CN102980536B - Brake pad steel back flatness detection system and method - Google Patents

Abstract

A kind of brake block steel back flatness detection system and method, this system comprises: image collecting device, some pressure detection are popped one's head in, upper computer module and power supply, image collecting device is connected with upper computer module, is sent to upper computer module in order to the brake block image on Real-time Collection streamline; Pressure detection probe is connected with upper computer module, pressure field information in order to gather brake block is sent to upper computer module, upper computer module, in order to analyze the image collected and pressure field information, analyzes the defect of brake block, obtains flatness situation and qualification rate; Power supply is popped one's head in image collecting device, pressure detection respectively and upper computer module is connected, with thinking that image collecting device, pressure detection probe and upper computer module provide electric power.The present invention has without the need to Human disturbance, counting accurately, and precision is high, production efficiency is high, the advantage that reduction labour intensity, real-time are high, practical.

Description

Brake pad steel back flatness detection system and method

technical field

The invention relates to the field of brake pad detection, in particular to a brake pad steel back flatness detection system and method.

Background technique

Automobile brake pads are the key components to ensure the safety of automobiles, and the flatness of the steel-backed products is an important shape and position error factor related to the quality of the brake pads. However, at present, the manual metering method is generally used to detect the flatness of the steel back of the brake pad. In this method, the worker reads the difference between the maximum and minimum readings of each point on the surface of the steel back to be measured as the measurement result of the flatness error value. The evaluation of flatness does not meet the minimum conditions, the accuracy is low, and the skill requirements of workers are high. Workers are prone to fatigue after working for a long time, the labor intensity is high, the efficiency is low, and it is easy to cause misoperation due to fatigue, which affects the measurement accuracy. Therefore, there are technical problems such as low measurement precision, low accuracy, high labor intensity and low efficiency in this kind of manual metering method for detecting the flatness of steel back products.

Contents of the invention

The purpose of the present invention is to provide a brake pad steel back flatness detection system to solve the problem of low measurement accuracy, low accuracy, high labor intensity and low efficiency in the prior art manual metering method to detect the brake pad steel back flatness question.

Another object of the present invention is to provide a method for detecting the flatness of the steel back of the brake pad, so as to solve the problem of low measurement accuracy, low accuracy, high labor intensity and low efficiency in the prior art manual metering method to detect the flatness of the steel back of the brake pad. technical problems.

In order to achieve the above object, the present invention provides a brake pad steel back flatness detection system, including: an image acquisition device, a number of pressure detection probes, a host computer module and a power supply, and the image acquisition device is connected to the host computer module for real-time acquisition of the assembly line The image of the brake pad on the upper computer is sent to the upper computer module; the pressure detection probe is connected to the upper computer module to collect the pressure field information of the brake pad and send it to the upper computer module, and the upper computer module is used to analyze the collected image and pressure field information Carry out analysis, analyze the defects of the brake pads, obtain the flatness and pass rate; the power supply is respectively connected with the image acquisition device, the pressure detection probe and the upper computer module, and is used to provide power for the image acquisition device, the pressure detection probe and the upper computer module; , the upper computer module further includes:

Human-computer interaction processing unit: used to accept the user's operation, realize the initialization work and parameter setting, and display the detection information and detection results in real time;

Image acquisition unit: respectively connected with the human-computer interaction processing unit and the image acquisition device, to drive the image acquisition device to collect the brake pad images on the assembly line in real time according to the user operations accepted by the human-computer interaction processing unit, and send the collected images to to the image processing unit;

Pressure field information acquisition unit: respectively connected with the human-computer interaction processing unit and the pressure detection probe, to drive the pressure detection probe to collect pressure field information according to the user operation accepted by the human-computer interaction processing unit, and send the collected pressure field information To the pressure field information processing unit;

Image processing unit: connected with the image acquisition unit to analyze and process the received brake pad images, analyze the defects of the brake pads, and obtain qualified and unqualified products;

Pressure field information processing unit: connected to the pressure field information collection unit, calculates the pressure field distribution of the brake pads, and calculates the flatness of the brake pads;

Statistical processing unit: connected with the image processing unit and the pressure field information processing unit, to count the flatness and qualification rate of a batch of brake pad products according to the processing results of the image processing unit and the pressure field information processing unit, and send them to the personnel computer interaction processing unit and database; and,

Database: used to store the flatness and qualification rate information of a batch of brake pad products.

According to the flatness detection system of the steel back of the brake pad described in the preferred embodiment of the present invention, the image acquisition device adopts a CMOS color camera.

According to the brake pad steel back flatness detection system described in the preferred embodiment of the present invention, the statistical processing unit generates a report on the flatness and pass rate of a batch of brake pad products in the form of an excel chart and sends it to the database and human computer interaction processing unit.

According to the brake pad steel back flatness detection system described in the preferred embodiment of the present invention, the number of the pressure detection probes is 20.

In order to achieve the above object, the present invention also provides a method for detecting the flatness of the steel back of the brake pad, comprising the following steps:

(1) Accept the user's operation, realize the initialization work and parameter setting;

(2) According to the user's operation, respectively drive the image acquisition device and the pressure detection probe to collect the brake pad image and pressure field information on the assembly line in real time;

(3) Use the gabor wavelet transform method to analyze and process the collected brake pad images, analyze the defects of the brake pads, and obtain qualified and unqualified products;

(4) Calculate the pressure field distribution of the brake pads through the collected pressure field information, and calculate the flatness of the brake pads;

(5) According to the results of steps (3) and (4), calculate the flatness and qualification rate of a batch of brake pad products, display the detection information and statistical results in real time, and store the statistical results.

According to the method for detecting the flatness of the steel back of the brake pad described in the preferred embodiment of the present invention, the parameter setting in step (1) includes: parallax coefficient, segmentation threshold, area operator, gabor parameter, and detection point related detection parameters, Effective detection points, X-axis correction coefficient and Y-axis correction coefficient.

According to the method for detecting the flatness of the steel back of the brake pad described in the preferred embodiment of the present invention, step (3) specifically includes:

First, extract the Gabor transformation features of multiple qualified samples, calculate the multi-directional and multi-scale Gabor transformation features of each pixel pixel by pixel, and form the Gabor feature representation of the steel back of the brake pad;

Then, Gabor transformation is performed on the defective brake pad products, the two are matched and registered, the flatness of the brake pad products is qualitatively analyzed, and unqualified brake pad products are found.

According to the method for detecting the flatness of the steel back of the brake pad described in the preferred embodiment of the present invention, between step (1) and step (2) further includes:

The pressure field information of steel back products with good flatness is collected, and the number of collections is 20. Through these standard pressure field information, a standard template of pressure field distribution is created and stored in the database.

According to the method for detecting the flatness of the steel back of the brake pad described in the preferred embodiment of the present invention, the step (4) is specifically: during the measurement, by collecting the pressure field information of the steel back product to be tested, the pressure field distribution diagram of the product to be tested is established , compared with the standard pressure field distribution map, the flatness error is calculated through the deviation program of the pressure curve, the greater the degree of deviation, the lower the flatness.

According to the method for detecting the flatness of the steel back of the brake pad in the preferred embodiment of the present invention, step (5) further includes: generating a report in the form of an excel chart to display the flatness and pass rate of a batch of brake pad products and storage.

The automobile brake pad steel back flatness detection system and method of the present invention combine the image method and the pressure field detection method at the same time, have fast running speed and accurate counting, and realize intelligent judgment of the flatness of the brake pad and statistical qualification rate. The present invention obtains the defects of the brake pads through image collection and analysis, combines the pressure field information analysis and processing to obtain the flatness of the brake pads, displays the detection information and detection results in real time, and stores the statistical results in a database. The invention combines the image method and the pressure field detection method to realize the online real-time detection of the brake pad steel back product, and generate a report and input it to the database for storage. The system is easy to operate, and the measurement accuracy and efficiency are greatly improved, reducing the labor intensity. Moreover, the present invention also provides convenient query processing through the interactive processing of the database, which facilitates subsequent query and further improves the accuracy. In addition, the present invention only needs one CMOS camera to collect images, and additionally configures 20 pressure detection probes to perform flatness detection. The device is cheap, saves a lot of manpower and material costs, and effectively reduces production costs. Therefore, compared with the prior art, the present invention has the advantages of no human interference, accurate counting, high precision, high production efficiency, reduced labor intensity, high real-time performance, strong practicability and low cost.

Description of drawings

Fig. 1 is the structural principle diagram of the brake pad steel back flatness detection system of the present invention;

Fig. 2 is a schematic diagram of a list of the flatness of a batch of brake pad steel backs obtained through statistics in the embodiment of the present invention.

Detailed ways

The present invention will be described in detail below in conjunction with the accompanying drawings.

Please refer to Fig. 1, a brake pad steel back flatness detection system, including: an image acquisition device 1, 20 pressure detection probes 2, a host computer module 3 and a power supply 4, the image acquisition device 1 adopts a CMOS color camera, and it is connected with the upper position It is connected with the computer module 3 to collect the brake pad image on the assembly line in real time and send it to the host computer module 3. The pressure detection probe 2 is connected to the upper computer module 3 to collect the pressure field information of the brake pads and send it to the upper computer module 3, and the upper computer module 3 is used to analyze the collected images and pressure field information to analyze the defects of the brake pads , to obtain flatness and pass rate; the power supply 4 is respectively connected to the image acquisition device 1, the pressure detection probe 2 and the host computer module 3 to provide power for the image acquisition device 1, the pressure detection probe 2 and the host computer module 3.

The upper computer module 3 further includes: a human-computer interaction processing unit 31: used to accept user operations, realize initialization work and parameter settings, and display detection information and detection results in real time; image acquisition unit 32: interact with the human-computer interaction processing unit 31 Connect with the image acquisition device 1, in order to drive the image acquisition device 1 to collect the brake pad image on the assembly line in real time according to the user operation accepted by the human-computer interaction processing unit 31, and send the collected image to the image processing unit 34, and can Adjusting parameters such as exposure and gain of the camera; pressure field information collection unit 33: respectively connected to the human-computer interaction processing unit 31 and the pressure detection probe 2, to drive the pressure detection probe 2 according to the user operation accepted by the human-computer interaction processing unit 31 Collect pressure field information, and send the collected pressure field information to the pressure field information processing unit 35; image processing unit 34: connected to the image acquisition unit 32, to analyze and process the received brake pad image, and analyze the brake pad defects, obtain qualified and unqualified products; pressure field information processing unit 35: connect with pressure field information collection sheet 33, calculate the pressure field distribution of brake pads, and calculate the flatness of brake pads; statistical processing unit 36: communicate with image processing unit 34 is connected with the pressure field information processing unit 35, in order to count the flatness and pass rate of a batch of brake pad products according to the processing results of the image processing unit 34 and the pressure field information processing unit 35, and a batch of The flatness and qualification rate of the next brake pad product generate a report and send it to the database 37 and the human-computer interaction processing unit 31. Database 37: used to store the flatness and qualification rate information of a batch of brake pad products.

Specifically, the image processing unit includes a Gabor filter subunit. The two-dimensional Gabor filter can capture the local structural information corresponding to the spatial position, spatial frequency and direction selectivity, and has the same two-dimensional sensory visual field profile as the simple cells of the mammalian visual cortex. It is a very good feature extraction algorithm with similar properties and strong spatial position and direction selectivity. The present invention utilizes the Gabor filter to perform feature extraction: firstly extract the Gabor transformation features of multiple qualified samples, calculate the multi-directional and multi-scale Gabor transformation features of each pixel point by pixel, and form the Gabor feature representation of the steel back of the brake pad; then Perform Gabor transformation on defective brake pad products, and perform matching and registration to obtain accurate flatness information. If the conventional matching and registration strategy is adopted, it is difficult to obtain accurate matching information, and then cannot effectively match, so that accurate defect information cannot be obtained.

Furthermore, parameter setting includes setting parallax coefficient, segmentation threshold, region operator, Gabor parameter, number of detection points, X-axis correction coefficient and Y-axis correction coefficient. in,

The parallax coefficient is used to balance the spatial position conversion parameters between the image collected by CMOS and the signal value collected by the detector. This parameter affects the fusion result of the two data, and the value range is 1~3.

The segmentation threshold is to segment the area of the brake pad from the collected color image, and the best brake pad area is obtained by grayscale and binarization of the color image, and the threshold range is 0.3~0.8.

The region operator uses the block region segmentation operation to retain the feature edge region and remove the large flat region. The threshold setting range is 3~8.

The Gabor parameter changes the frequency domain window size and direction operator of the inline gabor filter. Gabor transformations in different directions and scales are used to obtain prominent local features and general global flat features. The value range of the operator is 2 ~6.

The number of detection points is the number of effective detectors of the device, and the larger the size of the steel back of the brake pad, the greater the detection points required.

The X-axis correction coefficient performs X-axis correction on the effective signal value of the acquired detection point to eliminate the interference of the installation position on the detection signal.

The Y-axis correction coefficient performs Y-axis correction on the effective signal value of the acquired detection point to eliminate the interference of the installation position on the detection signal.

Based on the above-mentioned system, the present invention also provides a method for detecting the flatness of the steel back of the brake pad, comprising the following steps:

(1) Accept the user's operation to realize the initialization work and parameter setting.

The user performs parameter setting through the human-computer interaction processing unit 21, and the specific parameter setting includes: parallax coefficient, segmentation threshold, area operator, gabor parameter, and detection point-related detection parameters, effective detection points, X-axis correction coefficient and Y-axis Correction coefficient.

(2) According to the user's operation, respectively drive the image acquisition device and the pressure detection probe to collect the brake pad image and pressure field information on the assembly line in real time.

The image acquisition unit 32 and the pressure field information acquisition unit 33 respectively drive the CMOS color camera and the corresponding pressure detection probe 2 according to the relevant parameters set in step (1) to collect the brake pad image on the assembly line and the pressure field information of the brake pad in real time .

(3) The Gabor wavelet transform method is used to analyze and process the collected brake pad images, analyze the defects of the brake pads, and obtain qualified and unqualified products. Specifically:

First, extract the Gabor transformation features of multiple qualified samples, calculate the multi-directional and multi-scale Gabor transformation features of each pixel pixel by pixel, and form the Gabor feature representation of the steel back of the brake pad;

Then, Gabor transformation is performed on the defective brake pad products, the two are matched and registered, the flatness of the brake pad products is qualitatively analyzed, and unqualified brake pad products are found.

(4) Calculate the pressure field distribution of the brake pads through the collected pressure field information, and calculate the flatness of the brake pads.

During the measurement, the pressure field distribution map of the product to be tested is established by collecting the pressure field information of the steel back product to be tested, compared with the standard pressure field distribution map, and the flatness error is calculated through the deviation program of the pressure curve. The larger, the lower the flatness.

(5) According to the results of steps (3) and (4), calculate the flatness and qualification rate of a batch of brake pad products, display the detection information and statistical results in real time, and store the statistical results.

Statistical processing unit 36 counts the flatness and pass rate of a batch of brake pad products according to the processing results of image processing unit 34 and pressure field information processing unit 35, and the flatness of a batch of brake pad products is calculated in the form of an excel chart. Generate a report and send it to the database 37 and the human-computer interaction processing unit 31. As shown in Figure 2, it is a schematic diagram of a batch of brake pad steel back flatness list obtained by statistics in the embodiment of the present invention. The flatness value in the table represents the flatness of a steel back product, and the smaller the value, the smaller the error , the better the flatness.

In the above method, between step (1) and step (2), it also includes: collecting pressure field information of steel back products with good flatness, the number of collection is 20, and creating pressure field distribution through these standard pressure field information The standard templates for are stored in the database.

The invention combines the image method and the pressure field detection method to realize the online real-time detection of the brake pad steel back product, and generate a report and input it to the database for storage. The system is easy to operate, and the measurement accuracy and efficiency are greatly improved, reducing the labor intensity. Moreover, the present invention also provides convenient query processing through the interactive processing of the database, which facilitates subsequent query and further improves the accuracy. In addition, the present invention only needs one CMOS camera to collect images, and additionally configures 20 pressure detection probes to perform flatness detection. The device is cheap, saves a lot of manpower and material costs, and effectively reduces production costs. Therefore, compared with the prior art, the present invention has the advantages of no human interference, accurate counting, high precision, high production efficiency, reduced labor intensity, high real-time performance, strong practicability and low cost.

The above is only a preferred implementation example of the present invention, and is not intended to limit the present invention in any form, any content that does not deviate from the technical solution of the present invention, any simple modification made to the above implementation examples according to the technical essence of the present invention , equivalent changes and modifications all belong to the scope of the technical solution of the present invention.

Claims (10)

1. A brake pad steel back flatness detection system is characterized in that it comprises: an image acquisition device, some pressure detection probes, an upper computer module and a power supply, and the image acquisition device is connected with the upper computer module for real-time Collect the image of the brake pad on the assembly line and send it to the upper computer module; the pressure detection probe is connected to the upper computer module to collect the pressure field information of the brake pad and send it to the upper computer module, and the upper computer The module is used to analyze the collected images and pressure field information, analyze the defects of the brake pads, and obtain the flatness and pass rate; To provide power for the image acquisition device, the pressure detection probe and the host computer module; wherein, the host computer module further includes: Human-computer interaction processing unit: used to accept the user's operation, realize the initialization work and parameter setting, and display the detection information and detection results in real time; Image acquisition unit: respectively connected with the human-computer interaction processing unit and the image acquisition device, to drive the image acquisition device to collect the brake pad image on the assembly line in real time according to the user operation accepted by the human-computer interaction processing unit, and collect The received image is sent to the image processing unit; Pressure field information collection unit: respectively connected to the human-computer interaction processing unit and the pressure detection probe, to drive the pressure detection probe to collect pressure field information according to the user operation accepted by the human-computer interaction processing unit, and collect the collected The pressure field information is sent to the pressure field information processing unit; Image processing unit: connected to the image acquisition unit, used to analyze and process the received brake pad images, analyze the defects of the brake pads, and obtain qualified and unqualified products; Pressure field information processing unit: connected to the pressure field information collection unit, calculates the pressure field distribution of the brake pads, and calculates the flatness of the brake pads; Statistical processing unit: connected to the image processing unit and the pressure field information processing unit, used to count the flatness and qualification rate of a batch of brake pad products according to the processing results of the image processing unit and the pressure field information processing unit, and sent to the human-computer interaction processing unit and database; and, Database: used to store the flatness and qualification rate information of a batch of brake pad products. 2. The system for detecting the flatness of the steel back of the brake pad according to claim 1, wherein the image acquisition device adopts a CMOS color camera. 3. the brake pad steel back flatness detection system as claimed in claim 1, is characterized in that, described statistical processing unit sends the flatness of a batch of brake pad product flatness and qualified rate situation with the form of excel chart To the database and human-computer interaction processing unit. 4. The brake pad steel back flatness detection system according to claim 1, wherein the number of said pressure detection probes is 20. 5. A method for detecting the flatness of the steel back of the brake pad based on the flatness detection system of the steel back of the brake pad according to any one of claims 1-4, characterized in that, comprising the following steps: (1) Accept the user's operation, realize the initialization work and parameter setting; (2) According to the user's operation, respectively drive the image acquisition device and the pressure detection probe to collect the brake pad image and pressure field information on the assembly line in real time; (3) Use the gabor wavelet transform method to analyze and process the collected brake pad images, analyze the defects of the brake pads, and obtain qualified and unqualified products; (4) Calculate the pressure field distribution of the brake pads through the collected pressure field information, and calculate the flatness of the brake pads; (5) According to the results of steps (3) and (4), calculate the flatness and qualification rate of a batch of brake pad products, display the detection information and statistical results in real time, and store the statistical results. 6. the brake pad steel back flatness detection method as claimed in claim 5, is characterized in that, the parameter setting in step (1) comprises: parallax coefficient, segmentation threshold, area operator, gabor parameter, and, detection point correlation Detection parameters, effective detection points, X-axis correction coefficient and Y-axis correction coefficient. 7. the brake pad steel back flatness detection method as claimed in claim 5, is characterized in that, step (3) specifically comprises: First, extract the Gabor transformation features of multiple qualified samples, calculate the multi-directional and multi-scale Gabor transformation features of each pixel pixel by pixel, and form the Gabor feature representation of the steel back of the brake pad; Then, Gabor transformation is performed on the defective brake pad products, the two are matched and registered, the flatness of the brake pad products is qualitatively analyzed, and unqualified brake pad products are found. 8. the brake pad steel back flatness detection method as claimed in claim 5, is characterized in that, also comprises between step (1) and step (2): The pressure field information of steel back products with good flatness is collected, and the number of collections is 20. Through these standard pressure field information, a standard template of pressure field distribution is created and stored in the database. 9. The method for detecting the flatness of the steel back of the brake pad as claimed in claim 8, wherein the step (4) is specifically: during measurement, by collecting the pressure field information of the steel back product to be tested, the pressure of the product to be tested is established The field distribution map is compared with the standard pressure field distribution map, and the flatness error is calculated through the deviation program of the pressure curve. The greater the deviation, the lower the flatness. 10. The method for detecting the flatness of the brake pad steel back as claimed in claim 5, wherein step (5) further comprises: generating the flatness and pass rate of a batch of brake pad products in the form of an excel chart Reports are displayed and stored.