Haier Group has established a cloud-edge collaborative industrial internet platform tailored for the appliance industry to address the pain points in the digital and intelligent transformation of the household electrical appliance industry.Through embedding modules within the platform,intelligent allocation of cloud-edge resources and task optimization scheduling can be achieved.This module is segmented into three submodules:task response reception and processing,for immediate handling of tasks;task deployment,for arranging tasks across the network;and a task scheduling algorithm library,for optimizing task execution.It can efficiently manage cloud-edge computing resources at three levels:unified scheduling of large-scale tasks,collaborative deployment of heterogeneous computing,and real-time reconstruction of edge tasks,thereby fulfilling the instantaneous demands for heterogeneous computing,task deployment,and synergistic optimization.Now deployed across several factories,the platform serves as a practical blueprint fordigital and smart transformation in the appliance sector.
At present, network attacks have become a new type of weapon, and it has become a reality for hostile forces to use network attacks to successfully destroy key national infrastructure such as electricity. Smart terminal attacks on power grids generally target electricity specific protocols and specific business logic, and have characteristics such as clear targets, covert operations, and long latency. They are generally carried out through group or even national level attacks. At present, the intelligent terminal system of the power grid mainly draws on the mature technology of traditional IT systems in attack detection, detecting security events on the network side, and cannot detect abnormal security events targeting the system's business instruction level, such as forged control instructions. This study proposes a traffic anomaly detection technology based on single class support vector machine (OCSVM) for power grid network side flow detection. The basic idea of OCSVM is to use machine learning methods to binary data, and only one class of samples is needed to train the detection model. It is robust to noise sample data and well meets the data imbalance characteristics of industrial control systems.
1 背景 全球能源供应日趋紧张,能源价格持续上涨.全球大部分国家和地区都提出了"碳中和" 目标,并设立了相应的激励政策,世界各国都在大力推进可再生能源的发展.欧盟、印度等国家都迎来了光伏装机的历史新高,且市场需求日益旺盛.在"碳达峰、碳中和"战略引领下,中国的能源革命正在加速推进中,光伏作为绿色可再生能源正在进入大规模高质量发展阶段.为了实现"双碳"目标,国家推出多项政策促进能源改革,国家发改委在《"十四五"可再生能源发展规划》中明确,大力推进风电和光伏发电基地化开发.其中,以沙漠、戈壁、荒漠地区为重点的大型风电光伏基地建设加快推进,总规模达到4.55亿千瓦.
准确地获取油、气、水产量数据是油井生产管理的关键环节,同时也是储层动态分析的重要参数.通过准确的产量数据能够有效地评估油井地面和地下的状态,从而及时制定采油措施工艺和改变油井生产制度,实现延长油井开发周期和提高油藏整体采收率的目的.针对我国单井产量检测的实际需求以及具体油田工况,结合物联网技术,项目组研发设计出测量精准度高、自动化集成度高、支持A11标准功能的生产数据采集系统.该系统依托实时在线三相流量计设备,在新疆油田开展现场试验获得成功,真正实现了油井产量检测无人值守.油井生产数据采集系统上线后,采油厂取样及化验费用下降近50%,经济效益与社会效益良好,具备大规模推广价值.
华北工控是一家集行业专用嵌入式计算机产品研发、生产、销售及服务于一体的国家高新技术企业,主营产品涉及X86架构和ARM架构多样化的嵌入式计算机主板、嵌入式准系统、工业整机和工业平板电脑,可广泛应用于智慧医疗、人工智能、智慧零售、仓储物流、智慧城市、轨道交通、灯光工程、网络安全、智慧电网、国产化、工业自动化等行业领域.
