5G+MEC在家電業(yè)機(jī)器視覺檢測系統(tǒng)中的應(yīng)用
2022年電子技術(shù)應(yīng)用第12期
王 超,魯效平,,劉倫明,,孫 明,景大智,,于曉義
青島海爾工業(yè)智能研究院有限公司,山東 青島266500
摘要: 為了解決家電業(yè)依賴人工進(jìn)行外觀質(zhì)量檢測的長期痛點(diǎn),將5G+MEC的機(jī)器視覺關(guān)鍵技術(shù)進(jìn)行創(chuàng)新應(yīng)用,,構(gòu)建了智能化產(chǎn)品表面質(zhì)量檢測系統(tǒng)。檢測系統(tǒng)以云邊協(xié)同模式運(yùn)營,,支持圖片和視頻的邊緣端推理,,云端算法終端下載部署,支持異構(gòu)計(jì)算,,實(shí)時性高,。系統(tǒng)基于決策分析工具、人工智能,、大數(shù)據(jù)分析等技術(shù)對采集的數(shù)據(jù)進(jìn)行綜合管理及應(yīng)用,。同時,關(guān)聯(lián)企業(yè)MES,、SCADA,、WMS等系統(tǒng),,集成生產(chǎn)端數(shù)據(jù)、物料數(shù)據(jù),、市場追蹤反饋數(shù)據(jù),,實(shí)現(xiàn)產(chǎn)品全生命周期的數(shù)據(jù)互聯(lián)及質(zhì)量追溯。
中圖分類號: TP399
文獻(xiàn)標(biāo)識碼: A
DOI:10.16157/j.issn.0258-7998.222601
中文引用格式: 王超,,魯效平,,劉倫明,等. 5G+MEC在家電業(yè)機(jī)器視覺檢測系統(tǒng)中的應(yīng)用[J].電子技術(shù)應(yīng)用,,2022,,48(12):84-88.
英文引用格式: Wang Chao,Lu Xiaoping,,Liu Lunming,,et al. Application of 5G+MEC in machine vision inspection system of household appliance industry[J]. Application of Electronic Technique,2022,,48(12):84-88.
文獻(xiàn)標(biāo)識碼: A
DOI:10.16157/j.issn.0258-7998.222601
中文引用格式: 王超,,魯效平,,劉倫明,等. 5G+MEC在家電業(yè)機(jī)器視覺檢測系統(tǒng)中的應(yīng)用[J].電子技術(shù)應(yīng)用,,2022,,48(12):84-88.
英文引用格式: Wang Chao,Lu Xiaoping,,Liu Lunming,,et al. Application of 5G+MEC in machine vision inspection system of household appliance industry[J]. Application of Electronic Technique,2022,,48(12):84-88.
Application of 5G+MEC in machine vision inspection system of household appliance industry
Wang Chao,,Lu Xiaoping,Liu Lunming,,Sun Ming,,Jing Dazhi,Yu Xiaoyi
Qingdao Haier Institute of Industrial Intelligence Co.,,Ltd.,,Qingdao 266500,China
Abstract: In order to solve the long-term pain point that the household appliance industry relies on manual appearance quality inspection, this paper innovatively applies the key technology of 5G + MEC machine vision, and constructs an intelligent product surface quality inspection system. The detection system operates in the cloud side collaboration mode, supports edge reasoning of pictures and videos download and deployment of cloud algorithm terminals, supports heterogeneous computing, and has high real-time performance. The system comprehensively manages and applies the collected data based on decision analysis tools, artificial intelligence, big data analysis and other technologies. At the same time, the system is associated with MES, SCADA, WMS and other systems of enterprises,,and integrates production end data, material data and market tracking feedback data,,which can realize data interconnection and quality traceability in the whole life cycle of products.
Key words : detection system;household-appliance business,;machine vision,;5G;MEC
0 引言
隨著“中國智造2025”和“工業(yè)4.0”等概念的提出,,技術(shù)創(chuàng)新帶來的深刻變革快速推動經(jīng)濟(jì)的發(fā)展和社會進(jìn)步,,同時制造業(yè)對自動化、智能化生產(chǎn)模式的需求日益增長,。在家電制造過程中,,由于生產(chǎn)、裝配,、原材料等因素造成產(chǎn)品缺陷一直是困擾企業(yè)的重要問題[1],。家電產(chǎn)品在生產(chǎn)過程中需要員工對產(chǎn)品的質(zhì)量進(jìn)行終檢確定,以防不良產(chǎn)品流至市場,,中間環(huán)節(jié)涉及附件貼標(biāo)型號確定,、產(chǎn)品表面劃痕,、產(chǎn)品性能及安全測試、產(chǎn)品下線前的主要附件防差錯等質(zhì)檢環(huán)節(jié),,分散在不同的工位,,需要3~4位員工完成。傳統(tǒng)的質(zhì)量檢測主要依靠人工進(jìn)行抽檢,,存在漏檢,、誤檢、檢驗(yàn)標(biāo)準(zhǔn)不統(tǒng)一等問題,;家電產(chǎn)品型號多,,外觀檢測內(nèi)容事項(xiàng)多,完全依賴質(zhì)檢員經(jīng)驗(yàn),,感官難衡量,;質(zhì)檢數(shù)據(jù)無存檔,導(dǎo)致售后問題難以回溯,、定責(zé)[2],。
本文詳細(xì)內(nèi)容請下載:http://forexkbc.com/resource/share/2000005046。
作者信息:
王 超,,魯效平,,劉倫明,孫 明,,景大智,,于曉義
(青島海爾工業(yè)智能研究院有限公司,山東 青島266500)
此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載。