This paper proposes a fault diagnosis method based on an improved residual network (ResNet) for complex chemical processes. The can automatically and efficiently extract features from the extensive data generated by operation process. improvement is carried out in three aspects. Firstly, 1D convolution introduced construction of model to reduce number parameters training time, shortcut connections are used alleviate degradation problem traditional deep neural networks. Second, residual-CBAM...

In this paper, SOX (SO2 and SO3) removal emission characteristics of wet limestone-gypsum flue gas desulfurization (WFGD) are investigated based on the data collected from 95 ultra-low coal-fired power units. The study shows that overall efficiency single-absorber is above 97.5%, in which SO3 between 31% 70%. When inner structures installed into spray absorber, correlation inlet SO2 concentration becomes more obvious, however, with a tray maximum double-absorber reaches 99.74%, 27% 81%. With...

Voltage Stability Analysis has become more important as a result of insufficient reactive resources in bulk transmission systems. Usually the objective is to identify weak regions terms power deficiency and determine critical contingencies voltage stability margins for various transfers within regions. This paper presents practical method perform Analysis. A Python tool developed facilitate contingency screening PV analysis described. also addresses issues like criteria, cumulative errors...

The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These facilitate tailored LLM creation via natural language prompts without coding. However, trustworthiness third-party custom versions LLMs remains an essential concern. In this paper, we propose first instruction backdoor attacks against applications integrated with untrusted (e.g., GPTs). Specifically, these embed into version by designing instructions, outputting...

As the variety and scope of optimization problems continue to expand, applicability a single algorithm may not be universal. To address this challenge, paper introduces an enhanced iteration Golden Jackal Optimization (GJO) algorithm, termed Parallel Search-based (PGJO) algorithm. This integrates concept parallel search into initialization, updating, selection mechanisms. It includes chaotic mapping preselection during initialization phase, employs cloning-like strategy for population...

Abstract Since the beginning of 12th Five-Year Plan, coal-fired power plants have carried out large-scale denitration and ultra-low emission transformation in China, among which SCR technology is most widely used. However, some hidden problems process project implementation gradually emerged after operation due to various factors, such as centralized reconstruction task, lack technical experience, inadequate quality control main equipment, uneven catalysts, insufficient maintenance...

This paper presents how the new technologies and industry standards, such as CIM, CCAPI, object-oriented relational database, Java, multi-tiered architecture, multi-agent system artificial intelligence, are applied in a modern EMS. The fast development of computer, communication network database technologies, well demands power market, make developing generation EMS necessary possible. attributes scalability, user interface openness, flexibility conformance to standards. In this paper, based...

This paper develops an efficient and practical approach for solving the economic dispatch (ED) problem in environment of power markets. In this paper, bidding principles are analyzed algorithm is described detail. Based on theory analysis principles, we drew a conclusion that calculation principle ED equal incremental criterion generators case pay as-bid. According to criterion, Newton interpolation (NI) was adopted solve problem. order ensure validity efficiency algorithm, some measures...

A rock bolt refers to a reinforcing bar used commonly in geotechnical engineering. Also, defect identification of anchorage system determines the safe operation reinforced structures. In present paper, accurately extract information, CNN model based on time-frequency analysis is proposed, covering both time-domain and frequency-domain information. The effect number convolution kernels results discussed. By laboratory experiments, performances STFT-based with those input or input-based 1D are...

Zipf's Law, discovered by Harvard linguist Zipf in the 1940s, is an empirical Law reflecting general rule of word frequency distribution language. It describes link between (F) and its rank (R) as F×R=C (constant)[1]. A large number studies have been conducted to test applicability various languages diverse text types. However, language keeps developing changing, there a continuous need for verification most up-to-date materials texts different languages. In addition, categories should be...

In the management of data space, quality is very important to realize value data. How improve and tap potential data, this paper proposes a five-dimensional scale based on manufacturing multi-value chain collaborative which includes five dimensions generation, acquisition, pre-access processing, architecture construction access, effectively makes up for shortcomings current literature. Meanwhile, improved CRITIC model weighting method combined principal component were established calculate...

Considering typical AC-DC-AC multiple units, CRH2 motor car, in this paper we deduce its parametric equations under sine pulse width modulation, and set up a new nonlinear parameter model. Fractal situation of higher harmonic is analyzed based on chaos theory. Aiming at traction substations, calculation simulation are conducted, the result verified data from actual wave records, which proves that high-frequency can lead to system resonance expands application analysis method.