CN116226692A - Tightening abnormality identification method, device and medium based on dynamic time planning - Google Patents
Tightening abnormality identification method, device and medium based on dynamic time planning Download PDFInfo
- Publication number
- CN116226692A CN116226692A CN202310511106.7A CN202310511106A CN116226692A CN 116226692 A CN116226692 A CN 116226692A CN 202310511106 A CN202310511106 A CN 202310511106A CN 116226692 A CN116226692 A CN 116226692A
- Authority
- CN
- China
- Prior art keywords
- tightening
- final
- curve
- final torque
- abnormal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 200
- 230000005856 abnormality Effects 0.000 title claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 155
- 230000002159 abnormal effect Effects 0.000 claims abstract description 87
- 230000001186 cumulative effect Effects 0.000 claims description 10
- 238000012935 Averaging Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
- G01L5/24—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for determining value of torque or twisting moment for tightening a nut or other member which is similarly stressed
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- General Factory Administration (AREA)
Abstract
The embodiment of the invention discloses a tightening abnormality identification method, device and medium based on dynamic time planning. The method comprises the following steps: obtaining final torque and a tightening curve of a threaded connection part in multiple tightening processes, and generating a first final torque and a first tightening curve representing the average level of a normal tightening process and a second final torque and a second tightening curve representing the average level of an abnormal tightening process; calculating a first accumulated distance between a tightening curve and a first tightening curve in each tightening process and a second accumulated distance between the second tightening curve and the first tightening curve by using a dynamic time planning method; the tightening process with the first accumulated distance smaller than the second accumulated distance is identified as normal, and the rest tightening processes are identified as abnormal; and re-identifying whether the repeated tightening process is abnormal or not according to the identification result, the first final torque and the second final torque. The embodiment can comprehensively and accurately identify the abnormal tightening process.
Description
Technical Field
The embodiment of the invention relates to the field of artificial intelligence, in particular to a tightening abnormality identification method, device and medium based on dynamic time planning.
Background
When the whole automobile is assembled, the automobile is provided with 4000-6000 threaded connection parts, and the screwing process plays an important role in automobile assembly. The conventional tightening mode in the tightening process of the assembly shop is a torque-angle control method, and a tightening process curve (hereinafter referred to as a tightening curve) with a tightening angle as an abscissa and a tightening torque as an ordinate is often used for identifying whether an abnormality occurs in the tightening process, and the abnormal tightening process is identified to be used for tracing the cause of the abnormality.
In the prior art, several types of tightening anomalies are generally determined empirically, and an engineer observes a tightening curve to be identified to determine which anomaly belongs to, and if a corresponding anomaly type cannot be found, the tightening curve is considered normal. Because the prior experience cannot exhaust all tightening abnormality types, the mode is greatly influenced by human subjective factors, and the abnormal tightening process is easily and mistakenly identified as normal, the reasons for abnormality cannot be comprehensively and accurately traced.
Disclosure of Invention
The embodiment of the invention provides a tightening abnormality identification method, equipment and medium based on dynamic time planning, which can comprehensively and accurately identify an abnormal tightening process.
In a first aspect, an embodiment of the present invention provides a tightening anomaly identification method based on dynamic time planning, including:
obtaining final torque and a tightening curve of the threaded connection part in a multiple tightening process;
generating a first final torque and a first tightening curve representing the average level of the normal tightening process and a second final torque and a second tightening curve representing the average level of the abnormal tightening process according to the deviation degree of the final torque and the tightening curve of the multiple tightening processes from the ideal final torque;
calculating a first accumulated distance between a tightening curve and a first tightening curve in each tightening process and a second accumulated distance between the second tightening curve and the first tightening curve by using a dynamic time planning method;
the tightening process with the first accumulated distance smaller than the second accumulated distance is identified as normal, and the rest tightening processes are identified as abnormal;
and re-identifying whether the repeated tightening process is abnormal or not according to the identification result, the first final torque and the second final torque.
In a second aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
a memory for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the dynamic time planning-based tightening anomaly identification method of any of the embodiments.
In a third aspect, an embodiment of the present invention further provides a computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the tightening anomaly identification method based on dynamic time planning according to any one of the embodiments.
According to the embodiment of the invention, according to the ideal final torque of a specific threaded connection part, the tightening curves of a large number of tightening processes are analyzed to obtain a first tightening curve and a second tightening curve which initially represent the average level of a normal tightening process and an abnormal tightening process; and then measuring the similarity between the curves by using a dynamic time planning method, taking the similarity between the first tightening curve and the second tightening curve as a threshold value, and identifying that the similarity is larger than the threshold value as a normal identification process. The method takes the tightening curve of the normal process as a reference, ensures the similarity between the identification result and the normal process through a reasonable threshold value, avoids the influence of human factors, improves the accuracy of the identification of the normal tightening process, and reduces the probability of misidentifying the abnormal tightening process as normal. Meanwhile, in order to avoid misidentification caused by accidental factors, the final torque is added as an auxiliary identification factor on the basis of identification according to the tightening curve, whether the tightening process is normal or not is identified again, and the accuracy of identification is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a tightening anomaly identification method based on dynamic time planning according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a normal tightening curve according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of an abnormal tightening curve with jamming according to an embodiment of the present invention.
Fig. 4 is a schematic view of another abnormal tightening curve provided by an embodiment of the present invention.
Fig. 5 is a schematic view of yet another abnormal tightening curve provided by an embodiment of the present invention.
Fig. 6 is a schematic structural diagram of an electronic device according to 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 technical solutions of the present invention will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the invention, are within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Fig. 1 is a flowchart of a tightening anomaly identification method based on dynamic time planning according to an embodiment of the present invention. The method is suitable for the situation that the abnormal screwing process of the specific threaded connection part is automatically identified, and is executed by electronic equipment. As shown in fig. 1, the method specifically includes:
s110, obtaining final torque and tightening curves of the threaded connection part in multiple tightening processes.
In particular to the field of vehicles, the tightening data of the same threaded connection part in the multiple tightening process can be collected in the whole vehicle assembly process of the same vehicle type, wherein the tightening data comprise final torque and tightening curves which are used as data sources for identifying whether the tightening is abnormal or not. The data volume here is often relatively large to ensure that it can cover the tightening process in various situations. Illustratively, this step obtains a total of 8000 tightening steps of tightening data.
FIG. 2 toThe bolt gives a normal tightening curve of the threaded connection part by way of example, and it can be seen that the end face of the bolt does not contact the connecting piece at the initial stage of the screw-in of the bolt, and the clamping force is not formed, and the tightening torque only overcomes the friction force between the screw pair, and the torque is smaller, such asaThe interval before the point; when the end face of the bolt comes into contact with the connecting piece, the bolt is elastically deformed to generate a tightening torque which is approximately proportional to the tightening angle, e.g.aTo the point ofbA section therebetween; when the bolt is further screwed down, the screw reaches a plastic deformation zone, the screwing torque is not proportional to the rotation angle, the elastic force can slide down, even the screw breaks, such asbTo the point ofcA section therebetween. Wherein the maximum tightening torque during tightening is the final torque, i.e. in fig. 2bThe point corresponds to the tightening torque. The tightening curves of the remaining threaded connection portions are similar to those of fig. 2 and will not be described again here.
And S120, generating a first final torque and a first tightening curve representing the average level of the normal tightening process and a second final torque and a second tightening curve representing the average level of the abnormal tightening process according to the final torque of the multiple tightening processes and the deviation degree of the tightening curve from the ideal final torque.
Specifically, for a particular threaded connection, there is a fixed upper and lower range of final torque. The final torque of most tightening processes fluctuates within the upper and lower limits, but the tightening quality varies, and this embodiment distinguishes these tightening processes into normal tightening processes, which means a good tightening quality, and abnormal tightening processes, which means a poor tightening quality. The step extracts data characteristics representing average levels of normal tightening process and abnormal tightening process through processing a large amount of tightening data.
In one embodiment, the desired final torque representing the best tightening quality is first determined based on the upper and lower limits of the final torque of the threaded connection. Illustratively, the center of the upper and lower ranges is taken as the desired final torque for the threaded connection.
Then, the upper and lower limit ranges of the final torque are divided into a plurality of sections symmetrically distributed around the ideal final torque. The tightening data in different intervals have different degrees of deviation from the ideal tightening state.
Next, two symmetrical intervals (e.g., [ M-0.5] and [ M+0.5], in Newton-meters) are selected closest to the ideal final torque M. In one aspect, a plurality of final torques (e.g., 10) within the two intervals are averaged, with the average being taken as the first final torque representing the average level of the normal tightening process. On the other hand, a plurality of tightening curves (for example, 10 tightening curves corresponding to the above 10 final torques) in which the final torque falls within the two sections are extracted, the tightening torques corresponding to the same tightening angles in the plurality of tightening curves are averaged, and each of the averages is connected as one curve as a first tightening curve representing the average level of the normal tightening process. It should be noted that the ideal final torque is not directly used to represent the average level of the normal tightening process, because the ideal final torque is too ideal, and is difficult to achieve in practical application, and difficult to accurately reflect the characteristics of the actual tightening process; in this embodiment, the first final torque and the first tightening curve are determined by the measured data closest to the ideal final torque, so that the result is closer to the engineering reality.
Finally, around the ideal final torque M, more symmetrical intervals (e.g., [ M+0.5M+2 ], [ M+2M+3 ], [ M-3M-2], … [ M+10M+11 ]) and (M-11M-10 ] are selected from the near to the far, and the interval division is merely used as an example, and can be adjusted according to specific needs in practical applications. On the one hand, a plurality of (for example, 10) final torques in each two symmetrical intervals are respectively averaged, and the average value is taken as a plurality of final torques representing different deviation degrees, wherein each two symmetrical intervals corresponds to one final torque; the plurality of final torques representing different degrees of deviation are averaged, and the average value is taken as a second final torque representing the average level of the abnormal tightening process. On the other hand, a plurality of tightening curves of which the final torque falls in the rest symmetrical intervals are respectively extracted and fused into a second tightening curve representing the average level of the abnormal tightening process. Optionally, the following is performed for every two symmetric intervals among the remaining symmetric intervals: extracting a plurality of tightening curves of which the final torque falls in the two symmetrical intervals; the tightening torques corresponding to the same tightening angle in the tightening curves are averaged, and each average value is connected to form a tightening curve which represents the deviation degree of the two sections from the ideal final torque. After the operation is carried out on each two symmetrical intervals, a plurality of tightening curves representing different deviation degrees can be obtained; the tightening torques corresponding to the same tightening angles in the curves are averaged, and each average value is connected to form a curve which is used as a second tightening curve representing the average level of the abnormal tightening process.
S130, calculating a first accumulated distance between a tightening curve and a first tightening curve in each tightening process and a second accumulated distance between the second tightening curve and the first tightening curve by using a dynamic time planning method.
Compared with the final torque, the tightening curve comprises data of the whole tightening process, and can reflect the tightening quality more comprehensively and stably. The present embodiment thus first identifies whether the tightening process is normal by the tightening curve. Specifically, because the lengths of the transverse axes of the tightening curves are not necessarily the same (for example, after the clamping stagnation abnormality shown in fig. 3 occurs, the tightening angle is blocked at a certain angle and cannot be increased, so that the length of the transverse axis of the curve is shortened), the embodiment calculates the accumulated distance between the tightening curves by using the dynamic time planning method, and uses the accumulated distance as a basis for measuring the similarity of the tightening curves. The first cumulative distance is used for reflecting the similarity between a tightening curve (i.e. a tightening curve to be detected) and a first tightening curve (i.e. an optimal tightening curve) in each tightening process, and the second cumulative distance is used for reflecting the similarity between the first tightening curve (i.e. the optimal tightening curve) and a second tightening curve (i.e. an abnormal tightening curve).
Alternatively, taking the tightening curve to be detected and the first tightening curve as examples, the two curves may be respectively expressed as the following two sequences:
Q=q 1 ,q 2 ,…,q i ,…,q m
C=c 1 ,c 2 ,…,c j ,…,c n
wherein the sequenceQRepresenting a first tightening curve comprising
A value; sequence(s)CRepresenting a tightening curve to be tested, comprising +.>
A value.
A process of calculating the first accumulated distance using a dynamic time planning method includes the steps of:
first, a first tightening curve is calculatedQEach value of (2) and the tightening curve to be detectedCThe constraint distance of each value in the table is as follows:
wherein,,l(q i ,c j ) Representing a first tightening curveQMiddle (f)iPersonal valueq i With the tightening curve to be detectedCMiddle (f)jPersonal valuec j Is set in the number of the constraint distances of (a),l(q i-1 ,c j ) Representing a first tightening curveQMiddle (f)i-1 valueq i-1 With the tightening curve to be detectedCMiddle (f)jPersonal valuec j Is set in the number of the constraint distances of (a),l(q i-1 ,c j-1 ) Representing a first tightening curveQMiddle (f)i-1 valueq i-1 With the tightening curve to be detectedCMiddle (f)j-1 valuec j-1 Is set in the number of the constraint distances of (a),l(q i ,c j-1 ) Representing a first tightening curveQMiddle (f)iPersonal valueq i With the tightening curve to be detectedCMiddle (f)j-1 valuec j-1 Is set in the number of the constraint distances of (a),d(q i ,c j ) Representing a first tightening curveQMiddle (f)iPersonal valueq i With the tightening curve to be detectedCMiddle (f)jPersonal valuec j Is a euclidean distance of (c).
The three elements in (a) correspond to one advancing direction respectively, and the direction with the minimum constraint distance corresponding to each value can be selected from the advancing directions through the formula (1).
Then, in each direction selected by the formula (1), a first tightening curve is calculatedQEach value of (2) and the tightening curve to be detectedCThe cumulative distance of each value in (a) is as follows:
wherein,,
representing a first tightening curveQMiddle (f)iPersonal valueq i With the tightening curve to be detectedCMiddle (f)jPersonal valuec j Is>
Representing a first tightening curveQMiddle (f)i-1 valueq i-1 With the tightening curve to be detectedCMiddle (f)jPersonal valuec j Is>
Representing a first tightening curveQMiddle (f)i-1 valueq i-1 With the tightening curve to be detectedCMiddle (f)j-1 valuec j-1 Is>
Representing a first tightening curveQMiddle (f)iPersonal valueq i With the tightening curve to be detectedCMiddle (f)j-1 valuec j-1 Is a cumulative distance of (c). I.e.)>
The three elements in (a) also respectively correspond to one advanceDirection by->
Selected minimum direction and pass
The selected minimum direction is uniform.
As can be seen from the formulas (1) and (2), each point in the two sequences participates in the operation, and adding one point to any one sequence increases the calculated amount by at least a multiple of the length of the other sequence. In order to reduce the calculation amount, the embodiment improves the traditional dynamic time planning method according to the characteristics of the tightening curve. Specifically, as described in S110: in the initial stage of screwing in the bolt, the end face of the bolt is not contacted with the connecting piece, and the clamping force is not formed, at the moment, the screwing torque only overcomes the friction force between the screw thread pairs, and the torque is smaller, so that a section with smaller torque amplitude and basically stable exists in the initial stage of screwing in the curve, as shown in fig. 2aInterval before the point. Fig. 3, 4 and 5 show tightening curves under several abnormal conditions, and it can be seen that a section with smaller torque and relatively smooth exists in the initial stage of the abnormal curve, and the section cannot show normal or abnormal conditions. What truly represents different tightening qualities is a section in which torque increases sharply and changes differently after a stationary section, and curve shapes under different tightening qualities in the section may exhibit a large difference.
Therefore, in a specific embodiment, before calculating the first cumulative distance by using the formulas (1) and (2), the first tightening curve and the section where the initial torque of the tightening curve to be detected is stable are removed, and then the remaining two segments of tightening curves are processed by using a dynamic time planning method, so as to calculate the first cumulative distance. Optionally, the removed interval is a continuous interval starting from the start of the curve and having a tightening torque less than a set threshold value, wherein the set threshold value can be determined by calibrating the friction between the screw pair at the current tightening location. By removing the intervals, points participating in operation in the dynamic time planning method can be reduced, and the execution efficiency is improved; the specific gravity of the second half curve in the first accumulation distance can be increased, so that the difference between different tightening qualities can be reflected more accurately.
The calculation process of the second cumulative distance is similar, the section with stable torque at the initial stage of the first tightening curve and the second tightening curve can be removed first, and then the two reserved sections of tightening curves are processed by using a dynamic time planning method to calculate the second cumulative distance.
And S140, recognizing that the tightening process of which the first accumulated distance is smaller than the second accumulated distance is normal, and recognizing that the rest of the tightening processes are abnormal.
This step uses the similarity (i.e., the second cumulative distance) between the optimal tightening curve and the abnormal tightening curve as a threshold value for identifying whether the tightening process is normal or not by the tightening curve. If the first accumulated distance corresponding to the tightening curve of one tightening process is smaller than the threshold value, the one tightening process is considered to be normal. If the first accumulated distance corresponding to the tightening curve of one tightening process is greater than or equal to the threshold value, the one tightening process is considered abnormal. Because the second tightening curve is obtained by fitting the whole interval of the upper and lower limit ranges of the final torque and covers tightening data with different deviation degrees, the threshold value determined by the second tightening curve can objectively reflect the curve similarity under normal and abnormal states, thereby providing accurate identification results.
S150, re-identifying whether the repeated tightening process is abnormal or not according to the identification result, the first final torque and the second final torque.
In practical application, various errors in the sensor and the processor can influence the recognition result, and the step further utilizes final torque to perform secondary recognition after the tightening curve is used for recognizing whether the tightening process is normal, so that false recognition caused by accidental factors is avoided. Meanwhile, the abnormal tightening process plays a more important role in tracing the abnormal reasons, so that the judgment standard for the normal tightening process is strict during re-identification in order to ensure the comprehensiveness of abnormal data, and the situation that the abnormal tightening process is mistakenly identified as normal due to accidental factors is avoided. Specifically, according to the different utilization angles of the tightening data, the embodiment provides two alternative embodiments of the re-identification process:
the first alternative embodiment takes full advantage of the robustness of the data and re-identifies with the complete tightening data. Optionally, clustering the final torques in all tightening processes by taking the first final torque and the second final torque as initial clustering centers, wherein the first final torque corresponds to a normal category, the second final torque corresponds to an abnormal category, and the clustering result is the result of the second recognition. This identification is independent of the identification in S140 (referred to as primary identification), and the two are not interfered with each other, and can be performed simultaneously. After the identification is completed, the normal tightening process is identified in the two identifications, and the final normal tightening process is determined; the remaining tightening process is re-identified as abnormal.
Optionally, the clustering adopts a DBSCAN clustering algorithm, and the clustering parameters are set as follows in an exemplary way: cluster radius r=1.5, minimum point minpts=20 within cluster radius. The process of the second recognition comprises the steps of:
and firstly, marking the final torque in the clustering radius by taking the first final torque and the second final torque as initial clustering centers, wherein the class corresponding to the first final torque is marked as normal, and the class corresponding to the second final torque is marked as abnormal. Specifically, each final torque (namely the final torque to be detected) is sequentially input into a DBSCAN clustering algorithm, and the distance density between the final torque to be detected and the clustering center is calculated according to two set parameters r and MinPts. Taking the distance density between the final torque to be detected and each clustering center on the clustering radius as a corresponding threshold value; if the distance density between the final torque to be detected and the clustering center of the normal class is smaller than the corresponding threshold value, marking the torque to be detected as normal; and if the distance density between the final torque to be detected and the clustering center of the abnormal category is smaller than the corresponding threshold value, marking the torque to be detected as abnormal.
And step two, updating two clustering centers according to the marking result, returning to the operation of marking the final torque, and repeating the cycle until the marking result is unchanged in multiple cycles. Illustratively, the final torque marked as normal is averaged as a new cluster center for the normal category, and the final angle marked as abnormal is averaged as a new cluster center for the abnormal category.
And step three, re-identifying the tightening process corresponding to the final torque marked as normal finally as normal, and re-identifying the rest tightening processes as abnormal.
It should be noted that, in the prior art, the initial cluster center of the DBSCAN clustering algorithm is randomly selected, and the cluster center is continuously updated by marking and averaging data points, so that the cluster center is continuously close to the overall characteristics of two categories, and the clustering rationality is improved. The improvement of the present embodiment is that the first final torque and the second final torque are taken as initial cluster centers. Because the two values are calculated according to the deviation degree of the final torque of the repeated tightening process to the ideal final torque, the average level of the normal tightening process and the abnormal tightening process can be represented to a certain degree, the two values are used as initial clustering centers, the clustering accuracy can be greatly improved, the iterative cycle times are reduced, and the clustering efficiency is improved.
Optionally, to further avoid misidentification caused by accidental factors, the final angle of each tightening process, i.e. in fig. 2, may also be extracted from the tightening curvecAnd (5) carrying out third recognition on whether the screw-down angle corresponding to the point is abnormal or not according to the final angle. The final angle is also different for different tightening qualities (e.g., the final angle is smaller in the case of galling), and there is a range of upper and lower limits for the final angle for a particular threaded connection in a particular process. In one embodiment, the third identifying includes: determining an ideal final angle according to the upper limit range and the lower limit range of the final angle of the threaded connection part; dividing the upper limit range and the lower limit range of the final angle into a plurality of sections which are symmetrically distributed by taking the ideal final angle as a center; averaging the final angles in the two symmetrical intervals closest to the ideal final angle to obtain a first final angle representing the average level of the normal tightening process; respectively for the final angles in the rest symmetrical intervalsAveraging to obtain a plurality of final angles representing different deviation degrees, and determining a second final angle representing the average level of the abnormal tightening process according to the plurality of final angles; and clustering the final angles of all the tightening processes by taking the first final angle and the second final angle as initial clustering centers, wherein the first final angle corresponds to a normal category, the second final angle corresponds to an abnormal category, and a clustering result is a third recognition result. This process is similar to the second identification based on the final torque, and reference is made for specific details. Finally, the normal tightening process is identified in the three identifications, and the final normal tightening process is determined; the remaining tightening process is re-identified as abnormal.
In a second alternative embodiment, abnormal tightening data is gradually removed according to the prior recognition result, the accuracy of normal tightening data is continuously improved, and the more accurate tightening data is used for re-recognition. Taking a DBSCAN clustering algorithm as an example, the second recognition process comprises the following steps:
the first final torque and the second final torque are used as initial clustering centers, and the final torque in the clustering radius is marked; the final torque of the tightening process, which has been identified as abnormal by the tightening curve, is removed from the final torque marked as normal.
And step two, updating two clustering centers according to the removed marking result, returning to the operation of marking the final torque, and repeating the cycle until the removed marking result in multiple cycles is unchanged.
And step three, re-identifying the tightening process corresponding to the final torque marked as normal finally as normal, and re-identifying the rest tightening processes as abnormal.
It can be seen that unlike the first alternative embodiment, the present example removes the final torque that has been identified as abnormal by the tightening curve from the final torque that is marked as normal after each final torque has been marked in step one. By doing so, errors caused by introducing abnormal points in updating of the cluster center can be avoided. In detail, the recognition method of the present application uses the degree of strictness of the normal category as a basic principle, and the accuracy of the recognition result obtained by tightening the curve is greater than the recognition result obtained by final torque, so that the present embodiment improves the conventional clustering algorithm again, and before each update of the clustering center, firstly, the identified abnormal point is removed from the data point marked as normal, thereby improving the accuracy of the marked result. Meanwhile, in order to give consideration to the robustness of the data, in the embodiment, abnormal points are removed only in the marking links, but data removal is not performed in other links (for example, in distance density calculation), because the links only perform distance measurement, category division is not involved yet, and the stability of clustering can be ensured by larger data volume.
Optionally, in order to further avoid misidentification caused by accidental factors, a final angle may be introduced to identify whether the tightening process is abnormal for the third time. The identification process is similar to the first alternative embodiment, except that the final angle of the tightening process, which has been identified as abnormal by the tightening curve or the final torque, is removed from the final angle marked as normal after each time the final angle is marked; updating the two clustering centers according to the removed marking results, and starting the next cycle until the removed marking results in multiple cycles are kept unchanged; and re-identifying the tightening process corresponding to the final angle marked as normal finally as normal, and re-identifying the rest tightening processes as abnormal.
It can be seen that: in a first alternative embodiment, the three recognition processes are independent of each other and do not interfere with each other, and finally the scope of the normal process is narrowed by the intersection of the three recognition processes. In the second alternative embodiment, the process of three times of recognition is progressive, and from the aspect of accuracy of the result of single recognition, the tightening curve > the final torque > the final angle, so that three times of recognition are sequentially performed according to the sequence, and in the clustering cycle of the last two times of recognition, the recognition result of the previous time (or the last two times) is fully utilized, the error caused by abnormal data is removed as early as possible, the accuracy of the clustering center is continuously improved, the clustering convergence is accelerated, and the probability of abnormal error recognition as normal is further reduced.
In summary, according to the ideal final torque of the specific threaded connection part, the embodiment analyzes the tightening curves of a large number of tightening processes to obtain the first tightening curve and the second tightening curve which primarily represent the average level of the normal tightening process and the abnormal tightening process; and then measuring the similarity between the curves by using a dynamic time planning method, taking the similarity between the first tightening curve and the second tightening curve as a threshold value, and identifying that the similarity is larger than the threshold value as a normal identification process. The method takes the tightening curve of the normal process as a reference, ensures the similarity between the identification result and the normal process through a reasonable threshold value, avoids the influence of human factors, improves the accuracy of the identification of the normal tightening process, and reduces the probability of misidentifying the abnormal tightening process as normal. Meanwhile, in order to avoid misidentification caused by accidental factors, the embodiment adds final torque and final angle as auxiliary identification factors on the basis of identification according to a tightening curve, and identifies whether the tightening process is normally performed for the second time and the third time. The tightening quality information obtained by primary data analysis is fully utilized in the twice recognition, and two final torques and final angles representing average levels of a normal tightening process and an abnormal tightening process are used as initial clustering centers, so that the clustering accuracy is improved, and the clustering convergence rate is also increased. In addition, three times of recognition can be sequentially performed according to the recognition accuracy of a single factor and the sequence of the tightening curve > the final torque > the final angle, and the data information which is previously recognized as abnormal is excluded in the two later times of recognition, so that the accuracy of normal categories is continuously improved, and the probability of misrecognition of the abnormal as normal is further reduced. The measure ensures the comprehensiveness of the abnormal tightening process identification from different angles, is beneficial to tracing the abnormal reasons and improves the tightening quality.
Particularly, in the process of calculating the curve similarity by using a dynamic time planning method, taking the change rule of a tightening curve and the expression positions of different tightening masses in the curve into consideration, firstly cutting out a torque stable section at the initial stage of the curve according to friction torque at the initial stage of tightening, and then calculating the accumulated distance. On one hand, by doing so, curve data participating in operation can be reduced, and the calculation efficiency is improved; on the other hand, the specific gravity of the second-half curve with obvious characteristics in the accumulated distance can be improved, so that the difference of tightening curves with different tightening qualities is more obvious, and the normal tightening process and the abnormal tightening process are better identified.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of processors 60 in the device may be one or more, one processor 60 being taken as an example in fig. 6; the processor 60, the memory 61, the input means 62 and the output means 63 in the device may be connected by a bus or other means, in fig. 6 by way of example.
The memory 61 is a computer readable storage medium, and may be used to store a software program, a computer executable program, and a module, such as program instructions/modules corresponding to the tightening abnormality identification method based on dynamic time planning in the embodiment of the present invention. The processor 60 executes various functional applications of the apparatus and data processing by running software programs, instructions and modules stored in the memory 61, i.e., implements the above-described tightening abnormality identification method based on dynamic time planning.
The memory 61 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions; the storage data area may store data created according to the use of the terminal, etc. In addition, the memory 61 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 61 may further comprise memory remotely located relative to processor 60, which may be connected to the device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 62 may be used to receive entered numeric or character information and to generate key signal inputs related to user settings and function control of the device. The output 63 may comprise a display device such as a display screen.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the tightening anomaly identification method based on the dynamic time plan of any embodiment.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the C-programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims (10)
1. The tightening abnormality identification method based on dynamic time planning is characterized by comprising the following steps of:
obtaining final torque and a tightening curve of the threaded connection part in a multiple tightening process;
generating a first final torque and a first tightening curve representing the average level of the normal tightening process and a second final torque and a second tightening curve representing the average level of the abnormal tightening process according to the deviation degree of the final torque and the tightening curve of the multiple tightening processes from the ideal final torque;
calculating a first accumulated distance between a tightening curve and a first tightening curve in each tightening process and a second accumulated distance between the second tightening curve and the first tightening curve by using a dynamic time planning method;
the tightening process with the first accumulated distance smaller than the second accumulated distance is identified as normal, and the rest tightening processes are identified as abnormal;
and re-identifying whether the repeated tightening process is abnormal or not according to the identification result, the first final torque and the second final torque.
2. The method of claim 1, wherein the re-identifying whether the multiple tightening process is abnormal based on the identification, the first final torque, and the second final torque comprises:
marking the final torque in the clustering radius by taking the first final torque and the second final torque as initial clustering centers, wherein the class corresponding to the first final torque is marked as normal, and the class corresponding to the second final torque is marked as abnormal;
removing the final torque of the tightening process, which has been identified as abnormal by the tightening curve, from the final torque marked as normal;
updating the two clustering centers according to the removed marking result, returning to the operation of the final torque of the marking, and repeating the cycle until the removed marking result in multiple cycles is kept unchanged;
and re-identifying the tightening process corresponding to the final torque which is finally marked as normal, and re-identifying the rest tightening processes as abnormal.
3. The method of claim 1, wherein calculating a first cumulative distance of the tightening curve from the first tightening curve for each tightening process using the dynamic time planning method comprises:
respectively removing a section with stable torque at the initial stage in a tightening curve and a first tightening curve in any one tightening process;
and calculating a first accumulated distance between the reserved tightening curve of the one-time tightening process and the reserved first tightening curve by using a dynamic time planning method.
4. A method according to claim 3, wherein the removing the interval of torque plateau at the initial stage in the tightening curve and the first tightening curve of any one tightening process, respectively, comprises:
in the first tightening curve, a continuous section from the start point in which the tightening torque is smaller than the set threshold value is removed.
5. The method of claim 1, wherein generating a first final torque and a first tightening curve representing an average level of a normal tightening process and a second final torque and a second tightening curve representing an average level of an abnormal tightening process based on the degree of deviation of the final torque and the tightening curves from the ideal final torque of the plurality of tightening processes comprises:
determining an ideal final torque representing the best tightening quality according to the upper and lower limit ranges of the final torque of the threaded connection part;
dividing the upper limit range and the lower limit range of the final torque into a plurality of sections which are symmetrically distributed by taking the ideal final torque as a center;
selecting two symmetrical intervals closest to the ideal final torque, and averaging the final torques in the two symmetrical intervals to obtain a first final torque representing the average level of the normal tightening process;
and respectively averaging the final torques in the rest symmetrical intervals to obtain a plurality of final torques representing different deviation degrees, and determining a second final torque representing the average level of the abnormal tightening process according to the plurality of final torques.
6. The method of claim 1, wherein generating a first final torque and a first tightening curve representing an average level of a normal tightening process and a second final torque and a second tightening curve representing an average level of an abnormal tightening process based on the degree of deviation of the final torque and the tightening curves from the ideal final torque of the plurality of tightening processes comprises:
determining an ideal final torque representing the best tightening quality according to the upper and lower limit ranges of the final torque of the threaded connection part;
dividing the upper limit range and the lower limit range of the final torque into a plurality of sections which are symmetrically distributed by taking the ideal final torque as a center;
selecting two symmetrical intervals closest to the ideal final torque, extracting a plurality of tightening curves of which the final torque falls in the two symmetrical intervals, and fusing the tightening curves into a first tightening curve representing the average level of the normal tightening process;
and respectively extracting a plurality of tightening curves of which the final torque falls in the rest symmetrical intervals, and fusing the tightening curves into a second tightening curve representing the average level of the abnormal tightening process.
7. The method of claim 6, wherein the separately extracting a plurality of tightening curves having final torques falling within the remaining symmetrical intervals, fusing into a second tightening curve representing an average level of an abnormal tightening process, comprises:
extracting a plurality of tightening curves of which the final torque falls in every two symmetrical intervals in the rest symmetrical intervals;
averaging the tightening torques corresponding to the same tightening angles in a plurality of tightening curves in every two symmetrical intervals to generate a plurality of tightening curves representing different deviation degrees;
and averaging the tightening torques corresponding to the same tightening angles in the tightening curves representing different deviation degrees, and generating a second tightening curve representing the average level of the abnormal tightening process.
8. The method of claim 2, wherein after the re-identification of the tightening process that eventually marked as normal and the remaining tightening processes re-identified as abnormal, further comprising:
generating a first final angle representing the average level of the normal tightening process and a second final angle representing the average level of the abnormal tightening process according to the deviation degree of the final angle of the multiple tightening processes from the ideal final angle;
marking the final angles in the clustering radius by taking the first final angle and the second final angle as initial clustering centers, wherein the category corresponding to the first final angle is marked as normal, and the category corresponding to the second final angle is marked as abnormal;
removing, from the final angles marked as normal, the final angles of the tightening process that have been identified as abnormal by the tightening curve or the final torque;
updating the two clustering centers according to the removed marking result, returning to the operation of the final marking angle, and repeating the cycle until the removed marking result in multiple cycles is unchanged;
and re-identifying the tightening process corresponding to the final angle marked as normal finally as normal, and re-identifying the rest tightening processes as abnormal.
9. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the dynamic time planning-based tightening anomaly identification method of any one of claims 1-8.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the dynamic time-planning-based tightening anomaly identification method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310511106.7A CN116226692B (en) | 2023-05-09 | 2023-05-09 | Tightening abnormality identification method, device and medium based on dynamic time planning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310511106.7A CN116226692B (en) | 2023-05-09 | 2023-05-09 | Tightening abnormality identification method, device and medium based on dynamic time planning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116226692A true CN116226692A (en) | 2023-06-06 |
| CN116226692B CN116226692B (en) | 2023-07-28 |
Family
ID=86589525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310511106.7A Active CN116226692B (en) | 2023-05-09 | 2023-05-09 | Tightening abnormality identification method, device and medium based on dynamic time planning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116226692B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110146213A (en) * | 2018-06-01 | 2019-08-20 | 华晨宝马汽车有限公司 | For detecting the method and apparatus and storage medium for tightening quality of tightening tool |
| CN113656392A (en) * | 2021-08-23 | 2021-11-16 | 广汽丰田汽车有限公司 | Tightening data management method and device and computer-readable storage medium |
| CN113829034A (en) * | 2020-06-24 | 2021-12-24 | 华晨宝马汽车有限公司 | Quality monitoring method, system and equipment based on bolt tightening working curve |
| CN113899538A (en) * | 2021-09-29 | 2022-01-07 | 上汽大众汽车有限公司 | Bolt tightening monitoring method and system |
| CN114817850A (en) * | 2021-01-27 | 2022-07-29 | 华晨宝马汽车有限公司 | Method and system for anomaly detection of bolt tightening data |
| CN114850847A (en) * | 2021-02-04 | 2022-08-05 | 中国航发商用航空发动机有限责任公司 | Pipe joint assembling quality detection method |
| CN115081511A (en) * | 2022-05-16 | 2022-09-20 | 南京航空航天大学 | Screw tightening quality judgment method based on curve similarity and clustering |
| CN115541096A (en) * | 2022-10-28 | 2022-12-30 | 启明信息技术股份有限公司 | Abnormity analysis method for screw tightening curve |
| CN115922312A (en) * | 2023-03-15 | 2023-04-07 | 宁德时代新能源科技股份有限公司 | Screw tightening method, device, jig, apparatus, storage medium, and program product |
-
2023
- 2023-05-09 CN CN202310511106.7A patent/CN116226692B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110146213A (en) * | 2018-06-01 | 2019-08-20 | 华晨宝马汽车有限公司 | For detecting the method and apparatus and storage medium for tightening quality of tightening tool |
| CN113829034A (en) * | 2020-06-24 | 2021-12-24 | 华晨宝马汽车有限公司 | Quality monitoring method, system and equipment based on bolt tightening working curve |
| CN114817850A (en) * | 2021-01-27 | 2022-07-29 | 华晨宝马汽车有限公司 | Method and system for anomaly detection of bolt tightening data |
| CN114850847A (en) * | 2021-02-04 | 2022-08-05 | 中国航发商用航空发动机有限责任公司 | Pipe joint assembling quality detection method |
| CN113656392A (en) * | 2021-08-23 | 2021-11-16 | 广汽丰田汽车有限公司 | Tightening data management method and device and computer-readable storage medium |
| CN113899538A (en) * | 2021-09-29 | 2022-01-07 | 上汽大众汽车有限公司 | Bolt tightening monitoring method and system |
| CN115081511A (en) * | 2022-05-16 | 2022-09-20 | 南京航空航天大学 | Screw tightening quality judgment method based on curve similarity and clustering |
| CN115541096A (en) * | 2022-10-28 | 2022-12-30 | 启明信息技术股份有限公司 | Abnormity analysis method for screw tightening curve |
| CN115922312A (en) * | 2023-03-15 | 2023-04-07 | 宁德时代新能源科技股份有限公司 | Screw tightening method, device, jig, apparatus, storage medium, and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116226692B (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115982602B (en) | Photovoltaic transformer electrical fault detection method | |
| CN112039073B (en) | Collaborative optimization method and system suitable for fault judgment of power distribution room equipment | |
| CN118091234B (en) | Current transformer for fault diagnosis processing | |
| CN116611712A (en) | Semantic inference-based power grid work ticket evaluation system | |
| CN117453962B (en) | Data storage method and system of measuring instrument | |
| CN113568960A (en) | Real-time analysis method and system for data of Internet of things and computer readable storage medium | |
| CN105447444A (en) | OTDR event analysis algorithm based on difference window and template matching | |
| CN116226692B (en) | Tightening abnormality identification method, device and medium based on dynamic time planning | |
| CN118133068A (en) | Automatic identification and construction method and system for power grid topology | |
| CN105306252A (en) | Method for automatically judging server failures | |
| CN114879070A (en) | Battery state evaluation method and related equipment | |
| CN112637888B (en) | Coverage hole area identification method, device, equipment and readable storage medium | |
| EP3268747A1 (en) | Detecting a transient error in a body fluid sample | |
| CN113554079A (en) | Electric power load abnormal data detection method and system based on secondary detection method | |
| CN116763312B (en) | Abnormal emotion recognition method and system based on wearable equipment | |
| CN116743637B (en) | Abnormal flow detection method and device, electronic equipment and storage medium | |
| CN117154716A (en) | Planning method and system for accessing distributed power supply into power distribution network | |
| CN112395280B (en) | Data quality detection method and system | |
| TW201020806A (en) | Product quality fault detection method and real metrology data evaluation method | |
| CN112103911B (en) | Hidden fault discrimination method and device for relay protection system | |
| CN113297543A (en) | Method and device for calculating service life of cooling water in water cooling system and readable medium | |
| CN113610167A (en) | Equipment risk detection method based on metric learning and visual perception | |
| CN113807677A (en) | Method, device and equipment for determining oil field energy consumption index and storage medium | |
| CN111176931A (en) | Operation monitoring method, operation monitoring device, server and storage medium | |
| CN111044813B (en) | Charging mode identification method and device and terminal equipment |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20230606 Assignee: Zhongqi Intellectual Property (Guangzhou) Co.,Ltd. Assignor: China automobile information technology (Tianjin) Co.,Ltd. Contract record no.: X2024440000002 Denomination of invention: Method, equipment, and medium for identifying abnormal tightening based on dynamic time planning Granted publication date: 20230728 License type: Common License Record date: 20240105 |