CN116990321B - Image recognition-based sheath flat cable product quality analysis system - Google Patents
Image recognition-based sheath flat cable product quality analysis system Download PDFInfo
- Publication number
- CN116990321B CN116990321B CN202311264529.XA CN202311264529A CN116990321B CN 116990321 B CN116990321 B CN 116990321B CN 202311264529 A CN202311264529 A CN 202311264529A CN 116990321 B CN116990321 B CN 116990321B
- Authority
- CN
- China
- Prior art keywords
- product
- detected
- module
- unit
- temperature
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 76
- 230000007547 defect Effects 0.000 claims abstract description 82
- 239000011241 protective layer Substances 0.000 claims abstract description 31
- 238000007689 inspection Methods 0.000 claims abstract description 20
- 230000007306 turnover Effects 0.000 claims abstract description 7
- 238000007599 discharging Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 47
- 238000001931 thermography Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 18
- 230000001105 regulatory effect Effects 0.000 claims description 16
- 230000033228 biological regulation Effects 0.000 claims description 15
- 238000005452 bending Methods 0.000 claims description 12
- 238000005096 rolling process Methods 0.000 claims description 12
- 239000010410 layer Substances 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000017525 heat dissipation Effects 0.000 claims description 6
- 238000010438 heat treatment Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000001276 controlling effect Effects 0.000 claims description 5
- 238000005520 cutting process Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 230000004069 differentiation Effects 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/952—Inspecting the exterior surface of cylindrical bodies or wires
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R1/00—Details of instruments or arrangements of the types included in groups G01R5/00 - G01R13/00 and G01R31/00
- G01R1/02—General constructional details
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/003—Environmental or reliability tests
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8858—Flaw counting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Environmental & Geological Engineering (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a sheath flat cable product quality analysis system based on image recognition, which comprises a feeding port, a temperature adjusting module, a first checking module, a turnover module, a second checking module, an electric performance checking module, an analysis module and a discharging port; the feed inlet is used for feeding a product to be detected; the temperature adjusting module is used for adjusting the temperature; the first inspection module and the second inspection module are used for detecting defects of the product to be detected; the electrical performance checking module is used for detecting the electrical performance of the product to be detected; the analysis module is used for analyzing whether the quality of the product to be detected is qualified or not; the discharge port is used for delivering the detected product. According to the scheme, the image recognition technology is adopted, so that defects on the surface and inside of the protective layer of the sheath flat cable can be accurately analyzed, meanwhile, the quality of a cable product can be analyzed from multiple angles through checking the electrical property of the cable, and unqualified products are prevented from flowing out.
Description
Technical Field
The invention relates to the field of cable production, in particular to a sheath flat cable product quality analysis system based on image recognition.
Background
The prior art, such as CN114399237a, discloses a method and a system for intelligently detecting the quality of a cable production process, wherein the method comprises the following steps: obtaining product structure data of a first production cable; performing process complexity analysis to obtain first production complexity; if the first production complexity is within the preset production complexity, a quality detection model library is constructed, and a first matching detection model is obtained by carrying out process flow characteristic analysis on the first identification node and carrying out model matching from the quality detection model library; the first detection unit calls a first matching detection model to obtain quality detection information output by a first identification node; and (5) judging the quality to be qualified, and if the quality is qualified, detecting the second identification nodes until the detection of the plurality of identification nodes is finished.
Another typical cable reel quality detection system based on computer vision disclosed in the prior art of CN113552138A comprises a reel, a mobile terminal for shooting the reel, a quality detection cloud platform connected to the output end of the mobile terminal in a bidirectional electrical manner, the mobile terminal comprising a microprocessor, a camera unit and a 5G module, the mobile terminal being connected to the quality detection cloud platform by the 5G module in a wireless manner, the quality detection cloud platform comprising a data transceiver unit, a database, a central processor, an image analysis unit and a feedback analysis unit.
Looking again at a method and system for monitoring and improving the quality of an interconnecting cable system as disclosed in the prior art of WO2006050985A1, which compares the physical connection status of cable links in a network with management data concerning said cable links in network management, the coordinator system uses the data of one or several existing databases, analyzes the data retrieved based on one or more databases, and the system generation engineer uses the mapping system to perform detailed work of the measurements.
The traditional cable quality analysis is difficult to accurately detect and analyze for some complex defects such as tiny surface flaws or internal structure problems, and consumes more manpower and material resources, so as to solve the common problems in the field.
Disclosure of Invention
The invention aims to provide a sheath flat cable product quality analysis system based on image recognition aiming at the defects existing at present.
In order to overcome the defects in the prior art, the invention adopts the following technical scheme:
a sheath flat cable product quality analysis system based on image recognition comprises a feeding port, a temperature adjusting module, a first checking module, a turnover module, a second checking module, an electric performance checking module, an analysis module and a discharging port; the feed inlet is used for feeding a product to be detected; the temperature adjusting module comprises an adjusting bin and a plurality of adjusting components, the adjusting bin is used for adjusting the temperature of a product to be detected, and the adjusting components are arranged on the first checking module, the overturning module, the second checking module and the electrical performance checking module and used for adjusting the temperature of each module; the first inspection module is used for detecting defects of the first surface of the product to be detected and internal defects; the overturning module is used for overturning the product to be detected; the second inspection module is used for detecting defects of the second surface of the product to be detected; the electrical performance checking module is used for detecting the electrical performance of the product to be detected; the analysis module is used for analyzing whether the quality of the product to be detected is qualified or not; the discharge port is used for delivering the detected product.
Further, the first inspection module comprises a rolling device, a bending device, a first shooting device and a thermal imaging device, wherein the rolling device is used for rolling a product to be detected, the bending device is used for bending the product to be detected, the first shooting device is used for shooting defects on the first surface of the product to be detected, and the thermal imaging device is used for thermal imaging the product to be detected;
the second inspection module comprises a second shooting device, and the second shooting device is used for shooting defects on a second surface of the product to be inspected.
Further, the electrical performance inspection module comprises a power supply unit, a test unit and a detection clamp; the power supply unit is used for providing power, the test unit comprises a plurality of measuring circuits and a plurality of detectors, the test unit is used for testing the electrical properties of the product to be tested in the plurality of test circuits, and the detectors are used for detecting various parameters in the measuring circuits; the detection clamp is connected with the test unit, two detection clamps are arranged, and the two detection clamps are respectively used for clamping two ends of a product to be detected.
Still further, the analysis module includes signal receiving module, electrical property analysis module, protective layer quality analysis module and early warning module, signal receiving module is used for receiving the signal of first shooting device, second shooting device, thermal imaging device and measuring element, electrical property analysis module is used for analyzing the electrical property of waiting to detect the product, protective layer quality analysis module is used for analyzing the quality of the protective layer of waiting to detect the product, early warning module is used for sending the early warning signal to the user.
Further, the protection layer quality analysis module comprises an image processing unit, a defect analysis unit and a comparison unit; the image processing unit is used for processing images shot by the first shooting device, the second shooting device and the thermal imaging device, the defect analysis unit is used for analyzing the images processed by the image processing unit and generating defect scores, and the comparison unit is used for comparing data.
Further, the working process of the sheath flat cable product quality analysis system comprises the following steps:
s1, inputting a product to be detected into an adjusting bin through a feed inlet;
s2, a temperature regulation module sets a temperature index, a regulation bin regulates the temperature of a product to be detected to be the same as the temperature index, and a regulation component regulates the temperature of each system to be the same as the temperature index;
s3, the rolling device and the bending device roll and bend the product to be detected respectively; the first shooting device shoots a first surface of a product to be detected, the thermal imaging device shoots a thermal image of the product to be detected, and the images of the first shooting device and the thermal imaging device are sent to the analysis module;
s4, the turnover module turns over the product to be detected; the second shooting device shoots a second surface of the product to be detected;
s5, the electric performance checking module accesses the product to be detected into the measuring unit, and checks the electric performance of the product to be detected;
s6, analyzing the quality of the product to be detected by an analysis module, and if the quality does not reach the standard, conveying the product to be detected to an unqualified product storage bin through a discharge hole; if the quality reaches the standard, judging whether the specified detection times are reached, if so, conveying the product to be detected to a qualified product storage bin through a discharge hole, and if not, changing the temperature index set by the temperature regulation module, conveying the product to be detected to a regulation bin, and returning to S2.
Further, the analysis module analyzes the quality of the product to be detected, including the steps of:
s61, the image processing unit performs noise reduction processing on the images shot by the first shooting device, the second shooting device and the thermal imaging device;
s62, extracting defects of products to be detected in each image by a defect analysis unit;
s63, the defect analysis unit generates a defect score according to the following formula:
SCORE=；
wherein, SCORE is the defect SCORE, k is the defect number of the surface of the protective layer,the number of pixels included in the ith defect of the protective layer surface, < >>The gray value of the j pixel of the ith defect on the surface of the protective layer, K is the number of defects in the protective layer, +.>The number of pixels included for the mth defect inside the protective layer, < >>The gray value of the nth pixel of the mth defect in the protective layer is T, and is the difference between the actual temperature of the product to be detected and the optimal working temperature of the product to be detected;
s64, the comparison unit receives the data of the detector and the defect analysis unit, compares the voltage value and the current value detected by the detector with the corresponding electrical performance threshold, and if the data detected by the detector is within the range of the electrical performance threshold, the electrical performance of the product to be detected is normal; and comparing the defect score with a defect score threshold, and if the defect score is smaller than the defect score threshold, qualifying the protection layer of the product to be detected.
Further, the electrical performance inspection module inspects the electrical performance of the product to be inspected, including the following steps:
s51, the detection clamp is connected into a measuring circuit in the measuring unit, and two ends of a product to be detected are clamped;
s52, the power supply unit is started, and the detector detects the current value of the measuring circuit and the voltage value of the reference resistor in the measuring circuit and sends the detected current value and the voltage value to the analysis module;
s53, cutting off the power supply, changing the measuring circuit to which the detecting clamp is connected, and returning to S52 until the detecting clamp is connected to all the measuring circuits in the measuring unit.
The beneficial effect of this scheme: through adopting image recognition technology, can accurate analysis sheath flat cable's protective layer surface and inside defect, combine the upset module simultaneously to inspect the electrical property of cable, can realize analyzing the quality of cable product from the multi-angle, avoid unqualified product to flow out.
Drawings
The invention will be further understood from the following description taken 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 like parts in the different views.
FIG. 1 is a schematic diagram of the overall structure of the present invention.
Fig. 2 is a flow chart of the operation of the present invention.
FIG. 3 is a flow chart of the invention for analyzing the quality of a product to be inspected.
Fig. 4 is a flow chart of the electrical performance inspection of the product to be inspected according to the present invention.
Detailed Description
The following embodiments of the present invention are described in terms of specific examples, and those skilled in the art will appreciate the advantages and effects of the present invention from the disclosure herein. The invention is capable of other and different embodiments and its several details are capable of modification and variation in various respects, all without departing from the spirit of the present invention. The drawings of the present invention are merely schematic illustrations, and are not intended to be drawn to actual dimensions. The following embodiments will further illustrate the related art content of the present invention in detail, but the disclosure is not intended to limit the scope of the present invention.
Embodiment one: according to fig. 1, 2, 3 and 4, the embodiment provides a sheath flat cable product quality analysis system based on image recognition, which comprises a feeding port, a temperature adjusting module, a first checking module, a turnover module, a second checking module, an electrical performance checking module, an analysis module and a discharging port; the feed inlet is used for feeding a product to be detected; the temperature adjusting module comprises an adjusting bin and a plurality of adjusting components, the adjusting bin is used for adjusting the temperature of a product to be detected, and the adjusting components are arranged on the first checking module, the overturning module, the second checking module and the electrical performance checking module and used for adjusting the temperature of each module; the first inspection module is used for detecting defects of the first surface of the product to be detected and internal defects; the overturning module is used for overturning the product to be detected; the second inspection module is used for detecting defects of the second surface of the product to be detected; the electrical performance checking module is used for detecting the electrical performance of the product to be detected; the analysis module is used for analyzing whether the quality of the product to be detected is qualified or not; the discharge port is used for delivering the detected product.
Further, the first inspection module comprises a rolling device, a bending device, a first shooting device and a thermal imaging device, wherein the rolling device is used for rolling a product to be detected, the bending device is used for bending the product to be detected, the first shooting device is used for shooting defects on the first surface of the product to be detected, and the thermal imaging device is used for thermal imaging the product to be detected;
the second inspection module comprises a second shooting device, and the second shooting device is used for shooting defects on a second surface of the product to be inspected.
Specifically, the thermal imaging device is used for analyzing whether the inside of the product to be detected is defective or not by performing thermal imaging on the product to be detected so as to know the internal condition of the product to be detected.
Further, the electrical performance inspection module comprises a power supply unit, a test unit and a detection clamp; the power supply unit is used for providing power, the test unit comprises a plurality of measuring circuits and a plurality of detectors, the test unit is used for testing the electrical properties of the product to be tested in the plurality of test circuits, and the detectors are used for detecting various parameters in the measuring circuits; the detection clamp is connected with the test unit, two detection clamps are arranged, and the two detection clamps are respectively used for clamping two ends of a product to be detected.
Still further, the analysis module includes signal receiving module, electrical property analysis module, protective layer quality analysis module and early warning module, signal receiving module is used for receiving the signal of first shooting device, second shooting device, thermal imaging device and measuring element, electrical property analysis module is used for analyzing the electrical property of waiting to detect the product, protective layer quality analysis module is used for analyzing the quality of the protective layer of waiting to detect the product, early warning module is used for sending the early warning signal to the user.
Specifically, the product to be detected comprises a wire core and a protective layer, wherein the wire core is used for conveying electric energy, and the protective layer is used for protecting the wire core.
Further, the protection layer quality analysis module comprises an image processing unit, a defect analysis unit and a comparison unit; the image processing unit is used for processing images shot by the first shooting device, the second shooting device and the thermal imaging device, the defect analysis unit is used for analyzing the images processed by the image processing unit and generating defect scores, and the comparison unit is used for comparing data.
Further, the working process of the sheath flat cable product quality analysis system comprises the following steps:
s1, inputting a product to be detected into an adjusting bin through a feed inlet;
s2, a temperature regulation module sets a temperature index, a regulation bin regulates the temperature of a product to be detected to be the same as the temperature index, and a regulation component regulates the temperature of each system to be the same as the temperature index;
s3, the rolling device and the bending device roll and bend the product to be detected respectively; the first shooting device shoots a first surface of a product to be detected, the thermal imaging device shoots a thermal image of the product to be detected, and the images of the first shooting device and the thermal imaging device are sent to the analysis module;
s4, the turnover module turns over the product to be detected; the second shooting device shoots a second surface of the product to be detected;
s5, the electric performance checking module accesses the product to be detected into the measuring unit, and checks the electric performance of the product to be detected;
s6, analyzing the quality of the product to be detected by an analysis module, and if the quality does not reach the standard, conveying the product to be detected to an unqualified product storage bin through a discharge hole; if the quality reaches the standard, judging whether the specified detection times are reached, if so, conveying the product to be detected to a qualified product storage bin through a discharge hole, and if not, changing the temperature index set by the temperature regulation module, conveying the product to be detected to a regulation bin, and returning to S2.
Specifically, the temperature set by the temperature adjusting module is within the normal working temperature of the product to be detected, the normal working temperature is determined by the type of the product to be detected, and the electric performance and the protection layer quality of the product to be detected in different temperature states can be known through temperature adjustment, so that the quality of the product to be detected is more comprehensively analyzed.
Specifically, the designated detection times are determined by the normal working temperature range of the product to be detected, the product to be detected starts from the lowest temperature capable of working normally, and is detected every 10 ℃ until the highest temperature capable of working normally of the product to be detected is reached, so that the quality of the product to be detected at different temperatures is measured. For example, the normal working temperature of the product to be detected is between-11 ℃ and 43 ℃ when the product to be detected is produced, and the product to be detected is detected at-11, -1, 9, 19, 29, 39 and 43 ℃ once.
Further, the analysis module analyzes the quality of the product to be detected, including the steps of:
s61, the image processing unit performs noise reduction processing on the images shot by the first shooting device, the second shooting device and the thermal imaging device;
s62, extracting defects of products to be detected in each image by a defect analysis unit;
s63, the defect analysis unit generates a defect score according to the following formula:
SCORE=；
wherein, SCORE is the defect SCORE, k is the defect number of the surface of the protective layer,the number of pixels included in the ith defect of the protective layer surface, < >>The gray value of the j pixel of the ith defect on the surface of the protective layer, K is the number of defects in the protective layer, +.>The number of pixels included for the mth defect inside the protective layer, < >>The gray value of the nth pixel of the mth defect in the protective layer is T, and is the difference between the actual temperature of the product to be detected and the optimal working temperature of the product to be detected;
specifically, if a defect exists in the product, the position of the internal defect can generate uneven heat distribution, and the internal heat distribution of the product to be detected can be known according to the image shot by the thermal imaging device, so that the defect in the product to be detected is obtained.
S64, the comparison unit receives the data of the detector and the defect analysis unit, compares the voltage value and the current value detected by the detector with the corresponding electrical performance threshold, and if the data detected by the detector is within the range of the electrical performance threshold, the electrical performance of the product to be detected is normal; and comparing the defect score with a defect score threshold, and if the defect score is smaller than the defect score threshold, qualifying the protection layer of the product to be detected.
Specifically, if the electrical property of the product to be detected is normal and the quality of the protective layer is qualified, the quality of the product to be detected reaches the standard.
Further, the electrical performance inspection module inspects the electrical performance of the product to be inspected, including the following steps:
s51, the detection clamp is connected into a measuring circuit in the measuring unit, and two ends of a product to be detected are clamped;
s52, the power supply unit is started, and the detector detects the current value of the measuring circuit and the voltage value of the reference resistor in the measuring circuit and sends the detected current value and the voltage value to the analysis module;
s53, cutting off the power supply, changing the measuring circuit to which the detecting clamp is connected, and returning to S52 until the detecting clamp is connected to all the measuring circuits in the measuring unit.
The beneficial effect of this scheme: through adopting image recognition technology, can accurate analysis sheath flat cable's protective layer surface and inside defect, the electric property that passes through the upset module to the cable is inspected simultaneously, can realize analyzing the quality of cable product from the multi-angle, avoid unqualified product to flow out.
Embodiment two: this embodiment should be understood to include all the features of any one of the foregoing embodiments, and be further improved on the basis thereof, and further include a parameter adjustment method including a temperature adjustment module:
the system comprises a regulating bin, a regulating assembly, an algorithm unit, a detection unit and a control unit, wherein the regulating bin and the regulating assembly are both provided with the algorithm unit and the detection unit, the detection unit is used for measuring the actual temperature of a detection object, the detection object comprises a system regulated by a product to be detected and the regulating assembly, and the algorithm unit regulates and controls parameters of the regulating bin and the regulating assembly by utilizing the following formula:
parameter adjustment amount=a (t) (current error+b (t) cumulative error+c (t) error change rate);
wherein A (t), B (t) and C (t) are respectively adaptive parameters of proportion, integration and differentiation at the moment t; the current error is the error between the temperature index set at the time t and the actual temperature of the detection object; the accumulated error is an accumulated value of a plurality of errors generated from the start of temperature adjustment to the time t; the error change rate is the change rate of a plurality of errors generated from the start of temperature adjustment to the time t;
specifically, the parameter adjustment amount may be the power of the heating element or the heat dissipation element of the adjustment bin or the adjustment assembly, when the object of the parameter adjustment amount is the heating element or the heat dissipation element of the adjustment bin, the detection object is the product to be detected, and when the object of the parameter adjustment amount is the heating element or the heat dissipation element of the adjustment element, the detection object is each system adjusted by the adjustment element.
Specifically, the adjustment formula of the adaptive parameter is as follows:
A(t) = A0 + ΔA(t)； B(t) = B0 + ΔB(t) ；C(t) = C0 + ΔC(t)；
wherein A0, B0 and C0 are initial parameters preset by a person skilled in the art according to experience, and delta A (t), delta B (t) and delta C (t) are parameter correction amounts calculated according to error indexes at the moment t;
the error index is obtained according to the following formula:
D(t) =*dy；D1(t) =/>dy1；D2(t) =/>dy2
wherein D (t) is an A (t) error index, D1 (t) is a B (t) error index, and D2 (t) is a C (t) error index; d (t 0) is an error index of A (t) at the last parameter adjustment; d1 (t 0) is an error index of B (t) at the time of the last parameter adjustment; d2 (t 0) is an error index of C (t) at the time of the last parameter adjustment; t0 is the parameter adjustment amount in the last parameter adjustment, and t0 is stored and extracted by the algorithm unit; Δt is the time interval between two adjustments, which is determined by one skilled in the art as required when designing the algorithm unit; dy, dy1, dy2 are index correction steps for controlling the change amplitude of the error index, when D (t 0) >0.5, dy=0.7, when D (t 0) +.0.5, dy=0.3, when D1 (t 0) >0.5, dy1=0.7, when D1 (t 0) +.0.5, dy1=0.3, when D2 (t 0) >0.5, dy2=0.7, when D2 (t 0) +.0.5, dy2=0.3;
it is worth noting that the values of D (t), D1 (t), D2 (t) are set to 1 at the first adjustment.
From the error signal, a parameter correction amount can be calculated:
ΔA(t) = γp * D(t)； ΔB(t) = γi * ∫D1(t) dt ；ΔC(t) = γd * dD2(t)/dt；
where γp, γi and γd are adaptive parameter-adjusted initial gain parameters obtained empirically by those skilled in the art for controlling the speed and magnitude of parameter correction.
The beneficial effects of this embodiment are: by continuously regulating and controlling the parameters of the temperature regulating module, when the set temperature index and the actual temperature of the detection object are large in difference, the difference between the set temperature index and the actual temperature of the detection object can be quickly shortened; when the set temperature index and the actual temperature difference of the detection object are smaller, the parameters are finely adjusted, so that the performance and the stability of the temperature adjusting module are improved.
The foregoing disclosure is only a preferred embodiment of the present invention and is not intended to limit the scope of the invention, so that all equivalent technical changes made by applying the description of the present invention and the accompanying drawings are included in the scope of the present invention, and in addition, elements in the present invention can be updated as the technology develops.
Claims (7)
1. A sheath flat cable product quality analysis system based on image recognition is characterized in that: the device comprises a feed inlet, a temperature adjusting module, a first checking module, a turnover module, a second checking module, an electric performance checking module, an analysis module and a discharge outlet; the feed inlet is used for feeding a product to be detected; the temperature adjusting module comprises an adjusting bin and a plurality of adjusting components, the adjusting bin is used for adjusting the temperature of a product to be detected, and the adjusting components are arranged on the first checking module, the overturning module, the second checking module and the electrical performance checking module and used for adjusting the temperature of each module; the first inspection module is used for detecting defects of the first surface of the product to be detected and internal defects; the overturning module is used for overturning the product to be detected; the second inspection module is used for detecting defects of the second surface of the product to be detected; the electrical performance checking module is used for detecting the electrical performance of the product to be detected; the analysis module is used for analyzing whether the quality of the product to be detected is qualified or not; the discharge hole is used for discharging the detected product;
specifically, the first inspection module comprises a rolling device, a bending device, a first shooting device and a thermal imaging device, wherein the rolling device is used for rolling a product to be detected, the bending device is used for bending the product to be detected, the first shooting device is used for shooting defects on the first surface of the product to be detected, and the thermal imaging device is used for thermal imaging the product to be detected;
the second inspection module comprises a second shooting device, wherein the second shooting device is used for shooting defects on a second surface of the product to be detected; the regulating bin and the regulating assembly are both provided with an algorithm unit and a detection unit, the detection unit is used for measuring the actual temperature of a detection object, the detection object comprises a system regulated by a product to be detected and the regulating assembly, and the algorithm unit regulates and controls the parameters of the regulating bin and the regulating assembly by utilizing the following formula:
parameter adjustment amount=a (t) (current error+b (t) cumulative error+c (t) error change rate);
wherein A (t), B (t) and C (t) are respectively adaptive parameters of proportion, integration and differentiation at the moment t; the current error is the error between the temperature index set at the time t and the actual temperature of the detection object; the accumulated error is an error accumulated value generated from the start of temperature adjustment to the time t; the error change rate is the error change rate generated from the start of temperature adjustment to the time t;
specifically, the parameter adjustment amount is the power of the heating element or the heat dissipation element of the adjustment bin or the adjustment assembly, when the object of the parameter adjustment amount is the heating element or the heat dissipation element of the adjustment bin, the detection object is a product to be detected, and when the object of the parameter adjustment amount is the heating element or the heat dissipation element of the adjustment assembly, the detection object is each system adjusted by the adjustment assembly;
specifically, the adjustment formula of the adaptive parameter is as follows:
A(t) = A0 + ΔA(t)； B(t) = B0 + ΔB(t) ；C(t) = C0 + ΔC(t)；
wherein A0, B0 and C0 are initial parameters preset according to experience, and delta A (t), delta B (t) and delta C (t) are parameter correction amounts calculated according to error indexes at the moment t;
the error index is obtained according to the following formula:
D(t) =*dy；D1(t) =/>dy1；D2(t) =/>dy2
wherein D (t) is an A (t) error index, D1 (t) is a B (t) error index, and D2 (t) is a C (t) error index; d (t 0) is an error index of A (t) at the last parameter adjustment; d1 (t 0) is an error index of B (t) at the time of the last parameter adjustment; d2 (t 0) is an error index of C (t) at the time of the last parameter adjustment; t0 is the parameter adjustment amount in the last parameter adjustment, and t0 is stored and extracted by the algorithm unit; Δt is the time interval between two adjustments, which is determined on demand when designing the algorithm unit; dy, dy1, dy2 are index correction steps for controlling the change amplitude of the error index, when D (t 0) >0.5, dy=0.7, when D (t 0) < 0.5, dy=0.3, when D1 (t 0) >0.5, dy1=0.7, when D1 (t 0) < 0.5, dy1=0.3, when D2 (t 0) >0.5, dy2=0.7, when D2 (t 0) < 0.5, dy2=0.3;
the values of D (t), D1 (t), D2 (t) are set to 1 at the first adjustment.
Calculating a parameter correction amount based on the error signal:
ΔA(t) = γp * D(t)； ΔB(t) = γi * ∫D1(t) dt ；ΔC(t) = γd * dD2(t)/dt；
where γp, γi and γd are empirically derived adaptive parameter adjusted initial gain parameters for controlling the speed and magnitude of parameter correction.
2. The image recognition-based sheath flat cable product quality analysis system as claimed in claim 1, wherein: the electrical performance checking module comprises a power supply unit, a testing unit and a detecting clamp; the power supply unit is used for providing power, the test unit comprises a plurality of measuring circuits and a plurality of detectors, the test unit is used for testing the electrical properties of the product to be tested in the plurality of test circuits, and the detectors are used for detecting various parameters in the measuring circuits; the detection clamp is connected with the test unit, two detection clamps are arranged, and the two detection clamps are respectively used for clamping two ends of a product to be detected.
3. The image recognition-based sheath flat cable product quality analysis system as claimed in claim 2, wherein: the analysis module comprises a signal receiving module, an electrical property analysis module, a protection layer quality analysis module and an early warning module, wherein the signal receiving module is used for receiving signals of the first shooting device, the second shooting device, the thermal imaging device and the measuring unit, the electrical property analysis module is used for analyzing electrical properties of products to be detected, the protection layer quality analysis module is used for analyzing quality of protection layers of the products to be detected, and the early warning module is used for sending early warning signals to users.
4. A jacketed flat cable product quality analysis system based on image recognition as in claim 3, wherein: the protective layer quality analysis module comprises an image processing unit, a defect analysis unit and a comparison unit; the image processing unit is used for processing images shot by the first shooting device, the second shooting device and the thermal imaging device, the defect analysis unit is used for analyzing the images processed by the image processing unit and generating defect scores, and the comparison unit is used for comparing data.
5. The image recognition-based sheath flat cable product quality analysis system of claim 4, wherein the sheath flat cable product quality analysis system comprises the following steps:
s1, inputting a product to be detected into an adjusting bin through a feed inlet;
s2, a temperature regulation module sets a temperature index, a regulation bin regulates the temperature of a product to be detected to be the same as the temperature index, and a regulation component regulates the temperature of each system to be the same as the temperature index;
s3, the rolling device and the bending device roll and bend the product to be detected respectively; the first shooting device shoots a first surface of a product to be detected, the thermal imaging device shoots a thermal image of the product to be detected, and the images of the first shooting device and the thermal imaging device are sent to the analysis module;
s4, the turnover module turns over the product to be detected; the second shooting device shoots a second surface of the product to be detected;
s5, the electric performance checking module accesses the product to be detected into the measuring unit, and checks the electric performance of the product to be detected;
s6, analyzing the quality of the product to be detected by an analysis module, and if the quality does not reach the standard, conveying the product to be detected to an unqualified product storage bin through a discharge hole; if the quality reaches the standard, judging whether the specified detection times are reached, if so, conveying the product to be detected to a qualified product storage bin through a discharge hole, and if not, changing the temperature index set by the temperature regulation module, conveying the product to be detected to a regulation bin, and returning to S2.
6. The image recognition-based sheath flat cable product quality analysis system as claimed in claim 5, wherein: the analysis module analyzes the quality of the product to be detected, and comprises the following steps:
s61, the image processing unit performs noise reduction processing on the images shot by the first shooting device, the second shooting device and the thermal imaging device;
s62, extracting defects of products to be detected in each image by a defect analysis unit;
s63, the defect analysis unit generates a defect score according to the following formula:
SCORE=；
wherein, SCORE is the defect SCORE, k is the defect number of the surface of the protective layer,the number of pixels included in the ith defect of the protective layer surface, < >>The gray value of the j pixel of the ith defect on the surface of the protective layer, K is the number of defects in the protective layer, +.>The number of pixels included for the mth defect inside the protective layer, < >>The gray value of the nth pixel of the mth defect in the protective layer is T, and is the difference between the actual temperature of the product to be detected and the optimal working temperature of the product to be detected;
s64, the comparison unit receives the data of the detector and the defect analysis unit, compares the voltage value and the current value detected by the detector with the corresponding electrical performance threshold, and if the data detected by the detector is within the range of the electrical performance threshold, the electrical performance of the product to be detected is normal; and comparing the defect score with a defect score threshold, and if the defect score is smaller than the defect score threshold, qualifying the protection layer of the product to be detected.
7. The image recognition-based sheath flat cable product quality analysis system of claim 6, wherein the electrical performance inspection module inspects the electrical performance of the product to be inspected comprising the steps of:
s51, the detection clamp is connected into a measuring circuit in the measuring unit, and two ends of a product to be detected are clamped;
s52, the power supply unit is started, and the detector detects the current value of the measuring circuit and the voltage value of the reference resistor in the measuring circuit and sends the detected current value and the voltage value to the analysis module;
s53, cutting off the power supply, changing the measuring circuit to which the detecting clamp is connected, and returning to S52 until the detecting clamp is connected to all the measuring circuits in the measuring unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311264529.XA CN116990321B (en) | 2023-09-28 | 2023-09-28 | Image recognition-based sheath flat cable product quality analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311264529.XA CN116990321B (en) | 2023-09-28 | 2023-09-28 | Image recognition-based sheath flat cable product quality analysis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116990321A CN116990321A (en) | 2023-11-03 |
| CN116990321B true CN116990321B (en) | 2023-12-22 |
Family
ID=88534325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311264529.XA Active CN116990321B (en) | 2023-09-28 | 2023-09-28 | Image recognition-based sheath flat cable product quality analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116990321B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105424720A (en) * | 2015-11-11 | 2016-03-23 | 江苏长城电缆有限公司 | Cable detection device and detection method based on image processing |
| CN109765461A (en) * | 2019-02-21 | 2019-05-17 | 国网山东省电力公司临沂供电公司 | Transmission line of electricity monitoring system and method based on temperature monitoring |
| CN111351801A (en) * | 2020-03-11 | 2020-06-30 | 春光线缆有限公司 | Wire and cable defect detection system |
| CN113534012A (en) * | 2021-07-28 | 2021-10-22 | 广东电网有限责任公司 | Line loss detection device and detection method |
| CN217111777U (en) * | 2022-04-10 | 2022-08-02 | 上海比拉兹科技有限公司 | Car cable performance detection device |
| CN218099406U (en) * | 2022-07-14 | 2022-12-20 | 武汉联胜光电技术有限公司 | Multicore copper wire electrical property testing arrangement |
| CN115598177A (en) * | 2022-12-14 | 2023-01-13 | 西南交通大学（Cn） | Differential method based vehicle-mounted cable internal thermal defect contour detection method |
| CN116188752A (en) * | 2022-12-20 | 2023-05-30 | 广州番禺电缆集团有限公司 | Cable joint temperature anomaly detection device, method and equipment based on image recognition |
| CN116183629A (en) * | 2023-02-16 | 2023-05-30 | 应启围 | Cable damage detection device and detection method thereof |
-
2023
- 2023-09-28 CN CN202311264529.XA patent/CN116990321B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105424720A (en) * | 2015-11-11 | 2016-03-23 | 江苏长城电缆有限公司 | Cable detection device and detection method based on image processing |
| CN109765461A (en) * | 2019-02-21 | 2019-05-17 | 国网山东省电力公司临沂供电公司 | Transmission line of electricity monitoring system and method based on temperature monitoring |
| CN111351801A (en) * | 2020-03-11 | 2020-06-30 | 春光线缆有限公司 | Wire and cable defect detection system |
| CN113534012A (en) * | 2021-07-28 | 2021-10-22 | 广东电网有限责任公司 | Line loss detection device and detection method |
| CN217111777U (en) * | 2022-04-10 | 2022-08-02 | 上海比拉兹科技有限公司 | Car cable performance detection device |
| CN218099406U (en) * | 2022-07-14 | 2022-12-20 | 武汉联胜光电技术有限公司 | Multicore copper wire electrical property testing arrangement |
| CN115598177A (en) * | 2022-12-14 | 2023-01-13 | 西南交通大学（Cn） | Differential method based vehicle-mounted cable internal thermal defect contour detection method |
| CN116188752A (en) * | 2022-12-20 | 2023-05-30 | 广州番禺电缆集团有限公司 | Cable joint temperature anomaly detection device, method and equipment based on image recognition |
| CN116183629A (en) * | 2023-02-16 | 2023-05-30 | 应启围 | Cable damage detection device and detection method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116990321A (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170060664A1 (en) | Method for verifying bad pattern in time series sensing data and apparatus thereof | |
| US20150371134A1 (en) | Predicting circuit reliability and yield using neural networks | |
| CN111521915B (en) | High-voltage direct-current line corona onset field strength determination method and system | |
| JP3515756B2 (en) | Processing unit monitoring method | |
| CN116990321B (en) | Image recognition-based sheath flat cable product quality analysis system | |
| CN114022715A (en) | Method and device for detecting lead sealing defect of high-voltage cable terminal | |
| CN114757600A (en) | Heavy film inflation film manufacturing machine operation analysis management and control system based on data analysis | |
| CN113791337B (en) | Data processing-based quality analysis monitoring system for circuit board | |
| CN115147780A (en) | Infrared image identification method for cable accessory | |
| CN117239942B (en) | Ammeter with monitoring function | |
| CN112162011B (en) | Composite insulator defect detection method, equipment and storage medium | |
| JP5022746B2 (en) | Insulation abnormality diagnosis method and insulation abnormality diagnosis apparatus for electrical equipment | |
| CN117451785A (en) | Early warning method and system for thermal defect of suspension clamp | |
| US6154682A (en) | Self-checking circuit in microwave equipment | |
| CN117634938A (en) | Production quality detection method and system for seamless steel pipe | |
| CN114528721B (en) | Cable intermediate joint insulation state assessment method and system | |
| CN116184060A (en) | Abnormal monitoring method and system suitable for porcelain insulator live working | |
| CN109351786B (en) | Method for improving consistency of wire rod tissue based on infrared thermal imaging technology | |
| CN108469571B (en) | Cable state evaluation method based on multivariate test data analysis of trend line fitting | |
| CN113721116A (en) | Fault identification method and system based on partial discharge and oil pressure detection | |
| CN111179267A (en) | Quality monitoring method for laser cladding manufacturing process of part surface | |
| CN117309624B (en) | Temperature sensing cable performance evaluation method and system | |
| US20230333168A1 (en) | Method and device for battery detection | |
| CN116128810B (en) | Infrared defect detection method and system based on front end identification | |
| CN113649422A (en) | Hot image-based rough rolling billet quality detection system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |