Reliability Of Power Plants Research Articles

Reliability Analysis of Biomass Power Plant Using Loss of Load Probability Index at PT. Tanjung Buyu Perkasa Plantation

The main function of a power generation system is to provide reliable electrical energy. This study aims to determine the reliability of Biomass Power Plants at PT. Tanjung Bayu Perkasa Plantation (PT. TBPP) in the years 2020, 2021, and 2022 using the Loss of Load Probability (LOLP) index calculation method. LOLP is a reliability index that indicates the possibility that the power plant cannot meet the demand. The LOLP of biomass power plants at PT. TBPP in 2020 amounted to 1.2769 days per year. However, the LOLP in 2020 does not comply with the standards set by the Republic of Indonesia Minister of Energy and Mineral Resources Decree in 2018. In contrast, in 2021, it was 0.53403 days per year, and in 2022, it was 0.41748 days per year, both of which meet the standards of the Republic of Indonesia Minister of Energy and Mineral Resources Decree in 2018. The LOLP is affected by the Forced Outage Rate (FOR) and demands exceeding the capacity. Based on the LOLP of biomass power plants at PT. TBPP in 2020, 2021, and 2022, it can be concluded that the reliability of biomass power plants at PT. TBPP is at a higher level of reliability compared to the micro-hydro power plant in Pantai Baru Pandasimo with a LOLP of 51.3627 days per year and the steam power plant at Pertamina EP Asset IV Field Sukowati with LOLP of 4.259535 days per year. The recommendation for future research is to explore ways better to optimize boiler operations in steam power plants at PT. TBPP.

ADOPTING AND IMPLEMENTING PRACTICAL RELIABILITY TOOLS IN NIGERIA ELECTRIC POWER INDUSTRY

The dynamics of power plant operations and maintenance has changed drastically over the past decades. In the past, generation and supply of power to both the pub lic and industrial sectors was not competitive, partly because most of the businesses of power generation, transmission and distribution were owned and run by government. The event turned out to be no business as the managers of those plants were not faced with stiff competitions. And as such were not on their heels create, seek and apply new technologies in power operations and management. With the dwindling efficiencies, resulting in outages, black out, most countries developed and adopted new business models where the private sector were allowed to fully own and run the business of power generation, transmission and distribution especially with changing expectations of customers’ demands for energy; the power sector became more competitive, resulting in the exit of non-performers. Reliability and availability of power plants become a central focus. The successes recorded in global power sector serves as a business model for non performing countries to copy or modify and apply. This forms the theme of this research to show case how the Nigeria electric power industry can key in into this successful model to turn the fortune of the Nigeria electric power industry in a positive direction. This research presents reliability engineering principles that should be adopted by the Nigeria electric power industry in order to optimize plants’ operations and deliver the needed posi-watt and not nega-watt to the ever ready consumers. It is believed that if these measures are judiciously applied, the Nigeria electric power industry will make a huge jump and join the global counterparts in electric energy generation and supply of the needed power.

Small Modular Reactors: Opportunities and Challenges as Emerging Nuclear Technologies for Power Production

Abstract Small modular reactors (SMRs) have gained international attention due to their modular design, small footprint, and cost advantages compared to conventional reactors. Multiple types of SMRs are under development globally, and regulatory agencies are working toward a comprehensive and harmonized regulatory framework for ensuring safety and environmental protection. However, several aspects related to SMRs require further investigation, including the behavior of nuclear fuel under high pressures and temperatures (1000 °C), radiation exposure levels during normal and accident conditions, management of different types and volumes of nuclear waste, and their safe storage and disposal. Additionally, the modular design and compact size of SMRs make them suitable for deployment in remote locations, including the Arctic region. However, before introducing SMR technology, a thorough study of Arctic soil is necessary, particularly in the context of changing climate. Probabilistic risk assessment (PRA) plays a vital role in evaluating the safety and reliability of nuclear power plants, specifically focusing on assessing cross-unit interactions in the case of multimodule SMRs. Furthermore, given the use of low-enriched uranium fuel and the potential for limited on-site personnel in remote locations, effective nuclear safeguards and material accountancy measures are crucial to prevent the diversion of nuclear materials. In this paper, an investigation is conducted to explore the advantages and challenges involved in the deployment of emerging SMR technologies for electricity generation and other applications.

Analysing Effective and Ineffective Impacts of Maintenance Strategies on Electric Power Plants: A Comprehensive Approach

The maintenance strategy used in an electric power plant plays a crucial role in its overall performance and operational efficiency. An effective maintenance strategy describes the approach to exploiting various forms of maintenance (corrective, preventive, predictive, proactive, etc.) in an electric power plant. In this paper, the effective and ineffective impacts of maintenance strategies on power plants were examined. Also, the distinction between corrective, preventive, and aggressive maintenance was considered. In terms of effective impacts, a well-designed and executed maintenance strategy enhances the reliability and availability of the electric power plant by minimising unplanned downtime. It extends the lifespan of critical equipment, improves safety measures, increases energy efficiency, and contributes to long-term cost savings. However, in terms of ineffective impacts, poorly planned or executed maintenance strategies can result in increased downtime, higher repair costs, safety risks, decreased efficiency, and regulatory compliance issues. Neglecting maintenance can lead to equipment failures, reduced productivity, and potential environmental incidents.

Pyrocarbon Coating on Granular Al2O3 for HTGR-Type Power Reactor

Fourth-generation nuclear power systems are based on high-temperature gas-cooled reactors, in which the pebble fuel is the primary energy carrier. In this regard, applying protective pyrocarbon coatings on granulated fuel is an essential problem in ensuring the reliability of nuclear power plants. The article’s main idea is to research rational technological parameters of forming a pyrocarbon protective coating on the granules of a nuclear fuel model. For this purpose, granulated Al2O3 with the protective pyrocarbone coating was applied as a fuel model. The article’s aim is to study the effect of thermophysical parameters on applying a protective pyrocarbon coating on granulated Al2O3. During the experimental studies, thermal imaging of the pyrolysis process was used. The scientific novelty of the work is the equilibrium curves for the systems Al2O3:CH4, Al2O3:CH4:N2, and Al2O3:CH4:Ar. Their analysis allowed for evaluating rational thermochemical parameters of the pyrolysis process. As a result, rational thermophysical parameters of coating granulated Al2O3 with a pyrocarbon layer were evaluated, and the practical possibility of applying the pyrocarbon coating to granulated Al2O3 in the electrothermal fluidized bed was experimentally proven. It was shown that nitrogen does not significantly affect the target reaction product under a temperature of less than 1500 K. Also, the rational conditions for the pyrocarbon coating at a pressure of 0.1 MPa were realized at a temperature of 900–1500 K and using argon. Moreover, pyrocarbon was precipitated from hydrocarbon at 1073–1273 K. Overall, the need to add an inert gas for reducing the carbon black formation was proven to prevent a reduction of natural gas efficiency.

Reliability of photo-voltaic power plants

The quest for alternative energy sources, replacing the environmentally impacting fossil fuels, has resulted in the growing need to develop various new strategies in the field of renewable energies. A possible energy source is clean solar energy. The most common technology used is a silicon semiconductor device, which generates electrical output while interacting with light, known as Photo-Voltaic (PV) System. The reliability of PV modules and systems is critical to the commercial success of Photovoltaic systems. The technology combines multiple components, each of which could cause a system failure or energy losses. The reliability characterization measurements of a PV power system are complicated and only a few studies succeeded to design and simulate an efficient PV system. In the current study, two relatively large-scale solar farms were designed with an output of 20 MW. A comparison of the solar farms' performances was conducted, with an emphasis on the reliability indices of the systems. The obtained reliability indices are 83% and 88% for the studied solar farms.

Modeling the deadwood bearings wear surface by optical scanning

The development of a methodology for modeling the wear surface of deadwood bearings based on optical scanning is considered in the paper. It is noted that the deadwood bearings of the ship’s shaft line wear out unevenly during operation, which affects the stress-strain state of the shaft and the system parameters responsible for the occurrence of resonance of transverse, torsional and longitudinal vibrations. The methodology and results of an experimental study of bearing wear surfaces are presented. The applied optical scanning scheme makes it possible to obtain high-precision digital models of objects due to synchronous shooting of an object with two cameras. The measurement results are obtained by processing with specialized software. The results obtained are an addition to the methodology for determining the elastic force acting on the shaft from the side of a bearing that is unevenly worn along the length with a non-constant gap. Based on the obtained wear values, a solid-state model is constructed and the natural frequencies of transverse, torsional and longitudinal vibrations are determined. For the constructed model, the forms of natural oscillations for practically significant frequencies are obtained. It is noted that bearing wear affects not only the displacement of the natural frequencies values, but also the oscillations shape. The impact of the wear of the aft bearing on the bearing capacity of the shaft line, taking into account the contact interaction, is evaluated. The simulation has shown that the bearing wear surface forms an area of increased contact pressures that arise from the impact of the propeller shaft. Analysis of the propeller shaft tip has revealed the presence of an area of increased concentration of equivalent stresses formed at the place of bearing wear formation. The proposed method of modeling the deadwood bearings wear allows us to evaluate its effect on the magnitude of the displacement of natural frequencies and the change in the bearing capacity of the shaft line. The results obtained in this work are an addition to the existing calculations in the design and evaluation of the ship’s power plant reliability.

The Optimal Design of a Hybrid Solar PV/Wind/Hydrogen/Lithium Battery for the Replacement of a Heavy Fuel Oil Thermal Power Plant

Renewable energies are clean alternatives to the highly polluting fossil fuels that are still used in the power generation sector. The goal of this research was to look into replacing a Heavy Fuel Oil (HFO) thermal power plant in Limbe, southwest Cameroon, with a hybrid photovoltaic (PV) and wind power plant combined with a storage system. Lithium batteries and hydrogen associated with fuel cells make up this storage system. The total cost (TC) of the project over its lifetime was minimized in order to achieve the optimal sizing of the hybrid power plant components. To ensure the reliability of the new hybrid power plant, a criterion measuring the loss of power supply probability (LPSP) was implemented as a constraint. Moth Flame Optimization (MFO), Improved Grey Wolf Optimizer (I-GWO), Multi-Verse Optimizer (MVO), and African Vulture Optimization Algorithm (AVOA) were used to solve this single-objective optimization problem. The optimization techniques entailed the development of mathematical models of the components, with hourly weather data for the selected site and the output of the replaced thermal power plant serving as input data. All four algorithms produced acceptable and reasonably comparable results. However, in terms of proportion, the total cost obtained with the MFO algorithm was 0.32%, 0.40%, and 0.63% lower than the total costs obtained with the I-GWO, MVO, and AVOA algorithms, respectively. Finally, the effect of the type of storage coupled to the PV and wind systems on the overall project cost was assessed. The MFO meta-heuristic was used to compare the results for the PV–Wind–Hydrogen–Lithium Battery, PV–Wind–Hydrogen, and PV–Wind–Lithium Battery scenarios. The scenario of the PV–Wind–Hydrogen–Lithium Battery had the lowest total cost. This scenario’s total cost was 2.40% and 18% lower than the PV–Wind–Hydrogen and PV–Wind–Lithium Battery scenarios.

Simulation modelling of sampling and replacement of coal suppliers for thermal power plants

This paper embarks to the persistent suboptimal coal quality issues experienced in thermal power plants that hinder operational efficiency and sustainability. The research is divided into three main segments: formulation of a transport problem, creationof a coal supplier selection model, and construction of a MATLAB Simulink® simulation for detecting and refusing low-grade coal. The proposed supplier selection model, important for thermal power plants, considers factors such as potential transport delays and the necessity of reserve refueling to prevent fuel shortages. This model is expected to decrease fuel shortages and enhance the reliability and efficiency of thermal power plants. Additionally, a coal quality detection model has been developed using a sampling approach based on the Cochran formula, aiming to increase defect detection accuracy, thus reducing the likelihood of utilizing poor-quality coal. The model's unique feature is its dynamic adjustment of coal sample selection based on combustion results, enabling real-time response to coal quality inconsistencies. Upon detecting poor-qualitycoal, the power plants promptly switch to an alternate supplier, minimizing operational disruptions. The validity of the models was confirmed via simulation on various examples

Разработка метода исследования режимной надежности электроэнергетических систем

The article considers the urgent choice of a solution to the problem of reliable operation of power plants in the maneuvering modes. The performance reliability of power units is assessed. There are listed actual methods of studying the reliability of power plants, which are used in the practice of operation and design of power plants, in particular the electrical part in a statistical state. There is proposed a structural-functional method of studying the reliability of power plants, which allows to analyze the cause-and-effect relationships of the structural diagram elements in the stationary and transient modes of operation and obtain a synthesizing assessment of the final result of the power plant operation, taking into account the factors affecting the mode change. The scheme of directed graphs is illustrated: serial and parallel connection of elements, with direct and reverse stochastic connections. Formulas are given for calculating the availability factor (operability of an individual element or a functional circuit), as well as the inoperability factor due to the frequency of failures and remedial repairs. A case of practical application of the structural-functional method studying the reliability of power plants is considered. The elements of the block diagram of the power unit, turbine plant, electrical connections are listed. An algorithm for calculating the reliability of operation of a 250-300 MW power unit in the modes of start-up, shutdown, load control, stationary and emergency shutdown is considered. The logical sequence of operations of the technological process of the power unit is given. It is noted that the calculations were made on a personal computer in an interactive mode, labor costs amounted to about eight hours for an engineer of average qualification. According to the calculations performed, the conclusions were drawn for the power plant operating in the shunting mode as a whole: frequent starts/stops have a negative impact on the performance of power units, therefore, there is recommended a load mode within the allowable limits of power change.

Sensitivity neutronic analysis of accident tolerant fuel concepts in APR1400

Zirconium-based cladding materials used in nuclear power plants have been shown to pose safety concerns due to their susceptibility to oxidation and hydrogen production during high-temperature conditions, such as loss-of-coolant accidents. In order to address these concerns, alternative cladding materials that are more resistant to these conditions are being explored. This study investigates the potential of using silicon carbide (SiC) and iron-chromium-aluminum (FeCrAl) cladding materials to improve the safety and efficiency of nuclear power plants, particularly in the context of accident tolerant fuel (ATF) technology concepts. The study utilized Serpent Monte Carlo 2.31 to conduct neutronics analyses on the APR-1400 reactor, assessing the impact of SiC and FeCrAl cladding materials on fuel reactivity, neutron spectrum, Pu-239 inventory, and pin power distribution. A sensitivity analysis was conducted by adjusting parameters such as fuel enrichment, cladding thickness, and pellet diameter to determine the effects of the new materials on design parameters. Results of the analysis revealed that, by adjusting design parameters, SiC and FeCrAl materials could be used to meet the cycle length of the original fuel-cladding (zircalloy). Furthermore, using SiC cladding resulted in a hardening of the neutron spectrum, which increased the production of actinides such as plutonium. By analyzing the effects of changing parameters, including fuel enrichment, fuel geometry, and cladding material, the study concludes that SiC is a feasible substitute for conventional zirconium cladding. The findings of this study have practical implications for the safety and efficiency of nuclear power plants. The use of SiC and FeCrAl cladding materials could significantly reduce the risks associated with loss-of-coolant accidents and other high-temperature conditions, thereby improving the safety and reliability of nuclear power plants.

Artificial Intelligence Driven Nuclear Reactor Instrumentation and Control Measurements In-core and Out-core in Nuclear Power Plants

The use of Artificial Intelligence (AI) in nuclear in-core instrumentation and control has the potential to improve the safety and efficiency of nuclear power plants. In-core instrumentation refers to the sensors and other measurement devices that are used to monitor the conditions inside the nuclear reactor core, such as temperature, pressure, and neutron flux. These measurements are used to control the operation of the reactor and ensure that it is operating within safe limits from Probabilistic Risk Assessment (PRA) point of view. One way that AI can be used in nuclear in-core and out-core Instrumentation and Control (I&C) as well as Instrumentation and Measurement (I&M) is by analyzing the data from these sensors in real-time and using machine learning algorithms to identify patterns and trends. This can help operators to detect potential problems or anomalies before they become critical, allowing them to take proactive measures to prevent accidents or malfunctions. AI can also be used to optimize the operation of the reactor by analyzing data from past operations and using this information to develop more efficient control strategies. For example, AI algorithms could be used to identify the most effective combination of control parameters to maintain a stable and safe reactor operation, while minimizing the use of fuel and other resources. Overall, the use of AI in nuclear In-core instrumentation and control has the potential to improve the safety, efficiency, and reliability of nuclear power plants. As AI technology continues to advance, we can expect to see more widespread adoption of these technologies in the nuclear industry

Mathematical modeling of temperature stresses of heat-generating elements of elliptical cross-section

The work is devoted to improving the reliability of nuclear power plants. During operation, the fuel elements of nuclear reactors operate at sufficiently high temperatures. The heterogeneity of the temperature field leads to the appearance of so-called thermal stresses. The main objective of this work is mathematical modeling of temperature stresses of fuel elements of cylindrical and elliptical cross-sections reactors. Based on mathematical modeling, it was shown that the level of thermal stresses arising during the transition from a circular cross-section to an elliptical one decreases.

IMPROVING METHODS FOR MONITORING BEARING UNITS OF ELECTRIC MOTORS IN REVERSE WATER SUPPLY SYSTEMS OF NUCLEAR POWER PLANTS

Ensuring the reliability and safety of nuclear power plants is an urgent task for the Ukrainian energy industry. Permanent circulation of mineral turbine oil is necessary for lubrication of friction surfaces in bearing units of electric motors of water pumping units in cooling systems. Monitoring its condition can indicate the presence of equipment defects under the influence of various factors. Increasing the reliability of oil-filled equipment of nuclear power plants can be achieved by determining the content of dissolved gases in turbine oils; additives “Ionol”; mechanical impurities with the determination of their type. The content of dissolved gases and additives “Ionol” in turbine oils was determined by gas chromatography methods. For turbine oil and a mixture of “water in turbine oil” the physico-chemical and thermophysical properties were investigated – density; flash point; kinematic viscosity; acid number; the content of mechanical impurities, water, additives “Ionol”. The dependences of the concentrations of dissolved gases in turbine oil and the “water in turbine oil” mixture on temperature, as well as the nature of the effect of acoustic cavitation on the kinematic viscosity of the oil and the generation of dissolved gases, have been studied. The aim of the work is to increase the reliability of power equipment of nuclear power plants by improving the control of the physicochemical and thermophysical properties of mineral turbine oil of the brand “Tp-30” of the circulation system for supplying bearing oils with electric motor units of water pumping units of reverse water supply of nuclear power plants.

A novel brushless de‐excitation system for synchronous generators using a buck chopper with a freewheeling discharge resistor

AbstractA new de‐excitation system for advanced brushless excitation based on a synchronous generator is presented. The proposed system uses a discharge resistor in series with a freewheeling diode of a buck chopper. It improves the reliability of the entire power plant and can be used on several excitation systems. It can be used in case of programmed shutdown of the generator and also shows good results in voltage regulation without destroying the efficiency of the excitation system under nominal operation. An analysis of the system has allowed us to suggest a methodology to obtain the appropriate value of the discharge resistance to be used. The validation of the proposed system has been done through simulations in the Matlab/Simulink environment, supported by experimental tests.

Research on diagnosis method of centrifugal pump rotor faults based on IPSO-VMD and RVM

Centrifugal pump is a key part of nuclear power plant systems, and its health status is critical to the safety and reliability of nuclear power plants. Therefore, fault diagnosis is required for centrifugal pump. Traditional fault diagnosis methods have difficulty extracting fault features from nonlinear and non-stationary signals, resulting in low diagnostic accuracy. In this paper, a new fault diagnosis method is proposed based on the improved particle swarm optimization (IPSO) algorithm-based variational modal decomposition (VMD) and relevance vector machine (RVM). Firstly, a simulation test bench for rotor faults is built, in which vibration displacement signals of the rotor are also collected by eddy current sensors. Then, the improved particle swarm algorithm is used to optimize the VMD to achieve adaptive decomposition of vibration displacement signals. Meanwhile, a screening criterion based on the minimum Kullback-Leibler (K-L) divergence value is established to extract the primary intrinsic modal function (IMF) component. Eventually, the factors are obtained from the primary IMF component to form a fault feature vector, and fault patterns are recognized using the RVM model. The results show that the extraction of the fault information and fault diagnosis classification have been improved, and the average accuracy could reach 97.87%.

Экономическая эффективность разработки системы диагностики судового валопровода

The ship shafting ensures the operation of power plants for a significant number of ships of the Russian fleet. Improving the methods of increasing its reliability is an important and urgent task. Part of the loads acting on the propeller and intermediate shafts are random in time and magnitude, that is why it becomes necessary to create a diagnostic system to record the loads and assess the technical condition in real time. The project for creating such a system is knowledge-intensive and involves a large amount of R&D and attraction of investments. There has been suggested an approach to substantiate R&D based on the description of its novelty, commercialization prospects, market analysis and segmentation, business model and calculation of planned economic indicators. The results of the statistical analysis of ship shafting failures are given. An approach is proposed to improve the reliability of a ship power plant based on the simultaneous registration of torsional, transverse and longitudinal vibrations. A quantitative assessment of the market volume was carried out, taking into account the volatility of the exchange rate. The total market size is estimated by the number of vessels in operation by using the methodology of PAM, TAM, SAM and SOM indicators. The target audience of the project was determined by available distribution channels. A nine-block model and commercialization scheme have been developed. The results of calculating the economic efficiency of the investment project are given: net present value and internal rate of return. The results obtained and the applied approaches can serve as a basis for substantiating the investment attractiveness of high-tech projects in the shipbuilding industry.

Reliability Parameter Evaluation of Wind Turbine Based on Minimization of Dynamc Loads Acting on Power Plant Structural Components

An evaluation method of minimization of dynamic loads of big wind wheels with horizontal axis of rotation by replacing a steel lattice tower with a concrete tube was considered as the basic approach to obtain the calculated data of wind power plant reliability evaluation parameters based on dynamic loads minimization acting on power plant structural components. A certain degree of dynamic load minimization acting on vanes based on duly system preparation for external disturbances due to prediction of wind speed and power of electric energy input resulted in load minimization per a vane by 20 %. The problem of parameter reliability evaluation of wind power plant based on minimization of dynamic loads acting on power plant vanes under the condition of duly system preparation for external disturbances was solved enabling increasing of run-to-failure mean time by 8 %. Evaluation analysis of dynamic load minimization acting on power plant structural elements based on optimization model that accounts drive loading conditions at various operation conditions of wind electrical power plant was performed, as the result of rotor system load (“wind wheel - the driving gear”, “gear - generator”) decrease constitutes 20 %. The problem of reliability evaluation parameters of wind electric power plant based on dynamic load minimization acting on power plant structural elements was solved by implementing optimization model of drive loading conditions at various operational conditions of wind electric power plant increasing the rotor system (“wind wheel - driving gear”; “gear - generator”) run-to-failure mean time by 18 %. It was found that the proposed methods of efficiency improvement of wind power plant control enable to increase the operation lifecycle of wind power plant by 26 %.

Increasing the efficiency and reliability of gas turbine power plants through the use of additive technologies

The article is dedicated to the study of the feasibility of increasing the efficiency, reliability and manufacturability of existing gas turbine power plants with additive technologies that allow creating recuperators with regeneration degrees of 90...95%. The characteristics are presented for the following gas turbine power plants: TEEDA (Iran) 3.13 MW, ODK Perm Motors GTU-4P (Russia) 4.13 MW, Siemens SGT-100 (Germany) 5.1 MW, Solar Turbines Taurus 60 (USA) 5.67 MW. The research was carried out using the methods and programs of the Higher School of Power Engineering for the calculation of thermal circuits of GTPP. The dependences of effective efficiency, work ratio, effective specific work and specific consumption of conventional fuel of GTPPs under examination on compressor pressure ratio and regeneration factor are obtained. Solving the problem of increasing the regeneration factor in GTPP (above 0.9) requires the development of special designs of heat exchanger matrices of the recuperator, which is only possible with the use of additive technologies and new heat-resistant materials. Promising recuperators have a more complex design of heat exchange matrices, which ensures their being very compact. Such technical solutions can ensure the development and creation of fundamentally new designs of GTPP heat exchangers and significantly improve their technical characteristics.

Context-informed conditional anomaly detection approach for wave power plants: The case of air turbines

The reliability and energy production of wave power plants (WPPs) depend on sea-state conditions, operation efficiency and degradation of its constituent assets. Air turbines are key assets for the efficient and reliable operation of WPPs and ensuring their correct operation leads to enhance the efficiency of WPPs. However, the lack of run-to-failure data and scarce fault records hampers the development of predictive condition monitoring solutions. In this context, focusing on unsupervised health monitoring methods, this paper presents an air turbine conditional anomaly detection (CAD) approach with a practical case study tested and validated on the Mutriku wave power plant. In contrast to anomaly detection models, which model the health-state without taking into account the influence of the operating context, the proposed CAD approach learns the expected air turbine operation conditioned on specific sea-states information modelled through wave energy flux concepts. This is achieved through an ensemble of Gaussian Mixture models and the expectation–maximization algorithm. Results show that, the integration of sea-states in the anomaly detection learning process improves the discrimination capability of the CAD model compared with the anomaly detection model without sea-state information, reducing false positive events and improving the accuracy of the CAD model.