CN111177936B - Method for reducing vehicle load error and computer readable storage medium - Google Patents
Method for reducing vehicle load error and computer readable storage medium Download PDFInfo
- Publication number
- CN111177936B CN111177936B CN202010003158.XA CN202010003158A CN111177936B CN 111177936 B CN111177936 B CN 111177936B CN 202010003158 A CN202010003158 A CN 202010003158A CN 111177936 B CN111177936 B CN 111177936B
- Authority
- CN
- China
- Prior art keywords
- weight
- strain gauge
- value
- vehicle
- filtering
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/08—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for incorporation in vehicles
- G01G19/086—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for incorporation in vehicles wherein the vehicle mass is dynamically estimated
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Vehicle Body Suspensions (AREA)
Abstract
The invention provides a method for reducing vehicle load error and a computer readable storage medium, comprising the following steps: establishing a mapping relation between the value of the strain gauge and the weight of the standard weight; filtering the value of the strain gauge by using a Butterworth low-pass filter to obtain the value of the strain gauge after the first filtering; performing empirical mode decomposition on the value of the strain gauge subjected to the first filtering to reconstruct a signal to obtain a value of the strain gauge subjected to the second filtering; extracting a characteristic vector of time sequence weight data by utilizing wavelet transformation; inputting the characteristic vector into a multi-classification support vector classifier model, and identifying the running state of the vehicle; and outputting the weight of the vehicle in real time according to the running state of the vehicle and the numerical value of the strain gauge subjected to the second filtering. Errors brought to the strain gauge by the external environment are effectively eliminated, so that the weighing result is more accurate, and the real and stable vehicle load is obtained.
Description
Technical Field
The present invention relates to the field of vehicle load technologies, and in particular, to a method for reducing a vehicle load error and a computer-readable storage medium.
Background
According to the 44 th statistical report of the development conditions of the Chinese Internet issued by the Chinese Internet information center (CNNIC) in Beijing, the scale of the users of the Chinese online shopping reaches more than 6.39 hundred million. The Chinese express delivery traffic in 2018 reaches 507.1 hundred million, and the express delivery traffic in 2019 is predicted to exceed 600 hundred million according to the industry, which causes little pressure on express delivery transportation. Express delivery vehicle loading capacity now mainly relies on passing the weighbridge to measure, and weighing in the pound of passing the goods will cause the express delivery backlog undoubtedly in commodity circulation peak period. Along with 5G, big data and intelligent acceleration, realize that express delivery vehicle intelligent dispatch will promote express delivery conveying efficiency by a wide margin, will also be inevitable trend. The real-time load capacity of the vehicle is supported by basic data, which is undoubtedly an urgent problem to be solved. Various methods for measuring the dynamic weight of a vehicle exist, and the mainstream scheme is to install a strain gauge. However, the strain gauge has not been fully used up to now because of a large error caused by the environmental influence.
Various dynamic weighing schemes for vehicles exist, and most of them are implemented by calibrating strain gauge coefficients by using strain gauge data. But be applied to express delivery vehicle's dynamic weighing, have following shortcoming: the express delivery vehicle needs the courier to get on or off the goods frequently, and the self weight of the courier and the process of carrying the goods bring large errors to the strain gauge; the express delivery vehicle is traveling or not flame-out the in-process of getting in stock, because automobile body high frequency vibration has brought the high frequency error for the strainometer.
The prior art lacks a method and computer-readable storage medium for effectively reducing the vehicle load error.
Disclosure of Invention
The present invention provides a method for reducing a vehicle load error and a computer readable storage medium for solving the existing problems.
In order to solve the above problems, the technical solution adopted by the present invention is as follows:
a method of reducing vehicle weight error, comprising the steps of: s1: establishing a mapping relation between the value of the strain gauge and the weight of the standard weight; s2: filtering the value of the strain gauge by using a Butterworth low-pass filter to obtain the value of the strain gauge after the first filtering; s3: performing empirical mode decomposition on the value of the strain gauge subjected to the first filtering to reconstruct a signal to obtain a value of the strain gauge subjected to the second filtering; s4: extracting a characteristic vector of time sequence weight data by utilizing wavelet transformation; s5: inputting the characteristic vector into a multi-classification support vector classifier model, and identifying the running state of the vehicle; s6: and outputting the weight of the vehicle in real time according to the running state of the vehicle and the numerical value of the strain gauge subjected to the second filtering.
Preferably, the method further comprises the following steps: s7: and forming a weight curve according to the vehicle weight output in real time and outputting the weight curve. Preferably, the step of establishing a mapping relationship between the value of the strain gauge and the weight of the standard weight comprises the following steps: s11: collecting data, the data comprising: vector Y formed by weight of standard weighti(i ∈ 1.... N) and the corresponding strain gauge valuei，j(i ∈ 1,2, 3.., N; j ∈ 1,2, 3.., M), wherein N represents the total number of loaded standard weights, and M represents the total number of strain gauges; s12: and establishing a mapping relation between the value of the strain gauge and the weight of the standard weight by multiple linear regression: y ═ beta0+β1x1+β2x2+…+βixi+ epsilon, determining each strain gauge coefficient betai(i∈1，2，...M)。
Preferably, the empirical mode decomposition comprises:
wherein x (t) is the value of the strain gauge after the first filtering, IMFi(t) is the natural modal component, rn(t) is the remainder; LPkBy means of intrinsic mode IMFiAnd superposing the new mode of the numerical value of the strain gauge after the low-pass filtering is carried out, wherein the numerical value of the strain gauge is obtained after the second filtering.
Preferably, LP for said new modalitykThe evaluation indexes are as follows:
minf＝αmin(MMSE)+(1-α)min(SMSE)
wherein, the similarity index MMSE is LPkMean root mean square error, MSEjJ is 1,2, …, and m is the number of the strain gauges; average smoothness index SMSE is LPkAverage value of smoothness at each point, SMSEjIs LPkThe smoothness average value of the numerical value of each strain gauge; the optimal index minf is that the similarity index MMSE and the smoothness index SMSE simultaneously obtain the minimum value, alpha is a weight coefficient, and the function min is the minimum value.
Preferably, the extracting of the feature vector of the time series weight data by using the wavelet transform comprises the steps of: s41: buffering the value of the strain gauge within 30-60s, and obtaining the original weight corresponding to the value of the strain gauge according to the mapping relation between the value of the strain gauge and the weight of the standard weight; s42: and converting the time sequence weight data into time and frequency distribution data through wavelet transformation, wherein the time and frequency distribution data are the feature vectors.
Preferably, the formula of the wavelet transform is:
wherein, a is translation, b is scaling scale, x (t) is weight sequence to be input, t is time, psi (t) is mother wavelet, Morlet is selected, and the formula is as follows:
preferably, the vehicle running state is classified as: loading and unloading and non-loading and unloading states; the vehicle running state identification method comprises the following steps: and obtaining the characteristic vector x and a vehicle running state vector w corresponding to the characteristic vector, wherein the classification function is as follows:
wherein sign belongs to a sign function, 1 is output when the numerical value in the bracket is greater than 0, and-1 is output when the numerical value in the bracket is less than or equal to 0, and K is a kernel function, namely a Gaussian kernel function:
where σ is a hyper-parameter of the kernel function, x represents an input space value, xiThe value of the feature space is represented,
is a solution to the following quadratic programming:
0≤αi≤C
c >0 is a penalty parameter for the SVM algorithm.
b*Intercept of classification function, selecting alpha*One of
The component of (a) satisfies 0. ltoreq. alphaiC is less than or equal to C, calculating:
preferably, when the vehicle running state is a loading and unloading state, the vehicle weight is output in real time according to the value of the strain gauge subjected to the second filtering; and when the vehicle is in a non-loading and unloading state, taking the vehicle-mounted weight in the loading and unloading state at the latest moment as the current vehicle-mounted weight of the vehicle and outputting the vehicle-mounted weight.
The invention further provides a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method as set forth in any of the above.
The invention has the beneficial effects that: the method for reducing the vehicle load error and the computer-readable storage medium are provided, and errors brought to the strain gauge by the external environment are effectively eliminated by using a Butterworth filter and empirical mode decomposition, so that the weighing result is more accurate; according to the wavelet transformation, the vehicle weight sequence is converted into a characteristic signal with frequency changing along with time, the characteristic signal is input into a support vector model to judge the vehicle running state, errors brought to a strain gauge in the vehicle running process are eliminated, and the real and stable vehicle load is obtained.
Drawings
FIG. 1 illustrates a method for reducing vehicle loading error in accordance with an embodiment of the present invention.
FIG. 2 illustrates another embodiment of a method for reducing vehicle loading error.
Fig. 3 is a schematic view of a vehicle in an embodiment of the invention.
Fig. 4 is a schematic diagram of a method for establishing a mapping relationship between the value of the strain gauge and the weight of the standard weight according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating a method for extracting feature vectors of time-series weight data using wavelet transform according to an embodiment of the present invention.
FIG. 6 is a graph illustrating the weight of a strain gauge according to the original value in an embodiment of the present invention.
FIG. 7 is a graph illustrating weight versus value for a first filtered strain gauge in an embodiment of the present disclosure.
FIG. 8 is a graphical representation of the weight versus value for the strain gauge after the second filtering in an embodiment of the present disclosure.
Fig. 9 is a diagram illustrating the weight according to the vehicle running state and the value of the second filtered strain gauge in the embodiment of the present invention.
The system comprises a vehicle head 1, a vehicle carriage 2, a front vehicle axle 3, a rear vehicle axle 4, and strain gauges 5, 5A and 5B.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the embodiments of the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It will be understood that when an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or be indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or be indirectly connected to the other element. In addition, the connection may be for either a fixing function or a circuit connection function.
It is to be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in an orientation or positional relationship indicated in the drawings for convenience in describing the embodiments of the present invention and to simplify the description, and are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed in a particular orientation, and be in any way limiting of the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of the present invention, "a plurality" means two or more unless specifically limited otherwise.
Interpretation of related terms
Butterworth filter: the filter is also called as maximum flat filter, and is characterized in that the frequency response curve in the pass band is flat to the maximum extent without ripples, and gradually drops to zero in the stop band, and is always considered preferentially in the signal processing process.
Empirical Mode Decomposition (EMD) is a method for performing signal decomposition according to the time scale characteristics of data itself without setting any basis function in advance. This is essentially different from the fourier decomposition and wavelet decomposition methods that are built on a priori harmonic basis functions and wavelet basis functions. Due to the characteristics, the EMD method can be theoretically applied to the decomposition of any type of signals, so that the EMD method has obvious advantages in processing non-stationary and non-linear data, is suitable for analyzing non-linear and non-stationary signal sequences and has high signal-to-noise ratio.
As shown in FIG. 1, the present invention provides a method for reducing vehicle load error, comprising the steps of:
s1: establishing a mapping relation between the value of the strain gauge and the weight of the standard weight;
s2: filtering the value of the strain gauge by using a Butterworth low-pass filter to obtain the value of the strain gauge after the first filtering;
s3: performing empirical mode decomposition on the value of the strain gauge subjected to the first filtering to reconstruct a signal to obtain a value of the strain gauge subjected to the second filtering;
s4: extracting a characteristic vector of time sequence weight data by utilizing wavelet transformation;
s5: inputting the characteristic vector into a multi-classification support vector classifier model, and identifying the running state of the vehicle;
s6: and outputting the weight of the vehicle in real time according to the running state of the vehicle and the numerical value of the strain gauge subjected to the second filtering.
As shown in fig. 2, the method for reducing the vehicle load error in one embodiment of the present invention further includes:
s7: and forming a weight curve according to the vehicle weight output in real time and outputting the weight curve.
As shown in fig. 3, a vehicle body 2 is connected to the rear of a vehicle head 1, two strain gauges 5 are mounted directly above a front axle 3, two strain gauges 5A are mounted directly above a rear axle 4, and two strain gauges 5B are mounted on the rear side of the rear axle 4.
In one embodiment of the invention, the strain gauges can be symmetrically arranged on the front axle and the rear axle in even number, which can be more than 6; and converting the deformation of the axle into a strain gauge analog signal value through the strain gauge as a characteristic value input by the model. The strain gauges with even number of strain gauges are symmetrically arranged on the front axle part and the rear axle part, so that the stress of a carriage brought by goods can be uniformly acquired, and the condition that deformation caused by unbalanced stress is caught and lost, and the loss of precision is avoided.
As shown in fig. 4, the step of establishing a mapping relationship between the value of the strain gauge and the weight of the standard weight includes the following steps:
s11: collecting data, the data comprising: vector Y formed by weight of standard weighti(i ∈ 1.... N) and the corresponding strain gauge valuei,j(i ∈ 1,2, 3.., N; j ∈ 1,2, 3.., M), wherein N represents the total number of loaded standard weights, and M represents the total number of strain gauges;
s12: and establishing a mapping relation between the value of the strain gauge and the weight of the standard weight by multiple linear regression:
y＝β0+β1x1+β2x2+…+βixi+ε
determining the respective strain gauge coefficient betai(i∈1，2，...M)。
In one embodiment of the invention, N is at least 15.
The Butterworth filter is also called a maximum flat filter, and is often prioritized in the signal processing process because the pass band frequency response is flat. The filtering operation is performed every 30 to 60 seconds for the strain gauge data in consideration of the real-time property of the output vehicle-mounted weight. Theoretically, the higher the filter order, the closer to an ideal filter, but taking into account both the Gibbs effect and the filter performance. And finally, performing low-pass filtering on the strain gauge by adopting a 4-order Butterworth band-pass filter. The specification of the filter is designed as follows:
Fpass＝F(F＝0.2Hz)，Fstop＝1.05F，Apass＝3dB，Astop＝40dB。
it will be appreciated that the longer the time series applied to the filtering and EMD signals, the better, but the post-experimental trade-off is every 30 seconds, taking into account the real-time output of the data.
Empirical Mode Decomposition (EMD) is a novel adaptive signal time-frequency processing method, and is particularly suitable for analyzing and processing nonlinear non-stationary signals. The empirical mode decomposition comprises:
wherein x (t) is the value of the strain gauge after the first filtering, IMFi(t) is the natural modal component, rn(t) is the remainder; LPkBy means of intrinsic mode IMFiAnd superposing the new mode of the numerical value of the strain gauge after the low-pass filtering is carried out, wherein the numerical value of the strain gauge is obtained after the second filtering.
In order to further eliminate the error brought to the strain gauge by manual operation, an optimal noise reduction smooth model is selected to evaluate the new mode LP reconstructed by each inherent mode componentkThe evaluation indexes are as follows:
minf＝αmin(MMSE)+(1-α)min(SMSE)
wherein, the similarity index MMSE is LPkMean root mean square error, MSEjJ is 1,2, …, and m is the number of the strain gauges; average smoothness index SMSE is LPkAverage value of smoothness at each point, SMSEjIs LPkThe smoothness average value of the numerical value of each strain gauge; the optimum index minf isThe similarity index MMSE and the smoothness index SMSE simultaneously obtain the minimum value, alpha is a weight coefficient, and the function min is the minimum value.
In one embodiment of the invention, α is taken to be 0.3.
As shown in fig. 5, since certain features are lost by filtering the data in S2 and S3, extracting the feature vector of the time series weight data by using the wavelet transform includes the following steps:
s41: buffering the value of the strain gauge within 30-60s, and obtaining the original weight corresponding to the value of the strain gauge according to the mapping relation between the value of the strain gauge and the weight of the standard weight;
s42: and converting the time sequence weight data into time and frequency distribution data through wavelet transformation, wherein the time and frequency distribution data are the feature vectors.
The value range of the buffering time mainly takes two aspects into consideration: 1. extracting the effectiveness of the feature vector by using the wavelet; 2. and time delay when the vehicle running state is switched.
The formula for the wave transform is:
wherein, a is translation, b is scaling scale, x (t) is weight sequence to be input, t is time, psi (t) is mother wavelet, Morlet is selected, and the formula is as follows:
and inputting the obtained feature vector into a multi-classification support vector classifier, and classifying the vehicle running state into: loading and unloading and non-loading and unloading states; the vehicle running state identification method comprises the following steps:
and obtaining the characteristic vector x and a vehicle running state vector w corresponding to the characteristic vector, wherein the classification function is as follows:
wherein sign belongs to a sign function, 1 is output when the numerical value in the bracket is greater than 0, and-1 is output when the numerical value in the bracket is less than or equal to 0, and K is a kernel function, namely a Gaussian kernel function:
where σ is a hyper-parameter of the kernel function, x represents an input space value, xiThe value of the feature space is represented,
is a solution to the following quadratic programming:
0≤αi≤C
c >0 is a penalty parameter for the SVM algorithm.
b*Intercept of classification function, selecting alpha*One of
The component of (a) satisfies 0. ltoreq. alphaiC is less than or equal to C, calculating:
when the vehicle running state is a loading and unloading state, outputting the weight of the vehicle in real time according to the numerical value of the strain gauge subjected to the second filtering;
and when the vehicle is in a non-loading and unloading state, taking the vehicle-mounted weight in the loading and unloading state at the latest moment as the current vehicle-mounted weight of the vehicle and outputting the vehicle-mounted weight.
The method utilizes a Butterworth filter and empirical mode decomposition to effectively eliminate the error brought to the strain gauge by the external environment, so that the weighing result is more accurate; according to the wavelet transformation, the vehicle weight sequence is converted into a characteristic signal with frequency changing along with time, the characteristic signal is input into a support vector model to judge the vehicle running state, errors brought to a strain gauge in the vehicle running process are eliminated, and the real and stable vehicle load is obtained.
All or part of the flow of the method of the embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a processor, to instruct related hardware to implement the steps of the embodiments of the methods. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
In a specific embodiment, values of strain gauges of a vehicle over a period of time are taken, and a corresponding vehicle weight data map is obtained in each step by using the method of the present invention.
The vehicle load, calculated from the raw strain gage data, is shown in fig. 6 with intolerable noise interference. FIG. 7 shows the vehicle load after passing through a Butterworth filter, and it can be seen that some high frequency noise pollution is removed. FIG. 8 shows that the vehicle load is obtained after the EMD reconstructs strain gauge signals, noise pollution is basically eliminated, the load curve is stable, and the loading and unloading processes are clear. FIG. 9 shows the load of the vehicle after being judged by the longitudinal weighing machine model, and the load of the vehicle is in a locked state except for the loading and unloading processes, so that the vehicle weight curve is more real.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several equivalent substitutions or obvious modifications can be made without departing from the spirit of the invention, and all the properties or uses are considered to be within the scope of the invention.
Claims (7)
1. A method of reducing vehicle weight error, comprising the steps of:
s1: establishing a mapping relation between the value of the strain gauge and the weight of the standard weight;
s2: filtering the value of the strain gauge by using a Butterworth low-pass filter to obtain the value of the strain gauge after the first filtering;
s3: performing empirical mode decomposition on the value of the strain gauge subjected to the first filtering to reconstruct a signal to obtain a value of the strain gauge subjected to the second filtering;
s4: extracting a characteristic vector of time sequence weight data by utilizing wavelet transformation; the method for extracting the characteristic vector of the time sequence weight data by utilizing the wavelet transformation comprises the following steps:
s41: buffering the value of the strain gauge within 30-60s, and obtaining the original weight corresponding to the value of the strain gauge according to the mapping relation between the value of the strain gauge and the weight of the standard weight;
s42: converting time sequence weight data into time and frequency distribution data through wavelet transformation, wherein the time and frequency distribution data are characteristic vectors;
s5: inputting the characteristic vector into a multi-classification support vector classifier model, and identifying the running state of the vehicle; the vehicle operating state is classified into: loading and unloading and non-loading and unloading states; the vehicle running state identification method comprises the following steps:
and obtaining the characteristic vector x and a vehicle running state vector w corresponding to the characteristic vector, wherein the classification function is as follows:
wherein sign belongs to a sign function, 1 is output when the numerical value in the bracket is greater than 0, and-1 is output when the numerical value in the bracket is less than or equal to 0, and K is a kernel function, namely a Gaussian kernel function:
where σ is a hyperparameter of the kernel function, the eigenvector x represents the input space value, xiThe value of the feature space is represented,
is a solution to the following quadratic programming:
0≤αi≤C
c >0 is a penalty parameter of the SVM algorithm;
b*intercept of classification function, selecting alpha*One of
Is satisfied with
And (3) calculating:
s6: outputting the weight of the vehicle in real time according to the running state of the vehicle and the numerical value of the strain gauge subjected to the second filtering; when the vehicle running state is a loading and unloading state, outputting the weight of the vehicle in real time according to the numerical value of the strain gauge subjected to the second filtering;
and when the vehicle is in a non-loading and unloading state, taking the vehicle-mounted weight in the loading and unloading state at the latest moment as the current vehicle-mounted weight of the vehicle and outputting the vehicle-mounted weight.
2. The method of reducing vehicle load error of claim 1, further comprising:
s7: and forming a weight curve according to the vehicle weight output in real time and outputting the weight curve.
3. The method for reducing the vehicle load error according to claim 1, wherein the step of mapping the value of the strain gauge with the weight of the standard weight comprises the following steps:
s11: collecting data, the data comprising: vector Y formed by weight of standard weightiWhere i ∈ 1.., N and the corresponding strain gauge value form a matrix Xi,jWherein i belongs to 1,2, 3. j ∈ 1,2, 3.. multidot.M, wherein N represents the total number of loaded standard weights and M represents the total number of strain gauges;
s12: and establishing a mapping relation between the value of the strain gauge and the weight of the standard weight by multiple linear regression:
y＝β0+β1x1+β2x2+…+βixi+ε
determining the respective strain gauge coefficient betaiWhere i ∈ 1, 2.
4. The method of reducing vehicle load error of claim 1, wherein the empirical mode decomposition comprises:
wherein x (t) is the value of the strain gauge after the first filtering, IMFi(t) is the natural modal component, rn(t) is the remainder; LPkBy means of intrinsic mode IMFiAnd superposing the new mode of the numerical value of the strain gauge after the low-pass filtering is carried out, wherein the numerical value of the strain gauge is obtained after the second filtering.
5. The method of reducing vehicle load error of claim 4, wherein LP is performed for the new modekThe evaluation indexes are as follows:
minf＝αmin(MMSE)+(1-α)min(SMSE)
wherein, the similarity index MMSE is LPkMean root mean square error, MSEjJ is 1,2, …, and m is the number of strain gauges; average smoothness index SMSE is LPkAverage value of smoothness at each point, SMSEjIs LPkThe smoothness average value of the numerical value of each strain gauge; the optimal index minf is a minimum value obtained by the similarity index MMSE and the average smoothness index SMSE at the same time, alpha is a weight coefficient, and the function min is a minimum value.
6. The method for reducing vehicle payload error of claim 1, wherein the wavelet transform is of the formula:
wherein, a is translation, b is scaling scale, x (t) is weight sequence to be input, t is time, psi (t) is mother wavelet, Morlet is selected, and the formula is as follows:
7. a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010003158.XA CN111177936B (en) | 2020-01-02 | 2020-01-02 | Method for reducing vehicle load error and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010003158.XA CN111177936B (en) | 2020-01-02 | 2020-01-02 | Method for reducing vehicle load error and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111177936A CN111177936A (en) | 2020-05-19 |
| CN111177936B true CN111177936B (en) | 2021-03-23 |
Family
ID=70654360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010003158.XA Active CN111177936B (en) | 2020-01-02 | 2020-01-02 | Method for reducing vehicle load error and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111177936B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111912506A (en) * | 2020-05-28 | 2020-11-10 | 北京蜂云科创信息技术有限公司 | Method and device for determining the load state of a motor vehicle |
| CN113240821B (en) * | 2021-04-12 | 2022-08-26 | 西安科技大学 | Dynamic weighing truck non-stop charging system and method based on multi-information fusion |
| CN113688351A (en) * | 2021-08-06 | 2021-11-23 | 北京每日优鲜电子商务有限公司 | Method, device, electronic equipment and readable medium for detecting weight of article |
| CN113959549B (en) * | 2021-09-16 | 2023-07-21 | 三一汽车制造有限公司 | Weighing data processing method, device and storage medium |
| CN114993434B (en) * | 2022-05-20 | 2023-07-14 | 湖南科技大学 | Vehicle weight identification system and method based on EMD energy entropy of acoustic signals |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102901550B (en) * | 2012-11-15 | 2014-08-13 | 陕西电器研究所 | Method for implementing vehicle-mounted dynamic weighing |
| CN107727210B (en) * | 2017-09-21 | 2019-06-04 | 深圳市汉德网络科技有限公司 | A kind of vehicle-mounted weighing method of kitchen waste cart and system |
-
2020
- 2020-01-02 CN CN202010003158.XA patent/CN111177936B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111177936A (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111177936B (en) | Method for reducing vehicle load error and computer readable storage medium | |
| EP2502759B1 (en) | Apparatus, method and program for vehicle mass estimation | |
| Xu et al. | Roller bearing fault diagnosis using stacked denoising autoencoder in deep learning and Gath–Geva clustering algorithm without principal component analysis and data label | |
| Wang et al. | Vibration sensor based tool condition monitoring using ν support vector machine and locality preserving projection | |
| CN111121939B (en) | High-precision vehicle-mounted area weighing method | |
| Li et al. | Analysis of impact factors of tire wear | |
| CN111157092B (en) | Vehicle-mounted weighing automatic calibration method and computer readable storage medium | |
| CN111089643B (en) | Dynamic vehicle-mounted weighing method and system | |
| Huang et al. | Identification of vehicle suspension shock absorber squeak and rattle noise based on wavelet packet transforms and a genetic algorithm-support vector machine | |
| CN111397868B (en) | Breaker fault analysis method based on aggregation empirical mode decomposition algorithm | |
| CN112256686B (en) | MES-based fault data compression and prediction method and system | |
| CN109582741B (en) | Feature data processing method and device | |
| Minhas et al. | Improvement in classification accuracy and computational speed in bearing fault diagnosis using multiscale fuzzy entropy | |
| Huang et al. | Soft measurement of ball mill load based on multi-classifier ensemble modelling and multi-sensor fusion with improved evidence combination | |
| Li et al. | Application of the refined multiscale permutation entropy method to fault detection of rolling bearing | |
| CN110569915A (en) | automobile data clustering method and system based on intuitive fuzzy C-means | |
| CN114239396A (en) | Fan gear box state prediction method and system | |
| CN113869642A (en) | Enterprise activity determination method and device, electronic equipment and storage medium | |
| CN113314201A (en) | Neurology clinical nursing potential safety hazard analysis method and system | |
| Martins et al. | A variant of the AOR method for augmented systems | |
| Schmidt | Tire Pressure Monitoring using Weighted Horizontal Visibility Graphs | |
| Panda et al. | Epliptic seizure detection and classification using cumulative sum average filter TT-transform and harmony search algorithm based LLRBFN model | |
| CN113155422A (en) | Fault detection method, device and storage medium | |
| CN113496055B (en) | Method for reducing vibration of end wall, high damping end wall and device | |
| Meng et al. | Epileptic detection based on EMD and sparse representation in clinic EEG |
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 |