Reduce Maintenance Time Research Articles

Fault detection in the gas turbine of the Kirkuk power plant: An anomaly detection approach using DLSTM-Autoencoder

Developing a maintenance schedule for different parts of a power plant can help to prevent serious system damage while also having a direct effect on reducing maintenance time and costs. Moreover, the proposed procedure can provide a better understanding of the health state of the system. The occurrence of problems (anomalous behavior) in power plants usually takes time and happens gradually. Predicting the possibility of anomalous behavior arising can therefore result in the prediction of a failure. In this paper, the authors tried to propose a new method for reducing the volume of input data by extracting the latent layer output of an Autoencoder, which was then applied to identify features. We achieved this by keeping relevant features and learning the anomalous behavior's encoded representation. Furthermore, the latent layer output from the encoder was used to train a Deep Long-Short-Term Memory (DLSTM) model with three hidden layers for fault occurrence prediction by considering an anomaly detection approach. To this end, a threshold approach was used to determine the possibility of a fault occurring in the turbine, with data collected from the Kirkuk gas turbine power plant. Piezoelectric accelerometer CA 202 was utilized as a sensor to collect data in industry. Since most of the recorded data were normal and the amount of abnormal data was small, various techniques, i.e., flipping and jittering, were employed to create synthetic abnormal data and augment the applicable dataset. In summary, according to the proposed methodology, the system is modelled as a time series classification problem to mimic the anomaly detection problem. The results showed that the accuracy of the trained model for detecting turbine vibration as a system abnormality is over 86%. Also, the implementation of the proposed prediction model on the experimental dataset yielded satisfactory results for detecting and predicting the occurrence of faults in Kirkuk gas turbine power plant.

Research on pulse laser cleaning and rust removal technology in power systems

In this paper, pulse laser cleaning and angle grinder polishing were used to clean the surface rust of carbon steel, and the cleaning effects of different cleaning methods for carbon steel surface rust were studied. The change of the micro-region morphology and element composition of the cleaned surface was analyzed. Comparative experiments were conducted on the corrosion resistance and paint anticorrosion ability of cleaned metal surfaces. Through comparison and analysis, the use of laser cleaning technology can improve the surface cleanliness and corrosion resistance of metals, reduce maintenance times, and extend service life. Laser cleaning machines with a power of 100 W or above can effectively perform precision cleaning and can be widely promoted in the field of power systems.

Wind turbine inspection with drone: Advantages and disadvantages

The facilities on wind energy generation are increasingly finding usage areas in line with the ecologically friendly energy generation approach. One of the important activities of wind power generation facilities, which have high investment cost, low operating cost and low environmental impact is the maintenance and repair of wind turbines. A preventive maintenance approach is dominant to reduce maintenance times and eliminate lost time in wind turbines. Damage inspection of turbines has been evolved from tower crane access, rope access, camera viewing, and other applications to image with manual drones over the years. However, when these methods are evaluated within the framework of criteria such as cost, performance, occupational safety and data reliability, they are still insufficient and the need for inspection with autonomous drones arises. The advantages and disadvantages of autonomous drones used in the determination of damage in wind turbines are analyzed and the results are considered to contribute to the practitioners operating in the sector and academicians working in the field.

Virtual and Augmented Reality for Training and Maintenance of a Multiparameter Monitor

Virtual reality (VR) and augmented reality (AR) have experienced a significant boom in recent years regarding their features and utility. They have become reliable tools that are applied in different fields and disciplines (medicine, industry, science, teaching, training, and robotics, among others). In the present research work, these technologies are used as tools for the training and maintenance of medical equipment. An application was developed using flexible programming and design software, such as Vuforia, Unity, SolidWorks, Visual Studio, and hardware such as smartphones and the HTC VIVE glasses. Considering the existing need and based on surveys carried out to medical and hospital technical staff, significant results were obtained about the use of AR and VR in the area of medicine. The use of interactive applications enables autonomous training, which may be executed at any time and it is also user-friendly; in addition, it enables achieving reduced maintenance time and improves the process of acquiring abilities, thus releasing resources for other purposes.

Wettability and corrosion resistance of zirconium nitride films obtained via reactive high-power impulse magnetron sputtering

One of the main problems in ships is corrosion, which reduces the lifetime usage of ship parts and increases maintenance costs. Ceramic coatings can contribute to solving this situation. Zirconium nitrides obtained by reactive unbalanced magnetron sputtering technology are largely reported as coatings with high corrosion resistance. The present study used high-power impulse magnetron sputtering in a reactive atmosphere (R-HiPIMS), varying the nitrogen amount. SEM, EDS, XRD, AFM, and contact angle measurements were used to assess the obtained coatings’ performance. Corrosion resistance was evaluated using electrochemical impedance spectroscopy (EIS) (up to 168 h exposure) and potentiodynamic polarization (PP) in NaCl (3.5% wt.—“artificial seawater”) solution. According to the results, cross section micrographs showed strong densification of ZrN films regardless of the nitrogen amount. Besides, nitrogen increases during deposition influenced the drop of applied peak power (Pp) to the target and, consequently, influenced other film properties, such as roughness, wettability, and corrosion resistance. PP and EIS tests demonstrate the protective behavior of films under artificial seawater exposure. The results prove that the implementation of HiPIMS technology to obtain ZrN films could contribute to increasing the corrosion resistance of coated ship metallic parts and, hence, help maritime transportation to reduce maintenance time and cost.

Short-term aviation maintenance technician scheduling based on dynamic task disassembly mechanism

This paper focuses on the aviation maintenance technician scheduling (AMTS) problem and formulates AMTS and AMTS-DTDM model with a practical dynamic task disassembly mechanism (DTDM) and arrange maintenance technicians across shifts in short-term maintenance situations (less than 24–48 h). In DTDM, four technician scheduling modes are devised to flexibly disassemble the overtime work or reassigned it to other maintenance technicians according to work efficiency and progress, which could shorten the maintenance time and save the total cost. Moreover, a flexible time interval is designed to adjust the boundary of task disassembly. To further study the effectiveness of DTDM in reducing maintenance time and total costs, this paper divides both the AMTS and AMTS-DTDM models into three sub-models (i.e., two single-objective models and one multi-objective model), respectively. After that, we design solution methods as well as the encoding schemes compatible with both the AMTS model and the AMTS-DTDM model for different problem scales. Finally, to verify the effectiveness of DTDM, four groups of experiments are set up and particle swarm optimization (PSO) and multi-objective particle swarm optimization (MOPSO) are applied to compare AMTS and AMTS-DTDM sub-models. The experimental results show that the AMTS-DTDM model can effectively shorten the maintenance time and reduce the total costs for different scaled problems. Furthermore, the flexible time interval can facilitate more options for airlines to adjust the two above objectives to a small extent. The increase in flexible time may weaken the advantages of the AMTS-DTDM model while improving the rationality of the ultimate technician scheduling scheme.

Novel infrastructure for coral gardening and reefscaping

Since 1950, coral abundance has declined worldwide by an estimated 60%, and further dramatic declines are predicted. Although global reductions in carbon emissions are essential to prevent further loss, coral reef restoration has become imperative to maintain the ecosystem services that coral reefs provide to humans at local scales. Yet, currently coral restoration and gardening efforts are too expensive to scale up due to the labor-intensive nature of the methods and low success rates. Here, we present a suite of technologies that improve coral reef restoration and rehabilitation’s scalability, efficiency, and effectiveness. Our modular technologies are designed to streamline in and ex situ nursery workflows, reduce maintenance times, solve problems in transporting corals to outplanting sites, and enable rapid outplanting on natural and artificial substrates. These novel structures can act as coral seeding hubs, which placed strategically, can have the capacity to enhance coral reproduction and replenish degraded nearby reefs with larvae. They can be applied to coral restoration and reefscaping, complemented by unique eco-friendly, low-carbon-emission structures for the creation of architecturally and visually appealing habitats and underwater landscapes. Our technologies integrate novel monitoring approaches that support intelligent solutions to track genotypes, optimize and control stock management, apply assisted evolution approaches, and adaptive management through long-term monitoring.

Application of Data Analysis and Data Visualization in Medical Equipment: Take Infusion Pump as Example

To combine data analysis and data visualization with medical devices, provide a set of data analysis and data visualization solutions. This solutions can deeply excavate the data of the whole life cycle of medical equipment, and then play a guiding role in business. With the help of mature tools in the Internet field, YIYI and YOUSHU, we can quickly complete data collection and rich visualization effects, and introduce the concept of data analysis to deeply mine data. Taking the maintenance data of infusion pump as an example, the data collection is completed through YIYI, and the maintenance system is built on YOUSHU. The maintenance system of infusion pump system is simple and clear, with good visualization effect. It can quickly analyze maintenance failures, reduce maintenance times and maintenance costs, ensure the safety of the equipment. Moreover, the system can be easily transferred to other medical equipment, and can carry on the whole life cycle data research.

METHODOLOGY OF CONSTRUCTION OF TRANSPORT AND TECHNOLOGICAL SCHEMES OF DELIVERY OF SUPPORT MEANS FOR MAINTENANCE OF COMBAT AIRCRAFT AT THE AIRPORTS OF UKRAINE

The article analyzed the existing methods of building technologies for the maintenance of civil and military aircraft and identified mathematical methods that can be used to study the prospects for the development of aircraft maintenance systems, which allowed to form the purpose of the study in this development. The chosen topic is quite relevant, because the formation of transport and technological schemes for the delivery of support for the maintenance of combat aircraft can increase the efficiency of resource use and reduce the time for training at Ukrainian airports in a conflict situation. One of the ways to reduce maintenance time is to determine the effective distribution of transport and technical means for the preparation of aircraft. It was established that in the scientific developments of foreign scientists, solutions were proposed related to the construction of transport and technological schemes for the delivery of support for the maintenance of various types of aircraft. Most of these solutions were aimed at using agent-based simulation models for application to the process of generating combat sorties of aircraft - this made it possible to process a large amount of data and generate management decisions in the transport service system. Also, most authors propose to take into account the conditions of uncertainty and time constraints when building a methodology to improve the efficiency of aircraft maintenance. An algorithm for the rational distribution of transport resources for aircraft preparation at Ukrainian airports has been developed, based on the results of simulation modeling of the aircraft maintenance process under different service conditions (time of day and climatic conditions that affect the time of aircraft maintenance and the time of movement of vehicles along transportation routes). On the basis of the developed algorithm of rational distribution of transport resources for aircraft preparation, the technology of aircraft maintenance at Ukrainian airports is proposed, which indicates the sequence of operations aimed at determining and comparing the normative values of the duration of maintenance of the corresponding aircraft with the calculated values and determining their rational number. Keywords: methodology, transport and technological scheme, means of support, combat aircraft, airports.

Increasing the efficiency of operating time and reducing maintenance time of transport systems

The Gremikhinsky oil field contains heavy-grade, high-sulfur, high-resinous, paraffin-base crude oil, and the produced reservoir fluid is highly corrosive. All this results in the formation of asphaltene-resin-paraffin deposits (ARPD) and stable oil-water emulsions, which in turn leads to premature failure of downhole pumping equipment. In this work, the scope of measures to prevent malfunctions of pumping units is considered. The use of the SONKOR-9701 inhibitor through a special design of the ESP power cable with a capillary conveying line for supplying the chemical reagent to the reception delivers the chemical reagent directly to the required entry point with the most effective dosage and ensures a prompt change of the dosage and type of the reagent. With this technology, the reagent is not consumed for the repletion of the oil column in the annular space; its adsorption is on the surface of the casing and tubing. Thus, the reagent targeted with just specific technological causes and the greatest effect is ensured. Due to the introduction of a special cable with a capillary conveying line, it is planned to increase the average operating time for failure and, consequently, reduce the maintenance job at the Gremikhinsky oil field. It is also predicted the additional volume of extraction because of a special submersible cable device (SSCD), as well as by increasing the delivery (capacity) rate of the pump.

Sliding Thrust Bearings with Self-Generated Fluid Pivots

The article discusses the disadvantages of thrust sliding bearings with mechanical supports and mechanical balancing systems similar to the Kings-bury system. Requirements for the design of thrust bearings corresponding to the current level of development of dynamic equipment are formulated. The design of thrust bearings using a hydrostatic suspension is proposed to eliminate the disadvantages of thrust bearings with mechanical supports and balancing systems. The modern design of the bearing developed by TRIZ LTD with mechanical bearings, which meets the requirements of the optimal choice of bearing the best, is given in this article with its ad-vantages and disadvantages inherent in all mechanical systems. The given results of the TRIZ LTD work on the creation of thrust sliding bearings with the replacement of mechanical bearings and mechanical balancing of thrust elements with self-generated fluid elements are used with traditional oil systems. The developed original technical solutions made it possible to reduce the axial subsidence, the number of parts, axial dimensions, noise, axial vibration. Various designs of thrust bearings with self-generated fluid pivots, which most fully satisfy the requirements for the optimal choice of a thrust bearing design and their comparative characteristics in comparison with design of a thrust bearing with mechanical supports of bearing pads and a mechanical alignment system obtained during their testing at the bench are given. Thrust bearings with self-generated fluid pivots are recommended for new developments of rotary equipment, as well as for modernization of equipment operated to increase overhaul mileage, reduce maintenance time, increase reliability and efficiency of equipment due to higher bearing capacity, effective damping and practical axial subsidence from force.

Location-Aware Maintenance Strategies for Edge Computing Infrastructures

Efficient server maintenance and update is essential to prevent performance and security issues in edge computing environments. Despite many initiatives in maintenance planning, state-of-the-art approaches concentrate on carrying out updates in cloud data centers, ignoring aspects of the problem that are specific to the edge computing paradigm, such as user-location awareness. In this letter, we present two maintenance strategies, called Lamp and Laxus, that consider users’ locations when performing migration decisions to avoid delay bottlenecks during edge servers maintenance. Results show that the proposed strategies can reduce maintenance time by 44.27% compared to existing strategies while effectively avoiding delay bottlenecks.

Research on Gentle Loosening of Solidified Bolted Joints for Complex Capital Goods

The consideration of sustainability is increasingly becoming a focus in research and production. For example, the recycling process for products that are no longer usable should be optimally prepared by separating materials by type as far as possible. In addition, products should be made usable again by repair or replacement if only sub-components fail. In the case of complex capital goods, like aircraft engines, it is mandatory to preserve the product since damage to the joining partners can lead to immense costs. A decisive factor in this context are assembly connections, which have a major influence on the complexity of disassembly. Concerning this matter, detachable connections, like screwed joints, have many advantages for service, repair and recycling compared with permanent fixing solutions. They can reduce assembly time, simplify maintenance processes, and greatly reduce maintenance time and costs. However, during a product’s life cycle, threaded connections can corrode, leading to damage or even failure of the bolted joints. Beyond that, they can solidify and often only be disassembled destructively. In this article, we present an approach to improve the loosening of operational solidified screwed connections. It is well known that vibrations during operation can reduce the preload force of the connections. We exploit this aspect by inducing vibrations through micro impacts to alleviate the loosening torque of the solidified bolted connection. Depending on the direction of the vibration (torsional or axial), that can ensure a gentle and component-friendly disassembly to a greater or lesser extent in contrast to destroying the screw by drilling or shearing and splitting with the risk of damaging the product being maintained. The designed experimental setup with a piezo actuator allows us to investigate the amplitude and frequency of the induced vibrations for the required disassembly force. The results show that our approach enables component-conserving disassembly, as the forces can be significantly reduced.

A Bayesian Optimized Discriminant Analysis Model for Condition Monitoring of Face Milling Cutter Using Vibration Datasets

Abstract With the advent of industry 4.0, which conceptualizes self-monitoring of rotating machine parts by adopting techniques like data analytics, cloud computing, Internet of things, machine learning (ML), and artificial intelligence. The significant research area in predictive maintenance is tool condition monitoring (TCM) as the tool condition affects the overall machining process and its economics. Lately, machine learning techniques are being used to classify the tool’s condition in operation. These techniques are cost saving and help industries with adopting future-proof solutions for their operations. One such technique called discriminant analysis (DA) must be examined particularly for TCM. Owing to its less-expensive computation and shorter run times, using them in TCM will ensure the effective use of the cutting tool and reduce maintenance times. This article presents a Bayesian optimized discriminant analysis model to classify and monitor the tool condition into three user-defined classes. The data are collected using an in-house designed and developed data acquisition (DAQ) module setup on a Vertical Machining Center (VMC). The hyperparameter tuning has been incorporated using Bayesian optimization search, and the parameter that gives the best model was found out to be “linear,” achieving an accuracy of 93.3%. This study confirms the feasibility of machine learning techniques like DA in the field of TCM and using Bayesian optimization algorithms to fine-tune the model, making it industry ready.

Integration of wavelet decomposition and artificial neural network for failure prognosis of reciprocating compressors

AbstractCompressors in petrochemical plants are often crucial to process operations, and when a failure occurs, the outcome can be catastrophic. Many researches have been attempting to detect failure modes as early as possible to plan upfront repair and conceivably reduce maintenance time. A reciprocating compressor was selected as the target of this study, and a few years of historical records of maintenance parameters and maintenance work orders were gathered for analysis. The time history was divided into 13 events, and each event started with a normal operation and ended with a repair work order. Time‐domain features and wavelet decomposition features of the parameters were extracted, and the patterns stored within each event were identified using the artificial neural network and support vector machine. Moreover, a set of reasoning algorithms were developed to detect anomalies, and responsible failure modes were identified. For a specific type of compressor, the vibration signal was found to be related to most of the anomalies and thus used for evaluation. Results showed a >90% detection rate for failure mode diagnosis based on historical test data.

Novel Method for Wind Turbines Blades Damage Classification using Image Processing

Wind turbine generators are spreading around the world due to its advantages over fossil fuels. Structural monitoring of them is important to increase operation and reduce maintenance times. Visual inspection is highly influenced by the human factor due to the working conditions. Image processing supported by vision systems offers high advantages reducing times, being the software and processing algorithms, which generates added value. In this paper, a novel method for wind turbines blades damages analysis is presented using image processing and a classifier based on dimensional features. The image acquisition is performed using a reflex camera with a telephoto and geo-location enabled. The faults analyzed include cracks, edge erosion, and electric discharge.

Fault coil location of inter‐turn short‐circuit for direct‐drive permanent magnet synchronous motor using knowledge graph

Inter-turn short-circuit fault (ISF) degrades its reliability and may cause serious catastrophes for direct-drive permanent magnet synchronous motor (DDPMSM). Fault location technology can reduce maintenance time, increase the mean time between failure (MTBF), and then improve the reliability of DDPMSM. Hence, an intelligent fault locating system for DDPMSM is proposed in this paper. This system proposes a knowledge graph (KG) based diagnostic tool for detection and location of the fault coil. First, the fault model of the DDPMSM with multiple branches parallel winding is established, which is used to analyze the fault characteristics of motor. Second, the BDC and BRC are proposed as the fault indicator. The effectiveness and robustness of fault indicator are analyzed. Then, the KG system are designed and established according to the relationship between fault indicator and location of fault coil. Finally, the system is tested by data under different fault and operation conditions. The test results showed that the proposed fault locating system can detect and locate the fault coil in early stage. The minimum ratio of shorted turns to branch turns that can be detected is 0.52%. The minimum ratio of shorted turns to branch turns that can be located is 6.25%.

Development of a Double‐Breakaway Pass‐Through PIT Tag Antenna System for Flood‐Prone Rivers

AbstractPass‐through PIT antennae are often used in river and stream habitats to monitor the movement of aquatic species. Where these habitats are prone to high flows that contain suspended debris, traditional pass‐through antennae designs are particularly vulnerable to damage, which can be time consuming and expensive to repair and lead to extended gaps in data collection. We designed and tested a novel pass‐through half duplex (HDX) antenna system that allows the antenna loop to (1) break away from one river bank under predetermined strain and (2) split into two separate cables, thereby shedding entangled debris that could otherwise damage or dislodge the antenna system. After break away events, our system can be rapidly reconnected and redeployed without the need for personnel to enter the water, reducing maintenance time and costs while minimizing gaps in data. In locations where pass‐through antennae are prone to flood damage, this system offers distinct advantages over traditional designs.

Performance evaluation of ultra-class mining shovel track roller paths

ABSTRACT This paper outlines a scale test approach for roller-roller path contact proportional to the field impact observed in the undercarriage of ultra-class mining shovels. The scale test is a cost-effective means to predict the degree of roller contact fatigue deterioration as a function of the number of field-measurable duty cycles. The proposed test method will potentially permit more cost-effective, small-scale development testing of roller path technology for specific mining conditions for ultra-class shovel designers. The preliminary data reported in this paper indicate that the proposed test configuration can infer performance to end-of-life roller-roller path combinations within the confines of a given set of field loading conditions (coal mine in this case). The results open up a future opportunity to verify the sensitivity of damage models, leading to the advancement of roller-roller path systems with greater operational longevity and reducing maintenance time and cost through avoidance of catastrophic failure.

Improving the Efficiency of the Power Take-Off Drive

power tools that are used in various industries have power take-off drives for aggregating various machines and mechanisms. In the agro-industrial complex, one of the most common power tools are tractors manufactured by the Minsk Tractor Plant. The drive of power take-off in these tractors is carried out at the expense of the planetary mechanism. The wheel and the solar gear of the planetary mechanism are connected to the drums, alternately stopping the drums is carried out on and off the drive. The brake tape of the firing drum connected to the sun gear is most susceptible to wear, as the drum is loaded with a torque of at least one third of the torque to the drive of the aggregated machine.Due to the design features of the existing control mechanism, the turn–on time is 1.5-2 times less than recommended for devices of this kind. As a result, there is an intense wear of the friction lining of the inclusion drum tape.Regulation of the control mechanism of adjusting screws is carried out untimely, as a result, the durability of the tapes is very low.To improve the durability and efficiency of the power take-off drive, a drive-on design is proposed by electromagnets.Applying force to the tape by electromagnets at four points, instead of one in the previous design, will improve the braking efficiency of the inclusion drum.It is possible to include electromagnets not at the same time, but with some time offset, with a gradual pressing of the tape, starting with the portion of the tape closest to the axis of its suspension. This improves the fit of the tape to the drum inclusion.In the transition from a mechanical drive to an electrical device, the control operation is eliminated, which reduces maintenance time, significantly increases the life of the brake belt and increases the efficiency of the power take-off drive.