阅读说明：本技术 一种高速线性钻孔机的重孔检测系统 (Heavy hole detection system of high-speed linear drilling machine ) 是由 梁得强 于 2020-07-03 设计创作，主要内容包括：本发明涉及一种高速线性钻孔机的重孔检测系统,它包括以下识别步骤：步骤一,在服务器内建立重孔样本提取库,收集大量的重孔样本照片,利用深度卷积神经网络对图像进行预处理,提取样本照片中的重孔位置和特性,对重孔位置信息和特征信息记录并保存在样本提取库内,步骤二,通过CCD相机作为采集端对待检测产品的进行拍摄检测,拍摄后的视频实时上传至服务器,步骤三,服务器将步骤一提取的重孔特征信息和位置特征信息与步骤二中上传的视频进行对比,判断检测产品是否存在重孔现象,当检测到与重孔样本提取库内重孔相似特征,则及时圈出和记录位置信息,并发出警报。本发明的优点：检测精准,效率高。(The invention relates to a heavy hole detection system of a high-speed linear drilling machine, which comprises the following identification steps: step one, establishing a heavy hole sample extraction library in a server, collecting a large number of heavy hole sample photos, preprocessing the images by using a deep convolutional neural network, extracting the position and the characteristics of heavy holes in the sample photos, recording and storing the position information and the characteristic information of the heavy holes in the sample extraction library, step two, taking a CCD camera as a collection end to shoot and detect a product to be detected, uploading the shot video to the server in real time, step three, comparing the heavy hole characteristic information and the position characteristic information extracted in the step one with the video uploaded in the step two by the server, judging whether the detected product has a heavy hole phenomenon, and timely circling and recording the position information and sending an alarm when detecting the characteristics similar to the heavy holes in the heavy hole sample extraction library. The invention has the advantages that: the detection is accurate and efficient.)

1. A heavy hole detection system of a high-speed linear drilling machine is characterized in that: it comprises the following identification steps:

step one, establishing a heavy hole sample extraction library in a server, collecting a large number of heavy hole sample photos, preprocessing the images by utilizing a deep convolutional neural network, extracting the position and the characteristics of heavy holes in the sample photos, recording and storing the position information and the characteristic information of the heavy holes in the sample extraction library,

step two, shooting and detecting the product to be detected by taking the CCD camera as a collecting end, uploading the shot video to a server in real time,

step three, the server compares the heavy hole characteristic information and the position characteristic information extracted in the step one with the video uploaded in the step two, judges whether the detected product has the heavy hole characteristic, if the characteristic similar to the heavy hole in the heavy hole sample extraction library is detected, the position information is timely circled and recorded, and an alarm is given out,

and step four, after the detection is finished, the server automatically sums the heavy hole information characteristics and feeds back the heavy hole information characteristics in a unified manner.

Technical Field

The invention relates to the technical field of detection, in particular to a heavy hole detection system of a high-speed linear drilling machine.

Background

The linear motor is a driving device which directly converts electric energy into linear motion kinetic energy by using the principle of electromagnetic induction, and is a motor capable of realizing reciprocating linear motion. The device has the advantages of simple structure, high positioning precision, high reaction speed, high sensitivity and good follow-up property. Linear motor is as driven high-speed linear drilling machine, its positioning accuracy is high, repeated positioning accuracy is high, receive consumer's favor more and more, however in process of production, because the operation is misused, or high-speed linear drilling machine has appeared the problem, the product that leads to drilling appears heavy hole promptly superimposed heavy hole problem, then need abandon this unqualified product, but do not carry out the system that detects with aiming at heavy hole problem in present product, so usually be artifical visual detection, artifical visual detection is firstly the cost of labor is higher, secondly the easy visual fatigue of people, the mistake of emergence difficult to avoid in the testing process, lead to detecting inaccurate.

Disclosure of Invention

The invention aims to solve the problems and provides a heavy hole detection system of a high-speed linear drilling machine, which replaces manual detection to improve detection efficiency and accuracy.

In order to solve the technical problems, the technical scheme provided by the invention is as follows: a heavy hole detection system for a high speed linear drill comprising the steps of:

step one, establishing a heavy hole sample extraction library in a server, collecting a large number of heavy hole sample photos, preprocessing the images by utilizing a deep convolutional neural network, extracting the position and the characteristics of heavy holes in the sample photos, recording and storing the position information and the characteristic information of the heavy holes in the sample extraction library,

step two, shooting and detecting the product to be detected by taking the CCD camera as a collecting end, uploading the shot video to a server in real time,

step three, the server compares the heavy hole characteristic information and the position characteristic information extracted in the step one with the video uploaded in the step two, judges whether the detected product has the heavy hole characteristic, if the characteristic similar to the heavy hole in the heavy hole sample extraction library is detected, the position information is timely circled and recorded, and an alarm is given out,

and step four, after the detection is finished, the server automatically sums the heavy hole information characteristics and feeds back the heavy hole information characteristics in a unified manner.

After adopting the structure, the invention has the following advantages: the system provided by the invention replaces the traditional manual detection, improves the detection efficiency, provides a judgment basis through undetected judgment of the deep convolutional neural network, detects whether the hole is heavy or not, and improves the detection accuracy.

Detailed Description

The present invention is described in further detail below.

In the specific implementation of the invention, the heavy hole detection system of the high-speed linear drilling machine comprises the following identification steps:

step one, establishing a heavy hole sample extraction library in a server, collecting a large number of heavy hole sample photos, preprocessing the images by utilizing a deep convolutional neural network, extracting the position and the characteristics of heavy holes in the sample photos, recording and storing the position information and the characteristic information of the heavy holes in the sample extraction library,

step two, shooting and detecting the product to be detected by taking the CCD camera as a collecting end, uploading the shot video to a server in real time,

step three, the server compares the heavy hole characteristic information and the position characteristic information extracted in the step one with the video uploaded in the step two, judges whether the detected product has the heavy hole characteristic, if the characteristic similar to the heavy hole in the heavy hole sample extraction library is detected, the position information is timely circled and recorded, and an alarm is given out,

and step four, after the detection is finished, the server automatically sums the heavy hole information characteristics and feeds back the heavy hole information characteristics in a unified manner.

The working principle of the invention is as follows: the system provided by the invention replaces the traditional manual detection, improves the detection efficiency, provides a judgment basis through undetected judgment of the deep convolutional neural network, detects whether the hole is heavy or not, and improves the detection accuracy.

The present invention and its embodiments have been described above, but the description is not limitative, and the actual structure is not limited thereto. It should be understood that those skilled in the art should understand that they can easily make various changes, substitutions and alterations herein without departing from the spirit and scope of the invention as defined by the appended claims.