CN112320520A - Elevator abnormal vibration detection method based on residual error analysis - Google Patents
Elevator abnormal vibration detection method based on residual error analysis Download PDFInfo
- Publication number
- CN112320520A CN112320520A CN202011236543.5A CN202011236543A CN112320520A CN 112320520 A CN112320520 A CN 112320520A CN 202011236543 A CN202011236543 A CN 202011236543A CN 112320520 A CN112320520 A CN 112320520A
- Authority
- CN
- China
- Prior art keywords
- vibration
- peak
- abnormal
- value
- acceleration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
Landscapes
- Indicating And Signalling Devices For Elevators (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to an elevator abnormal vibration detection method based on residual error analysis, which comprises the following steps: a. acquiring acceleration data of elevator operation, performing residual decomposition, and calculating the peak-to-peak value of a decomposed residual sequence; b. detecting abnormal values in the peak-to-peak values, and enabling the abnormal values to form a vibration segment in a corresponding abnormal segment in the residual sequence in a combining mode; c. and analyzing the vibration attribute of the vibration section, and carrying out stage division on the acceleration to determine the vibration generation stage. The method can acquire more vibration related data including vibration duration, vibration intensity and vibration generation stage.
Description
Technical Field
The invention relates to an elevator abnormal vibration detection method based on residual error analysis.
Background
With the increase of the elevator keeping amount year by year, the elevator safety problem is more and more emphasized by people, vibration is one of common elevator faults, slight vibration makes people feel uncomfortable, and serious vibration can even shake people down in the elevator to influence the safety of passengers. Accurate real-time detection, timely maintenance to elevator vibration can avoid more serious incident to take place on the one hand, and on the other hand also can promote resident's the comfort of taking, have important meaning.
Patent CN107381271A discloses an intelligent elevator exception handling method and device based on the internet of things, which receive acceleration data acquired by an acceleration sensor through an internet of things server, and then judge whether the corresponding operation is an abnormal condition based on a preset acceleration threshold, wherein the method directly judges by the original acceleration, on one hand, the influence of the larger acceleration on the abnormal vibration in the acceleration and deceleration stage is not considered, and on the other hand, the stage information of the acceleration can not be given; patent CN110550518A discloses a sparse denoising self-coding-based elevator operation anomaly detection method, which first obtains time domain waveforms and frequency domain waveforms of normal and abnormal vibration of an elevator; and then, learning and training the samples by adopting single-layer sparse denoising self-coding, stacked sparse denoising self-coding and BP algorithm, wherein the method is complex, and needs prior knowledge to collect normal and abnormal acceleration samples when detecting abnormality, the steps are complex, and the abnormal samples which are not collected are difficult to identify.
Disclosure of Invention
The invention aims to provide an elevator abnormal vibration detection method based on residual error analysis, so that more vibration related data can be obtained.
In order to achieve the aim, the invention provides an elevator abnormal vibration detection method based on residual error analysis, which comprises the following steps of:
a. acquiring acceleration data of elevator operation, performing residual decomposition, and calculating the peak-to-peak value of a decomposed residual sequence;
b. detecting abnormal values in the peak-to-peak values, and enabling the abnormal values to form a vibration segment in a corresponding abnormal segment in the residual sequence in a combining mode;
c. and analyzing the vibration attribute of the vibration section, and carrying out stage division on the acceleration to determine the vibration generation stage.
According to one aspect of the present invention, the residual decomposition in step (a) includes filtering the originally collected acceleration sequence to obtain a smooth sequence;
and then subtracting the smooth sequence from the original acceleration sequence to obtain a residual sequence.
According to one aspect of the present invention, in the step (a), the peak-to-peak value is stored in the form of:
[(s1,e1,v1),(s2,e2,v2),(s3,e3,v3),…,(sn,en,vn)]；
wherein, the v value is a peak-to-peak value, s refers to the starting time of the section corresponding to the peak-to-peak value, and e refers to the ending time of the section corresponding to the peak-to-peak value.
According to an aspect of the present invention, in the step (b), an abnormal value is detected by a combination of a fixed threshold method and a boxplot method, and a value of the peak-to-peak value that is equal to or higher than a first threshold value is determined as the abnormal value, the first threshold value being:
Max(thre1,Q3+thre2*IQR)；
in the formula, thre1 is a fixed peak-to-peak value threshold, thre2 is a boxplot coefficient, Q3 is a median value between the median and the maximum value in the peak-to-peak value sequence, and IQR is a quartile distance.
According to an aspect of the present invention, in the step (b), the abnormal sections having a time interval smaller than a second threshold value, which is 0.1s, are combined to obtain the vibration section.
According to an aspect of the present invention, in the step (c), the vibration attributes include a vibration duration and a vibration intensity;
the vibration duration is the duration of the vibration section, and the vibration intensity is the maximum value of the peak-to-peak value in the vibration section.
According to an aspect of the present invention, in the step (c), for the filtered acceleration sequence, calculating a time period continuously greater than or less than a third threshold value, and determining whether the average value of absolute values of acceleration and the time length in the time period are greater than a fourth threshold value and a fifth threshold value, respectively;
the third threshold value is 0.05m/s2The fourth threshold value is 0.3m/s2And the fifth threshold is 2 s.
According to an aspect of the present invention, the acceleration stage start time t1, the acceleration stage start time t2, the deceleration stage start time t3, the deceleration stage end time t4 of the period in which the acceleration is continuously greater than or less than the third threshold value are determined;
assuming that the vibration starting time is s, the relation between s and t1-t4 and the vibration generation stage are as follows:
s belongs to [ t1, t2], and the vibration is in an acceleration stage;
s belongs to [ t3, t4], and vibrates in a deceleration stage;
s belongs to [ t2, t3], and vibrates in a constant speed stage;
s belongs to < -, t1 >, and the vibration is carried out before the acceleration stage;
s belongs to [ t4, - ], and vibrates after the deceleration stage;
if the staging fails, the stage is marked as other stage vibration.
According to one aspect of the invention, the filtering is a moving average or a moving median.
Elevator abnormal vibration detecting system based on residual analysis includes:
the acceleration acquisition module is used for acquiring the running acceleration data of the elevator in real time;
the residual error analysis module comprises a residual error decomposition unit for performing residual error decomposition on the elevator running acceleration data and a peak-to-peak value calculation unit for calculating a peak-to-peak value of the decomposed residual error;
the vibration identification module comprises an abnormal value detection unit for detecting abnormal values in the peak-to-peak value sequence and an abnormal region generation unit for combining the abnormal sections to generate vibration sections;
and the vibration post-analysis module comprises a vibration attribute calculation unit for calculating the vibration duration and the vibration intensity of the vibration section and a vibration stage analysis unit for performing stage division and determining the vibration generation stage.
According to the scheme of the invention, residual error analysis is carried out on the acceleration data acquired in real time to obtain the peak-to-peak value. Outliers in the peak-to-peak values are identified, and then segments corresponding to the outliers are merged to form a vibration segment. And analyzing the vibration attribute of the vibration section to obtain the vibration duration and the vibration intensity, and finally analyzing the position of the vibration section in the operation process to obtain the vibration generation stage.
According to one scheme of the invention, the calculation of the subsequent peak value is mainly based on a residual sequence obtained by subtracting the smooth sequence from the acceleration sequence, so that the influence of the acceleration and deceleration stage on residual identification can be eliminated. In addition, the residual error of the real vibration area is still large, and great convenience can be provided for subsequent vibration identification.
According to one scheme of the invention, the abnormal value in the peak value is detected by combining a fixed threshold value method and a box curve method, and particularly, the maximum threshold value is selected from the threshold values set by the two methods to be used as the first threshold value. Therefore, fluctuation abnormal conditions caused by device faults can be eliminated, and the set first threshold value can be ensured to reach the degree which can be perceived by a human body.
According to an aspect of the invention, the acceleration and deceleration phases may be determined by analyzing whether the acceleration is continuously greater than the third threshold. By analyzing whether the acceleration average value and the time length are respectively larger than the fourth threshold and the fifth threshold, the acceleration and deceleration stage with identification errors caused by small fluctuation can be eliminated.
Drawings
FIG. 1 is a flow chart schematically illustrating a detection method according to one embodiment of the present invention;
FIG. 2 is a diagram schematically representing a sequence of raw accelerations in accordance with the present invention;
FIG. 3 is a schematic representation of a smoothing sequence diagram according to the present invention;
FIG. 4 is a schematic representation of a residual sequence diagram according to the present invention;
FIG. 5 is a diagram of a sample peak-to-peak calculation;
fig. 6 is a schematic representation of the phase division according to the invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
The present invention is described in detail below with reference to the drawings and the specific embodiments, which are not repeated herein, but the embodiments of the present invention are not limited to the following embodiments.
Referring to fig. 1, according to the concept of the present invention, elevator operation acceleration data collected in real time is analyzed based on residual analysis to obtain an abnormal value position. And combining the abnormal sections (namely the sections corresponding to the abnormal values) to obtain vibration sections (or called vibration time periods), finally analyzing the vibration properties of the vibration sections, and combining the stage division results to obtain the stage of abnormal vibration. Therefore, the scheme of the invention can obtain the stage of abnormal vibration, and does not need to establish a complex detection network, thereby realizing more convenient implementation. The system for implementing the method comprises an acceleration acquisition module, a residual error analysis module, a vibration identification module and a post-vibration analysis module.
In the invention, the acceleration acquisition module acquires the elevator running acceleration data received by the elevator acceleration sensor in real time, and then residual error analysis can be carried out on the acceleration data. The residual analysis comprises residual decomposition and peak-to-peak calculation, which are respectively completed by two sub-units in the residual analysis module, namely a residual decomposition unit and a peak-to-peak calculation unit. The object of residual decomposition is the originally acquired acceleration (data) sequence, as shown in fig. 2. Firstly, filtering an original acceleration sequence to obtain a smooth sequence, thereby eliminating the influence of micro fluctuation on vibration identification. There are many filtering methods, and the filtering method in this embodiment is performed by using a moving (moving) average method, but of course, a filtering method with a good effect such as a moving median may be used. Specifically, the original acceleration sequence is slid according to a fixed window to perform a moving average operation, so that a smooth sequence (or called moving average sequence) can be obtained, as shown in fig. 3. The fixed window is actually an interval containing a plurality of adjacent running processes of the elevator, and the number of the running processes contained in the window is unchanged in the sliding process (namely, the fixed window). Then, the original acceleration sequence is subtracted by the smoothed sequence, so as to obtain a residual sequence, as shown in fig. 4. The main meaning of residual decomposition is that the influence of acceleration and deceleration stages can be removed. After residual decomposition, the influence of acceleration and deceleration stages is eliminated, and the residual of a real vibration area is still large, so that great convenience is provided for subsequent vibration identification. The peak-to-peak value calculation is the fluctuation amplitude of each zero-crossing point time period of the residual sequence, and can be calculated by using the existing method, for example, the peak-to-peak value can be calculated and obtained in the manner of the vibration peak-to-peak value in GB/T24474-. In the present invention, the calculated peak-to-peak value is stored in the form of:
[(s1,e1,v1),(s2,e2,v2),(s3,e3,v3),…,(sn,en,vn)]；
wherein, v is peak-to-peak value, s is the start time of the segment corresponding to the peak-to-peak value, and e is the end time of the segment corresponding to the peak-to-peak value.
The peak-to-peak value sequence can be obtained through the process, and then the abnormal peak-to-peak value in the sequence can be detected by the vibration identification module, wherein the peak-to-peak values are abnormal values. The step is also completed by two sub-units in the vibration identification module, namely an abnormal value detection unit and an abnormal area generation unit. In the invention, an abnormal value detection unit detects an abnormal value by combining a fixed threshold value method and a box curve method. Specifically, it is determined that a point in the peak-to-peak sequence that is greater than or equal to a first threshold is an abnormal value, and the first threshold is the maximum value in the fixed threshold method and the box plot method, that is:
Max(thre1,Q3+thre2*IQR)；
where thre1 is a fixed peak-to-peak threshold,also called absolute threshold, and can take on a value of 0.5m/s2Thus, the degree of human perception can be achieved; thre2 is a boxplot coefficient, for a conventional boxplot 1.5, the invention takes 2.0, so that a more abnormal value can be obtained; q3 is the median between the median and maximum in the peak-to-peak sequence; IQR is the interquartile distance, i.e., the distance from the 25 th to the 75 th percentile. Therefore, the abnormal value is sensed by using the box line graph, so that the condition that the fluctuation is increased due to the fault of the sensor is eliminated, and the threshold can be ensured to reach the human body sensing degree by combining the set fixed threshold.
In the above detection process, when the abnormal value detection means detects an abnormal (large) peak-to-peak value, the data is input to the abnormal region generation means, and the vibration segment is generated by the abnormal region generation means. Specifically, the abnormal segments (also generated by the unit) corresponding to the peak-to-peak values of the abnormality with a small time interval (i.e., smaller than the second threshold) are combined, so as to obtain the vibration segment. According to the above-mentioned peak-to-peak saving mode, if (s1, e1, v1) and (s3, e3, v3) are detected as abnormal peak-to-peak values and s3 and e1 are closer in time interval, then combination can be performed to obtain a vibration period of (s1, e 3). The second threshold value for judging whether the abnormal sections can be merged is 0.1 s.
And then, the vibration section can be analyzed, and the step is completed by two subunits of the post-vibration analysis module, namely a vibration attribute calculation unit and a vibration stage analysis unit. The vibration attribute calculated by the vibration attribute calculation unit includes a vibration duration, which is a duration of the vibration section. The larger the vibration intensity is, the more intense the vibration is, and the stronger the feeling of vibration felt by the passenger is. It is therefore also necessary to analyze the vibration intensity, which is the maximum value of the peak-to-peak value in the vibration section in the present invention.
The acceleration phase is then divided by a vibration phase analysis unit, the main purpose being to obtain the phase at which the vibration occurs. The method comprises the steps of firstly, carrying out stage division on the acceleration to obtain key time points of each stage, and then comparing the time of a vibration interval with the key time points of each stage to obtain the stage of vibration generation. In particular, according to moving averagesThe subsequent acceleration sequence calculates the time period continuously greater or less than the third threshold value, so that the acceleration phase and the deceleration phase can be known. In order to eliminate the acceleration and deceleration stage caused by the identification error due to the tiny fluctuation, in the invention, the third threshold value needs to be more than 0m/s2Slightly larger, specifically 0.05m/s2. If the average acceleration value is too small or the duration is too short, the vibration is considered to be minute vibration, and this should be removed. Therefore, the present invention also determines whether the average value of the absolute values of the accelerations and the time length in the obtained time periods (i.e., the time periods greater than or less than the third threshold value) are greater than the fourth threshold value and the fifth threshold value, respectively. In the present invention, the fourth threshold is 0.3m/s2And the fifth threshold is 2 s. Thus, the influence caused by the tiny fluctuation can be eliminated to the maximum extent. The acceleration phase start time t1, acceleration phase start time t2, deceleration phase start time t3, and deceleration phase end time t4 of the above-described period are then determined. Assuming that the vibration starting time is s, the relationship between s and t1-t4 and the vibration generation stage correspond to:
s belongs to [ t1, t2], and the vibration is in an acceleration stage;
s belongs to [ t3, t4], and vibrates in a deceleration stage;
s belongs to [ t2, t3], and vibrates in a constant speed stage;
s belongs to < -, t1 >, and the vibration is carried out before the acceleration stage;
s belongs to [ t4, - ], and vibrates after the deceleration stage;
if the four time points are not obtained, it is proved that the acquired data or the uploaded data in the stage are failed, and the stage division is failed. At this time, it should be marked as "other stage vibration". Therefore, the vibration reason can be better analyzed in the vibration generation stage, and the vibration problem is conveniently solved.
The above description is only one embodiment of the present invention, and is not intended to limit the present invention, and it is apparent to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An elevator abnormal vibration detection method based on residual error analysis comprises the following steps:
a. acquiring acceleration data of elevator operation, performing residual decomposition, and calculating the peak-to-peak value of a decomposed residual sequence;
b. detecting abnormal values in the peak-to-peak values, and enabling the abnormal values to form a vibration segment in a corresponding abnormal segment in the residual sequence in a combining mode;
c. and analyzing the vibration attribute of the vibration section, and carrying out stage division on the acceleration to determine the vibration generation stage.
2. The method for detecting abnormal vibration of elevator based on residual error analysis according to claim 1, wherein the residual error decomposition in step (a) comprises filtering the originally collected acceleration sequence to obtain a smooth sequence;
and then subtracting the smooth sequence from the original acceleration sequence to obtain a residual sequence.
3. The residual analysis-based elevator abnormal vibration detection method according to claim 1, wherein in the step (a), the peak-to-peak value is stored in the form of:
[(s1,e1,v1),(s2,e2,v2),(s3,e3,v3),…,(sn,en,vn)]；
wherein, the v value is a peak-to-peak value, s refers to the starting time of the section corresponding to the peak-to-peak value, and e refers to the ending time of the section corresponding to the peak-to-peak value.
4. The method of claim 1, wherein the abnormal vibration of the elevator is detected by a combination of a fixed threshold method and a box plot method, and the abnormal value is determined to be a value above a first threshold value among peak-to-peak values, the first threshold value being:
Max(thre1,Q3+thre2*IQR)；
in the formula, thre1 is a fixed peak-to-peak value threshold, thre2 is a boxplot coefficient, Q3 is a median value between the median and the maximum value in the peak-to-peak value sequence, and IQR is a quartile distance.
5. The residual analysis-based elevator abnormal vibration detection method according to claim 1, wherein in the step (b), the abnormal sections having a time interval smaller than a second threshold value are combined to obtain the vibration section, and the second threshold value is 0.1 s.
6. The residual analysis-based elevator abnormal vibration detection method according to claim 5, wherein in the step (c), the vibration attributes include vibration duration and vibration intensity;
the vibration duration is the duration of the vibration section, and the vibration intensity is the maximum value of the peak-to-peak value in the vibration section.
7. The residual analysis-based elevator abnormal vibration detection method according to claim 2, wherein in the step (c), for the filtered acceleration sequence, a time period continuously greater than or less than a third threshold is calculated, and it is determined whether the average value of absolute values of acceleration and the length of time in the time period are greater than a fourth threshold and a fifth threshold, respectively;
the third threshold value is 0.05m/s2The fourth threshold value is 0.3m/s2And the fifth threshold is 2 s.
8. The residual analysis-based elevator abnormal vibration detection method according to claim 7, wherein the acceleration phase start time t1, the acceleration phase start time t2, the deceleration phase start time t3, the deceleration phase end time t4 of the period in which the acceleration is continuously greater than or less than the third threshold value are determined;
assuming that the vibration starting time is s, the relation between s and t1-t4 and the vibration generation stage are as follows:
s belongs to [ t1, t2], and the vibration is in an acceleration stage;
s belongs to [ t3, t4], and vibrates in a deceleration stage;
s belongs to [ t2, t3], and vibrates in a constant speed stage;
s∈[-,t1]vibrating before the acceleration stage;
s∈[t4,-]vibrating after the deceleration stage;
if the staging fails, the stage is marked as other stage vibration.
9. The method of claim 2, wherein the filtering is a moving average or a moving median.
10. A system for implementing the residual analysis-based elevator abnormal vibration detection method of any one of claims 1 to 9, comprising:
the acceleration acquisition module is used for acquiring the running acceleration data of the elevator in real time;
the residual error analysis module comprises a residual error decomposition unit for performing residual error decomposition on the elevator running acceleration data and a peak-to-peak value calculation unit for calculating a peak-to-peak value of the decomposed residual error;
the vibration identification module comprises an abnormal value detection unit for detecting abnormal values in the peak-to-peak value sequence and an abnormal region generation unit for combining the abnormal sections to generate vibration sections;
and the vibration post-analysis module comprises a vibration attribute calculation unit for calculating the vibration duration and the vibration intensity of the vibration section and a vibration stage analysis unit for performing stage division and determining the vibration generation stage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011236543.5A CN112320520B (en) | 2020-11-09 | 2020-11-09 | Elevator abnormal vibration detection method based on residual error analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011236543.5A CN112320520B (en) | 2020-11-09 | 2020-11-09 | Elevator abnormal vibration detection method based on residual error analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112320520A true CN112320520A (en) | 2021-02-05 |
| CN112320520B CN112320520B (en) | 2022-12-06 |
Family
ID=74316746
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011236543.5A Active CN112320520B (en) | 2020-11-09 | 2020-11-09 | Elevator abnormal vibration detection method based on residual error analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112320520B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113247730A (en) * | 2021-06-10 | 2021-08-13 | 浙江新再灵科技股份有限公司 | Elevator passenger screaming detection method and system based on multi-dimensional features |
| CN114715752A (en) * | 2022-06-08 | 2022-07-08 | 凯尔菱电（山东）电梯有限公司 | Abnormity detection method and system for elevator |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002362848A (en) * | 2001-04-04 | 2002-12-18 | Toshiba Elevator Co Ltd | Elevator control device |
| CN106199703A (en) * | 2016-08-26 | 2016-12-07 | 中国矿业大学 | A kind of microseism focus is automatically positioned and Reliability Synthesis evaluation methodology |
| CN106826394A (en) * | 2017-02-26 | 2017-06-13 | 邵阳学院 | Lathe main shaft diameter is to glitch detection method and device under machining state |
| CN108592853A (en) * | 2018-04-09 | 2018-09-28 | 中国铁道科学研究院 | Track plates arch upward position identifying method, device, storage medium and equipment |
| CN108584592A (en) * | 2018-05-11 | 2018-09-28 | 浙江工业大学 | A kind of shock of elevator car abnormity early warning method based on time series predicting model |
| CN108750856A (en) * | 2017-12-13 | 2018-11-06 | 浙江新再灵科技股份有限公司 | A kind of elevator platform detecting system and method based on vibration analysis |
| CN109019216A (en) * | 2018-09-27 | 2018-12-18 | 上海昶屹机电科技有限公司 | Elevator faults intelligent diagnosis system and method |
| CN109061474A (en) * | 2018-10-15 | 2018-12-21 | 株洲中车时代电气股份有限公司 | A kind of motor bearings trouble-shooter |
| CN109484937A (en) * | 2018-09-14 | 2019-03-19 | 温州大学 | A kind of enhancing of mine hoist state-detection is synchronous to extract transform method |
| CN109612729A (en) * | 2018-12-25 | 2019-04-12 | 天津金岸重工有限公司 | A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings |
| CN109839265A (en) * | 2019-03-28 | 2019-06-04 | 西安建筑科技大学 | It is a kind of based on the mechanical Rubbing faults diagnostic method of m ultiwavelet core-support vector regression |
| CN109896385A (en) * | 2019-03-08 | 2019-06-18 | 浙江新再灵科技股份有限公司 | A kind of speed processed offline method for the elevator that there is vibration in one section of operational process |
| CN110057610A (en) * | 2019-04-25 | 2019-07-26 | 上海联影医疗科技有限公司 | Vibration information determines method, apparatus, medical imaging equipment and storage medium |
-
2020
- 2020-11-09 CN CN202011236543.5A patent/CN112320520B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002362848A (en) * | 2001-04-04 | 2002-12-18 | Toshiba Elevator Co Ltd | Elevator control device |
| CN106199703A (en) * | 2016-08-26 | 2016-12-07 | 中国矿业大学 | A kind of microseism focus is automatically positioned and Reliability Synthesis evaluation methodology |
| CN106826394A (en) * | 2017-02-26 | 2017-06-13 | 邵阳学院 | Lathe main shaft diameter is to glitch detection method and device under machining state |
| CN108750856A (en) * | 2017-12-13 | 2018-11-06 | 浙江新再灵科技股份有限公司 | A kind of elevator platform detecting system and method based on vibration analysis |
| CN108592853A (en) * | 2018-04-09 | 2018-09-28 | 中国铁道科学研究院 | Track plates arch upward position identifying method, device, storage medium and equipment |
| CN108584592A (en) * | 2018-05-11 | 2018-09-28 | 浙江工业大学 | A kind of shock of elevator car abnormity early warning method based on time series predicting model |
| CN109484937A (en) * | 2018-09-14 | 2019-03-19 | 温州大学 | A kind of enhancing of mine hoist state-detection is synchronous to extract transform method |
| CN109019216A (en) * | 2018-09-27 | 2018-12-18 | 上海昶屹机电科技有限公司 | Elevator faults intelligent diagnosis system and method |
| CN109061474A (en) * | 2018-10-15 | 2018-12-21 | 株洲中车时代电气股份有限公司 | A kind of motor bearings trouble-shooter |
| CN109612729A (en) * | 2018-12-25 | 2019-04-12 | 天津金岸重工有限公司 | A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings |
| CN109896385A (en) * | 2019-03-08 | 2019-06-18 | 浙江新再灵科技股份有限公司 | A kind of speed processed offline method for the elevator that there is vibration in one section of operational process |
| CN109839265A (en) * | 2019-03-28 | 2019-06-04 | 西安建筑科技大学 | It is a kind of based on the mechanical Rubbing faults diagnostic method of m ultiwavelet core-support vector regression |
| CN110057610A (en) * | 2019-04-25 | 2019-07-26 | 上海联影医疗科技有限公司 | Vibration information determines method, apparatus, medical imaging equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 田原嫄: "基于振动信号残差法的齿轮故障诊断分析与仿真", 《组合机床与自动化加工技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113247730A (en) * | 2021-06-10 | 2021-08-13 | 浙江新再灵科技股份有限公司 | Elevator passenger screaming detection method and system based on multi-dimensional features |
| CN113247730B (en) * | 2021-06-10 | 2022-11-08 | 浙江新再灵科技股份有限公司 | Elevator passenger screaming detection method and system based on multi-dimensional features |
| CN114715752A (en) * | 2022-06-08 | 2022-07-08 | 凯尔菱电（山东）电梯有限公司 | Abnormity detection method and system for elevator |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112320520B (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112320520B (en) | Elevator abnormal vibration detection method based on residual error analysis | |
| CN111353482B (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| JP7133315B2 (en) | Failure prediction system | |
| JP5783808B2 (en) | Abnormal sound diagnosis device | |
| CN107451004B (en) | Turnout fault diagnosis method based on qualitative trend analysis | |
| JP5148457B2 (en) | Abnormality determination apparatus, method, and program | |
| CN103565433B (en) | Method and device for improving fetal monitoring efficiency | |
| JP4928612B2 (en) | Method and apparatus for monitoring sensor noise | |
| JP6215944B2 (en) | Processing related to eyelid movement to detect drowsiness | |
| TW201350804A (en) | Abnormal sound diagnostic equipment | |
| CN111170103B (en) | Equipment fault identification method | |
| CN113343928A (en) | Method and device for detecting corrugation of high-speed railway steel rail on variable-speed road section and computer equipment | |
| Huang et al. | Multiple time-frequency curve extraction Matlab code and its application to automatic bearing fault diagnosis under time-varying speed conditions | |
| CN107563403B (en) | Working condition identification method for high-speed train operation | |
| JP2016050404A (en) | Abnormality detection method at support part of railway bridge | |
| EP3649568B1 (en) | Method for automatic detection of physical modes in a modal analysis model | |
| JP2008108250A (en) | Abnormality detection system for movable body and abnormality detection method for movable body | |
| CN105940608B (en) | Appraisal procedure for sensor signal | |
| US6199019B1 (en) | Unsteady signal analyzer and medium for recording unsteady signal analyzer program | |
| Mohammed et al. | Fault diagnosis of rotating machine based on audio signal recognition system: an efficient approach | |
| CN109919511B (en) | Existing railway line shape evaluation method and system | |
| CN107782548B (en) | Rail vehicle part detection system | |
| CN110613429A (en) | Motion sickness detection method | |
| CN113537156B (en) | Vibration data cleaning method based on interval standard deviation and spectrum analysis | |
| US20160109355A1 (en) | Data analysis apparatus and data analysis method |
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 |