CN211402188U

CN211402188U - Cloud cloth inspecting system

Info

Publication number: CN211402188U
Application number: CN201921765387.4U
Authority: CN
Inventors: 金玲玲
Original assignee: Shenzhen Lintsense Technology Co ltd
Current assignee: Shenzhen Lintsense Technology Co ltd
Priority date: 2019-10-18
Filing date: 2019-10-18
Publication date: 2020-09-01
Anticipated expiration: 2029-10-18

Abstract

The application discloses cloth inspection system in high in clouds includes: the system comprises an industrial personal computer, a real-time camera device, a cloud host and a cloth inspecting machine, wherein the real-time camera device, the cloud host and the cloth inspecting machine are connected to the industrial personal computer; the real-time camera device is used for shooting cloth surface images on the cloth inspecting machine, and the cloth surface images collected by the real-time camera device are transmitted to the cloud host through the industrial personal computer; the cloud host is used for detecting the cloth surface image and transmitting a detection result to the industrial personal computer; and the industrial personal computer is used for sending a control signal to the cloth inspecting machine according to the detection result. According to the scheme of the embodiment of the application, the leakage of the core data in the database can be prevented, and meanwhile, the condition that the GPU of the industrial control machine is easy to damage in the transportation process in the prior art is also avoided.

Description

Cloud cloth inspecting system

Technical Field

The application relates to the technical field of fabric detection, in particular to high in clouds perching system

Background

In the production line of fabrics such as woven fabric, knitted fabric, nonwoven fabric, etc., it is necessary to detect whether defects, such as stains, holes, fuzz, etc., exist on the produced fabrics. The traditional manual detection often has the problems of low detection precision and low detection speed, and in recent years, the requirements of customers on the product quality are higher and higher, so that the problems of improving the detection accuracy and saving manpower are concerned.

Due to the high error rate and low efficiency of manual detection, in recent years, a machine vision-based cloth defect detection technology is gradually developed to replace manual detection, namely cloth inspecting machine, which uses a camera to collect cloth images and uses a detection algorithm (such as a neural network model) operated by an industrial personal computer to detect the cloth images so as to identify defects. The detection algorithm is usually deployed on a GPU (Graphics Processing Unit) of the industrial personal computer, and a database for identifying the defects is also deployed on the industrial personal computer, which causes core data in the database to be easily leaked, and causes high after-sale cost due to easy damage of the GPU of the industrial personal computer in the transportation process.

Disclosure of Invention

In view of the above problem, the embodiment of the utility model provides a high in clouds perching system, it can solve the technical problem that above-mentioned background art part mentioned.

According to the utility model discloses a high in clouds perching system, include: the system comprises an industrial personal computer, a real-time camera device, a cloud host and a cloth inspecting machine, wherein the real-time camera device, the cloud host and the cloth inspecting machine are connected to the industrial personal computer; the real-time camera device is used for shooting cloth surface images on the cloth inspecting machine, and the cloth surface images collected by the real-time camera device are transmitted to the cloud host through the industrial personal computer; the cloud host is used for detecting the cloth surface image and transmitting a detection result to the industrial personal computer; and the industrial personal computer is used for sending a control signal to the cloth inspecting machine according to the detection result.

Further, the real-time camera device comprises a line-scan camera or a surface-scan camera.

Furthermore, the real-time camera device is connected with the industrial personal computer through an image acquisition device.

Furthermore, the cloud host adopts a multi-GPU parallel computing technology.

Furthermore, the industrial personal computer comprises a human-computer interaction interface for cloth inspection operation.

Further, the cloud host is connected with the industrial personal computer through a mobile wireless access network.

Further, the mobile radio access network is a 5G mobile radio access network.

Can see from above description, the utility model discloses a scheme deploys GPU on the high in the clouds host computer, and corresponding database that is used for discerning the fault also deploys on the high in the clouds host computer, during the detection, the industrial computer detects corresponding image data transmission to the high in the clouds host computer to according to the testing result control cloth inspection machine of high in the clouds host computer, the high in the clouds host computer need not to place at the user scene, so can prevent the core data leakage in the database, the easy condition of damaging of industrial computer GPU in the transportation among the prior art has also been avoided simultaneously.

Drawings

Fig. 1 is a schematic view of a cloud cloth inspecting system according to an embodiment of the present invention.

Detailed Description

The embodiments of the present invention will be described in detail below, and the embodiments described with reference to the drawings are exemplary only for explaining the present invention, and should not be construed as limiting the present invention.

In the description of the present invention, "a plurality" means two or more unless specifically limited otherwise.

In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; may be mechanically connected, may be electrically connected or may be in communication with each other; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meaning of the above terms in the present invention can be understood according to specific situations by those skilled in the art.

The following disclosure provides many different embodiments or examples for implementing different features of the invention. In order to simplify the disclosure of the present invention, the components and settings of the specific examples are described below. Of course, they are merely examples and are not intended to limit the present invention. In addition, the present disclosure provides examples of various specific processes and materials, but one of ordinary skill in the art may recognize applications of other processes and/or use of other materials.

Referring to fig. 1, the cloud cloth inspection system according to an embodiment of the present invention may specifically include: the industrial computer to and be connected to real-time camera device, high in the clouds host computer and the cloth inspection machine of industrial computer, wherein, high in the clouds host computer specifically can dispose the detection algorithm who is used for detecting the cloth cover fault. The detection algorithm may be, for example, a neural network model detection algorithm.

In this embodiment, the cloud host may deploy the detection algorithm on a GPU (graphics processing Unit), which is also called a display core, a visual processor, a display chip, or an accelerator card, and is a microprocessor specially used for image operation on a computer, a workstation, and a part of mobile devices (such as a tablet computer, a smart phone, and the like). In particular, the GPU may be installed in the housing of the cloud host. In this embodiment, a detection algorithm deployed on the GPU may detect whether a defect exists on the surface of the fabric.

In this embodiment, the real-time camera device may include a line scan camera or a surface scan camera, and specifically, may be a CCD line scan camera or a CCD surface scan camera, which is used to capture a cloth cover image on the cloth inspecting machine. The CCD (Charge Coupled Device) is a semiconductor Device for recording light changes in a digital camera. In another embodiment, the real-time imaging device may employ a CIS Sensor camera or a CMOS Sensor camera, the above-mentioned CIS (Contact Image Sensor) is a photoelectric conversion device, and the CMOS (Complementary Metal Oxide Semiconductor) is a Sensor having a sensitivity generally lower by 10 times than that of the CCD Sensor. In specific implementation, the real-time camera device may be connected to an industrial personal computer through an image acquisition device, and the image acquisition device may be, for example, a PCI image acquisition card. The real-time camera device can be arranged on the cloth inspecting machine body.

In this embodiment, the industrial personal computer may include a human-computer interaction interface for the perching operation, and the user may set perching parameters through the human-computer interaction interface, which may be an operation interface of perching software. During specific implementation, the industrial personal computer receives the cloth cover image shot by the real-time camera device and then transmits the cloth cover image to the cloud host.

In this embodiment, the cloud host may employ a multi-GPU parallel computing technique. In specific implementation, two GPUs, namely GPU1 and GPU2, can be integrated into one workstation, a separate copy of the detection algorithm model is placed on each GPU, and the parameters of the model are updated synchronously after all the GPUs process a batch of data. Of course, the number of GPUs may be determined according to actual needs. Therefore, the present invention is not limited. The cloud host can be connected with the industrial personal computer through the mobile wireless access network. In a specific implementation, the mobile radio access network may be a 5G mobile radio access network. The cloud host receives the cloth surface image transmitted by the industrial personal computer, and the cloth surface image is identified by using a detection algorithm deployed on the GPU so as to detect whether defects exist on the cloth surface. And the cloud host transmits the detection result to the industrial personal computer. Of course, the above connection method is only for illustration, and in the specific implementation, other connection methods other than the above connection method may be adopted according to specific situations.

In this embodiment, the industrial computer generates control signal and sends to cloth inspection machine according to the testing result of high in the clouds host computer, and cloth inspection machine carries out the cloth inspection operation according to control signal. Specifically, the cloth inspection machine can include controlling means, controlling means can adopt PLC (Programmable Logic Controller) switch board or signal input output device (I/O) for example, controlling means accessible serial ports connected's mode is connected with the industrial computer, when receiving the control signal of industrial computer, controlling means accessible Modbus RTU industrial transmission protocol control all kinds of driving motor realize the operation of checking cloth, specifically, accessible control batches driving motor and realizes shutting down the operation, or pastes mark driving motor through control and realize that the mark operation is pasted to the fault, can also control alarm device and report to the police, alarm device can be bee calling organ, it can send reputation to report to the police. The relevant operating data of cloth inspection machine can transmit to the industrial computer, and the convenience of customers looks over, for example sensor data.

The detailed description set forth above in connection with the appended drawings describes exemplary embodiments but does not represent all embodiments that may be practiced or fall within the scope of the claims. The term "exemplary" used throughout this specification means "serving as an example, instance, or illustration," and does not mean "preferred" or "advantageous" over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.

The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. High in clouds perching system, its characterized in that includes: the system comprises an industrial personal computer, a real-time camera device, a cloud host and a cloth inspecting machine, wherein the real-time camera device, the cloud host and the cloth inspecting machine are connected to the industrial personal computer; wherein the content of the first and second substances,

the real-time camera device is used for shooting cloth surface images on the cloth inspecting machine, and the cloth surface images collected by the real-time camera device are transmitted to the cloud host through the industrial personal computer;

the cloud host is used for detecting the cloth surface image and transmitting a detection result to the industrial personal computer;

and the industrial personal computer is used for sending a control signal to the cloth inspecting machine according to the detection result.

2. The cloud perching system of claim 1, wherein said real-time camera comprises a line-scan camera or a surface-scan camera.

3. The cloud perching system of claim 2, wherein said real-time camera device is connected to said industrial personal computer via an image acquisition device.

4. The cloud perching system of claim 1, wherein said cloud host employs a multi-GPU parallel computing technique.

5. The cloud perching system of claim 1, wherein said industrial personal computer comprises a human-computer interaction interface for perching operations.

6. The cloud perching system of claim 1, wherein said cloud host is connected to said industrial personal computer via a mobile wireless access network.

7. The cloud perching system of claim 6, wherein said mobile radio access network is a 5G mobile radio access network.