Reliable Operation Of Equipment Research Articles

Complex system anomaly detection via learnable temporal-spatial graph with degradation tendency segmentation

To guarantee the safety and reliability of equipment operation, such as liquid rocket engine (LRE), carrying out system-level anomaly detection (AD) is crucial. However, current methods ignore the prior knowledge of mechanical system itself, and seldom unite the observations with the inherent relation in data tightly. Meanwhile, they neglect the weakness and nonindependence of system-level anomaly which is different from component fault. To overcome above limitations, we propose a separate reconstruction framework using worsened tendency for system-level AD. To prevent anomalous feature being attenuated, we first propose to divide single sample into two equal-length parts along the temporal dimension. And we maximize the mean maximum discrepancy (MMD) between feature segments to force encoders to learn normal features with different distributions. Then, to fully explore the multivariate time series, we model temporal-spatial dependence by temporal convolution and graph attention. Besides, a joint graph learning strategy is proposed to handle prior knowledge and data characteristics simultaneously. Finally, the proposed method is evaluated on two real multi-sensor datasets from LRE and the results demonstrate the effectiveness and potential of the proposed method on system-level AD.

A Deep Learning Method for Bearing Cross-Domain Fault Diagnostics Based on the Standard Envelope Spectrum.

Intelligent fault diagnostics based on deep learning provides a favorable guarantee for the reliable operation of equipment, but a trained deep learning model generally has low prediction accuracy in cross-domain diagnostics. To solve this problem, a deep learning fault diagnosis method based on the reconstructed envelope spectrum is proposed to improve the ability of rolling bearing cross-domain fault diagnostics in this paper. First, based on the envelope spectrum morphology of rolling bearing failures, a standard envelope spectrum is constructed that reveals the unique characteristics of different bearing health states and eliminates the differences between domains due to different bearing speeds and bearing models. Then, a fault diagnosis model was constructed using a convolutional neural network to learn features and complete fault classification. Finally, using two publicly available bearing data sets and one bearing data set obtained by self-experimentation, the proposed method is applied to the data of the fault diagnostics of rolling bearings under different rotational speeds and different bearing types. The experimental results show that, compared with some popular feature extraction methods, the proposed method can achieve high diagnostic accuracy with data at different rotational speeds and different bearing types, and it is an effective method for solving the problem with cross-domain fault diagnostics for rolling bearings.

Unknown fault detection of rolling bearings guided by global–local feature coupling

Fault diagnosis technology can effectively prevent the occurrence of faults and reduce safety hazards, which is of great significance in nuclear power, aerospace, manufacturing, and other fields. Given the stringent demands of safe and reliable equipment operation in practical production environments, acquiring a comprehensive set of fault samples becomes challenging. At present, many deep learning-based methods have been researched on this problem. However, these methods do not account for the identification of novel faults that may emerge. In this paper, we propose a novel global and local feature joint learning method for unknown fault detection, which addresses this problem by applying the knowledge learned by the supervised feature extraction process to the unsupervised clustering process. In particular, we propose a dual-branch framework for detecting unknown faults, which is based on multi-scale coupled feature extraction. This framework establishes correlations between features at different scales and employs the coupling of global and local features to facilitate the detection of unknown faults. Additionally, we propose a causal modeling method for global and local features, aiming to uncover the true causal relationship among global and local features and fault categories. Moreover, we propose a consistent prediction method to ensure the coherence of prediction results between the global and local branches. We evaluate the performance of our model using the CWRU, PU, and RB datasets, and the results demonstrate its superiority over state-of-the-art methods in terms of clustering accuracy and normalized mutual information.

Remaining useful life prediction method for Degradation–Shock dependence: Case of a subsea hydraulic control system

Predicting the remaining useful life (RUL) is crucial for ensuring reliable equipment operation. This study addresses the challenges of RUL prediction in modeling the effects of external shocks and internal degradation, with emphasis on the dependency relationship between the two factors. A novel hybrid method for RUL prediction is proposed. The proposed method combines degradation models and field data to realize RUL assessment under the influence of system degradation and external shocks. A dependency factor is introduced to effectively incorporate the influence of degradation stage and shock intensity on system failure. A comprehensive uncertainty analysis is performed, in consideration of random degradation, unpredictable shock events, and the dynamic evolution of degradation stages and performance degradation processes. Numerical simulations are conducted on a hydraulic control system to demonstrate the effectiveness and accuracy of the proposed method. The robustness and reliability of the proposed approach in predicting the RUL of the hydraulic control system are demonstrated, with particular emphasis on the method's capability to handle the complexities of dependency modeling and uncertainty analysis. Results show that the proposed method can realize dependency modeling of the hydraulic control system, accurately predict its RUL, and analyze the vulnerability of its subsystems.

Icephobic Coating Based on Epoxy/Polydimethylsiloxane Interpenetrating Polymer Network Gel

Ice accretion endangers the safety and reliability of equipment operation in frigid regions. Silicone polymer icephobic coatings present themselves as an effective strategy. However, they face durability challenges, which is a crucial foundation for expanding their application. In this work, a durable icephobic coating was prepared based on an epoxy/polydimethylsiloxane (PDMS) interpenetrating polymer network (IPN) gel. In the process, epoxy was used to improve mechanical performance. IPN technology was used to integrate PDMS and epoxy. Low-molecular-weight silicone oil was used to adjust the elastic modulus of the coating by reducing crosslinking. The mechanical properties, icephobicity and durability of the coatings were characterized through elastic modulus measurements, ice adhesion strength tests, and icing/deicing cycle tests, respectively. Results shows the ice adhesion strength of the epoxy/PDMS IPN gel coating was approximately 8 kPa when the elastic modulus was 0.18 MPa. Additionally, the epoxy/PDMS IPN gel has good durability, weather resistance, and substrate adhesion. After 25 icing/deicing cycle tests, the coating remained undamaged, and the ice adhesion strength was stable in the range of 3–14 kPa. Within the range of −5 to −30 °C, the ice adhesion strength of the coating was stable and less than 20 kPa. After 168 h of salt spray aging test, the ice adhesion strength of the coating was maintained at 48.72 ± 5.27 kPa. This can provide a reference for an icephobic coating design.

Leveraging Classical Statistical Methods for Sustainable Maintenance in Automotive Assembly Equipment

Predictive maintenance management plays a crucial role in ensuring the reliable operation of equipment in industry. While continuous monitoring technology is available today, equipment without sensors limits continuous equipment state data recording. Predictive maintenance has been effectively carried out using artificial intelligence algorithms for datasets with sufficient data. However, replicating these results with limited data is challenging. This work proposes the use of time series models to implement predictive maintenance in the equipment of an automotive assembly company with few records available. For this purpose, three models are explored—Holt–Winters Exponential Smoothing (HWES), Autoregressive Integrated Moving Average (ARIMA), and Seasonal Autoregressive Integrated Moving Average (SARIMA)—to determine the most accurate forecasting of future equipment downtime and advocate the use of SAP PM for effective maintenance process management. The data were obtained from five equipment families from January 2020 to December 2022, representing 36 registers for each piece of equipment. After data fitting and forecasting, the results indicate that the SARIMA model best fits seasonal characteristics, and the forecasting offers valuable information to help in decision-making to avoid equipment downtime, despite having the highest error. The results were less favorable when handling datasets with random components, requiring model recalibration for short-term forecasting.

A study of mixer-feeder equipment operational reliability

Modern livestock development trends in the agricultural production structure include the use of feed mixers and distribution equipment. However, a stream of malfunctions and failures is reported for mixer-feeders due to factors that are specific to agricultural enterprises in Ukraine, which reduce the operational reliability of feed mixers and distributors. The study aims to evaluate the quantitative indicators of the in-service reliability of mixer-feeders and develop methods to improve them. The reliability test plan [NMT] was used, which implies a certain number of research objects (N), objects undergoing repair in case of performance loss (M), and tests terminated when the operating time (T) is reached. Initial information was collected and processed, and empirical data on the time between failures of KUHN PROFILE 12.2 DS and PROFILE 14.2 DS mixer-feeders in Ukraine were analysed. The analysis established that the faulty condition of mixers-feeders in the initial operation period is caused by the second complexity group failures. Failures related to the loss of the grinding and mixing mechanism, which limits the average time between failures of the feed mixture and distribution equipment, were identified among the second complexity malfunction group. A statistical analysis of the mixer-feeder failure occurrence was carried out. The failure probability of the grinding-mixing mechanism of the feed mixer was determined to be within the normal distribution law. The main parameters of the given theoretical distribution law were determined by calculation results. The calculations determined that the average time between failures is 3152.0 motor-hours; the standard deviation is 902.6 motor-hours; and the coefficient of variation is 0.40. An average time between failures of the study objects was proved to be consistent with the normal distribution law following Kolmogorov’s agreement criterion. Calculations determined that the average reliability index value, according to the normal distribution law, is within the confidence intervals: 1964.2 motor-hours – lower confidence limit; 4339.8 motor-hours – upper confidence limit. The obtained results may be used to improve the mixer-feeder operational reliability

Thermal conversion of aviation oils

These days, strict requirements to aeronautical equipment are imposed to enhance reliability, durability, and environmental compatibility. Aeronautical equipment operation reliability depends not only on its structural and technologic abilities, but also on the fact how aviation oils, fuels and technical fluid meet quality requirements during operation. During the aircraft engine operation, oils are subjected to the thermal impact. As a consequence, their properties and composition change which can affect the engine operation, on the whole. The most promising means of improving thermal resistance of aviation oils is developing new ones and improving available oil compositions. Therefore, it is feasible to analyze the kinetic properties of the oil thermal conversion which will make it possible to predict their resistance within the extensive temperature range. The paper investigates thermal decomposition kinetics of aviation oils MS-8P, TN-98 and TN-600 used on different types of aircraft in civil aviation of the Republic of Belarus by the method of a thermo-gravimetric analysis. The composition of oil samples has been researched into by IR spectroscopy, chromatography-mass spectroscopy methods. A comparative analysis of research results of new oils and oils drained from aircraft engines indicates that even under insignificant overheat during the operation, a change in the hydrocarbon composition occurs, and the hydrocarbon content of basic types varies to some extent. The oil thermolysis research reveals that potential overheat after engine shutdown complies with the temperatures at which the decomposition commences. Thermal conversion products of oil carbohydrates will contribute to the defect formation in friction subunits. As a result of test data processing of thermal conversion of aviation oils MS-8P, TN-98, TN-600, the principles of their decomposition as well as macrokinetic parameters, allowing us to precisely evaluate the effect of oils operation temperature conditions on their conversion rate, have been specified. It is essential while simulating the aircraft engine operation and predicting variations of oil quality properties during their operation.

Exploration of Key Technologies for Equipment Operation and Maintenance Based on New Power Systems

With the construction and development of the new generation of power system (thereafter, it is displaced with PS), intelligent power equipment is more widely used and higher requirements for the flexibility, controllability and safety of PS emerge. This article focused on the key technologies of equipment operation and maintenance (O&M) in the PS, aiming to improve the challenges faced by traditional PS through new energy power and intelligent PS. The article studied the development of new PS, analyzed intelligent PS from the perspectives of intelligent maintenance, online fault diagnosis and status monitoring and evaluation, compared the capacity of new energy equipment and simulated the wind PS simulation structure diagram. Setting the Longyangxia Hydropower Station as an instance, it explored the complementarity between solar and hydro energy in the hydropower station. By studying the service life of transformers in 50 PS of Longyangxia Hydropower Station, it was found that amorphous alloys and silicon steel were relatively excellent and a total of 8 rounds of power generation equipment in the PS passed the safety assessment. The article proposed a long-term maintenance research method for the key technologies of equipment O&M in the new PS, achieving precise management and efficient maintenance of equipment and ensuring safe and reliable operation of equipment under complex working conditions.

STEAMCODER: Spatial and Temporal Adaptive Dynamic Convolution Autoencoder for Anomaly Detection

The anomaly detection algorithm greatly improves the reliability of equipment operation. Traditional anomaly detection algorithms are mostly designed for large data sets, making it difficult to detect anomalies when where is not enough accumulated equipment data. Therefore, detecting anomalies during the cold-start stage is also challenging. In industrial production, the working conditions of the equipment are constantly adjusted, and the amount or characteristics of data for training also change frequently. Hence, an adaptive algorithm is required to address these problems. We design a novel algorithm called Spatial-TEmporal Adaptive dynaMic Convolution autoencODER for Anomaly Detection (STEAMCODER), specifically. This algorithm first converts the data into a spatial–temporal anomaly feature matrix and then utilizes a dynamic convolution autoencoder to analyze the matrix and detect anomalies. Finally, we conduct extensive experiments to validate the performance of STEAMCODER and the results demonstrated its superiority compared to state-of-the-art algorithms in adaptive anomaly detection, including F1 score and other indicators. Furthermore, STEAMCODER is capable of filtering false positives caused by glitch data, enabling the early detection of equipment anomalies.

Numerical study on the heat transfer characteristics of a microchannel heat exchanger with liquid lead–bismuth eutectic and supercritical CO2 as working fluids

The Lead-cooled Fast Reactor (LFR) is a promising option for fourth-generation nuclear energy systems, with the supercritical carbon dioxide (sCO2) Brayton cycle being the preferred power cycle for future nuclear energy systems. Lead-bismuth eutectic (LBE) is a more suitable reactor coolant than lead due to its lower melting point. High-efficiency microchannel heat exchanger (MCHE) may be an ideal choice for the intermediate heat exchanger (IHX) in liquid lead–bismuth fast reactors. To prevent the channels of MCHE from being blocked by liquid LBE, a new structure of MCHE is proposed, in which the liquid LBE flow channel has a large equivalent diameter and corresponds to two sCO2 microchannels. In this study, the heat transfer characteristics of conventional and new structures of MCHE were investigated using numerical simulation. The results indicate that the temperature change at the inlet of the liquid LBE channel enhances the heat transfer of both liquid LBE and sCO2. Under constant temperature and pressure, the velocity of sCO2 has a significant effect on the convective heat transfer of sCO2, but has little effect on liquid LBE. Based on the reliability of equipment operation, this study recommends the use of the heat exchanger form in case 5. Compared with case 3, altering the velocity of liquid LBE results in a 7.1–8.3% increase in the convective heat transfer coefficient of liquid LBE, and a ∼38% increase in the convective heat transfer coefficient of sCO2. Similarly, changing the velocity of sCO2 leads to a 6.1–7.5% increase in the convective heat transfer coefficient of liquid LBE, and a 32.8–38.0% increase in the convective heat transfer coefficient of sCO2. For sCO2 heat transfer calculation, Yoon's heat transfer correlation is recommended, while Kirillov's heat transfer correlation is suggested for liquid LBE heat transfer calculation. The deviation between numerical calculation results and correlations is less than 18.1% and 12.7%, respectively.

Active voltage damping method with negative DC link current feedback in electric and hybrid electric transmissions

Electric and hybrid electric transmissions in traction drive have a limited capacity power source. Since the traction drive operates in the torque source mode, the DC link voltage becomes unstable and goes into oscillatory mode. This leads to the software protection reaction which prevents the traction inverter overvoltage breakdown. The transition boundary to the oscillatory mode is determined by the power and the value of the capacitance installed in the electric transmission DC link. To increase reliability of the traction inverters, large-capacity electrolytic capacitors are replaced with small-capacity film capacitors which makes the system more prone to oscillations. To solve this problem, active damping methods are used allowing changing the engine dynamic characteristics by means of the control system. The software methods with power and torque proportional control are most widely used. Proportional power control is the simplest method in which the traction drive simulates an RL load. The torque proportional control method adjusts the torque reference according to the change in the DC link voltage. This paper proposes a new negative DC link feedback method. In this case, the torque is adjusted dynamically depending on the current consumed by the traction inverter from the electric transmission common DC link. Mathematical modeling methods were used to compare the known and proposed methods of DC link voltage active damping. Mathematical models have been developed in the MATLAB Simulink environment which makes it possible to investigate the damping capacity at various values of the power consumed by the traction inverter. It is shown that the proposed method with negative DC link current feedback demonstrated tuning simplicity. In comparison with proportional power and torque control methods, the proposed option is robust when setting parameters, provides a large damping coefficient over the entire range of traction drive power, and has a short duration of the transient process. The proposed method can be used to suppress DC link voltage oscillations on any type of hybrid electric and all-electric vehicles traction inverters and ensures stable and reliable equipment operation.

Principle Analysis and Fault Handling of MCC400A Electric Wheel Automatic Lubrication Control System

Selecting the appropriate lubricating grease, applying the right amount of lubrication, suitable intervals, and the correct lubrication points can significantly reduce equipment maintenance and spare parts costs, while enhance the reliability of equipment operation. A well-functioning automatic lubrication system for mining dump trucks can greatly minimize friction and wear, thus extending the lifespan of bearings and mechanical components. Through in-depth analysis of the principles of the MCC400A electric wheel automatic lubrication control system and combined with on-site troubleshooting processes, we have accumulated valuable maintenance experience. This experience holds great significance for maintenance personnel to master troubleshooting techniques for automatic lubrication control systems. By understanding the system principles and analyzing the root causes of issues, we can precisely locate and resolve faults. Additionally, by leveraging modern technology effectively, we can enhance system stability and reliability, further improving equipment operational efficiency. In conclusion, optimized lubrication practices and a thorough understanding of the system will contribute significantly to the sustainable operation of equipment and reduced maintenance costs.

Ensuring the Reliability of Gas Supply Systems by Optimizing the Overhaul Planning

The aim of the article is the development of methods for optimal overhaul planning of compressor station equipment. Nowadays, due to uncertainties in the forecast of gas supply flow rates, increasing the reliability and energy efficiency of main gas pipelines is an urgent problem. The dependence of operating costs for major repairs on the maintenance periodicity is extreme. Reducing equipment’s maintenance period leads to an increase in repair costs. It also increases the reliability of equipment operation. Overall, all these facts reduce the probability of emergency failures and related expenses for emergency recovery, gas losses, and undersupply to consumers. Therefore, an optimal maintenance frequency exists, at which the total operating costs will be minimal. A procedure for optimizing the periodicity of repairs and equipment replacement is proposed. It was realized by constructing an objective function as a dependence of exploitation costs on the inter-repair period of major repairs. A probabilistic approach was applied to assess the aging process. The characteristics of the equipment’s state are described by distribution densities (i.e., pre-repair, inter-repair, and full-service life), which vary depending on product initialization time. The main characteristics of major repairs are their duration and intensity, which are evaluated by the quality factor related to repair costs. The extremum of the objective function is sought by the method of competing options. It was determined that the optimal management of the frequency of equipment replacement can be realized by choosing the optimal values of the average service life, average operation time of units until the first planned and preventive repair, and quality factor. As a result, the required technical condition for the technological equipment is ensured under minimum operating costs without reducing the system’s reliability.

A two-stage Gaussian process regression model for remaining useful prediction of bearings

Bearing is one of the most important supporting components in mechanical equipment and its health status has a significant impact on the overall performance of equipment. The remaining useful life (RUL) prediction of bearings is critical in adopting a condition-based maintenance strategy to ensure reliable equipment operation. To accurately predict the RUL of bearings, this paper proposes a two-stage Gaussian process regression (GPR) model, which combines the flexibility of the Gaussian process and the physical mechanism of the Wiener process. Compared with the conventional GPR model, the proposed model can reasonably adapt to the statistical characteristics of bearings degradation and provide more stable predictions. In addition, the paper proposes a new degradation detection approach based on the Euclidean distance to distinguish the two stages of the bearing service life cycle, which considers the global characteristics of bearing degradation and can accurately detect the beginning point of bearing degradation. The experimental results show that the proposed two-stage GPR model can help to improve the precision and accuracy of degradation path tracking and RUL prediction.

A Self-Supervised Bearing Failure Detection Method with STFT and Point-wise CNN Feature Extraction

As the most important parts, bearings are widely used in many types of mechanical and electronic equipment. Bearing failure often leads to serious consequences. Therefore, the fault detection of bearings is the key to ensuring the safe and reliable operation of equipment. At present, most feature extraction methods are based on signal processing algorithms. However, for some types of bearings, these feature extraction methods may lose some important information. The bearing vibration data is unbalanced data, which may lead to diagnostic errors. A new self-supervised bearing failure detection method with STFT point-wise CNN feature extraction and auto-encoder is proposed in this paper. Firstly, a point-wise CNN extracts the features from the signal after STFT. Then the auto-encoder compresses and reconstructs the features. Finally, the distance between the auto-encoder input and output is used to judge the signal is abnormal or not. The CWRU bearing vibration signal data set is used as test case. We also proposed the distance ratio as an evaluation index in the experiment. The proposed bearing fault detection method in this paper has a lower data requirement and better effect based on the results.

Эко-НИОКР – 18 лет для охраны птиц на объектах электросетевого комплекса России

Эко-НИОКР – 18 лет для охраны птиц на объектах электросетевого комплекса России

Design of Control System for Industrial Defective Product Sorting Station Based on IOT2050

Aiming at the problems of many types of abnormal states in industrial defective sorting stations, long time consuming analysis of abnormal causes, and untimely equipment monitoring, the control system of industrial defective sorting stations based on IOT2050 is designed. With Siemens PLC-1200 as the main body, combined with TIA Portal and IOT2050, it realizes the design of software and hardware configuration, programming, WinCC screen and industrial cloud platform of industrial defective sorting station control system. The simulation results show that the system runs stably, realizes automatic production operation and data monitoring, and is of great significance to ensure the reliable operation of equipment.

Increasing the manoeuvrability of power units of the thermal power plants due to applying the hydrogen-oxygen systems

The article describes a method for providing additional peak power of a power-unit with help of an additional energy circuit involving a peak turbine and a hydrogen–oxygen system for energy storage and generation. This method is described on the example of K-300-240 turbine power unit. The proposed technical solutions result in the nominal, most economical mode of a power-unit operation during a day. Consequently, the specific fuel consumption is decreased, and reliability of equipment operation is increased. We have developed the technology for high-pressure gases generating that is realized in the membrane-less electrolysers. Thus, there is no need in the use of expensive and energy-intensive compressor equipment for the energy storage systems. That means that the cost of power unit modernization is reduced. Taking into account the environmental and economic factors, the use of hydrogen–oxygen systems for energy storage at the power generating enterprises provides a value of the energy return coefficient that is practically the same as for hydro-storage power plant. But capital costs of power unit modernization are significantly lowered and negative impact on the environment is minimal.

Study and early warning of comprehensive distribution box state based on maximum likelihood parameter estimation of Weibull distribution

With the expansion of the power grid scale and the improvement of distribution box automation, the structure of the distribution network has become more complex, and the maintenance task is heavy. The traditional post-maintenance and regular maintenance modes could not satisfy the requirements of distribution network equipment operation reliability. Firstly, according to the maintenance mode, the failure rate curve is proposed based on Weibull distribution. The service age reduction factor and the current failure rate of the equipment are mapped in this paper to the failure rate curve based on Weibull distribution. Secondarily, they are used to calculate the actual service age of equipment. The annual failure rate of equipment is used to count and determine the failure rate increment factor. Thirdly, the ant colony algorithm is applied to Weibull distribution maximum likelihood parameter estimation. Finally, an example analysis verified that the parameter accuracy of ant colony algorithm estimation is higher. Thus, the correctness of the state-based equipment failure rate estimation method is verified, which lays a foundation for the formulation of a maintenance plan.