CN114951047B - Universal intelligent sorting method in vibration feeding based on optical fiber sensor - Google Patents
Universal intelligent sorting method in vibration feeding based on optical fiber sensor Download PDFInfo
- Publication number
- CN114951047B CN114951047B CN202210580632.4A CN202210580632A CN114951047B CN 114951047 B CN114951047 B CN 114951047B CN 202210580632 A CN202210580632 A CN 202210580632A CN 114951047 B CN114951047 B CN 114951047B
- Authority
- CN
- China
- Prior art keywords
- workpiece
- data
- subsequence
- segmentation threshold
- optical fiber
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Sorting Of Articles (AREA)
Abstract
The invention discloses a general intelligent sorting method in vibration feeding based on an optical fiber sensor, which comprises the following steps: collecting brightness characteristic data of the surface of a workpiece by using an optical fiber sensor, and preprocessing the data; generating subsequences of all workpiece data, respectively calculating Euclidean distances between the subsequences and the workpiece data, searching a segmentation threshold value with the maximum information gain after classification and the corresponding most distinguishing subsequence, and constructing a classification decision tree model; and calculating the Euclidean distance between the workpiece data to be matched and the most distinguishable subsequence, wherein the workpiece gesture is required when the Euclidean distance is smaller than a segmentation threshold value, and the workpiece gesture is removed when the Euclidean distance is larger than the segmentation threshold value. The invention can automatically find the most distinguishable subsequence of the workpiece, has high recognition accuracy and excellent universality; the invention can accurately and effectively realize sorting under different conditions, improves the convenience and the intellectualization of pattern recognition, and has higher robustness.
Description
Technical Field
The invention relates to a mode identification and signal processing technology, in particular to a general intelligent sorting method in vibration feeding based on an optical fiber sensor.
Background
In the production process of enterprises, in order to realize automatic and efficient assembly, workpieces need to enter the next assembly process in a specific gesture, and the workpiece enters in other gestures, which can influence the efficiency of the assembly process, even the whole assembly process can not normally run, so that the workpieces conveyed in the production process need to be identified in an online gesture. The workpiece can only enter the next working procedure in the required posture of the assembly working procedure, and other workpiece postures are not required to be removed, so that the system is required to sort the workpiece postures.
At present, most enterprises basically realize online sorting of workpiece postures, most are based on machine vision sorting systems, and the sorting process is high in precision and speed, but the sorting process is performed by using an industrial camera, so that equipment is difficult to install and debug, the cost is high, the equipment is not suitable for small and medium-sized enterprises, the requirements on users are high, and professional training is often required. Or workpiece sorting based on a single optical fiber sensor, the collected data of the surface of the workpiece is limited, and only specific types of workpieces can be identified, so that the universality is poor. The universal intelligent sorting method in vibration feeding based on the optical fiber sensor can automatically extract the most distinguishable workpiece features, and solves the problems of complicated use process and poor universality.
Disclosure of Invention
The invention aims to: the invention aims to provide a general intelligent sorting method in vibration feeding based on an optical fiber sensor, so that the production cost is reduced and the workpiece general sorting in vibration feeding is realized.
The technical scheme is as follows: the invention relates to a general intelligent sorting method in vibration feeding based on an optical fiber sensor, which comprises the following steps:
(1) Collecting brightness characteristic data of the surface of a workpiece by using an optical fiber sensor, and preprocessing the data;
(2) Generating subsequences of all workpiece data, respectively calculating Euclidean distances between the subsequences and the workpiece data, searching a segmentation threshold value with the maximum information gain after classification and the corresponding most distinguishing subsequence, and constructing a classification decision tree model;
(3) And calculating the Euclidean distance between the workpiece data to be matched and the most distinguishable subsequence, wherein the workpiece gesture is required when the Euclidean distance is smaller than a segmentation threshold value, and the workpiece gesture is removed when the Euclidean distance is larger than the segmentation threshold value.
The preprocessing of the data in the step (1) specifically comprises:
calculating the average value of the workpiece surface brightness characteristic data and the ambient light data acquired by the optical fiber sensor in each period, and then calculating the difference value to remove the ambient light interference; and then filtering out the high-frequency signal by using a frequency domain filtering method, reserving the low-frequency contour component, and performing data compression.
The searching of the most distinguishable subsequence in the step (2) specifically comprises the following steps:
generating all the workpiece data subsequences after dimension reduction, and calculating Euclidean distances between the workpiece data subsequences and the workpiece sequences; the obtained distances are arranged in ascending order, and the average value of two adjacent distances is taken as a segmentation threshold d th Less than the segmentation threshold d th Is divided into a posture greater than d th Separated into other poses; and calculating the information gain of the system after the classification of the segmentation threshold value by utilizing the information entropy theory, and taking the workpiece subsequence corresponding to the maximum information gain and the segmentation threshold value as the most distinguishable subsequence.
The step (3) specifically comprises the following steps:
the most distinguishable workpiece subsequence obtained in step (2) and the corresponding segmentation threshold d th Calculating the Euclidean distance between the workpiece data to be matched and the most distinguishable subsequence, which is smaller than the segmentation threshold d th The required workpiece gesture is larger than the threshold value and is eliminated.
A computer storage medium having stored thereon a computer program which when executed by a processor implements a method for intelligent sorting in vibratory feeding based on fiber optic sensors as described above.
The beneficial effects are that: compared with the prior art, the invention has the following advantages:
1. the invention adopts the method of general intelligent sorting in vibration feeding based on the optical fiber sensor to identify and sort the workpiece gesture, can automatically find the most distinguishing subsequence of the workpiece, has high identification accuracy, and has the remarkable advantage of universality, and the identification result is not influenced by the change of the workpiece type.
2. The invention can accurately and effectively realize sorting for different workpieces and workpieces running at different speeds or when the ambient light changes, improves the convenience and the intellectualization of pattern recognition, and has higher robustness.
Drawings
Figure 1 is a flow chart of the steps of the present invention,
figure 2 is a flow chart of a most discriminating sub-sequence for finding a workpiece,
FIG. 3 is a diagram showing the classification of the most distinguished subsequences and their corresponding segmentation threshold,
fig. 4 is a schematic diagram of classification of workpiece data to be matched.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, a general intelligent sorting method in vibration feeding based on an optical fiber sensor comprises the following steps:
(1) And collecting the brightness characteristic data of the surface of the workpiece by using an optical fiber sensor, and preprocessing the data.
The data preprocessing in the step (1) specifically comprises the following steps:
demodulating the workpiece data acquired by the optical fiber sensor, wherein the demodulated workpiece data is shown in the following formula:
AA＝(aa 1 ,aa 2 ,…,aa n )
in the formula aa i Representing the demodulated workpiece data, the calculation process is as follows:
aai＝aa p -aa q
in paa i Representing workpiece data acquired when the optical fiber sensor is in low-level PAA, rs RFA Indicating that the fiber sensor is at high level RS RFA Ambient light data collected at the time, a p And a q Respectively representing workpiece brightness characteristic data and ambient light data after mean value calculation in one period, wherein T is a trigger period, and m represents a demarcation point at which a data first-order response process reaches a stable state; then the demodulated workpiece data is transformed from time domain to frequency domain, a frequency domain filtering method is used for filtering high-frequency signals, retaining low-frequency contour components, and thenData compression.
(2) Generating subsequences of all the workpiece data, respectively calculating Euclidean distance between the subsequences and the workpiece data, searching a segmentation threshold value with the maximum information gain after classification and the corresponding most distinguishing subsequence, and constructing a classification decision tree model.
The searching of the most distinguishable subsequence in step (2) is specifically:
(2.1) generating candidate subsequences: inputting all collected workpiece data sets D to generate all subsequences meeting MINLEN less than or equal to |S|lessthan or equal to MAXLEN, wherein MINLEN is more than or equal to 1, MAXLEN is less than or equal to min|T i |(T i ∈D)。
(2.2) calculating a subsequence distance: the Euclidean distance of the candidate subsequence to each piece of workpiece data in the dataset is calculated, and the results are sorted in ascending order into objects_history.
(2.3) setting a distance division threshold d_th: d_th is set to the average of the adjacent two distances in the objects_history.
(2.4) calculating an information Gain: and calculating the information gain of the candidate subsequence after dividing the data set D through the dividing threshold d_th, and recording the maximum information gain and the corresponding dividing threshold d_th.
(2.5) repeating the steps (2.2) - (2.4), and searching the workpiece subsequence corresponding to the maximum system information gain after classification and the segmentation threshold d_th, wherein the process is shown in fig. 2.
(2.6) building a classification decision tree model according to the most discriminative subsequence and its corresponding segmentation threshold d_th, as shown in fig. 3.
(3) And calculating the Euclidean distance between the workpiece data to be matched and the most distinguishable subsequence, wherein the workpiece gesture is required when the Euclidean distance is smaller than a segmentation threshold value, and the workpiece gesture is removed when the Euclidean distance is larger than the segmentation threshold value.
The step (3) specifically comprises the following steps:
the most distinguishable workpiece subsequence obtained in step (2) and the corresponding segmentation threshold d th Calculating the Euclidean distance between the workpiece data to be matched and the most distinguishable subsequence, which is smaller than the segmentation threshold d th I.e., the desired workpiece pose, is eliminated above the threshold, as shown in fig. 4.
A computer storage medium having stored thereon a computer program which when executed by a processor implements a method for intelligent sorting in vibratory feeding based on fiber optic sensors as described above.
Claims (2)
1. The universal intelligent sorting method in vibration feeding based on the optical fiber sensor is characterized by comprising the following steps:
(1) Collecting brightness characteristic data of the surface of a workpiece by using an optical fiber sensor, and preprocessing the data; the preprocessing is specifically to calculate the average value of the workpiece surface brightness characteristic data and the ambient light data acquired by the optical fiber sensor in each period and then calculate the difference value so as to remove the ambient light interference; then filtering out high-frequency signals by using a frequency domain filtering method, reserving low-frequency contour components, and performing data compression;
(2) Generating subsequences of all workpiece data, respectively calculating Euclidean distances between the subsequences and the workpiece data, searching a segmentation threshold value with the maximum information gain after classification and the corresponding most distinguishing subsequence, and constructing a classification decision tree model; the searching of the most distinguishing subsequence specifically comprises the following steps: generating all compressed workpiece data subsequences, and calculating Euclidean distances between the compressed workpiece data subsequences and the workpiece sequences; the obtained distances are arranged in ascending order, and the average value of two adjacent distances is taken as a segmentation threshold d th Less than the segmentation threshold d th Is divided into a posture greater than d th Separated into other poses; calculating information gain of the system after classification of the segmentation threshold value by utilizing an information entropy theory, and taking a workpiece subsequence corresponding to the maximum information gain and the segmentation threshold value as the most distinguishable subsequence;
(3) The Euclidean distance between the workpiece data to be matched and the most distinguishable subsequence is calculated, the workpiece gesture is required when the Euclidean distance is smaller than a segmentation threshold value, and the workpiece gesture is removed when the Euclidean distance is larger than the segmentation threshold value, specifically: the most distinguishable workpiece subsequence obtained in step (2) and the corresponding segmentation threshold d th Calculating the Euclidean distance between the workpiece data to be matched and the most distinguishable subsequence, which is smaller than the segmentation threshold d th I.e. the required workpiece gesture is greater than theAnd eliminating the threshold value.
2. A computer storage medium having a computer program stored thereon, which when executed by a processor implements a method for intelligent sorting of optical fiber sensor-based vibratory feeding according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210580632.4A CN114951047B (en) | 2022-05-26 | 2022-05-26 | Universal intelligent sorting method in vibration feeding based on optical fiber sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210580632.4A CN114951047B (en) | 2022-05-26 | 2022-05-26 | Universal intelligent sorting method in vibration feeding based on optical fiber sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114951047A CN114951047A (en) | 2022-08-30 |
| CN114951047B true CN114951047B (en) | 2023-08-22 |
Family
ID=82955420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210580632.4A Active CN114951047B (en) | 2022-05-26 | 2022-05-26 | Universal intelligent sorting method in vibration feeding based on optical fiber sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114951047B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2576528A1 (en) * | 1985-01-30 | 1986-08-01 | Hotchkiss Brandt Sogeme | Processing method for the separating of objects |
| CN101697167A (en) * | 2009-10-30 | 2010-04-21 | 邱建林 | Clustering-decision tree based selection method of fine corn seeds |
| CN104063710A (en) * | 2014-06-13 | 2014-09-24 | 武汉理工大学 | Method for removing abnormal spectrum in actual measurement spectrum curve based on support vector machine model |
| CN104751166A (en) * | 2013-12-30 | 2015-07-01 | 中国科学院深圳先进技术研究院 | Spectral angle and Euclidean distance based remote-sensing image classification method |
| CN107671011A (en) * | 2017-09-20 | 2018-02-09 | 南京创优科技有限责任公司 | A kind of feeding sorting unit based on grey states sequence |
| CN209291395U (en) * | 2018-12-28 | 2019-08-23 | 深圳市大恒精密技术有限公司 | Material optical fiber screening device |
| CN113721121A (en) * | 2021-09-02 | 2021-11-30 | 长江存储科技有限责任公司 | Fault detection method and device for semiconductor process |
| CN113791062A (en) * | 2021-09-17 | 2021-12-14 | 宁波谱泰克科学仪器有限公司 | Method for judging fixed substance type based on Raman spectrum |
| CN113989577A (en) * | 2021-12-24 | 2022-01-28 | 中科视语(北京)科技有限公司 | Image classification method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018185320A1 (en) * | 2017-04-07 | 2018-10-11 | Limagrain Europe | Method for sorting corn kernels of a batch of corn kernels |
-
2022
- 2022-05-26 CN CN202210580632.4A patent/CN114951047B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2576528A1 (en) * | 1985-01-30 | 1986-08-01 | Hotchkiss Brandt Sogeme | Processing method for the separating of objects |
| CN101697167A (en) * | 2009-10-30 | 2010-04-21 | 邱建林 | Clustering-decision tree based selection method of fine corn seeds |
| CN104751166A (en) * | 2013-12-30 | 2015-07-01 | 中国科学院深圳先进技术研究院 | Spectral angle and Euclidean distance based remote-sensing image classification method |
| CN104063710A (en) * | 2014-06-13 | 2014-09-24 | 武汉理工大学 | Method for removing abnormal spectrum in actual measurement spectrum curve based on support vector machine model |
| CN107671011A (en) * | 2017-09-20 | 2018-02-09 | 南京创优科技有限责任公司 | A kind of feeding sorting unit based on grey states sequence |
| WO2019056402A1 (en) * | 2017-09-20 | 2019-03-28 | 南京创优科技有限责任公司 | Grayscale state sequence based feed sorting device |
| CN209291395U (en) * | 2018-12-28 | 2019-08-23 | 深圳市大恒精密技术有限公司 | Material optical fiber screening device |
| CN113721121A (en) * | 2021-09-02 | 2021-11-30 | 长江存储科技有限责任公司 | Fault detection method and device for semiconductor process |
| CN113791062A (en) * | 2021-09-17 | 2021-12-14 | 宁波谱泰克科学仪器有限公司 | Method for judging fixed substance type based on Raman spectrum |
| CN113989577A (en) * | 2021-12-24 | 2022-01-28 | 中科视语(北京)科技有限公司 | Image classification method and device |
Non-Patent Citations (1)
| Title |
|---|
| 汪金花.欧氏距离.《遥感技术与应用》.测绘出版社,2015,(第1版),第102-103页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114951047A (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858406B (en) | Key frame extraction method based on joint point information | |
| CN101576956B (en) | On-line character detection method based on machine vision and system thereof | |
| US20160196467A1 (en) | Three-Dimensional Face Recognition Device Based on Three Dimensional Point Cloud and Three-Dimensional Face Recognition Method Based on Three-Dimensional Point Cloud | |
| CN108491838B (en) | Pointer type instrument indicating number reading method based on SIFT and HOUGH | |
| CN110472652B (en) | Small sample classification method based on semantic guidance | |
| CN103415825A (en) | System and method for gesture recognition | |
| CN102629385A (en) | Object matching and tracking system based on multiple camera information fusion and method thereof | |
| CN106296742A (en) | A kind of online method for tracking target of combination Feature Points Matching | |
| CN110308795B (en) | Dynamic gesture recognition method and system | |
| CN103425969A (en) | Detection system and detection method for identifying type of wheel hub | |
| CN110689535A (en) | Workpiece identification method and device, electronic equipment and storage medium | |
| CN109840480B (en) | Interaction method and interaction system of smart watch | |
| CN110852388A (en) | Improved SMOTE algorithm based on K-means | |
| CN111784093A (en) | Enterprise rework auxiliary judgment method based on electric power big data analysis | |
| CN112070837A (en) | Part positioning and grabbing method and system based on visual analysis | |
| CN114951047B (en) | Universal intelligent sorting method in vibration feeding based on optical fiber sensor | |
| Özaydın et al. | A comparison of cnn and classic features for image retrieval | |
| US20170024869A1 (en) | Image processing device, image sensor, and image processing method | |
| Wu et al. | Location recognition algorithm for vision-based industrial sorting robot via deep learning | |
| CN105631857B (en) | A kind of scratch detection method and apparatus of optical element surface | |
| CN104954743B (en) | A kind of polyphaser semantic association method for tracking target | |
| CN112329191A (en) | Modal identification method and transition mode fault detection method in multi-mode process | |
| CN109993118B (en) | Action recognition method and system | |
| Ding et al. | Similar hand gesture recognition by automatically extracting distinctive features | |
| CN110969111A (en) | Automatic identification and classification method for mechanical part digital drawing |
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 |