CN113305880B - Industrial robot consistency detection system and method based on DTW distance - Google Patents
Industrial robot consistency detection system and method based on DTW distance Download PDFInfo
- Publication number
- CN113305880B CN113305880B CN202110506514.4A CN202110506514A CN113305880B CN 113305880 B CN113305880 B CN 113305880B CN 202110506514 A CN202110506514 A CN 202110506514A CN 113305880 B CN113305880 B CN 113305880B
- Authority
- CN
- China
- Prior art keywords
- sequence
- similarity
- robots
- industrial robot
- detected
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/0095—Means or methods for testing manipulators
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
- Numerical Control (AREA)
Abstract
The invention provides a DTW distance-based industrial robot consistency detection method, which comprises the following steps: obtaining feedback currents of N robots in normal operation and respectively extracting single period sequence data T of the feedback currents of the N robots in normal operation i (ii) a According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 (ii) a Acquiring a sequence to be detected corresponding to feedback current when the robot runs in real time; respectively calculating single-period sequence data T of feedback current of N robots in normal operation through DTW algorithm i Similarity between them to obtain similarity range S s (ii) a Calculating the similarity S between the sequence to be detected and the reference sequence by DTW algorithm t (ii) a According to the similarity S t And a similarity range S s And detecting the consistency of the industrial robot. The invention can improve the accuracy of consistency detection of the industrial robot. Correspondingly, the invention further provides an industrial robot consistency detection system based on the DTW distance.
Description
Technical Field
The invention relates to the technical field of robots, in particular to a DTW distance-based industrial robot consistency detection system and method.
Background
In most disciplinary areas, time series is a common representation of data. For time series processing, a common task is to compare the similarity of two sequences. The industrial robot can produce a large amount of time series data every day, and through the similarity between the time series data of waiting to detect and the benchmark time series data, can detect industrial robot uniformity, judges industrial robot's health status.
In the prior art, similarity between time series data to be detected and reference time series data is generally determined by calculating Euclidean distance between the two data, and then consistency of the industrial robot is detected. However, the lengths of the time-series data to be detected and the reference time-series data may be misaligned, and the similarity between the time-series data to be detected and the reference time-series data is determined by calculating the euclidean distance, which is easy to cause an industrial robot consistency detection error.
Disclosure of Invention
Based on this, in order to solve the problem that the similarity between the time sequence data to be detected and the reference time sequence data is judged by calculating the Euclidean distance in the prior art, and the detection error of the consistency of the industrial robot is easily caused, the invention provides a DTW distance-based industrial robot consistency detection system and method, and the specific technical scheme is as follows:
an industrial robot consistency detection system based on DTW distance, comprising:
an acquisition module for acquiring feedback currents of the N robots in normal operation and respectively extracting single period sequence data T of the feedback currents of the N robots in normal operation i According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 Acquiring a sequence to be detected corresponding to the feedback current when the robot runs in real time;
a DTW algorithm module for calculating single period sequence data T of feedback current of the N robots in normal operation by DTW algorithm i Similarity between them to obtain similarity range S s And the similarity S between the sequence to be detected and the reference sequence t ；
A detection module for detecting the similarity S t And the similarity range S s And detecting the consistency of the industrial robot.
The DTW distance-based industrial robot consistency detection system firstly obtains feedback currents of N robots in normal operation and respectively extracts single period sequence data T of the feedback currents of the N robots in normal operation i According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 And acquiring a sequence to be detected corresponding to the feedback current when the robot operates in real time, and then respectively calculating single period sequence data T of the feedback current when the N robots operate normally i Similarity between them to obtain similarity range S s And the similarity S between the sequence to be detected and the reference sequence t And finally according to said similarity S t And the similarity range S s The consistency of the industrial robot is detected, and the consistency is sufficientThe condition that the time sequence data lengths of the industrial robot are inconsistent is considered, the problem that in the prior art, the similarity between the time sequence data to be detected and the reference time sequence data is judged by calculating the Euclidean distance, so that the consistency detection error of the industrial robot is easily caused can be effectively solved, the consistency detection accuracy of the industrial robot is improved, and the health state of the industrial robot can be judged quickly and accurately.
Further, the industrial robot consistency detection system also comprises a conversion module, wherein the conversion module is used for respectively extracting single period sequence data T of feedback current when the N robots normally operate i Front, by the formula
And performing unit conversion on the feedback current of the N robots in normal operation. Wherein, I i For feedback current, I, during normal operation of N robots e And (3) setting i to be 1,2 and 3 Λ N for the rated current of the corresponding motor of the robot arm.
Further, the obtaining module passes formula T 0 ＝(T 1 +T 2 +Λ+T N ) Acquiring the reference sequence T by the aid of the/N 0 。
Correspondingly, the invention provides an industrial robot consistency detection method based on DTW distance, which comprises the following steps:
obtaining feedback currents of N robots in normal operation and respectively extracting single period sequence data T of the feedback currents of the N robots in normal operation i ；
According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 ；
Acquiring a sequence to be detected corresponding to feedback current when the robot runs in real time;
respectively calculating single-period sequence data T of feedback current of N robots in normal operation through DTW algorithm i Similarity between them to obtain similarity range S s ；
Calculating the waiting for detection by DTW algorithmSimilarity between sequence and the reference sequence S t ；
According to the similarity S t And the similarity range S s And detecting the consistency of the industrial robot.
Further, the similarity S is determined according to t And the similarity range S s The specific method for detecting the consistency of the industrial robot comprises the following steps:
judging the similarity S t Whether or not it is larger than the similarity range S s Maximum value of (d);
if the similarity S t Whether or not it is larger than the similarity range S s If so, judging that the sequence to be detected is inconsistent with the reference sequence, and judging that the robot has a fault.
Further, single cycle sequence data T of feedback currents at the time of normal operation of the N robots are extracted respectively i First, the formula is passed
Performing unit conversion on feedback currents of N robots in normal operation;
wherein, I i For feedback current, I, during normal operation of N robots e And (3) setting i to be 1,2 and 3 Λ N for the rated current of the corresponding motor of the robot arm.
Further, the reference sequence T 0 By the formula T 0 ＝(T 1 +T 2 +Λ+T N ) And obtaining the/N.
Further, the model of the robot is HSR-JR 630.
Accordingly, the present invention provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the DTW distance based industrial robot consistency detection method as described above.
Drawings
The invention will be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. Like reference numerals designate corresponding parts throughout the different views.
Fig. 1 is an overall flow chart of an industrial robot consistency detection method based on DTW distance in an embodiment of the present invention;
fig. 2 is a schematic diagram of a reference sequence of an industrial robot consistency detection method based on DTW distance in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to embodiments thereof. It should be understood that the detailed description and specific examples, while indicating the scope of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only and do not represent the only embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The terms "first" and "second" used herein do not denote any particular order or quantity, but rather are used to distinguish one element from another.
In an embodiment of the present invention, an industrial robot consistency detection system based on DTW distance includes:
acquisition moduleAnd the system is used for acquiring feedback currents of the N robots in normal operation and respectively extracting single period sequence data T of the feedback currents of the N robots in normal operation i According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 Acquiring a sequence to be detected corresponding to the feedback current when the robot runs in real time;
a DTW algorithm module for calculating single period sequence data T of feedback current of the N robots in normal operation by DTW algorithm i Similarity between them to obtain a similarity range S s And the similarity S between the sequence to be detected and the reference sequence t ；
A detection module for detecting the similarity S t And the similarity range S s And detecting the consistency of the industrial robot.
The DTW (Dynamic time warping) distance-based industrial robot consistency detection system firstly acquires feedback currents of N robots in normal operation through an acquisition module and respectively extracts single period sequence data T of the feedback currents of the N robots in normal operation i According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 And acquiring a sequence to be detected corresponding to the feedback current when the robots run in real time, and then respectively calculating single period sequence data T of the feedback current when the N robots run normally through a DTW algorithm module i Similarity between them to obtain similarity range S s And the similarity S between the sequence to be detected and the reference sequence t And finally, according to the similarity S by a detection module t And the similarity range S s The consistency of the industrial robot is detected, the condition that the length of the time sequence data of the industrial robot is inconsistent is fully considered, the problem that in the prior art, the similarity between the time sequence data to be detected and the reference time sequence data is judged by calculating the Euclidean distance, so that the consistency detection error of the industrial robot is easily caused can be effectively solved, and the consistency detection method of the industrial robot improves the quality of the industrial robotThe consistency detection accuracy can quickly and accurately judge the health state of the industrial robot.
In one embodiment, the industrial robot consistency detection system further comprises a conversion module for respectively extracting single period sequence data T of feedback current when the N robots normally operate i Front, by the formula
And performing unit conversion on the feedback current of the N robots in normal operation.
Wherein the obtaining module passes formula T 0 ＝(T 1 +T 2 +Λ+T N ) Acquiring the reference sequence T by the aid of the/N 0 。
In one embodiment, as shown in fig. 1, the present invention provides a DTW distance-based industrial robot consistency detection method, including the following steps:
obtaining feedback currents of N robots in normal operation and respectively extracting single period sequence data T of the feedback currents of the N robots in normal operation i ；
According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 As shown in fig. 2;
acquiring a sequence to be detected corresponding to feedback current when the robot runs in real time;
respectively calculating single-period sequence data T of feedback current of N robots in normal operation through DTW algorithm i Similarity between them to obtain similarity range S s ；
Calculating the similarity S between the sequence to be detected and the reference sequence by a DTW algorithm t ；
According to the similarity S t And the similarity range S s And detecting the consistency of the industrial robot.
Specifically, the single period sequence data T of the feedback current when the N robots normally operate i The similarity between the two machines comprises the same machineSingle-period sequence data T of feedback current during normal operation of robot i Similarity between the two robots and single period sequence data T of feedback current when different robots of the same model normally operate i The similarity between them. The sequence to be detected is certain periodic sequence data of feedback current when the robot runs in real time. If the minimum value of the similarity is S 1 The maximum value of the similarity is S 2 Then the similarity range S s ＝{S 1 ,S 2 }。
Suppose that the sequence to be detected Q ═ Q 1 ,q 2 ,Λq i Λq n The reference sequence C ═ C 1 ,c 2 ,Λc j Λc n And n is the data length of the sequence to be detected and the reference sequence. In order to calculate the DTW distance between the sequence to be detected and the reference sequence, an n-dimensional matrix is required to be constructed, and the matrix element (i, j) represents q i And c i Distance d (q) between two points i ,c j ). Distance d (q) i ,c j ) Using Euclidean distances, i.e. d (q) i ,c j )＝(q i -c j ) 2 。
The DTW algorithm is to find a point starting from the origin to (q) n ,c n ) The shortest path of (2), the combination of consecutive elements in the matrix starting from (1,1) to ending at (n, n) is called the regular path W. If the sum of the elements of a regular path shape is the minimum in all paths, then the minimum is the DTW distance of Q and C.
Let the kth element of w be w k ＝(i,j) k Then the shortest distance between Q and C is
Wherein n is more than or equal to K is less than or equal to 2 n-1.
Finally, the similarity between Q and C is determined by defining an accumulated distance R (i, j) as the current position d (Q) i ,c j ) I.e.:
R(i,j)＝d(q i ,c j )+min{R(i-1,j-1),R(i-1,j),R(i,j-1)}
in practical applications, it is assumed that the sequence Q 1 And Q 2 ，Q 1 Is the sequence to be detected obtained after Q translation, Q 2 Is a sequence to be detected which is not identical to Q. There is a condition, Q 1 The similarity distance (i.e., similarity) to Q will be greater than Q 2 Similar distance to Q. In fact, Q 1 Q is more similar, however, by calculating the comparison of similar distances, Q is obtained 2 Results more similar to Q. Obviously, this result is not acceptable.
Since the accumulated distance R (i, j) is related to the number of nodes in the shortest path and the length of each diagonal, an adjustment parameter λ may be introduced in consideration of the number of nodes in the shortest path and the length of the diagonal.
In one embodiment, the adjustment parameter
Wherein, l is the node number of the shortest path, and m is the length of each diagonal of the shortest path.
And the larger the value is, the longer the diagonal line of the shortest path is, and the similarity distance between the final sequence to be detected and the reference sequence is lambda multiplied by R (i, j).
By introducing the adjustment coefficient, the similarity between the sequence to be detected and the reference sequence can be better calculated, and errors are avoided.
The longer the longest common substring between two sequences, tends to mean that the smaller the similarity distance, the more similar the two sequences. For this purpose, the adjustment coefficients can be modified taking into account the length of the longest common substring between the sequence to be detected and the reference sequence.
In one embodiment, the adjustment parameter
The similarity distance between the final sequence to be detected and the reference sequence is lambda multiplied by R (i, j). Wherein a is the length of the longest common substring between the sequence to be detected and the reference sequence, and n is the sequence to be detected orLength of the reference sequence.
In one embodiment, in order to comprehensively consider the longest common substring length between the sequence to be detected and the reference sequence, the number of nodes of the shortest path, and the influence of the length of each diagonal on the DTW distance, the adjustment parameter
The similarity distance between the sequence to be detected and the reference sequence is lambda multiplied by R (i, j). Wherein l is the number of nodes of the shortest path, m is the length of each diagonal of the shortest path, a is the length of the longest common substring between the sequence to be detected and the reference sequence, n is the length of the sequence to be detected or the reference sequence,
the coefficient of the length is represented by,
to represent
Rounding up. Therefore, the influence of the longest common substring length between the sequence to be detected and the reference sequence, the number of nodes of the shortest path and the length of each diagonal on the DTW distance is comprehensively considered, and the similarity between the sequence to be detected and the reference sequence can be better calculated by introducing the adjustment coefficient, so that errors are avoided.
Firstly obtaining feedback currents of N robots in normal operation and respectively extracting single-period sequence data T of the feedback currents of the N robots in normal operation i According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 And acquiring a sequence to be detected corresponding to the feedback current when the robot operates in real time, and then respectively calculating single period sequence data T of the feedback current when the N robots operate normally i Similarity between them to obtain similarity range S s And the similarity S between the sequence to be detected and the reference sequence t Finally the block is according toThe similarity S t And the similarity range S s The industrial robot consistency detection method based on the DTW distance fully considers the condition that the lengths of the time sequence data of the industrial robot are inconsistent, can effectively solve the problem that in the prior art, the similarity between the time sequence data to be detected and the reference time sequence data is judged by calculating the Euclidean distance, so that the consistency detection error of the industrial robot is easily caused, improves the accuracy of consistency detection of the industrial robot, and can quickly and accurately judge the health state of the industrial robot.
In one embodiment, the similarity S is determined according to t And the similarity range S s The specific method for detecting the consistency of the industrial robot comprises the following steps:
judging the similarity S t Whether or not it is larger than the similarity range S s Maximum value of (d);
if the similarity S t Whether or not it is larger than the similarity range S s If so, judging that the sequence to be detected is inconsistent with the reference sequence, and judging that the robot has a fault.
In one embodiment, the single period sequence data T of the feedback current when the N robots normally operate is extracted respectively i First, the formula is passed
Performing unit conversion on feedback currents of N robots in normal operation;
wherein, I i For feedback current, I, during normal operation of N robots e And (3) setting i to be 1,2 and 3 Λ N for the rated current of the corresponding motor of the robot arm.
The feedback current can be converted from dimensionless to ampere by unit conversion of the feedback current of the N robots in normal operation.
Wherein the reference sequence T 0 By the formula T 0 ＝(T 1 +T 2 +Λ+T N ) (ii) N acquisition, model of the robotIs HSR-JR 630.
In one embodiment, the invention provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the DTW distance based industrial robot consistency detection method as described above.
All possible combinations of the technical features of the above embodiments may not be described for the sake of brevity, but should be considered as within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (9)
1. An industrial robot consistency detection system based on DTW distance, characterized in that the industrial robot consistency detection system comprises:
an acquisition module for acquiring feedback current of N robots in normal operation and respectively extracting single period sequence data T of the feedback current of N robots in normal operation i According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 Acquiring a sequence to be detected corresponding to the feedback current when the robot runs in real time;
a DTW algorithm module for calculating single period sequence data T of feedback current of the N robots in normal operation by DTW algorithm i Similarity between them to obtain a similarity range S s And the similarity S between the sequence to be detected and the reference sequence t ；
A detection module for detecting the similarity S t And the similarity range S s Detecting the consistency of the industrial robots;
wherein the similarity distance between the sequence to be detected and the reference sequence is lambda multiplied by R (i, j),
l is the number of nodes of the shortest path, m is the length of each diagonal of the shortest path, a is the length of the longest common substring between the sequence to be detected and the reference sequence, n is the length of the sequence to be detected or the reference sequence,
the coefficient of the length is represented by,
to represent
Rounded up upwards of d (q) i ,c j ) Denotes q i And c j Distance between two points, R (i, j) ═ d (q) i ,c j )+min{R(i-1,j-1),R(i-1,j),R(i,j-1)}，q i The i point of the sequence to be detected, c j Is the jth point of the reference sequence.
2. The DTW distance-based industrial robot consistency detection system according to claim 1, wherein the industrial robot consistency detection system further comprises a conversion module for extracting single period sequence data T of feedback current when N robots normally operate respectively i Front, by the formula
Performing unit conversion on feedback currents of N robots in normal operation;
wherein, I i For feeding back electricity when N robots normally runFlow, I e The rated current of the corresponding motor of the robot arm is 1,2,3 … N.
3. The DTW distance-based industrial robot consistency detection system of claim 1, wherein the acquisition module passes formula T 0 ＝(T 1 +T 2 +…+T N ) Acquiring the reference sequence T by the aid of the/N 0 。
4. A DTW distance-based industrial robot consistency detection method is characterized by comprising the following steps:
obtaining feedback currents of N robots in normal operation and respectively extracting single period sequence data T of the feedback currents of the N robots in normal operation i ；
According to single period sequence data T of feedback current when N robots normally operate i Obtaining a reference sequence T 0 ；
Acquiring a sequence to be detected corresponding to feedback current when the robot runs in real time;
respectively calculating single-period sequence data T of feedback current of N robots in normal operation through DTW algorithm i Similarity between them to obtain similarity range S s ；
Calculating the similarity S between the sequence to be detected and the reference sequence by a DTW algorithm t ；
According to the similarity S t And the similarity range S s Detecting the consistency of the industrial robots; wherein the similarity distance between the sequence to be detected and the reference sequence is lambda multiplied by R (i, j),
l is the number of nodes of the shortest path, m is the length of each diagonal of the shortest path, a is the length of the longest common substring between the sequence to be detected and the reference sequence, n is the length of the sequence to be detected or the reference sequence,
the coefficient of the length is represented by,
to represent
Rounded up upwards of d (q) i ,c j ) Denotes q i And c j Distance between two points, R (i, j) ═ d (q) i ,c j )+min{R(i-1,j-1),R(i-1,j),R(i,j-1)}，q i The i point of the sequence to be detected, c j Is the jth point of the reference sequence.
5. The DTW distance-based industrial robot consistency detection method as recited in claim 4, wherein the similarity S is based on t And the similarity range S s The specific method for detecting the consistency of the industrial robot comprises the following steps:
judging the similarity S t Whether or not it is larger than the similarity range S s Maximum value of (d);
if the similarity S t Whether or not it is larger than the similarity range S s If so, judging that the sequence to be detected is inconsistent with the reference sequence, and judging that the robot has a fault.
6. The DTW distance-based industrial robot consistency detection method as claimed in claim 4, wherein the single period sequence data T of the feedback current when the N robots normally operate is extracted respectively i First, the formula is passed
Performing unit conversion on feedback currents of N robots in normal operation;
wherein, I i For feedback current, I, during normal operation of N robots e I is 1,2,3 … for rated current of corresponding motor of robot armN。
7. The DTW distance-based industrial robot consistency detection method as recited in claim 4, wherein the reference sequence T is 0 By the formula T 0 ＝(T 1 +T 2 +…+T N ) And obtaining the/N.
8. The DTW distance-based industrial robot consistency detection method as defined in claim 4, wherein the model of the robot is HSR-JR 630.
9. A computer-readable storage medium, characterized in that it stores a computer program which, when being executed by a processor, implements the DTW distance-based industrial robot consistency detection method according to any of the preceding claims 4 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110506514.4A CN113305880B (en) | 2021-05-10 | 2021-05-10 | Industrial robot consistency detection system and method based on DTW distance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110506514.4A CN113305880B (en) | 2021-05-10 | 2021-05-10 | Industrial robot consistency detection system and method based on DTW distance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113305880A CN113305880A (en) | 2021-08-27 |
| CN113305880B true CN113305880B (en) | 2022-08-05 |
Family
ID=77372765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110506514.4A Active CN113305880B (en) | 2021-05-10 | 2021-05-10 | Industrial robot consistency detection system and method based on DTW distance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113305880B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115712841B (en) * | 2022-11-18 | 2023-08-15 | 南京航空航天大学 | Spacecraft part state evaluation method based on data distribution characteristics of periodic data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008134706A (en) * | 2006-11-27 | 2008-06-12 | Nippon Telegr & Teleph Corp <Ntt> | Data stream monitoring device, data stream monitoring method, its program and recording medium |
| CN102542262A (en) * | 2012-01-04 | 2012-07-04 | 东南大学 | Waveform identification method based on operating-characteristic working condition waveform library of high-speed rail |
| CN108445838A (en) * | 2018-04-28 | 2018-08-24 | 华中科技大学 | A kind of numerically-controlled machine tool processing quality analysis method, grader and equipment |
| CN110757510A (en) * | 2019-10-31 | 2020-02-07 | 广东工业大学 | Method and system for predicting remaining life of robot |
| CN111612204A (en) * | 2019-02-25 | 2020-09-01 | 丰田研究所股份有限公司 | System, method, and storage medium for optimizing performance of a battery pack |
-
2021
- 2021-05-10 CN CN202110506514.4A patent/CN113305880B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008134706A (en) * | 2006-11-27 | 2008-06-12 | Nippon Telegr & Teleph Corp <Ntt> | Data stream monitoring device, data stream monitoring method, its program and recording medium |
| CN102542262A (en) * | 2012-01-04 | 2012-07-04 | 东南大学 | Waveform identification method based on operating-characteristic working condition waveform library of high-speed rail |
| CN108445838A (en) * | 2018-04-28 | 2018-08-24 | 华中科技大学 | A kind of numerically-controlled machine tool processing quality analysis method, grader and equipment |
| CN111612204A (en) * | 2019-02-25 | 2020-09-01 | 丰田研究所股份有限公司 | System, method, and storage medium for optimizing performance of a battery pack |
| CN110757510A (en) * | 2019-10-31 | 2020-02-07 | 广东工业大学 | Method and system for predicting remaining life of robot |
Non-Patent Citations (1)
| Title |
|---|
| "基于DTW相似判定的周期性时间序列预测方法";李文海 等;《计算机科学》;20190605;第46卷(第5期);第157-162页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113305880A (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112380098B (en) | Timing sequence abnormality detection method and device, computer equipment and storage medium | |
| CN108959778B (en) | Method for predicting residual life of aircraft engine based on consistency of degradation modes | |
| EP1630635A2 (en) | Method and apparatus for improved fault detection in power generation equipment | |
| US20200397346A1 (en) | Annotation method, annotation device, storage medium, and identification system | |
| CN112633421A (en) | Method and device for detecting abnormal electricity utilization behavior of user | |
| CN113305880B (en) | Industrial robot consistency detection system and method based on DTW distance | |
| JP6240050B2 (en) | Bias estimation apparatus, method and program thereof, and fault diagnosis apparatus, method and program thereof | |
| CN112882954A (en) | Distributed database operation and maintenance dynamic threshold value warning method and device | |
| US7529651B2 (en) | Accurate linear parameter estimation with noisy inputs | |
| CN115800272A (en) | Power grid fault analysis method, system, terminal and medium based on topology identification | |
| CN107924182B (en) | Monitoring device, control method of monitoring device, and recording medium | |
| JP2003044123A (en) | Plant diagnostic device | |
| CN109308051B (en) | Numerical controller | |
| TW202113703A (en) | Work element analysis device and work element analysis method | |
| CN117314890B (en) | Safety control method, device, equipment and storage medium for button making processing | |
| CN111259338B (en) | Component failure rate correction method and device, computer equipment and storage medium | |
| JP7181464B2 (en) | Power estimation program, power estimation device and power estimation method | |
| JP7251955B2 (en) | Detection device and machine learning method | |
| JP6448745B2 (en) | Bias estimation apparatus, method and program thereof | |
| CN114972695B (en) | Point cloud generation method and device, electronic equipment and storage medium | |
| CN115828481A (en) | Power distribution network topology identification method and system based on approximate Markov blanket | |
| CN114185882A (en) | Bad data correction method and device, storage medium and electronic equipment | |
| KR20220028727A (en) | Method and Apparatus for Real Time Fault Detection Using Time series data According to Degradation | |
| CN114336612B (en) | Power station and electric quantity loss calculation method of fault equipment of power station and related application equipment | |
| JP5191443B2 (en) | Multidimensional signal pair compression apparatus, multidimensional signal pair compression method, and program |
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 |