Scholarlink

<p>The widespread adoption of Industrial Control Systems (ICS) and Internet of Things (IoT) devices has significantly increased data transmission frequency and equipment connectivity in industrial production processes, while simultaneously introducing cybersecurity risks such as data breaches, malicious attacks, and system failures. Traditional industrial practices, plagued by inefficient thermal energy utilization and severe energy waste, have hindered the green and sustainable development of industrial economies. Our research employs data mining techniques to collect and analyze thermal energy usage data from industrial processes, identifying low-efficiency operational segments and uncovering patterns and root causes of thermal losses. By integrating thermodynamic principles with industrial engineering knowledge, we developed an optimized strategy. The implementation of an AI-driven decision system enables real-time monitoring of thermal energy consumption, dynamically adjusting resource allocation to maximize energy efficiency. In terms of cybersecurity, machine learning algorithms are employed to analyze network traffic data in real time, detecting anomalies and potential threats. This establishes an AI-based intrusion detection and defense system that enhances cybersecurity defenses for industrial control systems. Simulation and field tests demonstrate that adopting the AI decision support system has led to significant improvements in thermal energy efficiency, effective control of energy waste, reduced environmental pollution, and substantially enhanced cybersecurity capabilities. The system now monitors and mitigates cyberattacks in real time, lowering the probability of cybersecurity incidents and ensuring stable industrial operations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Network security and collaborative artificial intelligence decision making application in industrial economic development based on data mining algorithms

  • 期刊论文

  • 发表日期：

    2026年3月17日

查看全文
  • Zou Qiaoling

摘要

The widespread adoption of Industrial Control Systems (ICS) and Internet of Things (IoT) devices has significantly increased data transmission frequency and equipment connectivity in industrial production processes, while simultaneously introducing cybersecurity risks such as data breaches, malicious attacks, and system failures. Traditional industrial practices, plagued by inefficient thermal energy utilization and severe energy waste, have hindered the green and sustainable development of industrial economies. Our research employs data mining techniques to collect and analyze thermal energy usage data from industrial processes, identifying low-efficiency operational segments and uncovering patterns and root causes of thermal losses. By integrating thermodynamic principles with industrial engineering knowledge, we developed an optimized strategy. The implementation of an AI-driven decision system enables real-time monitoring of thermal energy consumption, dynamically adjusting resource allocation to maximize energy efficiency. In terms of cybersecurity, machine learning algorithms are employed to analyze network traffic data in real time, detecting anomalies and potential threats. This establishes an AI-based intrusion detection and defense system that enhances cybersecurity defenses for industrial control systems. Simulation and field tests demonstrate that adopting the AI decision support system has led to significant improvements in thermal energy efficiency, effective control of energy waste, reduced environmental pollution, and substantially enhanced cybersecurity capabilities. The system now monitors and mitigates cyberattacks in real time, lowering the probability of cybersecurity incidents and ensuring stable industrial operations.