein the similarity degree is determined by at least one of the following items: data correlation, time sequence shape similarity, frequency component similarity and time sequence data fitting goodness.
In some embodiments of the application, optionally, the target sensing signal is different from a sampling frequency of a second signal set of the plurality of sensing signals, and determining whether each of the second signal sets is the similar sensing signal according to a similarity degree of the target sensing signal to the second signal set comprises: determining candidate signals from each of the second signal sets according to a temporal shape similarity of the target sense signal to the same; aligning each of the candidate signals with the target sense signal using an interpolation algorithm; and determining whether the aligned candidate signal is the similar sensing signal according to a similarity degree with the target sensing signal, wherein the similarity degree is determined by at least one of the following items: data correlation, time sequence shape similarity, frequency component similarity, time sequence data goodness of fit.
In some embodiments of the present application, optionally, a fitting model is constructed by replacing convolutional layers of a depth residual network with regression depth residual networks of fully connected layers, wherein the fitting model is used to implement the fitting algorithm; constructing a Base Model based on a Stacking strategy to construct a fitting Model for realizing the fitting algorithm; and/or performing regression analysis by empirical mode decomposition to construct a fitting model for implementing the fitting algorithm.
In some embodiments of the present application, optionally, verifying the application performance thereof according to the characteristics of the fitted signal with respect to the vehicle fault diagnosis includes: extracting the characteristics of the fitting signals relative to the vehicle fault diagnosis to carry out fault diagnosis on the vehicle with known fault; and determining the application performance according to the fault diagnosis result, wherein the application performance comprises found faults and not found faults.
In some embodiments of the application, optionally, the fitting algorithm and the screening rules of the similar sensing signals are solidified for fitting the target sensing signal in case the application appears to find a fault; and adjusting the fitting algorithm and/or the filtering rules of the similar sensed signals if the application appears to find no fault.
According to another aspect of the present application, a system is provided for fitting an object sensor for a vehicle for generating an object sensing signal. The system comprises: an extraction unit configured to determine a characteristic of the target sensing signal generated by the target sensor with respect to vehicle fault diagnosis; a receiving unit configured to receive a plurality of sensing signals from the in-vehicle sensor; and a fitting unit configured to: screening out similar sensing signals from the plurality of sensing signals according to the similarity degree with the target sensing signal; fitting the similar sensing signals based on a fitting algorithm to generate a fitted signal for fitting the target sensing signal; a verification unit configured to verify an application performance thereof based on a characteristic of the fitted signal with respect to the vehicle failure diagnosis; and an adjusting unit configured to determine whether to adjust the fitting algorithm and/or the filtering rule of the similar sensing signals according to the application performance.
In some embodiments of the present application, optionally, the extraction unit is configured to: acquiring a first sensing signal in a fault state and a second sensing signal in a non-fault state through the target sensor; extracting time domain and/or frequency domain features of the first sensing signal and the second sensing signal; and determining the time domain and/or frequency domain characteristics of the target sensing signal related to vehicle fault diagnosis according to the difference of the time domain and/or frequency domain characteristics of the first sensing signal and the second sensing signal.
In some embodiments of the application, optionally, the target sensing signal and a first signal of the plurality of sensing signals have the same sampling frequency, and the fitting unit is configured to determine whether the first signal is the similar sensing signal according to a similarity degree of the first signal and the target sensing signal, wherein the similarity degree is determined by at least one of the following items: data correlation, time sequence shape similarity, frequency component similarity and time sequence data fitting goodness.
In some embodiments of the application, optionally, the target sensing signal is different in sampling frequency from a second set of signals of the plurality of sensing signals, and the fitting unit is configured to determine whether each of the second set of signals is the similar sensing signal according to its degree of similarity to the target sensing signal: determining candidate signals from each of the second signal sets according to a temporal shape similarity of the target sense signal to the same; aligning each of the candidate signals with the target sense signal using an interpolation algorithm; and determining whether the aligned candidate signal is the similar sensing signal according to a similarity degree with the target sensing signal, wherein the similarity degree is determined by at least one of the following items: data correlation, time sequence shape similarity, frequency component similarity, time sequence data goodness of fit.
In some embodiments of the application, optionally, the verification unit is configured to extract features of the fitted signal with respect to the vehicle fault diagnosis to perform fault diagnosis on a vehicle known to have a fault; and determining the application performance according to the fault diagnosis result, wherein the application performance comprises found faults and not found faults.
In some embodiments of the application, optionally, the adjusting unit is configured to cure the fitting algorithm and the screening rule of the similar sensing signals for fitting the target sensing signal if the application appears to find a fault; and adjusting the fitting algorithm and/or the screening rules of the similar sensing signals if the application appears that no fault is found.
According to another aspect of the present application, there is provided a computer-readable storage medium having instructions stored therein, which when executed by a processor, cause the processor to perform any one of the methods as described above.
According to the method and the system for fitting the target sensor for the vehicle and the storage medium, accurate fitting of the target sensor can be achieved under the condition that the target sensor is not added, a fitted signal can be used for fault detection and the like, and therefore development cost of the vehicle can be reduced.
Drawings
The above and other objects and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings, in which like or similar elements are designated by like reference numerals.
FIG. 1 illustrates a method of fitting an object sensor for a vehicle according to one embodiment of the present application;
FIG. 2 illustrates a system for fitting an object sensor for a vehicle according to one embodiment of the present application.
Detailed Description
For the purposes of brevity and explanation, the principles of the present application are described herein with reference primarily to exemplary embodiments thereof. However, those skilled in the art will readily recognize that the same principles are equally applicable to all types of methods and systems for fitting a target sensor for a vehicle, storage medium, and that these same or similar principles may be implemented therein, with any such variations not departing from the true spirit and scope of the present application.
One aspect of the present application provides a method of fitting an object sensor for a vehicle, wherein the object sensor is used to generate an object sensing signal. As shown in fig. 1, a method 10 of fitting an object sensor for a vehicle (hereinafter referred to as method 10) includes the steps of: determining a characteristic of the target sensing signal generated by the target sensor with respect to the vehicle malfunction diagnosis in step S102; receiving a plurality of sensing signals from in-vehicle sensors in step S104; screening out a similar sensing signal from the plurality of sensing signals according to a degree of similarity to the target sensing signal in step S106; fitting the similar sensing signals based on a fitting algorithm to generate a fitting signal for fitting the target sensing signal in step S108; verifying the application performance of the fitted signal according to the characteristics of the fitted signal with respect to the vehicle fault diagnosis in step S110; it is determined in step S112 whether to adjust the fitting algorithm and/or the filtering rule of the similar sensing signals according to the applied performance. A fit to the target sense signal that would have been produced by the target sensor can be achieved via the above steps of method 10.
The method 10 determines a feature of the target sensing signal generated by the target sensor with respect to the vehicle failure diagnosis (abbreviated as "extract failure feature" in the drawing) in step S102. Specifically, the following process may be included: acquiring a first sensing signal in a fault state and a second sensing signal in a non-fault state through a target sensor; extracting time domain and/or frequency domain characteristics of the first sensing signal and the second sensing signal; and determining the time domain and/or frequency domain characteristics of the target sensing signal relative to the vehicle fault diagnosis according to the difference of the time domain and/or frequency domain characteristics of the first sensing signal and the second sensing signal.
In some examples, data characteristics for fault diagnosis and localization in a target sensor signal (e.g., a signal generated by a target sensor fitted as a sample in an actual vehicle) may be determined in step S102. Taking the motor mounted vibration sensor (target sensor) as an example for fault diagnosis, fault diagnosis and positioning can be realized through the following steps: (a) The high-frequency vibration signals of a normal part and a fault part are collected, and the frequency response range of the vibration signals needs to be determined by combining component mechanism analysis. (b) Extracting signal features, and for vibration signals, common feature indexes of time domains are as follows: waveform index, pulse index, kurtosis index, margin index, peak-to-peak value and the like; the frequency domain indexes comprise center of gravity frequency, mean square frequency, root mean square frequency, frequency variance, frequency standard deviation and the like. Time domain features are generally used to reflect equipment status, for fault monitoring, trend forecasting; while frequency domain features are typically used to diagnose fault type, cause and location. (c) And (4) judging the abnormity, namely comparing the normal part with the fault part according to the extracted signal characteristics to determine distinguishing characteristics and a deviation threshold value. (d) And (4) fault diagnosis, namely determining time domain expression and frequency domain expression under different fault modes by combining the inherent frequency information of the equipment determined by mechanism analysis.
The above steps may be used to extract a target sensing signal that can be used to determine a particular fault, and the target sensing signal generated by the target sensor may be used to determine whether such a fault exists. The data characteristics used for abnormality judgment and fault diagnosis according to the target sensor signals can be used as reference to guide the extraction idea of the key signals. Furthermore, after fitting the target sensor signal with the received sensing signal, the validity of the fitted signal (fault found, no fault found) can be determined according to the above steps (b), (c) and (d).
The method 10 receives a plurality of sensing signals from in-vehicle sensors (abbreviated as "receiving sensing signals" in the figure) in step S104. The in-vehicle sensors referred to herein are sensors that are present in the vehicle or are essential in developing the vehicle in accordance with conventional experience (e.g., motor speed sensors, rain sensors, etc.), and redundancy between signals generated by these sensors may not be significant.
Although existing sensors may not be able to directly generate the desired target sensing signal, the sensing signals generated by these existing sensors can be used to fit the desired target sensing signal since there may be correlation (or redundancy in the generated signal information) in the information collected by the sensors. In some examples, some existing sensors may produce more than one sensing signal, and in other examples, some existing sensors may produce only a corresponding one sensing signal. The sensing signals can be arranged into a signal matrix, and of course, the received sensing signals can be packaged and encapsulated in other forms.
The method 10 selects a similar sensing signal from the plurality of sensing signals according to the similarity degree with the target sensing signal in step S106 (abbreviated as "selecting a similar sensing signal" in the figure). The sensing signals received in step S104 may not all be suitable for fitting the target sensing signal, and for this reason these sensing signals need to be screened. In particular, which sensing signals remain may be evaluated according to a similarity of the received sensing signal and the target sensing signal with respect to time domain features and/or frequency domain features (e.g., data correlation between the two, timing shape similarity, frequency component similarity, timing data goodness-of-fit, or a combination thereof). For example, if the target sensing signal is related to a vehicle vibration condition, the received light intensity sensing signal may be mathematically similar to the target sensing signal to a low degree and thus is not suitable for fitting the target sensing signal. Furthermore, since the sampling frequencies of the received sensing signal and the target sensing signal may be the same or different, in some examples, the similarity degree between the sensing signal and the target sensing signal needs to be determined according to the sampling frequency of the sensing signal.
In some embodiments of the present application, in a case where the target sensing signal and a certain signal (e.g., a first signal) of the plurality of sensing signals have the same sampling frequency, it may be determined whether the first signal is a similar sensing signal according to a degree of similarity of the first signal and the target sensing signal. The similarity between the two can be determined by comprehensively considering the following centralized mathematical measures: data correlation, time sequence shape similarity, frequency component similarity and time sequence data goodness of fit of the first signal and the target sensing signal.
For data correlation evaluation, the data correlation between The first signal and The target sensing signal may be determined according to The spearman algorithm, the MIC (The maximum Information Coefficient) algorithm. For the evaluation of the similarity of the time sequence shapes, the similarity can be determined by combining an EMD (Empirical Mode composition) algorithm with a DTW (dynamic time warping) algorithm. The similarity of frequency components between the two can be evaluated by combining the EMD algorithm with the Spectral Coherence algorithm. In addition, the goodness-of-fit evaluation of the time series data between the two can be mainly determined by a machine learning algorithm, or the machine learning algorithm is combined with a stepwise regression method. As will be understood by those skilled in the art after reading this application, the above specific algorithm can be implemented by referring to the prior art in this field, and will not be described herein in detail.
In some embodiments of the present application, in a case where the target sensing signal and some of the plurality of sensing signals (e.g., the second signal set) have different sampling frequencies, it may be determined whether each of the second signal set is a similar sensing signal according to a degree of similarity of the target sensing signal and the second signal set. Specifically, whether or not it is a similar sensing signal can be determined by: first, candidate signals are determined from each of the second signal sets according to their timing shape similarities to the target sense signal. This step primarily screens out significantly uncorrelated signals using the fact that the timing shape similarity is insensitive to the sampling frequency of the signal. Second, an interpolation algorithm is employed to align each of the candidate signals with the target sense signal. Finally, it may be determined whether the aligned candidate signal is a similar sensing signal according to a degree of similarity with the target sensing signal, wherein the degree of similarity is determined by at least one of the following items: data correlation, time sequence shape similarity, frequency component similarity, time sequence data goodness of fit.
The method 10 fits the similar sensing signals based on a fitting algorithm to generate a fitted signal for fitting the target sensing signal in step S108 (abbreviated as "generating fitted signal based on fitting algorithm" in the figure). The fitting algorithm is also referred to herein as a fitting model or an algorithmic model. In some embodiments of the present application, the fitting algorithm is constructed by: (1) The fitting algorithm is implemented by replacing the convolutional layers of the depth residual network (ResNet) with a regression depth residual network of fully connected layers (ResNet for regression), wherein the regression depth residual network may comprise ten or more network levels. (2) Based on a Stacking strategy, selecting a plurality of linear regression algorithms and nonlinear regression algorithms, obtaining the predicted values of the Base Model and the Base Model after tuning, and carrying out the next training by adopting two modes: (1) directly inputting the predicted value into a Meta Model for training; (2) predicted values and actual data are input into a Meta Model for training. From the predicted effect, a multi-tier Base Model can be constructed. (3) Linear regression analysis was performed by Empirical Mode Decomposition (EMD) in combination with methods (1) and (2). Specifically, the corresponding algorithm model may be selected based on a MSE (Mean squared error) and fault diagnosis effect comparison. The working principles of the regression depth residual error network, the Stacking strategy and the empirical mode decomposition are not repeated in this document, and those skilled in the art can implement the relevant processes according to the existing algorithm after reading the present application.
Further, the method 10 verifies the application behavior of the fitting signal (abbreviated as "verifying the behavior of the fitting signal" in the drawing) in step S110; and adjusting the fitting algorithm and/or the filtering rule of the similar sensing signals according to the application performance in step S112 (abbreviated as "adjusting the fitting algorithm and the filtering rule" in the figure). The fitted signal needs to be further tested in practice, so as to adjust the fitting algorithm (for example, adjust partial parameters of the model) and the screening rule of the similar sensing signals (for example, add partial sensor signals) according to the practical result.
In some embodiments of the present application, verifying the applied representation of the fitted signal comprises: extracting the characteristics of the fitting signal with respect to the vehicle fault diagnosis, and performing fault diagnosis on the vehicle known to have a fault (the extraction process may be performed with reference to the extraction processes of (b), (c), and (d) in step S102); and determining application performance according to the fault diagnosis result, wherein the application performance comprises found faults and not found faults. In some embodiments, a fitting algorithm and screening rules of similar sensing signals are cured in the event that the application appears to find a fault for fitting the target sensing signal. Furthermore, in case the application shows that no fault is found, the fitting algorithm and/or the screening rules of similar sensing signals may then be adjusted in order to optimize the resulting fitted signal in the next cycle.
Another aspect of the present application provides a system for fitting an object sensor for a vehicle, the object sensor for generating an object sense signal. As shown in fig. 2, the system 20 for fitting an object sensor for a vehicle (hereinafter, referred to as the system 20) includes an extraction unit 202, a reception unit 204, a fitting unit 206, a verification unit 208, and an adjustment unit 210. The particular principles of operation of the various units in system 20 may be in accordance with the corresponding steps described above with respect to method 10, and the various units may implement the fitting to the target sensor in accordance with the particular procedures described above. The above contents are incorporated herein by reference for the sake of brevity and are not described in detail herein.
The extraction unit 202 of the system 20 may determine characteristics of the target sense signal generated by the target sensor with respect to vehicle fault diagnostics. Specifically, the extraction unit 202 may collect, by the target sensor, a first sensing signal in a fault state and a second sensing signal in a non-fault state; extracting time domain and/or frequency domain features of the first sensing signal and the second sensing signal; and determining the time domain and/or frequency domain characteristics of the target sensing signal related to vehicle fault diagnosis according to the difference of the time domain and/or frequency domain characteristics of the first sensing signal and the second sensing signal.
The receiving unit 204 of the system 20 may receive the plurality of sensing signals from the in-vehicle sensor, and the fitting unit 206 may screen out similar sensing signals from the plurality of sensing signals according to the degree of similarity with the target sensing signal, and fit the similar sensing signals based on a fitting algorithm to generate a fitted signal for fitting the target sensing signal.
In addition, as shown in fig. 2, the system 20 further includes a verification unit 208 and an adjustment unit 210. Wherein the verification unit 208 may verify the application behavior of the fitted signal. The adjusting unit 210 may adjust the fitting algorithm and/or the filtering rules of the similar sensing signals according to the applied performance.
In some embodiments of the present application, in a case that the sampling frequency of the target sensing signal is the same as that of a first signal in the plurality of sensing signals, the fitting unit 206 may determine whether the first signal is a similar sensing signal according to a similarity degree of the first signal and the target sensing signal, wherein the similarity degree is determined by at least one of the following items: data correlation, time sequence shape similarity, frequency component similarity and time sequence data fitting goodness.
In some embodiments of the present application, in case that the sampling frequency of the target sensing signal is different from that of the second signal set of the plurality of sensing signals, the fitting unit 206 may determine whether each of the second signal sets is a similar sensing signal according to the similarity degree of the target sensing signal to it: determining candidate signals from each of the second signal sets according to a temporal shape similarity of the target sensing signal to the second signal set; aligning each of the candidate signals with the target sense signal using an interpolation algorithm; and determining whether the aligned candidate signal is a similar sensing signal according to a similarity degree with the target sensing signal, wherein the similarity degree is determined by at least one of the following items: data correlation, time sequence shape similarity, frequency component similarity, time sequence data goodness of fit.
In some embodiments of the present application, the verification unit 208 may verify the fitted signal according to the characteristics of the fitted signal with respect to the vehicle fault diagnosis, perform fault diagnosis on the vehicle known to have a fault, and determine an application performance according to the fault diagnosis result, where the application performance includes that a fault is found and no fault is found.
In some embodiments of the present application, the adjusting unit 210 may solidify the fitting algorithm and the screening rule of the similar sensing signals in case of applying the condition that the fault is found for fitting the target sensing signal, and adjust the fitting algorithm and/or the screening rule of the similar sensing signals in case of applying the condition that the fault is not found.
According to another aspect of the present application, there is provided a computer readable storage medium having stored therein instructions that, when executed by a processor, cause the processor to perform any one of the methods of fitting an object sensor for a vehicle as described above. Computer-readable media, as referred to in this application, includes all types of computer storage media, which can be any available media that can be accessed by a general purpose or special purpose computer. By way of example, computer-readable media may include RAM, ROM, EPROM, E 2 PROMs, registers, hard disks, removable disks, CD-ROMs or other optical disk storage, magnetic disk storage or other magnetic storage devices, or can be used to carry or storeAny other transitory or non-transitory medium that stores desired program code means in the form of instructions or data structures and that can be accessed by a general purpose or special purpose computer, or a general purpose or special purpose processor. A disk, as used herein, typically reproduces data magnetically, whereas a disc reproduces data optically with a laser. Combinations of the above should also be included within the scope of computer-readable media. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.
The above are merely specific embodiments of the present application, but the scope of the present application is not limited thereto. Other possible variations or substitutions may occur to those skilled in the art based on the teachings herein, and are intended to be covered by the present disclosure. In the present invention, the embodiments and features of the embodiments may be combined with each other without conflict. The scope of protection of the present application is subject to the description of the claims.
Claims (14)
1. A method of fitting an object sensor for a vehicle, the object sensor for generating an object sense signal, the method comprising:
determining a characteristic of the target sense signal generated by the target sensor with respect to vehicle fault diagnosis;
receiving a plurality of sensing signals from the in-vehicle sensor;
screening out similar sensing signals from the plurality of sensing signals according to the similarity degree with the target sensing signal;
fitting the similar sensing signals based on a fitting algorithm to generate a fitted signal for fitting the target sensing signal;
verifying the application performance of the fitted signal according to the characteristic of the fitted signal about the vehicle fault diagnosis; and
determining whether to adjust the fitting algorithm and/or the screening rules of the similar sensing signals according to the application performance.
2. The method of claim 1, wherein determining a characteristic of the target sense signal generated by the target sensor with respect to vehicle fault diagnosis comprises:
acquiring a first sensing signal in a fault state and a second sensing signal in a non-fault state through the target sensor;
extracting time domain and/or frequency domain features of the first sensing signal and the second sensing signal; and
and determining the time domain and/or frequency domain characteristics of the target sensing signal related to vehicle fault diagnosis according to the difference of the time domain and/or frequency domain characteristics of the first sensing signal and the second sensing signal.
3. The method of claim 1 or 2, wherein the target sensing signal is the same as a sampling frequency of a first signal of the plurality of sensing signals, and determining whether the first signal is the similar sensing signal according to a degree of similarity of the first signal to the target sensing signal, wherein the degree of similarity is determined by at least one of: data correlation, time sequence shape similarity, frequency component similarity, time sequence data goodness of fit.
4. The method of claim 1 or 2, wherein the target sense signal is different in sampling frequency from a second set of signals of the plurality of sense signals, and determining whether each of the second set of signals is the similar sense signal according to its degree of similarity to the target sense signal comprises:
determining candidate signals from each of the second signal sets according to a temporal shape similarity of the target sense signal to the same;
aligning each of the candidate signals with the target sensing signal using an interpolation algorithm; and
determining whether the aligned candidate signal is the similar sensing signal according to a similarity degree with the target sensing signal, wherein the similarity degree is determined by at least one of the following items: data correlation, time sequence shape similarity, frequency component similarity, time sequence data goodness of fit.
5. The method according to claim 1 or 2, wherein the fitting algorithm is constructed according to the following:
constructing a fitting model by replacing the convolutional layer of the depth residual error network with the regression depth residual error network of the fully-connected layer, wherein the fitting model is used for realizing the fitting algorithm;
constructing a Base Model based on a packing strategy to construct a fitting Model for realizing the fitting algorithm; and/or
Regression analysis is performed by empirical mode decomposition to construct a fitting model for implementing the fitting algorithm.
6. The method according to claim 1 or 2, wherein verifying its application performance from the fitted signal with respect to the characteristics of vehicle fault diagnosis comprises:
extracting the characteristic of the fitted signal about the vehicle fault diagnosis to carry out fault diagnosis on the vehicle with known fault; and
and determining the application performance according to the fault diagnosis result, wherein the application performance comprises found faults and not found faults.
7. The method of claim 6, wherein the fitting algorithm and the screening rules of the similar sensing signals are cured for fitting the target sensing signal if the application appears to find a fault; and
adjusting the fitting algorithm and/or the screening rules of the similar sensing signals in case the application appears to find no fault.
8. A system for fitting an object sensor for a vehicle, the object sensor for generating an object sense signal, the system comprising:
an extraction unit configured to determine a characteristic of the target sensing signal generated by the target sensor with respect to vehicle fault diagnosis;
a receiving unit configured to receive a plurality of sensing signals from the in-vehicle sensor; and
a fitting unit configured to:
screening out similar sensing signals from the plurality of sensing signals according to the similarity degree with the target sensing signal;
fitting the similar sensing signals based on a fitting algorithm to generate a fitted signal for fitting the target sensing signal;
a verification unit configured to verify an application performance thereof based on a characteristic of the fitted signal with respect to the vehicle failure diagnosis; and
an adjusting unit configured to determine whether to adjust the fitting algorithm and/or the filtering rule of the similar sensing signals according to the application performance.
9. The system of claim 8, the extraction unit configured to:
acquiring a first sensing signal in a fault state and a second sensing signal in a non-fault state through the target sensor;
extracting time domain and/or frequency domain features of the first sensing signal and the second sensing signal; and
and determining the time domain and/or frequency domain characteristics of the target sensing signal related to vehicle fault diagnosis according to the difference of the time domain and/or frequency domain characteristics of the first sensing signal and the second sensing signal.
10. The system of claim 8 or 9, wherein the target sensing signal is the same as a sampling frequency of a first signal of the plurality of sensing signals, and the fitting unit is configured to determine whether the first signal is the similar sensing signal according to a degree of similarity of the first signal to the target sensing signal, wherein the degree of similarity is determined by at least one of: data correlation, time sequence shape similarity, frequency component similarity, time sequence data goodness of fit.
11. The system of claim 8 or 9, wherein the target sensing signal is different in sampling frequency from a second set of signals of the plurality of sensing signals, and the fitting unit is configured to determine whether each of the second sets of signals is the similar sensing signal according to its degree of similarity to the target sensing signal:
determining a candidate signal from each of the second signal sets according to a timing shape similarity to the target sensing signal;
aligning each of the candidate signals with the target sensing signal using an interpolation algorithm; and
determining whether the aligned candidate signal is the similar sensing signal according to a similarity degree with the target sensing signal, wherein the similarity degree is determined by at least one of the following items: data correlation, time sequence shape similarity, frequency component similarity and time sequence data fitting goodness.
12. The system of claim 8 or 9, wherein the verification unit is configured to perform fault diagnosis on a vehicle known to have a fault using the fitted signal; and
and determining the application performance according to the fault diagnosis result, wherein the application performance comprises found faults and not found faults.
13. The system of claim 12, wherein the adjustment unit is configured to cure the fitting algorithm and the screening rules of the similar sensing signals for fitting the target sensing signal if the application appears to find a fault; and
adjusting the fitting algorithm and/or the screening rules of the similar sensing signals in case the application appears to find no fault.
14. A computer readable storage medium having instructions stored therein, which when executed by a processor, cause the processor to perform a method of fitting an in-vehicle object sensor as claimed in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210679611.8A CN115169385A (en) | 2022-06-16 | 2022-06-16 | Method and system for fitting target sensor for vehicle, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210679611.8A CN115169385A (en) | 2022-06-16 | 2022-06-16 | Method and system for fitting target sensor for vehicle, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115169385A true CN115169385A (en) | 2022-10-11 |
Family
ID=83484532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210679611.8A Pending CN115169385A (en) | 2022-06-16 | 2022-06-16 | Method and system for fitting target sensor for vehicle, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115169385A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024114512A1 (en) * | 2022-11-29 | 2024-06-06 | 蔚来动力科技(合肥)有限公司 | Method and device for detecting fault of electric drive system, and vehicle and storage medium |
-
2022
- 2022-06-16 CN CN202210679611.8A patent/CN115169385A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024114512A1 (en) * | 2022-11-29 | 2024-06-06 | 蔚来动力科技(合肥)有限公司 | Method and device for detecting fault of electric drive system, and vehicle and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Damage identification in civil engineering structures utilizing PCA‐compressed residual frequency response functions and neural network ensembles | |
| JP6361175B2 (en) | Abnormality diagnosis apparatus and program | |
| CN102375452B (en) | Event-driven data mining method for improving fault code settings and isolating faults | |
| US7496798B2 (en) | Data-centric monitoring method | |
| KR102141391B1 (en) | Failure data management method based on cluster estimation | |
| CN107209512B (en) | Method, system and the computer program in the study stage of the acoustics or vibration analysis for machine | |
| KR102123522B1 (en) | Failure diagnostic method based on cluster of fault data | |
| CN105971901A (en) | Centrifugal pump fault diagnosis method based on complete ensemble empirical mode decomposition and random forest | |
| CN112346941A (en) | Fault diagnosis method and device | |
| JP7102941B2 (en) | Information processing methods, information processing devices, and programs | |
| US20140095132A1 (en) | System and method for rating computer model relative to empirical results for dynamic systems | |
| CN108292247A (en) | Method and apparatus for the supply chain for using channel information verification electronic equipment in side in signature analysis | |
| CN112362368A (en) | Fault diagnosis method, device and system for train traction motor and readable medium | |
| CN115169385A (en) | Method and system for fitting target sensor for vehicle, and storage medium | |
| CN116304909A (en) | Abnormality detection model training method, fault scene positioning method and device | |
| CN113254693A (en) | Image recognition and retrieval for component failure analysis | |
| CN113544486B (en) | Fault diagnosis system, fault prediction method, and computer-readable recording medium | |
| CN117591986B (en) | Real-time automobile data processing method based on artificial intelligence | |
| CN117538710A (en) | Intelligent early warning method and system for local dynamic discharge monitoring | |
| CN110781612A (en) | Fault diagnosis method and device for ball screw, computer device and storage medium | |
| CN114167237A (en) | GIS partial discharge fault identification method and system, computer equipment and storage medium | |
| WO2020162425A1 (en) | Analysis device, analysis method, and program | |
| CN116699400A (en) | Generator rotor short-circuit fault monitoring system, method and readable storage medium | |
| CN115655757A (en) | Method and system for determining vehicle-mounted superconducting magnet monitoring system and storage medium | |
| CN115398442A (en) | Device and automation method for evaluating sensor measurement values and use of the device |
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 |