《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 其他 > 設(shè)計(jì)應(yīng)用 > “雨燕”敏捷智能計(jì)算系統(tǒng)及應(yīng)用研究
“雨燕”敏捷智能計(jì)算系統(tǒng)及應(yīng)用研究
2021年電子技術(shù)應(yīng)用第4期
方 科1,寧 琨2,潘 靈1
1.敏捷智能計(jì)算四川省重點(diǎn)實(shí)驗(yàn)室,四川 成都 610036;2.東方電氣風(fēng)電有限公司,四川 德陽618000
摘要: 針對(duì)部分工業(yè)所處惡劣邊緣環(huán)境往往缺乏充足的計(jì)算存儲(chǔ)和網(wǎng)絡(luò)資源,但又具有典型的超實(shí)時(shí)毫秒級(jí)數(shù)據(jù)密集型應(yīng)用場(chǎng)景需求,從總體架構(gòu)、軟硬件組成、關(guān)鍵技術(shù)3個(gè)方面介紹了基于敏捷智能計(jì)算技術(shù)的“雨燕”系統(tǒng)。該系統(tǒng)已在風(fēng)電設(shè)備中得到驗(yàn)證性應(yīng)用,提升了用戶優(yōu)化風(fēng)機(jī)運(yùn)維檢測(cè)能力,減少停機(jī)損失,降低運(yùn)維成本,同時(shí)展望了依托敏捷智能集群計(jì)算技術(shù)實(shí)現(xiàn)從單體風(fēng)機(jī)智能運(yùn)維到大規(guī)模風(fēng)場(chǎng)智能運(yùn)營的智慧風(fēng)電應(yīng)用前景。
中圖分類號(hào): TP393
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.201331
中文引用格式: 方科,寧琨,潘靈. “雨燕”敏捷智能計(jì)算系統(tǒng)及應(yīng)用研究[J].電子技術(shù)應(yīng)用,2021,47(4):9-16,23.
英文引用格式: Fang Ke,Ning Kun,Pan Ling. Research and application on agile intelligent system named “SWIFT”[J]. Application of Electronic Technique,2021,47(4):9-16,23.
Research and application on agile intelligent system named “SWIFT”
Fang Ke1,Ning Kun2,Pan Ling1
1.Sichuan Key Laboratory of Agile Intelligent Computing,Chengdu 610036,China; 2.Dongfang Electric Wind Power Co.,Ltd.,Deyang 618000,China
Abstract: In view of the lack of sufficient computing, storage and communication network resources for computing equipment at the edge of inclement industrial environments, and the requirement for ms-level data processing response, the agile intelligent system named “SWIFT” was introduced from the general architecture, hardware and software composition and key technology. This system has been verified in wind power equipment, which improves the user′s ability to optimize wind turbine operation and maintenance detection, and reduces downtime loss and operation cost. At the same time, it also discussed that the agile intelligent cluster computing technology could be applied in not only intelligent operation and maintenance of single wind turbine,but also the intelligent operation of large-scale wind farm.
Key words : edge computing;operations and maintenance;intelligent clustering;wind power

0 引言

    隨著全球工業(yè)數(shù)字化浪潮的到來,5G、AI、大數(shù)據(jù)等新技術(shù)不斷涌現(xiàn)。智能計(jì)算正在興起,成為“新基建”當(dāng)中與工業(yè)互聯(lián)網(wǎng)、物聯(lián)網(wǎng)等行業(yè)系統(tǒng)的重要結(jié)合點(diǎn)和改變數(shù)據(jù)信息服務(wù)模式的關(guān)鍵創(chuàng)新之一,有望帶來更多的顛覆性業(yè)務(wù)模式[1]

    許多企業(yè)已經(jīng)針對(duì)工業(yè)資產(chǎn)實(shí)現(xiàn)了數(shù)字化,并通過建立集中的物聯(lián)網(wǎng)平臺(tái)來收集、處理和分析這些資產(chǎn)數(shù)據(jù)。但行業(yè)智能時(shí)代,除了需要對(duì)海量數(shù)據(jù)分析以實(shí)現(xiàn)各種智能場(chǎng)景外,更需要不斷優(yōu)化計(jì)算力,使其能匹配行業(yè)數(shù)字化帶來的數(shù)據(jù)爆炸式處理壓力[2-4]。鑒于部分工業(yè)所處惡劣邊緣環(huán)境(例如海上石油勘探平臺(tái)、風(fēng)電)往往缺乏充足的計(jì)算存儲(chǔ)和網(wǎng)絡(luò)資源,但又具有典型的超實(shí)時(shí)毫秒級(jí)數(shù)據(jù)密集型應(yīng)用場(chǎng)景需求,僅依靠邊緣計(jì)算技術(shù)是無法適用于機(jī)器學(xué)習(xí)和深度學(xué)習(xí)模型的[5-9]。若能進(jìn)一步建立深度學(xué)習(xí)計(jì)算框架對(duì)應(yīng)用場(chǎng)景提供實(shí)時(shí)決策能力,擴(kuò)展數(shù)據(jù)邊緣性低延遲計(jì)算能力,提高非傳統(tǒng)計(jì)算硬件的利用率,比如數(shù)字信號(hào)處理器(DSP)、現(xiàn)場(chǎng)可編程門陣列(FPGA)、多核CPU等,則可從這些工業(yè)應(yīng)用中獲取更多的價(jià)值。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://ihrv.cn/resource/share/2000003456




作者信息:

方  科1,寧  琨2,潘  靈1

(1.敏捷智能計(jì)算四川省重點(diǎn)實(shí)驗(yàn)室,四川 成都 610036;2.東方電氣風(fēng)電有限公司,四川 德陽618000)

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。