Automatic identification and focusing method for ultrasonic scanning detection

Abstract

The invention discloses an automatic identification and focusing method for ultrasonic scanning detection, relates to the field of electronic component detection, and aims to solve the problems of high working repeatability and low working efficiency of manual identification and focusing calibration of an existing ultrasonic scanning transducer. Under the condition that the number, the types and the models of the components are uncertain, the ultrasonic scanning range is automatically detected and recognized, Z-axis accurate focusing is achieved, and semi-automatic work of ultrasonic scanning of the components is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of electronic component detection, and in particular relates to an automatic identification and focusing method for ultrasonic scanning detection. Background Art

[0002] Electronic components are an important part of the whole equipment and the basis for ensuring the normal and stable operation of the whole equipment. The reliability of electronic components affects the reliability of the whole equipment. With the low-cost requirements in recent years, the use of plastic-encapsulated components in the aviation field has gradually increased due to their low price, light weight, and excellent thermal matching. However, due to the unsealed nature of plastic-encapsulated components, if stratification occurs inside the plastic encapsulation material, it is very easy to cause failures such as popcorn effect and corrosion due to the entry of water vapor. Therefore, the identification of stratification of plastic-encapsulated components can greatly eliminate defective components.

[0003] Ultrasonic scanning microscopes are mainly used for layered identification of plastic-encapsulated components. Due to their non-destructive characteristics, they are often used in batch screening of plastic-encapsulated components, destructive physical analysis and other projects. As the scale of corporate products continues to expand, components are gradually showing the characteristics of small batches, multiple types and large numbers. Ultrasonic scanning inspection projects are batch work. The traditional method manually identifies the component model and package size after placing batch samples, sets the scanning range for different samples, and repeatedly adjusts the focus until it focuses on the observation surface. The working technology is difficult and highly repetitive, resulting in low detection efficiency. Summary of the invention

[0004] In view of this, the method for automatic identification and focusing of ultrasonic scanning detection of the present invention solves the technical problem that the methods in the prior art result in low efficiency in detecting electronic components.

[0005] A method for automatic identification and focusing of ultrasonic scanning detection, which detects components based on machine vision, includes a water tank containing deionized water, a sensor, a probe and a controller, wherein the probe is installed on a transmission device, and the controller is electrically connected to the sensor, the probe and the transmission device respectively. The method includes the following steps:

[0006] Step 1: placing components, wherein components of the same model are placed in the water tank;

[0007] Step 2: Component position acquisition, wherein the sensor can sense the change in the weight of the water tank, and use two cameras to acquire images of the left side and the top side of the water tank and transmit them to the controller to generate a left view and a top view respectively, and the cameras are electrically connected to the controller;

[0008] Step 3: image preprocessing, the left view and the top view are preprocessed respectively, wherein the left view and the top view are grayscale processed to reduce image pixel information, and are processed respectively by binarization processing;

[0009] Step 4: Component range identification, wherein the area where the components are located in the processed top view is determined, and the area is used as the scanning range;

[0010] Step 5: Component height recognition, wherein the height of the outline of the component in the processed left view is determined, and the height of the outline is used as the height of the component;

[0011] Step 6: Identify and move the characteristic components, determine the center position of the components according to the contour of the components in the area, and move the probe to the top of the center position of the components through the transmission device;

[0012] Step 7: focusing components, wherein the descending height of the probe is calculated according to the height and the frequency of the ultrasonic wave emitted by the probe, and the transmission device descends the probe according to the descending height;

[0013] Step eight: Start scanning, wherein the transmission device drives the probe to scan in the scanning range in a horizontal movement manner to obtain an ultrasonic scanning detection image of the component.

[0014] The technical beneficial effects of the present invention are:

[0015] The embodiment of the present invention can apply an ultrasonic scanning microscope for automatic scanning range identification and focusing. When the number, type and model of components are uncertain, it can accurately and quickly automatically detect and identify the scanning range and preliminarily focus on the component detection layer, and can be applied to screening tests in the field of component detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 is a schematic diagram of the device of the present invention;

[0018] Figure 2 A schematic diagram of the scanning range identification process of the method of the present invention;

[0019] Figure 3 Schematic diagram of the automatic focusing process of the method of the present invention. DETAILED DESCRIPTION

[0020] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0021] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0022] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0023] like Figures 1 to 3 The method for automatic identification and focusing of ultrasonic scanning detection shown in the figure detects components based on machine vision, including a water tank containing deionized water, a sensor, a probe and a controller, the probe is installed on the transmission device, and the controller is electrically connected to the sensor, the probe and the transmission device respectively. The sensor is preferably a weighing sensor, a device that can sense and convert weight information, which converts the weight of an object into an electrical signal output for measurement and control, for example, a resistive strain weighing sensor, and the method includes the following steps:

[0024] Step 1: Place components, where components of the same model are placed in the water tank;

[0025] Step 2: Component position acquisition, wherein the sensor can sense the change in the weight of the water tank, and use two cameras to acquire images of the left side and the top side of the water tank and transmit them to the controller, generating a left view and a top view respectively, and the camera is electrically connected to the controller;

[0026] Step 3: Image preprocessing. The left view and the top view are preprocessed separately. Specifically, the left view and the top view are grayscaled to reduce the image pixel information and then binarized respectively.

[0027] Step 4: Component range identification. Determine the area where the components are located in the processed top view, and use this area as the scanning range.

[0028] Step 5: Component height identification. Determine the contour height of the components in the processed left view, and use this contour height as the height of the components.

[0029] Step 6: Identify and move the feature components. Determine the center position of the components according to the contours of the components in the area, and move the probe to directly above the center position of the components through the transmission device.

[0030] Step 7: Component focusing. Calculate the descent height of the probe based on the height and the frequency of the ultrasonic wave emitted by the probe, and the transmission device lowers the probe according to the descent height, including: the controller calculates the descent height of the probe according to the size parameters of the components and the probe information. The size parameters include the height h of the sample to be measured and the height H of the actual water surface in the water tank, and the probe information includes the probe frequency and the probe focal length.

[0031] Descent height WP In the formula, the descent height WP is the distance between the probe and the sample surface and needs to satisfy WP < H - h. If this range or condition is not met, the transmission device feeds back information, such as prompting the user to add deionized water to the water tank. F is the focal length information of the probe, C tm The speed of the ultrasonic wave emitted by the probe in the plastic package, C w The speed of the ultrasonic wave emitted by the probe in water. MD is the penetration depth of the ultrasonic wave emitted by the probe in the material. Generally, it is half of the sample height h.

[0032] Step 8: Start scanning. The transmission device drives the probe to scan in the scanning range in a horizontal movement manner to obtain the ultrasonic scanning detection image of the components.

[0033] As a specific implementation provided in this case, the determination of the scanning range and height in steps 4 and 5 includes that the controller uses a machine learning algorithm to extract the processed top view and left view. The machine learning algorithm is a convolutional neural network algorithm, satisfying:

[0034] In the formula, f is the convolutional neural network algorithm, w represents the weights of the neural network, b is the bias of the model, i refers to the number of neurons in the model, x i represents the calculation matrix.

[0035] Furthermore, the transmission device is a stepping linear motor device and includes three moving axes XYZ, which can move the probe universally;

[0036] The camera has a zoom function, and the camera zoom range can be manually adjusted and configured;

[0037] Step 8: Start scanning. The user clicks the "Start Scan" button in the detection software to start scanning.

[0038] The present invention uses image recognition technology and ultrasonic analysis technology as core technologies. When the number, type and model of components are uncertain, the ultrasonic scanning range and Z-axis are automatically detected and identified, and the Z-axis is accurately focused, so as to realize semi-automatic ultrasonic scanning of components. When the number, type and model of components are uncertain, the ultrasonic scanning range and Z-axis are automatically detected and identified, and the semi-automatic ultrasonic scanning of components is realized. Compared with the traditional large-scale manual component scanning and focusing work for users and inspectors, the manpower requirements are high, and the ultrasonic scanning and detection work as a whole presents the problems of large workload and low work efficiency. The ultrasonic scanning microscope is used for automatic scanning range identification and focusing. When the number, type and model of components are uncertain, the scanning range can be accurately and quickly automatically detected and identified, and the component detection layer can be initially focused, which can be applied to screening tests in the field of component detection.

[0039] Operation process

[0040] Step 1: Start the system

[0041] Turn on the power supply and device terminal, power on the device, open the system control software and enter the standby mode, turn on the camera, adjust the light source angle, brightness and device focal length, and the image acquisition and preprocessing module is ready.

[0042] Step 2: Preset information

[0043] Enter the component model, package, and scan quantity information to be scanned in the software.

[0044] Enter the probe's frequency and focal length information into the software;

[0045] Step 3: Component scanning range identification

[0046] The user places the samples to be tested in the sample tank one by one and clicks the "Scan Range Identification" button of the detection software. The photoelectric sensor is used to determine whether there are products to be tested in the image acquisition area. If it is detected that components have been placed, the top camera is turned on and takes images. After image preprocessing, feature extraction is performed to complete the confirmation of the component's XY direction scanning range.

[0047] Step 4: Extract core components

[0048] The user clicks the "Component Alignment" button and uses the XY-direction overhead camera to capture and pre-process the image for feature extraction, identify the scanned sample contour, and determine the center position of the component sample based on the contour line.

[0049] Step 7: Component Autofocus

[0050] When the user clicks the "Auto Focus" button, the side camera starts and takes pictures of the water surface height and the left view of the component. The water surface information is extracted based on the image, and the component package height is confirmed based on the component information filled in by the user and the camera image. At the same time, the distance from the top of the component to the water surface is calculated, and the software confirms the Z-axis movement limit of the probe.

[0051] 1) The probe automatically moves to the center of any component and begins to slowly descend to the water surface.

[0052] 2) The software automatically displays the message "probe enters water" and slows down the descent speed;

[0053] 3) The software controls the probe to move downward at a step rate of 0.5 mm according to the moving limit until it reaches the height automatically calculated by the software; the user can click "Pause" on the software interface at any time.

[0054] Step 8: Start scanning

[0055] The user clicks the "Start Scan" button in the detection software to start scanning.

[0056] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for automatic identification and focusing of ultrasonic scanning detection, which detects components based on machine vision, characterized in that: The method comprises a water tank containing deionized water, a sensor, a probe and a controller, wherein the probe is mounted on a transmission device, and the controller is electrically connected to the sensor, the probe and the transmission device respectively. The method comprises the following steps: Step 1: placing components, wherein components of the same model are placed in the water tank; Step 2: Component position acquisition, wherein the sensor can sense the change in the weight of the water tank, and use two cameras to acquire images of the left side and the top side of the water tank and transmit them to the controller to generate a left view and a top view respectively, and the cameras are electrically connected to the controller; Step 3: image preprocessing, the left view and the top view are preprocessed respectively, wherein the left view and the top view are grayscale processed to reduce image pixel information, and are processed respectively by binarization processing; Step 4: Component range identification, wherein the area where the components are located in the processed top view is determined, and the area is used as the scanning range; Step 5: Component height recognition, wherein the height of the outline of the component in the processed left view is determined, and the height of the outline is used as the height of the component; Step 6: Identify and move the characteristic components, determine the center position of the components according to the contour of the components in the area, and move the probe to the top of the center position of the components through the transmission device; Step 7: focusing components, wherein the descending height of the probe is calculated according to the height and the frequency of the ultrasonic wave emitted by the probe, and the transmission device descends the probe according to the descending height; Step eight: Start scanning, wherein the transmission device drives the probe to scan in the scanning range in a horizontal movement manner to obtain an ultrasonic scanning detection image of the component.

2. The method according to claim 1, characterized in that The step 7 of calculating the descending height of the probe according to the height and the frequency of the ultrasonic wave emitted by the probe comprises: The controller calculates the descending height of the probe according to the dimension parameters of the components and the probe information, wherein the dimension parameters include the height h of the sample to be tested and the height H of the actual water surface of the water tank, and the probe information includes the probe frequency and the probe focal length; Wherein, WP is the distance between the probe and the sample surface and needs to satisfy WP < H - h, F is the focal length information of the probe, C tm is the speed of the ultrasonic wave emitted by the probe when propagating in the plastic encapsulant, C w is the speed of the ultrasonic wave emitted by the probe when propagating in water, and MD is the penetration depth of the ultrasonic wave emitted by the probe in the material.

3. The method according to claim 1, characterized in that The penetration depth of ultrasonic waves emitted by the MD probe in the material is half of the height h of the sample to be tested.

4. The method according to claim 1, characterized in that The determination of the scanning range and height in step 4 and step 5 includes, The controller uses a machine learning algorithm to extract the processed top view and left view. The machine learning algorithm is a convolutional neural network algorithm that satisfies: In the formula, f is the convolutional neural network algorithm, w represents the weight of the neural network, b is the deviation of the model, i refers to the number of neurons in the model, and x i Represents a calculation matrix.

5. The method according to claim 1, characterized in that The transmission device is a stepping linear motor device and includes three moving axes XYZ, which can move the probe universally; The camera has a zoom function, and the zoom range of the camera can be manually adjusted and configured.

Images