Equipment Maintenance Research Articles

Optimizing costs and sustainability for gamma knife radiosurgery: A cost and breakeven analysis at India's largest neurosurgery centre.

Establishing and maintaining gamma knife facility incurs significant costs, mandating healthcare institutions to meticulously assess financial implications for sustainability. This study explores the financial implications of setting up and operating a Gamma Knife facility, with an aim to ascertain user charges for achieving breakeven. The study was conducted from January to June 2019 at the largest neurosurgery centre of an Institute of National Importance (INI), in Delhi, India. Applying both Traditional and Time-Driven Activity-Based Costing (TD-ABC) methodologies, capital and operating expenses were calculated. (1US$ = INR 70.4 -Average value for the year 2019). The average cost per gamma knife radio surgery procedure was calculated to be US $2,469 (INR 1,73,832), with major costs attributed to machinery & equipment (43.6%), followed by manpower (32.5%), electricity (9.67%), equipment maintenance (8.61%) etc. The initial investment to establish a Gamma Knife facility is significantly higher with an MRI unit (Model A) at US $ 9,836,423 (INR 69,24,84,164) compared to one without (Model B) at US $7,294,986 (INR 51,35,66,988). Currently, the patient has to pay US $1,065 (INR 75,000) for a gamma knife radio surgery, which poses a challenge for achieving breakeven since the variable cost for the same is US $1,367 (INR 96,239) per procedure. The study serve as a tool for strategic planning, pricing adjustments, and enhancing operational efficiencies, thus ensuring that such high-end technologies can be sustainably integrated into the public healthcare landscape of a developing country like India.

Utilization of Wastewater from Air Conditioner Circulation Systems for Clean Water Energy Efficiency and Industrial Equipment Maintenance

There is significant wasteful use of clean water for operating equipment during field and laboratory practice. Additionally, damage to laboratory equipment has been reported due to the use of untreated water. These issues, along with previous research on managing air conditioner (AC) wastewater at the Lampung State Polytechnic, form the basis for our initiative to utilize AC wastewater as a sustainable resource. Proper management of this abundant water source can support the operation and maintenance of laboratory equipment. The research findings demonstrate that circulating AC wastewater to operate a Soxhlet extraction system for 4.5 hours can reduce clean water consumption by 0.65 cubic meters, equivalent to a cost savings of IDR 43,200. Furthermore, the results indicate improved efficiency, effectiveness, and overall equipment performance when using AC wastewater compared to conventional methods. Contribution to Sustainable Development Goals (SDGs) SDG 6 – Clean Water and SanitationSDG 9 – Industry, Innovation, and Infrastructure:SDG 12 - Responsible Consumption and ProductionSDG 13 - Climate Action

Simulation Research on Data Acquisition and Supervisory Control System of Distribution Network Based on Vector Regression Model

With the gradual maturity of deep learning and the Internet of Things, a smart grid is urgently needed to be established. For the intellectualization of the power grid, non-intrusive load monitoring (NILM) technology is the key step of intellectualization. The traditional load monitoring method is an invasive scheme, in which monitoring sensors are usually installed at the output end of each grid load. This method requires a lot of manpower and material resources in terms of equipment installation and maintenance, which is difficult to sustain. Therefore, monitoring electrical appliances are installed at the entrance of the distribution network to decompose the classification and operation status of the individual electrical appliances in the grid. Aiming at the problem of long-term multi-state electrical apparatus monitoring, this paper mainly optimizes the two optimal deep learning models Seq2Seq and WindowGRU based on activation function optimization, regular function optimization and neural network structure optimization. PReLU, Leaky-ReLU and ELU are used and tested. For the optimization based on regular functions, the value of F1-score is 0.9700, which is 0.1534 more than the optimization algorithm Seq2SeqLR in this paper. Meanwhile, it can also reach 0.8100 for other devices, which is 0.2373 more than the nilmTCN designed in this paper. The Recall value of the identification is improved to 0.6673, which is significantly higher than that of other models. It is proved that the research contents of this paper can improve the effective analysis of load energy consumption data, and can minimize unnecessary energy consumption to achieve the purpose of saving electricity.

Reliability-based reinforcement learning driven maintenance policy optimization

The study presents a reinforcement learning (RL) method called the Q-learning algorithm to determine the best maintenance policy for equipment. This involves an artificial intelligence agent making decisions and an environment representing the equipment. The agent creates maintenance policies and takes actions, while the environment determines state transitions and rewards based on the actions chosen. The optimization of the maintenance policy starts with predicting equipment reliability using sensor data. This prediction method combines Back Propagation Neural Network (BPNN) algorithms with the Boxing Match Algorithm (BMA), an evolutionary meta-heuristic algorithm. A novel weight update strategy enhances the performance of artificial neural networks in reliability prediction. This integrated model, BMA-BPNN, aims to improve the accuracy of forecasted reliability. The study involves forecasting equipment reliability to determine critical levels, incorporating cost and risk considerations into decision-making for optimizing maintenance policies. As a result, the Q-learning algorithm is used to identify the best maintenance actions based on equipment reliability. Implementing an automated maintenance system that considers equipment reliability and costs can help reduce accidents resulting from maintenance program deficiencies. This study thus contributes to the field by providing an efficient approach to equipment maintenance.

"HEALTH INSPECTIONS OF RESTAURANT ESTABLISHMENTS IN THE ATTICA REGION, GREECE. NON-COMPLIANCE DATA WITHIN THE FOOD HYGIENE SECTOR".

Ensuring food safety is a fundamental priority for public health. The catering sector has become prominent as a convenient and cost-effective method of food supply worldwide. Adherence to proper food hygiene practices is crucial for preventing foodborne diseases. The inspection of food items is a key component of internal controls that enables the identification of non-compliance with food hygiene standards. The present study aims to assess Attica restaurant businesses' compliance with international food hygiene standards (FAO/WHO Codex Alimentarius) and European legislation on unsafe food. From January to July 2023, 74 randomly selected restaurants of small, medium, and large capacity in Attica were examined through inspections in terms of compliance for food hygiene standards. The inspections were based on a) the completion of forms and b) the collection of water and food samples for laboratory microbiological analysis. Data were collected using a predefined form, referencing the manual of Codex Alimentarius regarding food hygiene standards (CAC/RCP 1-1969 / CAC/RCP 39-1993). Additionally, the assessment included the identification of unsafe food placement in accordance with Regulation EC/178/2002 on food safety, as well as Greek national legislation (European Commission, 2002; Hellenic Republic, 2006, 2014). The highest non-compliance rates are in "adequacy of facilities" (14.12%), "equipment maintenance and sanitization" (12.30%), "pest control" (12.45%), "personal hygiene" (7.58%), and "efficient separation of raw materials" (9.76%). Non-compliance rates for other food hygiene parameters (cooking practices, meal apportionment, storage, transport, reheating, etc.) were considerably lower. The inspection results showed that medium-sized restaurant businesses present the highest rate (56.41%) of total non-compliance compared to large-sized businesses (29.68%) and small-sized businesses (13.91%). This study demonstrate that restaurant businesses generally adhere to food hygiene and safety standards at a satisfactory level. There is a need for restaurant operators to prioritize enhancing compliance, particularly in addressing critical issues that could potentially result in outbreaks of foodborne diseases. Running Title: "Health inspections of restaurant establishments in Greece".

Innovative virtual reality solutions for technical training in heavy construction equipment repair and maintenance

The construction industry is significantly impacted by heavy construction equipment, including bulldozers, excavators, and vehicles. This equipment speeds up building, moves supplies, and builds infrastructure. Using heavy construction equipment correctly can boost productivity and shorten project timelines. Due to their complexity and scale, this equipment must be maintained and repaired. Poor maintenance and repair of heavy construction equipment can reduce performance, damage, and even cause accidents. Due to these problems, this study focuses on the design and development of a simulation training application to enhance the technical skills of workers in maintaining and repairing heavy construction equipment using virtual reality (VR) technology, the development of this application will be carried out using Unreal Engine 5 and thereafter tested and implemented at PT Menara Indonesia or M-Knows Consulting, Indonesia. At the end of this study, the design and development of a VR training simulation application for heavy equipment repair has been successfully completed. After testing the VR application and conducting user acceptance tests, it was concluded that the created VR application greatly assists M-Knows Consulting in training workers to perform maintenance and repair on heavy equipment, with a user acceptance rate of 84%.

Machine Learning based Material Demand Prediction of Construction Equipment for Maintenance

Machine Learning based Material Demand Prediction of Construction Equipment for Maintenance

Evaluation of Production Capability of Transportation Equipment and Loading Equipment in Limestone Mining at PT X, South Sulawesi

This study focuses on the evaluation of the production capacity of loading and hauling equipment in limestone mining operations at PT. X, South Sulawesi Province. The selection of this topic is based on the importance of operational efficiency in limestone mining which has a direct impact on the productivity and sustainability of the cement industry. The main objectives of this study are to determine the actual production of loading and hauling equipment, determine the number of equipment needed to meet production targets and identify compatibility factors between mechanical equipment at the mining site. The methods used include field data collection involving measurement of cycle time and production capacity of loading and hauling equipment. The data obtained are then processed using statistical methods to ensure the accuracy of the results. Data analysis is carried out by considering variables such as work efficiency, cycle time, and equipment capacity. The results show that Kobelco SK 480 LC has the highest production capacity (509.34 tons/hour), followed by Komatsu PC 400 (448.25 tons/hour) and PC 300 (417.05 tons/hour). To achieve the Crusher production target of 1450 tons/hour, a combination of loading equipment and dump trucks with a compatibility factor between 0.87 and 0.92 is required, indicating potential for increased efficiency. It is recommended to improve maintenance of equipment and mining roads to optimize productivity.

A lightweight and rapidly converging transformer based on separable linear self-attention for fault diagnosis

Abstract Reaching reliable decisions on equipment maintenance is facilitated by the implementation of intelligent fault diagnosis techniques for rotating machineries. Recently, the Transformer model has demonstrated exceptional capabilities in global feature modeling for fault diagnosis tasks, garnering significant attention from the academic community. However, it lacks sufficient prior knowledge regarding rotation invariance, scale, and shift, necessitating pre-training on extensive datasets. In comparison, contemporary convolutional neural networks exhibit greater ease of optimization. This limitation becomes particularly evident when applying the Transformer model in fault diagnosis scenarios with limited data availability. Moreover, the increasing the number of parameters and FLOPs. Pose a challenge to its suitability for mobile services due to the limited computational resources available on edge devices. To mitigate these issues, this paper introduces a novel lightweight Transformer (SepFormer) based on separable linear self-attention (LSA) for fault diagnosis task. The SepFormer performs a novel sequence-level feature embedding to better leverage the inductive bias inherent in the convolutional layers. Furthermore, it integrate a novel separable LSA mechanism into the Transformer architecture, effectively mitigating the computational burden concerns and significantly enhancing the training convergence speed. Extensive experiments are conducted extensively on a bearing fault dataset and gear fault dataset. The experimental results demonstrate that the SepFormer achieves a top-1 accuracy exceeding state-of-the-art approaches by more than 5%, while utilizing the fewest FLOPs. Moreover, the optimizability of SepFormer surpasses that of CNN, ensuring its superior preservation of inductive bias.

Intelligent Control Systems for Mechanical Engineering Technology Tasks

The article is devoted to solving the main tasks set in the work with the aim of analyzing and substantiating the implementation of intelligent control systems in technological processes of mechanical engineering, with an emphasis on increasing efficiency, accuracy, and reliability of production. The use of multi-agent systems and decentralized control systems, which significantly enhance the flexibility and adaptability of production, is analyzed. Special attention is paid to the role of physics-informed neural networks in fault diagnosis, which ensures increased reliability and reduced maintenance costs for equipment. The effectiveness of applying machine learning algorithms to optimize production processes, particularly in material processing and equipment maintenance, is evaluated. The impact of integrating intelligent control systems on production performance and quality, especially in the processes of milling and bonding large parts, is considered. Practical recommendations have been developed for the implementation of an adaptive intelligent production management system (AIPMS), which combines multi-agent systems, neural networks, digital twins, and innovative materials. The implementation of the artificial intelligence concept in production processes will contribute to the further development of mechanical engineering from a technological perspective, enabling enterprises to adopt innovations more rapidly, increase automation, and enhance the adaptability of technological processes, which in turn will lead to significant improvements in product quality and competitiveness. The use of such systems allows optimizing technological processes, reducing the number of defects, lowering energy consumption, and improving environmental efficiency

COMPREHENSIVE ANALYSIS OF METHODS IN PLANNING TECHNICAL MAINTENANCE AND REPAIR OF EQUIPMENT

This article focuses on issues related to the comprehensive analysis of methods for planning equipment maintenance and repair.Considerable attention in the article is paid to the methods of V. V. Semenov, which allow developing schedules for equipment maintenance and repair, help to detect vulnerable areas in operation and carry out preventive measures before equipment malfunctions occur. The methods of V. V. Semenov not only play an important role in the standardization processes, which significantly affects the improvement of the quality of maintenance and repair work, but also touch upon the issue of the quality of repair work. The methods take into account the features of all types of equipment, which contributes to the use of individual approaches to each equipment. However, we have identified shortcomings in the methods, which are reflected in the table; the main one was identified and established as the use of the book value of the equipment, adopted as the basis for calculating standards. Market-oriented methods are used for high-quality planning of equipment maintenance and repair. The author sees the solution to problems in planning equipment maintenance and repair in the fact that these methods use the market value of equipment as a basis for calculating standards, the advantages of which are described in detail in the article. The methods developed by the author determine financial planning and create a reasonable basis for budgeting for equipment maintenance and repair, in a market economy they take into account changes in the market value of equipment, contribute to more accurate economic and financial forecasting, and allow more attention to be paid to assessing the financial risks associated with the operation of obsolete equipment and requiring the development of a strategy to reduce them. In conclusion, it should be noted that the author's methods under consideration are of primary importance in determining the equipment cost estimate, taking into account the costs of equipment maintenance and repair, which contributes to improved investment planning. Thus, based on the comprehensive analysis of the methods, it can be concluded that the use of market-oriented methods in planning contributes to effective asset management and an increase in the overall profitability of industrial enterprises.

The Impact of Pesticides Exposure on Thyroid Function in Rafsanjan Farmers in 2023-2024: A Case-Control Study

Introduction: Pesticides, particularly highly toxic organophosphates, are widely used in agriculture and can disrupt the endocrine system. This study aims to determine thyroid function indicators in agricultural workers exposed to pesticides in Rafsanjan city, Iran, in 2023. Material and Methods: This 10-month (from March 2023 to January 2024) case-control study involved 150 participants (men farmers) divided into three groups: pesticide-spraying farmers, rural non-farmers, and urban non-exposed individuals. Socio-demographic information, medical history, and lifestyle factors data were collected by a detailed checklist. Thyroid enzyme levels, including thyroid stimulating hormone (TSH), total triiodothyronine (TT3), total thyroxine (TT4), and free thyroxine (FT4) were tested by ELISA kits. The collected data were analyzed and compared across the groups by one-way analysis of variance (ANOVA), chi-square and Pearson's correlation coefficient. Results: Significant differences were observed in serum levels of thyroid function indicators such as TSH, Total T4, and Free T4 among the three groups (spraying farmers, rural residents near pistachio orchards, and urban residents), except for Total T3, which showed no significant difference. Moreover, there was a relationship between thyroid function variables in the spraying group and factors such as using personal protective equipment (PPE), days of spraying per year, hours of spraying per day, distance from home to pistachio orchards, and levels of pesticide exposure. However, these relationships were not statistically significant. Conclusion: The study found no significant effect of pesticide exposure on thyroid function, possibly due to minimal skin contact and equipment maintenance practices among farmers. Further investigations are recommended

Management of the technical condition of agricultural machinery using digital technologies

The studies were conducted to substantiate the development of devices and software for managing the technical condition of agricultural machinery using elements of artificial intelligence. The use of artificial intelligence makes it possible to implement a strategy for predictive maintenance and repair of C3 equipment – an integrated approach that allows you to determine the condition of a machine in operation and estimate when maintenance should be carried out. To do this, it is necessary to develop electronic diagnostic devices and sensors that can be combined into a single intelligent information complex that allows you to quickly collect and process large amounts of data on the parameters of the technical condition of agricultural machinery through the use of artificial intelligence. The object of the study is the hydromechanical gearbox of the Kirovets tractor for agricultural and industrial purposes. In 2022–2024, developed data collection devices, software and methods for assessing the technical condition of machines using artificial intelligence and neural network algorithms, and also described the manufactured digital diagnostic devices. Using the example of analyzing the operating parameters of the hydromechanical gearbox of the Kirovets tractor, the introduced concept of technical condition is specified, which consists in calculating the Yn parameter using a neural network, characterizing the nominal, permissible, limiting or emergency technical condition, and establishing recommendations to the owner on the type of possible work and service. Thanks to monitoring and analyzing the operating parameters of the gearbox using AI and continuous updating of the technical condition, technical maintenance and repair are carried out in a timely manner, which ensures technical condition management and increased reliability of agricultural machinery, minimizes failures and related equipment downtime.

Research on Predicting Super-Relational Data Links for Mine Hoists Within Hyper-Relational Knowledge Graphs

Hyper-relational knowledge graphs can enhance the intelligence, efficiency, and reliability of industrial production by enabling equipment collaboration and optimizing supply chains. However, the construction of knowledge graphs in industrial fields faces significant challenges due to the complexity of hyper-relational data, the sparsity of industrial datasets, and limitations in existing link prediction methods, which struggle to capture the nuanced relationships and qualifiers often present in industrial scenarios. This paper proposes the HyLinker model, designed to improve the representation of entities and relations through modular components, including an entity neighbor aggregator, a relation qualifier aggregator, MoE-LSTM (Mixture of Experts Long Short-Term Memory), and a convolutional bidirectional interaction module. Experimental results demonstrate that the proposed method performs well on both public datasets and a self-constructed hoisting machine dataset. In the Mine Hoist Super-Relationship Dataset (MHSD-100), HyLinker outperforms the latest models, with improvements of 0.142 in MRR (Mean Reciprocal Rank) and 0.156 in Hit@1 (Hit Rate at Rank 1), effectively addressing the knowledge graph completion problem for hoisting machines and providing more accurate information for equipment maintenance and fault prediction. These results demonstrate the potential of HyLinker in overcoming current challenges and advancing the application of hyper-relational knowledge graphs in industrial contexts.

MATHEMATICAL MODEL OF THE MOVEMENT OF TABLE BEET ROOT CROP ALONG THE SPIRALS OF A VIBRATING CLEANER

A pressing issue in the technological process of table beet production is the cleaning of root crops from adhered soil, loose impurities, and plant residues after harvesting. The efficiency of this process significantly determines the quality of the final product, its suitability for long-term storage, and subsequent processing. Modern root crop cleaning technologies widely use mechanical methods, among which vibrational and spiral cleaning systems hold a special place. However, many existing designs have several shortcomings, such as insufficient impurity removal efficiency or an increased risk of root crop damage. This study presents a new design of a vibrational spiral cleaner developed to enhance the efficiency of table beet root cleaning. A mathematical model of the root crop's movement along the working channel of the cleaner was constructed to analyze and optimize the operation of this design. It is during this movement that adhered soil, loose impurities, and plant residues are removed. Based on the developed equivalent scheme, a system of differential equations describing the dynamics of the root crop's movement along the surface of the working channel was formulated. Numerical solutions of this system on a personal computer made it possible to study the influence of structural parameters (spiral geometry, pitch, and material) and kinematic parameters (vibration frequency and amplitude) on the speed of root crop movement and the cleaning quality. The analysis of the obtained results showed that optimizing the cleaner's parameters ensures uniform cleaning, reduces the likelihood of root crop damage, and increases the overall process efficiency. The results of this research have practical significance for the further improvement of cleaner designs and their implementation in industrial technologies. The application of the proposed technical solutions will contribute to improving the cleaning quality of table beet root crops, enhancing production efficiency, and reducing equipment maintenance costs.

Algorithms of training programs for simulator training of ship's engine room personnel

The ship's engine room personnel (mechanics, electromechanics) ensure the technical operation and safe functioning of the ship's power systems. Professional training and retraining of marine specialists of ship's engine rooms is necessary due to the constant improvement of equipment and automation of electric power systems of modern ships. To ensure high-quality training of the ship's engine room team, simulator training is used with a set of modern simulators of ship power plants and electric power systems that meet the standards of the International Convention on Standards of Training, Certification and Watchkeeping for Seafarers. In the course of the study, block diagrams of training algorithms have been developed; program features and examples of their operation have been shown. The obtained algorithms for training on simulators make it possible to implement both the initial training of cadets and the retraining of specialists when improving their qualifications. In the course of simulator practice, the opportunity to develop competencies for working with high-voltage equipment (3–10 kV) of modern ships in accordance with the requirements of the STCW Convention and the STCW Code is of particular importance. Algorithms for training in high-voltage equipment maintenance should be introduced into the educational process to improve the level of qualification of specialists.

Analysis of Identifying and Correcting the Digital Printing Defects in Pakistan's Textile Industry

This paper provides an in-depth examination of the issues hindering the adoption of digital textile printing in Pakistan. It presents background on commonly used printing techniques, and analyses industry data to identify major printing defects using quality tools such as Pareto charts and correlation analysis. The root causes of the main defects were determined through cause-effect diagrams and the 5 Whys approach. Preventive solutions are proposed in connection with fabric preparation, process controls, equipment maintenance, training, and sustainable practices. Instead of recommending broad strategies, the study focused on actionable solutions for addressing specific challenges in digital printing, including practical measures for improving operational efficiency in recycling. The analysis provides a comprehensive roadmap for Pakistan's textile industry to overcome current limitations and successfully transition to digital systems for improved productivity, innovation, profitability and global competitiveness.

The Utilisation of Solar-Powered Boreholes for Groundwater Supply: Addressing Water Scarcity in the Polokwane Municipality, Mankweng Cluster

In many African countries, including South Africa, groundwater remains vital for rural communities, yet sustainable methods of its supply still require improvement. The purpose of this study is to enhance groundwater supply through an innovative and sustainable borehole system that improves reliability and ensures a consistent water supply. This study was motivated by the need to provide sustainable water access in rural communities by addressing critical gaps in existing groundwater supply systems, thereby enhancing community resilience. This study identified a problem of water scarcity in the Polokwane Municipality, Mankweng Cluster, where the existing borehole systems are inadequate to supply groundwater. Handpumps demand significant physical effort, grid-powered boreholes cease to operate during frequent power cuts, and the inconsistent diesel supply further limits borehole operation. The study was conducted using a qualitative approach, involving data collection through interviews that were analysed using content analysis. Findings indicate several challenges, including power cuts, diesel supply shortages, poor infrastructure maintenance, vandalism, and theft of equipment, which affect the proper operation of boreholes. The study concludes that water scarcity in the Mankweng Cluster stems from inadequate water infrastructure. The study recommends implementing a solar-powered borehole system that uses photovoltaic energy to pump water from underground aquifers.

Optimizing Container Crane Performance: Enhancing Loading and Unloading Productivity at PT. Kaltim Kariangau Terminal

Container terminals are critical nodes in global trade, where productivity hinges on the efficiency of handling equipment like container cranes. At PT. Kaltim Kariangau, a terminal jointly managed by PT. Pelindo and the East Kalimantan provincial government, operational challenges persist despite infrastructure enhancements. In 2023, an additional crane was introduced to the terminal, increasing the total to three. However, issues such as prolonged idle times and equipment malfunctions adversely impacted crane efficiency. This research evaluates crane performance using BCH (Box/Crane/Hour) and BSH (Box/Ship/Hour) metrics to assess their effect on loading and unloading productivity. The analysis reveals that in 2023, the average crane performance was 27 boxes/hour, a level classified as good. Paradoxically, overall productivity declined post-crane addition compared to prior operations. Using regression analysis, the study identifies a strong positive correlation (R = 0.7316) between crane performance and terminal productivity, with a coefficient of determination (R²) indicating that crane efficiency accounts for 54% of productivity variations. The findings highlight that improved crane performance directly enhances operational output, where each unit increase in BCH corresponds to a 1.809-unit rise in productivity. Hypothesis testing confirms that crane performance significantly influences loading and unloading efficiency. These results underscore the need for effective equipment utilization and maintenance strategies to optimize terminal operations. The research concludes that while infrastructure upgrades are essential, addressing operational inefficiencies is critical to achieving sustainable productivity improvements.

A Data-Driven Feature Extraction Process of Interleaved DC/DC Converter Due to the Degradation of the Capacitor in the Aircraft Electrical System

In recent years, preventive maintenance has emerged as a focal point of research in the aerospace field. The concept of equipment maintenance, exemplified by prognosis and health management (PHM), has permeated every aspect of development and design. Extracting degradation features presents a fundamental and challenging task for health assessment and remaining useful life prediction. To facilitate the efficient operation of the incipient fault diagnosis model, this paper proposes a data-driven feature extraction process for converters, which consists of two main stages. First, feature extraction and comparison are conducted in the time domain, frequency domain, and time–frequency domain. By employing wavelet decomposition and the Hilbert transform method, a highly correlated time–frequency domain feature is obtained. Second, an improved feature selection approach that combines the ReliefF algorithm with the correlation coefficient is proposed to effectively minimize redundancy within the feature subset. Furthermore, an incipient fault diagnosis model is established using neural networks, which verifies the effectiveness of the data-driven feature extraction process presented herein. Experimental results indicate that this method not only maintains fault diagnosis accuracy but also significantly reduces training time.