CN113865885B - Method and device for detecting bicycle loss - Google Patents
Method and device for detecting bicycle loss Download PDFInfo
- Publication number
- CN113865885B CN113865885B CN202111126944.XA CN202111126944A CN113865885B CN 113865885 B CN113865885 B CN 113865885B CN 202111126944 A CN202111126944 A CN 202111126944A CN 113865885 B CN113865885 B CN 113865885B
- Authority
- CN
- China
- Prior art keywords
- characteristic
- acceleration
- riding
- loss
- vehicle body
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 5
- 230000001133 acceleration Effects 0.000 claims description 75
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000008030 elimination Effects 0.000 claims description 9
- 238000003379 elimination reaction Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 10
- 238000012423 maintenance Methods 0.000 abstract description 4
- 238000009987 spinning Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 8
- 238000012360 testing method Methods 0.000 description 4
- 101100268665 Caenorhabditis elegans acc-1 gene Proteins 0.000 description 3
- 101100268668 Caenorhabditis elegans acc-2 gene Proteins 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
Abstract
The invention relates to a method and a device for detecting bicycle loss, belonging to the technical field of bicycles and spinning, wherein the method is divided into an off-line stage and an on-line stage, the off-line stage works to collect riding characteristics and loss characteristics of various lost bicycle bodies and construct a characteristic database, the on-line stage is a stage of identifying a state in real time, a user is unknown about the loss condition of the bicycle, the riding characteristics collected in real time are utilized for detecting the loss condition of the detected bicycle body, and the invention calculates the bicycle loss condition by collecting the riding characteristics and analyzing and processing on the premise of not depending on additional detection equipment, thus leading the user to know the loss condition of the bicycle in time for maintenance or repair, and the invention has the characteristics of low cost, non-invasiveness, easy maintenance and high prediction accuracy.
Description
Technical Field
The invention belongs to the technical field of bicycles and spinning, and particularly relates to a method and a device for detecting bicycle loss.
Background
With the emphasis of environmental protection in various countries in recent years, various countries respectively advocate the widespread use of bicycles as vehicles to reduce energy consumption in order to advocate the concept of energy conservation and environmental protection. Furthermore, with the increasing emphasis of sports, riding has become a widely used sport, and bicycles are becoming more of the important items.
There is a strong need for quantifiable movement, which becomes easier and easier as smart phones, internet and sensor technologies develop. The user can clearly grasp the speed, the acceleration, the trampling frequency, the power and the like in the process of riding exercise. However, most of the existing bicycle loss detection methods are post detection, and possible faults and losses cannot be early warned in advance.
Disclosure of Invention
In order to solve the above-mentioned problems, a method and apparatus for detecting bicycle wear have been proposed.
In order to achieve the above purpose, the present invention provides the following technical solutions:
A method for detecting bicycle wear, comprising the steps of:
Step S100, collecting historical riding characteristics and vehicle body loss characteristics associated with the historical riding characteristics in an off-line manner, and constructing a characteristic database;
Step S200, collecting real-time riding characteristics, comparing the historical riding characteristics with the real-time riding characteristics in similarity, taking the maximum value of the similarity as a similarity output target, obtaining a reference vehicle body loss condition, calculating the occurrence probability of the reference vehicle body loss condition under the condition of the real-time riding characteristics, and taking the maximum value of the occurrence probability as a final output target.
Further, the riding characteristics include a speed characteristic, a torsion characteristic, a pedaling frequency characteristic, a first acceleration characteristic acquired by a first sensor, and a second acceleration characteristic acquired by a second sensor.
Further, historical riding characteristic collection is performed by using test vehicles with known and different loss conditions, wherein the loss conditions are vehicle body loss characteristics.
Further, in step S100, the method for constructing the feature database includes:
Step S101, carrying out band elimination sampling on acceleration characteristics to obtain acceleration noise characteristics through calculation, wherein the acceleration characteristics comprise first acceleration characteristics and second acceleration characteristics, and the acceleration noise characteristics comprise first acceleration noise characteristics and second acceleration noise characteristics;
step S102, acquiring speed characteristics, torsion characteristics and pedal frequency characteristics of the same time sequence as the first acceleration characteristics and the second acceleration characteristics, calculating power characteristics, and constructing a characteristic database.
Further, in step S101, the method for calculating the acceleration noise feature is as follows:
Wherein acc_bs is the acceleration noise characteristic, b is the molecular coefficient of the band-stop filter, acc is the acceleration characteristic, n is the order of the band-stop filter, k is the kth element of one convolution operation, and i is the ith element of the data column.
Further, in step S102, the power characteristic calculating method includes:
Where l is moment, fre is pedaling frequency, f is torsion of the same time sequence, n is the order of band elimination filtering, k is the kth element of one convolution operation, and i is the ith element of the data column.
Further, in the characteristic acquisition time domain, the acceleration noise characteristic and the power characteristic are obtained through integral calculation, and the speed characteristic, the torsion characteristic and the pedal frequency characteristic are all average values in the characteristic acquisition time domain.
Further, in step S102, the feature combination storage format of the feature database is:
Wherein acc_bs_1 is the first acceleration noise feature, acc_bs_2 is the second acceleration noise feature, v is the average speed feature, P is the power feature, label is the labeling value of the vehicle body loss feature, n is the order of band elimination filtering, i is the ith element of the data column.
Further, in the feature database, the loss features of the vehicle body are marked by 1-N to form label, and when the algorithm runs, the label is converted into one-hot codes.
Further, in step S200, the real-time riding characteristic acquisition method includes:
Collecting a first acceleration characteristic and a second acceleration characteristic, respectively caching the first acceleration characteristic and the second acceleration characteristic to the collections acc_1 'and acc_2', when the number of elements in the collections reaches n, sampling the band stop to obtain band stop collections acc_bs_1 'and acc_bs_2', respectively calculating the frequency band with the largest mean value, middle error and amplitude of the band stop collections, simultaneously, collecting the speed characteristics of the same time sequence to form a speed collection, calculating the mean value and recording as The torque characteristic and the pedal frequency characteristic of the same time sequence are collected, and the power characteristic is calculated and recorded as P'.
Further, in step S200, similarity comparison is performed by using a gaussian kernel function, and the method is as follows:
Where similarity is similarity, fea realtime is a real-time riding feature (i.e. a real-time feature) after processing, fea database is a historical riding feature (i.e. an offline feature) in the feature database, σ is a middle error of the corresponding feature, and gaussian kernel is an e index obtained after taking the negative of the two norms/variances of the two features, so the calculation process of the above formula is as follows:
j is the j-th feature combination in the feature database, Δfea j is the deviation of the real-time feature vector from the corresponding offline feature,/> Is the transpose of Δfea j.
Further, the maximum similarity is used as a similarity output target, and the vehicle body loss condition associated with the maximum similarity is the reference vehicle body loss condition label.
Further, in step S200, the real-time riding characteristics are substituted into the bayesian full probability formula, and the occurrence probability of the reference vehicle body loss condition is calculated under the condition of the real-time riding characteristics:
wherein, To refer to the occurrence probability of the loss feature of the car body under the condition of real-time riding feature,/>To the occurrence probability of real-time riding characteristics under the condition of referencing the loss characteristics of the vehicle body, and
Num (label) is the number of label samples in the feature database, p (label) is the occurrence probability of the reference vehicle body loss feature in the feature database,Is the probability of occurrence of the riding feature in real time.
Further, since the collected riding characteristics are independent of each other, then:
Wherein p (acc_bs_1 ') is the probability of occurrence of the first acceleration noise feature, p (acc_bs_2') is the probability of occurrence of the second acceleration noise feature, For the probability of occurrence of the mean velocity feature, P (P') is the probability of occurrence of the power feature,/>Num (data) is the number of corresponding feature samples in the feature database, p (acc_bs_2'),/>And/>The calculation process is the same as that of p (acc_bs_1'), and will not be described in detail.
Further, through real-time riding characteristics, a full probability formula and a characteristic database, the occurrence probability of each reference vehicle body loss characteristic under the condition of real-time riding characteristics is calculated, and the reference vehicle body loss characteristic corresponding to the maximum value of the occurrence probability is used as a final output result.
Further, when the final output target is larger than the set threshold, the user is warned and reminded.
In addition, the present invention also provides an apparatus for detecting bicycle loss, comprising:
the sensor is used for monitoring the movement of riding characteristics;
a display for displaying the riding characteristics;
And the processor is respectively in communication connection with the sensor and the display, is used for processing the real-time riding characteristics and displaying the processed real-time riding characteristics through the display, and simultaneously, the processor presets historical riding characteristics and vehicle body loss characteristics related to the historical riding characteristics, and compares and solves the historical riding characteristics with the real-time riding characteristics, and outputs and displays the vehicle body loss characteristics related to a final output result.
Further, the sensor includes an inertial measurer for acquiring a first acceleration characteristic and a power meter for acquiring a second acceleration characteristic, a speed characteristic, a torsion characteristic and a pedal frequency characteristic.
Further, the bicycle comprises a GPS module which is in communication connection with the processor and is used for acquiring the position characteristics of the bicycle, and the position characteristics are displayed through a display.
Further, the system also comprises an alarm module which is in communication connection with the processor, wherein a threshold value is preset in the processor, and when the final output result is larger than the set threshold value, the alarm module alarms and reminds the user.
Preferably, the display, the processor, the GPS module and the alarm module may be integrated inside the stopwatch.
The beneficial effects of the invention are as follows:
1. through sensor and processor cooperation, carry out rough location to bicycle trouble position, the location process does not involve the part and dismantles the operation, avoids investigation part one by one, improves bicycle loss detection efficiency.
2. On the premise of not depending on additional detection equipment, the riding characteristics are collected by using the sensor, the riding characteristics are analyzed by using the processor, the loss condition of the bicycle is calculated, and the fault early warning is carried out, so that the bicycle has the characteristics of low cost, non-invasiveness and easiness in maintenance.
3. The bicycle is characterized by riding feedback during riding to perform fault detection, early warning is performed in advance, the detection accuracy is high, and the purposes of predicting the quality of the bicycle body and finding the problem of the bicycle body in advance are achieved.
4. And the loss condition of the vehicle body is detected and estimated by utilizing the acceleration characteristic, the speed characteristic, the torsion characteristic, the pedal frequency characteristic and the power characteristic, so that the accuracy is improved.
5. Through real-time detection, the user can know the loss condition of the bicycle at the first time and maintain or repair in time.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic representation of clustering of different loss features in a feature space;
FIG. 3 is a schematic diagram showing the comparison of the predicted result of the test sample with the actual situation.
Detailed Description
In order to make the technical solution of the present application better understood by those skilled in the art, the technical solution of the present application will be clearly and completely described in the following with reference to the accompanying drawings, and based on the embodiments of the present application, other similar embodiments obtained by those skilled in the art without making any inventive effort should be included in the scope of protection of the present application. In addition, directional words such as "upper", "lower", "left", "right", and the like, as used in the following embodiments are merely directions with reference to the drawings, and thus, the directional words used are intended to illustrate, not to limit, the application.
Embodiment one:
as shown in fig. 1, a method for detecting bicycle wear, comprising the steps of:
step S100, acquiring historical riding characteristics and vehicle body loss characteristics associated with the historical riding characteristics in an off-line mode, and constructing a characteristic database, wherein the riding characteristics comprise speed characteristics, torsion characteristics, pedal frequency characteristics, first acceleration characteristics acquired by a first sensor and second acceleration characteristics acquired by a second sensor.
Historical riding characteristic collection is carried out by using test vehicles with known and different loss conditions, wherein the loss conditions are vehicle body loss characteristics.
The construction method of the characteristic database comprises the following steps:
Step S101, band elimination sampling is carried out on acceleration characteristics, and acceleration noise characteristics are obtained through calculation, wherein the acceleration characteristics comprise first acceleration characteristics and second acceleration characteristics, and the acceleration noise characteristics comprise first acceleration noise characteristics and second acceleration noise characteristics.
The method for calculating the acceleration noise characteristics comprises the following steps:
Where acc_bs is the acceleration noise characteristic, b is the molecular coefficient of the band-stop filter (here, the finite impulse response), acc is the acceleration characteristic, n is the order of the band-stop filter, k is the kth element of a convolution operation, and i is the ith element of the data column.
Step S102, acquiring speed characteristics, torsion characteristics and pedal frequency characteristics of the same time sequence as the first acceleration characteristics and the second acceleration characteristics, calculating power characteristics, and constructing a characteristic database.
The power characteristic calculating method comprises the following steps:
Where l is moment, fre is pedaling frequency, f is torsion of the same time sequence, n is the order of band elimination filtering, k is the kth element of one convolution operation, and i is the ith element of the data column.
In the characteristic acquisition time domain, the acceleration noise characteristic and the power characteristic are obtained through integral calculation, and the speed characteristic, the torsion characteristic and the pedal frequency characteristic are all average values in the characteristic acquisition time domain.
The feature combination storage format of the feature database is as follows:
Wherein acc_bs_1 is the first acceleration noise feature, acc_bs_2 is the second acceleration noise feature,/> For the average value speed characteristic, P is the power characteristic, label is the vehicle body loss characteristic labeling value, n is the order of band elimination filtering, and i is the ith element of the data column. In the feature database, the loss features of the vehicle body are marked by 1-N to form label, and when the algorithm runs, the label is converted into one-hot codes.
As shown in fig. 2, the x-axis represents the power characteristic, y represents the first acceleration noise characteristic (i.e., acc_1 band-stop characteristic), and the z-axis represents the second acceleration noise characteristic (i.e., acc_2 band-stop characteristic). Wherein loss 1 represents the first loss feature, indicated by o in the figure. Loss 2 represents a second loss feature, denoted by o. Loss 3 represents a third loss feature, represented by x. Loss 4 represents a fourth loss feature, denoted by v in the figure. The riding characteristics of bicycles with different wear characteristics are represented by different markers. As can be seen directly from fig. 2: the riding characteristics and the loss characteristics have obvious classification boundaries in the characteristic space, so that the detection and prediction of the loss condition of the vehicle body by utilizing the acceleration characteristics, the speed characteristics, the torsion characteristics, the pedal frequency characteristics and the power characteristics are further explained, and the method belongs to a reasonable method and provides a basis for the characteristic classification of the method.
Step S200, collecting real-time riding characteristics, comparing the historical riding characteristics with the real-time riding characteristics in similarity, taking the maximum value of the similarity as a similarity output target, obtaining a reference vehicle body loss condition, calculating the occurrence probability of the reference vehicle body loss condition under the condition of the real-time riding characteristics, and taking the maximum value of the occurrence probability as a final output target.
Firstly, the real-time riding characteristic acquisition method comprises the following steps:
Collecting a first acceleration characteristic and a second acceleration characteristic, respectively buffering the first acceleration characteristic and the second acceleration characteristic to a set acc_1 'and acc_2', when the number of elements in the set reaches n (where n is synonymous with the above), performing band-stop sampling to obtain a band-stop set acc_bs_1 'and acc_bs_2', respectively calculating the frequency band with the maximum mean value, medium error and amplitude of the band-stop set, simultaneously, collecting the speed characteristic of the same time sequence to form a speed set (composed of n elements where n is synonymous with the above), calculating the mean value and recording as The torque characteristic and the pedal frequency characteristic of the same time sequence are collected, and the power characteristic is calculated and recorded as P'.
Secondly, similarity comparison is carried out by utilizing a Gaussian kernel function, and the method comprises the following steps:
Wherein similarity is similarity, fea realtime is a real-time riding characteristic after processing, fea database is a historical riding characteristic in a characteristic database, sigma is a middle error of a corresponding characteristic, and a gaussian kernel function is a two-norm/variance of two characteristics and is calculated as an e index after being taken as a negative, so that the calculation process of the formula is as follows:
j is the j-th feature combination in the feature database, Δfea j is the deviation of the real-time feature vector from the corresponding offline feature,/> Is the transpose of Δfea j. And taking the maximum similarity as a similarity output target, wherein the vehicle body loss condition associated with the maximum similarity is the reference vehicle body loss condition label'.
Finally, substituting the real-time riding characteristics into a Bayesian full probability formula, and calculating the occurrence probability of the reference vehicle body loss condition under the condition of the real-time riding characteristics:
wherein, To refer to the occurrence probability of the loss feature of the vehicle body under the condition of real-time riding features, and simultaneously,/>The target is output for the degree of similarity,To refer to the probability of occurrence of a real-time riding feature with reference to a body loss feature,
And is also provided withNum (label) is the number of label samples in the feature database, p (label) is the occurrence probability of the reference vehicle body loss feature in the feature database,/>Is the probability of occurrence of the riding feature in real time. Since the acquired riding characteristics are independent of each other,
Then: Wherein p (acc_bs_1 ') is the probability of occurrence of the first acceleration noise feature, p (acc_bs_2') is the probability of occurrence of the second acceleration noise feature,/> For the probability of occurrence of the mean velocity feature, P (P') is the probability of occurrence of the power feature,Num (data) is the number of corresponding feature samples in the feature database, p (acc_bs_2'),/>And/>The calculation process is the same as that of p (acc_bs_1'), and will not be described in detail.
That is, the occurrence probability of each reference vehicle body loss feature under the real-time riding feature condition is calculated through the real-time riding feature, the full probability formula and the feature database, and the reference vehicle body loss feature corresponding to the maximum value of the occurrence probability is used as a final output result. And when the final output target is larger than the set threshold, alarming and reminding the user.
In summary, the method for detecting bicycle wear is divided into an offline stage and an online stage, wherein the offline stage is used for collecting riding characteristics and wear characteristics of various worn bicycle bodies and constructing a characteristic database, the process does not need user operation, the user can only call, the online stage is a stage for identifying a state in real time, the user is not aware of the wear condition of the bicycle, and the process mainly uses the riding characteristics collected in real time to detect the wear condition of the tested bicycle bodies. That is, under the premise of not depending on additional detection equipment, the sensor is utilized to collect riding characteristics, the processor is utilized to analyze the riding characteristics, the sensor and the processor are matched to roughly locate the fault part of the bicycle, fault early warning is carried out, the part disassembly operation is not involved in the locating process, parts are prevented from being checked one by one, the loss detection efficiency of the bicycle is improved, and the bicycle has the characteristics of low cost, non-invasiveness and easiness in maintenance.
200 Test samples were taken for each of the 4 different loss conditions of the bicycle shown in fig. 2, and a comparison diagram of the predicted result of the method with the actual condition was adopted, as shown in fig. 3. By calculation, the prediction accuracy of loss 1 (representing the first loss feature) was 100%, the prediction accuracy of loss 2 (representing the second loss feature) was 95%, the prediction accuracy of loss 3 (representing the third loss feature) was 90%, and the prediction accuracy of loss 4 (representing the fourth loss feature) was 95%. That is, the loss condition of the bicycle body is detected and estimated by utilizing the acceleration characteristic, the speed characteristic, the torsion characteristic, the pedal frequency characteristic and the power characteristic, the accuracy is high, a user can know the loss condition of the bicycle at the first time, early warning is carried out in advance, and the bicycle is maintained or maintained in time.
Embodiment two:
The utility model provides a device for detecting bicycle loss, includes the sensor that is used for riding the characteristic and carries out motion monitoring, is used for showing the display and the treater of riding the characteristic, wherein, the treater respectively with sensor, display communication are connected for handle real-time characteristic of riding to the characteristic of riding after will handling shows through the display, simultaneously, the treater presets the historical characteristic of riding and the automobile body loss characteristic that is correlated with the characteristic of riding of history, and the treater compares the characteristic of riding of history and the characteristic of riding in real time and calculates, exports and shows the automobile body loss characteristic that is correlated with final output.
The bicycle comprises a bicycle body, a processor, a GPS module, a display and a control module, wherein the GPS module is in communication connection with the processor and is used for acquiring the position characteristics of the bicycle, and the position characteristics are displayed through the display. In other embodiments, the system further comprises an alarm module in communication connection with the processor, wherein a threshold value is preset in the processor, and when the final output result is greater than the set threshold value, the alarm module alarms and reminds the user.
Preferably, the sensor comprises an inertial measurer for acquiring a first acceleration characteristic and a power meter for acquiring a second acceleration characteristic, a speed characteristic, a torsion characteristic and a pedal frequency characteristic. The display, processor, GPS module and alarm module may be integrated inside the stopwatch.
The foregoing detailed description of the application has been presented for purposes of illustration and description, but is not intended to limit the scope of the application, i.e., the application is not limited to the details shown and described.
Claims (5)
1. A method for detecting bicycle wear, comprising the steps of:
Step S100, collecting historical riding characteristics and vehicle body loss characteristics associated with the historical riding characteristics in an off-line manner, and constructing a characteristic database;
the riding characteristics comprise a speed characteristic, a torsion characteristic, a pedal frequency characteristic, a first acceleration characteristic obtained by a first sensor and a second acceleration characteristic obtained by a second sensor;
The construction method of the characteristic database comprises the following steps:
Step S101, carrying out band elimination sampling on acceleration characteristics to obtain acceleration noise characteristics through calculation, wherein the acceleration characteristics comprise first acceleration characteristics and second acceleration characteristics, and the acceleration noise characteristics comprise first acceleration noise characteristics and second acceleration noise characteristics;
the method for calculating the acceleration noise characteristics comprises the following steps:
Wherein acc_bs is the acceleration noise characteristic, b is the molecular coefficient of the band-stop filter, acc is the acceleration characteristic, n is the order of the band-stop filter, k is the kth element of one convolution operation, and i is the ith element of the data column;
step S102, acquiring speed characteristics, torsion characteristics and pedal frequency characteristics of the same time sequence as the first acceleration characteristics and the second acceleration characteristics, calculating power characteristics, and constructing a characteristic database;
The power characteristic calculating method comprises the following steps:
Wherein l is moment, fre is pedaling frequency, f is torsion of the same time sequence, n is the order of band elimination filtering, k is the kth element of one convolution operation, and i is the ith element of a data column;
The feature combination storage format of the feature database is as follows:
Wherein acc_bs_1 is the first acceleration noise feature, acc_bs_2 is the second acceleration noise feature,/> For the average value speed characteristic, P is the power characteristic, label is the vehicle body loss characteristic labeling value, n is the order of band elimination filtering, i is the ith element of the data column;
Step S200, collecting real-time riding characteristics, comparing the historical riding characteristics with the real-time riding characteristics in similarity, taking the maximum value of the similarity as a similarity output target, obtaining a reference vehicle body loss condition, calculating the occurrence probability of the reference vehicle body loss condition under the condition of the real-time riding characteristics, and taking the maximum value of the occurrence probability as a final output target.
2. The method for detecting bicycle loss according to claim 1, wherein in step S200, similarity comparison is performed by using a gaussian kernel function, a similarity maximum value is used as a similarity output target, a vehicle body loss condition associated with the similarity maximum value is used as a reference vehicle body loss condition, a real-time riding characteristic is substituted into a bayesian full probability formula, occurrence probability of the reference vehicle body loss condition in the case of the real-time riding characteristic is calculated, and a reference vehicle body loss characteristic corresponding to the occurrence probability maximum value is used as a final output result.
3. An apparatus for detecting bicycle loss using the method for detecting bicycle loss as claimed in claim 1 or 2, comprising:
the sensor is used for monitoring the movement of riding characteristics;
a display for displaying the riding characteristics;
And the processor is respectively in communication connection with the sensor and the display, is used for processing the real-time riding characteristics and displaying the processed real-time riding characteristics through the display, and simultaneously, the processor presets historical riding characteristics and vehicle body loss characteristics related to the historical riding characteristics, and compares and solves the historical riding characteristics with the real-time riding characteristics, and outputs and displays the vehicle body loss characteristics related to a final output result.
4. A device for detecting bicycle wear as in claim 3 further including a GPS module in communication with the processor for acquiring a position characteristic of the bicycle and wherein the position characteristic is displayed by the display.
5. The apparatus for detecting bicycle wear according to claim 4, further comprising an alarm module communicatively coupled to the processor, wherein the processor has a predetermined threshold, and wherein the alarm module alerts the user when the final output is greater than the predetermined threshold.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111126944.XA CN113865885B (en) | 2021-09-26 | 2021-09-26 | Method and device for detecting bicycle loss |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111126944.XA CN113865885B (en) | 2021-09-26 | 2021-09-26 | Method and device for detecting bicycle loss |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113865885A CN113865885A (en) | 2021-12-31 |
CN113865885B true CN113865885B (en) | 2024-04-26 |
Family
ID=78994254
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111126944.XA Active CN113865885B (en) | 2021-09-26 | 2021-09-26 | Method and device for detecting bicycle loss |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113865885B (en) |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101633379A (en) * | 2008-07-24 | 2010-01-27 | 久鼎金属实业股份有限公司 | Method for detecting failure of electric boosting bicycle |
DE102011077181A1 (en) * | 2011-06-08 | 2012-12-13 | Robert Bosch Gmbh | Method and device for detecting wear on an electric bicycle |
CN103018058A (en) * | 2012-12-17 | 2013-04-03 | 北京交通大学 | Similarity-based fault isolation method of train suspension system |
CN106585800A (en) * | 2016-12-19 | 2017-04-26 | 北京拜克洛克科技有限公司 | Smart bike fault detection method, device and system and smart bike |
JP2018188115A (en) * | 2017-04-28 | 2018-11-29 | 健次 白井 | Bicycle alarm device |
CN109374048A (en) * | 2018-10-25 | 2019-02-22 | 安徽信息工程学院 | A kind of electric vehicle loss detection system and its control method |
CN111077886A (en) * | 2019-12-31 | 2020-04-28 | 上海申铁信息工程有限公司 | Station fault real-time monitoring system |
JP2020104817A (en) * | 2018-12-28 | 2020-07-09 | パナソニックIpマネジメント株式会社 | Failure detection device, electric bicycle and failure detection method |
CN111881980A (en) * | 2020-07-29 | 2020-11-03 | 上海钧正网络科技有限公司 | Vehicle fault detection method and device, computer equipment and storage medium |
JP2020183767A (en) * | 2019-04-26 | 2020-11-12 | 株式会社東芝 | Abrasion prediction device, abrasion prediction method and computer program |
CN111982540A (en) * | 2020-09-17 | 2020-11-24 | 东阳坎层电子科技有限公司 | Detection board device capable of automatically detecting bicycle faults |
WO2020233428A1 (en) * | 2019-05-17 | 2020-11-26 | 深圳市德塔防爆电动汽车有限公司 | Safety failure risk prediction method for electric vehicle, and electric vehicle |
CN113344118A (en) * | 2021-06-28 | 2021-09-03 | 南京大学 | Bicycle gray fault detection system and detection method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102169791B1 (en) * | 2018-11-19 | 2020-10-26 | 주식회사 글로비즈 | Railway vehicle major component and system diagnosis apparatus |
-
2021
- 2021-09-26 CN CN202111126944.XA patent/CN113865885B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101633379A (en) * | 2008-07-24 | 2010-01-27 | 久鼎金属实业股份有限公司 | Method for detecting failure of electric boosting bicycle |
DE102011077181A1 (en) * | 2011-06-08 | 2012-12-13 | Robert Bosch Gmbh | Method and device for detecting wear on an electric bicycle |
CN103018058A (en) * | 2012-12-17 | 2013-04-03 | 北京交通大学 | Similarity-based fault isolation method of train suspension system |
CN106585800A (en) * | 2016-12-19 | 2017-04-26 | 北京拜克洛克科技有限公司 | Smart bike fault detection method, device and system and smart bike |
JP2018188115A (en) * | 2017-04-28 | 2018-11-29 | 健次 白井 | Bicycle alarm device |
CN109374048A (en) * | 2018-10-25 | 2019-02-22 | 安徽信息工程学院 | A kind of electric vehicle loss detection system and its control method |
JP2020104817A (en) * | 2018-12-28 | 2020-07-09 | パナソニックIpマネジメント株式会社 | Failure detection device, electric bicycle and failure detection method |
JP2020183767A (en) * | 2019-04-26 | 2020-11-12 | 株式会社東芝 | Abrasion prediction device, abrasion prediction method and computer program |
WO2020233428A1 (en) * | 2019-05-17 | 2020-11-26 | 深圳市德塔防爆电动汽车有限公司 | Safety failure risk prediction method for electric vehicle, and electric vehicle |
CN111077886A (en) * | 2019-12-31 | 2020-04-28 | 上海申铁信息工程有限公司 | Station fault real-time monitoring system |
CN111881980A (en) * | 2020-07-29 | 2020-11-03 | 上海钧正网络科技有限公司 | Vehicle fault detection method and device, computer equipment and storage medium |
CN111982540A (en) * | 2020-09-17 | 2020-11-24 | 东阳坎层电子科技有限公司 | Detection board device capable of automatically detecting bicycle faults |
CN113344118A (en) * | 2021-06-28 | 2021-09-03 | 南京大学 | Bicycle gray fault detection system and detection method |
Also Published As
Publication number | Publication date |
---|---|
CN113865885A (en) | 2021-12-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112766182B (en) | Broaching tool wear state identification method | |
CN113485302B (en) | Vehicle operation process fault diagnosis method and system based on multivariate time sequence data | |
CN104386449A (en) | Intelligent protection device for online detection of head/tail wheels of mining belt conveyor | |
CN108710637B (en) | Real-time detection method for abnormal taxi track based on space-time relationship | |
CN113878214B (en) | Welding quality real-time detection method and system based on LSTM and residual distribution | |
CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
CN104807640A (en) | Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics | |
CN111776006B (en) | Pre-alarming method and device for train axle temperature | |
CN106405384A (en) | Simulation circuit health state evaluation method | |
CN112464951A (en) | Fishery safety emergency disposal system and method based on Internet of things | |
Liu et al. | Active incremental learning for health state assessment of dynamic systems with unknown scenarios | |
CN108280424A (en) | A kind of rolling bearing method for predicting residual useful life based on sparse coding | |
CN110243598B (en) | Train bearing temperature processing method and device and storage medium | |
CN113865885B (en) | Method and device for detecting bicycle loss | |
CN112129290A (en) | System and method for monitoring riding equipment | |
CN113314142A (en) | Engine fault detection method, system, storage medium and equipment | |
CN105910806A (en) | Filling pump early health status monitoring method | |
CN111717210B (en) | Detection method for separation of driver from steering wheel in relative static state of hands | |
CN116644278A (en) | Sample screening and feature extraction-based dual-model bearing anomaly detection algorithm | |
CN113160549B (en) | System and method for automatically identifying vehicle accident | |
CN113609964A (en) | Motor abnormal vibration early warning method and system | |
CN106841859A (en) | The electric energy quality monitoring method for early warning and system of feature based data Optimum Matching | |
CN113400309A (en) | Motion state identification method of upper limb assistance exoskeleton robot | |
CN115556099B (en) | Sustainable learning industrial robot fault diagnosis system and method | |
CN115356133A (en) | Bogie operation condition on-line monitoring, real-time classification and identification algorithm |
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 |