Intelligent operation, maintenance, and control system for public building: Towards infection risk mitigation and energy efficiency

Smart substations are an important part of establishing a strong smart grid. In view of the large variety of secondary equipment in the current power system, the rapid increase in quantity, and the complex working conditions of the current power supply company maintenance classes to inspect substations, a design method for the intelligent operation and maintenance system of secondary equipment in smart substations is proposed in this article. First, the intelligent operation and maintenance system architecture of the secondary equipment of the smart substation is established via Redis and ActiveMQ technologies. Then the system function module model is established. Finally, taking a 220kV substation in a certain area of southern China as an example, a new type of intelligent substation secondary equipment intelligent operation and maintenance system was installed and connected to the main line system, and the effectiveness of the proposed method was verified.

In recent years, with the development of big data technologies and applications, more and more enterprises realize that big data will play an important role in enterprises, which leads to a significant increase of big data platforms adopted by enterprises. Intelligent operation and maintenance could complete system state evaluation, abnormal diagnosis, alarm and prediction by means of data analysis, so as to reduce the complexity and workload of system operation and maintenance. In order to simplify the operation and maintenance of big data platform, intelligent operation and maintenance of big data platform has become a trend. In this context, the intelligent operation and maintenance system for big data platform is designed and implemented. The system realizes the collection, aggregation and storage, analysis with query and visualization of the runtime data of the big data platform. By providing a series of intelligent operation and maintenance functions, the complexity and workload of operation and maintenance personnel are reduced. In this thesis, the unified scoring model of big data platform is proposed; the HDFS capacity prediction method is proposed to manage the storage capacity of big data platform more actively; the task scheduling method based on platform free time analysis is proposed to optimize the platform efficiency.

Heating, ventilation and air conditioning (HVAC) systems are the most energy-consuming building implements for the improvement of indoor environmental quality (IEQ). We have developed the optimal control strategies for HVAC system to respectively achieve the optimal selections of ventilation rate and supplied air temperature with consideration of energy conservation, through the fast prediction methods by using low-dimensional linear ventilation model (LLVM) based artificial neural network (ANN) and low-dimensional linear temperature model (LLTM) based contribution ratio of indoor climate (CRI(T)). To be continued for integrated control of multi-parameters, we further developed the fast prediction model for indoor humidity by using low-dimensional linear humidity model (LLHM) and contribution ratio of indoor humidity (CRI(H)), and thermal sensation index (TS) for assessment. CFD was used to construct the prediction database for CO2, temperature and humidity. Low-dimensional linear models (LLM), including LLVM, LLTM and LLHM, were adopted to expand database for the sake of data storage reduction. Then, coupling with ANN, CRI(T) and CRI(H), the distributions of indoor CO2 concentration, temperature, and humidity were rapidly predicted on the basis of LLVM-based ANN, LLTM-based CRI(T) and LLHM-based CRI(H), respectively. Finally, according to the self-defined indices (i.e., EV, ET, EH), the optimal balancing between IEQ (indicated by CO2 concentration, PMV and TS) and energy consumption (indicated by ventilation rate, supplied air temperature and humidity) were synthetically evaluated. The total HVAC energy consumption could be reduced by 35% on the strength of current control strategies. This work can further contribute to development of the intelligent online control for HVAC systems.

This article focuses on the research and optimization application of all-optical network intelligent operation and control algorithms for new electrical power system (EPS). With the continuous improvement of the reliability requirements for communication networks by the new EPS, it is urgent to enhance the perception ability of network nodes to improve fault response and operation efficiency. However, current intelligent operation and maintenance equipment often finds it difficult to quickly and accurately locate the source of the fault after a network failure occurs, which limits the efficiency of operation and maintenance. This article proposes an all-optical network intelligent operation and maintenance system that integrates artificial intelligence (AI) technology to address this issue. The system first constructs a fault diagnosis model based on Generative Adversarial Networks (GANs), fits historical fault data to generate a reliable training dataset, and combines feature selection strategies to extract the optimal feature combination, achieving high-precision fault recognition. At the same time, an improved Dijkstra algorithm is further introduced to establish a localization mechanism for equipment disconnection fault sections. The results show that the proposed system can not only accurately diagnose various network faults, but also achieve precise and fast positioning of off grid fault sections, significantly improving the intelligent operation and maintenance capabilities and reliability of all-optical networks in power communication scenarios.

With the acceleration of the construction of smart grids, the explosive growth of information brought about by weather, equipment, and electricity/gas/heat multi-energy scenarios in the power system has made it difficult for traditional power simulation systems to meet people’s needs for smart power grid construction. And the combination of machine learning, deep learning, cloud computing and digital twin technology in the Internet of Things has become the key to the current grid construction. This article first analyzes the application of digital twin technology in battery management, creates an intelligent battery operation and maintenance management and advanced measurement system based on the Internet of Things, and provides a certain reference for improving the detection level of battery operation and maintenance management systems.

This paper proposes an intelligent operation and maintenance system based on distributed tracking technology, which integrates the Jaeger distributed tracking system and Prometheus monitoring system to build an operation and maintenance solution that includes three core functions: data collection, anomaly detection, and fault alarm. The system adopts dynamic baseline algorithm combined with quantile analysis to realize service call time-consuming anomaly detection, and designs multilevel alarm strategies to improve the effectiveness of alarms. Experiments show that the system exhibits excellent performance under different fault types. The F1scores of database, network, CPU, and memory faults are 0.96, 0.9189, 0.9074, and 0.8865, respectively, and the average alarm delay is about 15 seconds.

Ensemble of long short-term memory prediction and variable universe fuzzy control for seismic response reduction using electromagnetic dynamic vibration absorber

In order to achieve the micro-grid operation and management, Studying the micro-grid operation and maintenance knowledge base. Based on the advanced Petri net theory, the fault diagnosis model of micro-grid is established, and the intelligent diagnosis and analysis method of micro-grid fault is put forward. Based on the technology, the functional system and architecture of the intelligent operation and maintenance system of micro-grid are studied, and the microcomputer fault diagnosis function is introduced in detail. Finally, the system is deployed based on the micro-grid of a park, and the micro-grid fault diagnosis and analysis is carried out based on the micro-grid operation. The system operation and maintenance function interface is displayed, which verifies the correctness and reliability of the system.

A description of a new class of organizational and technical systems is given – intelligent road-building compaction control systems, the principles of operation of which provide for ensuring a given quality of compaction of asphalt mixtures in the process of road construction. The development of systems of that class is due, in the first place, to the transition to digital and intelligent control systems in construction. A scientific problem related to the relevance of creating methods for intelligent control of compaction of asphalt mixtures that affect the quality of road surfaces was formulated. To succeed, the usage of neural network structures was proposed. The usage will allow real-time monitoring of changes in the compaction quality index and efficient controlling of road machines using both the driver's manual means and the automatic compaction control system. The properties of the system under study – which determine the principles of its functioning: intelligence, informativity, speed, interconnectedness of subsystems, controllability and modularity – were presented. The above principles of the functioning of the proposed system, which are part of the methodology for managing the quality of asphalt compaction of pavement roads, were implemented in a set of methods and algorithms. Among them should be noted a new method of intelligent continuous control of compaction in the process of laying asphalt mixtures, an advanced method of intelligent prediction of compaction quality by vibrating rollers.

With the rapid development of artificial intelligence technology, digital transformation has opened up a new path for intelligent operation and maintenance of power grid production project management. Aiming at the problem that traditional operation and maintenance mode is difficult to dynamically adapt to real-time changes of equipment status, complex task scheduling and emergency response, this study proposes a new intelligent operation and maintenance decision-making optimization model based on deep reinforcement learning. The core adopts deep double-Q network algorithm. Through reinforcement learning framework, the model takes equipment operating parameters (temperature, current, voltage, etc.) as inputs, combines experience playback and target network mechanism, and dynamically generates operation and maintenance policies. Experiments show that compared with CNN, LSTM and the original DQN algorithm, the deep double-Q network performs best on cumulative reward (1,643.2) and discounted cumulative reward (2,198.5), and the convergence speed is improved by about 25%. The actual deployment in the regional power grid verifies its effectiveness in minute-level fault response and resource optimization, with an operation and maintenance cost reduction rate of 21.3%. This study provides a reusable methodological framework for grid intelligent operation and maintenance, and helps to improve the efficiency of life cycle management.

Обоснован перечень задач самообучения интеллектуальных систем управления автономными роботами и мультиагентными робототехническими группировками. Обсуждаются основные проблемы создания интеллектуальных самообучающихся систем управления. Показано, что один из наиболее перспективных подходов к реализации процессов самообучения в интеллектуальных системах управления автономными роботами и многоагентными робототехническими группировками связан с использованием метода автоматического построения деревьев классификации. Приводятся результаты комплексного моделирования.

Ventilation impacts on infection risk mitigation, improvement of environmental quality and energy efficiency for subway carriages

Lighting system control techniques in commercial buildings: Current trends and future directions

Based on heat balance analysis, the dynamic heating model of asphalt tank of mixture equipment was established, the heating time and using time nodes were determined, and the trapezoidal dynamic heating process of asphalt tank was also formed to realize the intelligent control and reduce energy consumption. After analyzing different schemes, the control scheme of the combination of feed-forward and feedback to realize intelligent control system for asphalt tank was adopted, which could ensure that the asphalt in the tank is in the operating temperature and the mixing equipment works continuously when the asphalt was used completely. In addition, a simulated analysis of calculation model, which was adopted by intelligent control system, was made in combination of entitative engineering. Results showed that compared with traditional process of heating asphalt, this intelligent heating control system could reduce the heat consumption by 15.8% under the condition of continuous construction.

With the progress of computer technology and intelligent control system, it is necessary to introduce the PLC together with the current systems. In this paper, we conduct research on the new intelligent industrial control and communication system based on PLC technique. As Industry 4.0 at the core of intelligent factory, the products made in its basic idea is integrated with dynamic digital memory, perception and communication ability, carrying the whole supply chain and all kinds of information required for life cycle. PLC biggest characteristic is to constitute the traditional relay model computer software technology, formed a unique style in relay ladder graph based image programming language, the PLC control system in the form of program to achieve its control function. In the simulation section, we implement our proposed system in detail and conduct numerical analtsis and simulation. The result is acceptable and accurate.