Machine Reliability Research Articles

Operation risk assessment of Flexible Manufacturing Networks subject to quality-reliability coupling

In flexible manufacturing network (FMN), the growth of product types increases the diversity of interacting behaviors between machine reliability and product quality, and the product diversity and machine flexibility promote the explosion of processing routes and processing sequences, increasing the gap between current risk evaluation of manufacturing systems and engineering practice. To fill this gap, a novel operation risk assessment framework is constructed for the complex FMN. In detail, to model the reliability-quality interactions, a mathematical framework describing a complete manufacturing process involving "feedstock quality (Q1) - machine degradation (R) - product processing quality (Q2) - quality inspection status (I)" is proposed for complex FMN, solving the measurement of interacting behaviors between machine reliability and product quality in an FMN that suffers from both multiple process routes and multi-type products. Then, an effective evaluation framework is proposed to evaluate the connectivity risk of multiple process routes and the quality risk of multiple product types in a complex FMN, providing a concurrent solution for risk evaluation under both complex system structures and complex quality-reliability interrelationships. At last, a simulation experiment verifies the effectiveness of our proposed methods and reveals differences in the operation risk of different product types in an FMN.

Unlocking Global Efficiency with Enhanced Milling Machines Worldwide

This study investigates the effectiveness of six milling machines at PT. INKA, a railroad car manufacturing company, focusing on CNC Plano 133 and Horizontal Milling 142. Utilizing Overall Equipment Effectiveness (OEE) and Age Replacement methods, the research aims to optimize machine performance and propose preventive maintenance strategies. Data spanning from January 2021 to December 2022 were collected and analyzed. Results indicate that both CNC Plano 133 and Horizontal Milling 142 exhibit suboptimal OEE values, primarily due to breakdown losses. Applying Age Replacement within 10 days significantly enhances reliability, with post-replacement reliability reaching 100%. The findings underscore the importance of preventive maintenance in improving milling machine reliability and overall productivity, thereby enhancing competitiveness and sustainability in the manufacturing sector. Highlight: Improved productivity: Preventive maintenance boosts milling machines' reliability and effectiveness. Resource efficiency: Analyzing OEE minimizes downtime, optimizes production output. Competitive edge: Enhanced performance sustains competitiveness, strengthens manufacturing sector's sustainability. Keyword: Milling machines, Overall Equipment Effectiveness (OEE), Preventive maintenance, Age Replacement, Manufacturing industry

Ensuring the reliability of filtration systems for transport and processing machines by redundancy

The relevance of this study is subordinated to the existing global trend of applying the scientific paradigm of redundancy of individual systems of transport and technological machines. This approach ensures the uninterrupted technological process of crop production following the regulatory reliability indicators. The purpose of this study was to identify failures of subsystems and elements of transport and technological machines depending on the operating time and to ensure reliability by redundancy. The study covered the methodological approaches to the formation of reliability of transport and technological machines. The study analysed the areas of ensuring the reliability of transport and technological machines on the example of machinery and equipment for animal husbandry. Methodical approaches to ensuring the indicators of reliability and maintainability during the operation of a self-propelled mixer were covered. A systematic approach to the self-propelled mixer as a complex transport and technological machine was developed. The principal subsystems that define a self-propelled mixer as a complex transport and technological system were identified. During the study, two groups of failures were identified, which lead to the loss of performance of the research objects. The features of using information and structural redundancy to improve the reliability of filtration systems of self-propelled mixers were presented. The technical condition of the engine air filter should be checked and cleaned after 50 hours, while the cartridge should be replaced after 1000 hours of operation. The functioning of the cabin filtration subsystem is ensured by a condenser, evaporator, desiccant filter, air filter, which should be checked and cleaned every 500 hours, while spare parts should be available in stock for replacement after one year of use. The formed criteria for assessing the technical condition of air filtration systems of a self-propelled mixer will provide a higher level of reliability and expand the list of their parameters. The methodology presented in this study allows increasing the reliability and maintainability of self-propelled mixers, to provide a methodical approach to the formation of reliability of engine air filtration and operator’s cabin air filtration subsystems

Reliability Analysis of Hinged Hydraulic System of Remanufactured EPB Shield Machine

Abstract To verify the reliability of the Earth Pressure Balance (EPB shield machine) hinged system, firstly, this paper analyses the reliability of the remanufactured EPB shield machine hinged system and then aims at the problem of the high failure rate of the hinged system in EPB shield machine. A fault tree model was established, and the qualitative and quantitative analysis of the fault tree was carried out. Finally, it is determined that the main cause of the oil cylinder malfunction in the hinged system is the insufficient pressure caused by the malfunction of the solenoid valve’s directional switching.

Vibration Response of Metal Plate and Shell Structure under Multi-Source Excitation with Welding and Bolt Connection

There are many excitation sources and complex vibration environments in combine harvesters. The coupling and superposition of different vibration signals on the plate and shell seriously affect the working parts of the body. This also reduces the reliability of the whole machine. At present, domestic and foreign research on existing harvesters mainly focuses on harvesting performance, with less research on vibration characteristics. Therefore, in this paper, the vibration response of the metal plate–shell under the two connection modes of bolt connection and welding is studied, in order to optimize the design and structure of the plate–shell structure of the combine harvester and improve the overall performance. First, the welded and bolted plates are numerically modeled using Hypermesh pre-processing functions. Then, the boundary conditions are simulated by continuous variable stiffness elastic constraint experiments. Finally, the intrinsic vibration dynamic model of the four-sided simply supported plate and four-sided solidly supported plate is established using the modal superposition method. By analyzing the modal frequencies and vibration patterns, the following results are obtained. The connection method between the plate and the frame has a significant impact on the inherent vibration characteristics of the plate. The bolt connection will make the plate’s intrinsic vibration frequency higher than that of the welding method, but the effect on the plate’s intrinsic vibration pattern is more minor. At the same time, in order to verify the accuracy of the model, the actual modal vibration patterns and frequencies of the same proportion of plates in the modal test are compared with the results of modal vibration patterns and frequencies obtained by Ansys. The errors of the two dynamic model analytical methods are within 1% and 3%, respectively. This result verifies the accuracy of the dynamic model of the metal plate and shell structure under different connection methods.

Analysis of the influence of assembly deviation and repeated assembly on sealing performance of detachable aviation pipe joint

Detachable pipe joints are an important component of aviation hydraulic systems, and their sealing performance is related to the safety and reliability of the entire machine. This paper focuses on the impact of assembly deviation and repeated assembly on the sealing performance of 35 MPa aviation pipe joints. The sealing performance of pipe joints was quantitatively evaluated using the sealing contact strength theory, and the influence of assembly deviation on sealing performance was studied using the finite element method. Designed a repeated tightening test device for pipe joints and conducted repeated tightening tests. A method for analyzing the initial loss of axial force, usage loss, and friction torque during repeated tightening of pipe joints has been established. Finally, combining experimental data and simulation calculations, the influence of repeated tightening on the sealing contact strength was analyzed. This study provides an analysis method and influencing law for the sealing performance of 35 MPa level detachable aviation pipe joints under assembly deviation and repeated assembly. The research content can provide theoretical guidance for the assembly process design of pipe joints.

Influence of Tungsten Carbide on the Deposition Process and Properties of New Fe-WC Composite Electroplated Coatings

Electrodeposition of wear-resistant compositions on the surfaces of parts makes it possible to increase the reliability and durability of machines. Studies have been carried out on the process of applying Fe-WC composite galvanic coatings (CGC) from a suspension electrolyte containing 550–600 g/L FeCl2∙H2O and microabrasive tungsten carbide powder. A high incorporation of dispersed phase particles into the coating was obtained. The properties of Fe-WC composite coatings were studied. A relationship has been established between the concentration of tungsten carbide particles in the electrolyte and the current efficiency of the composition as well as the WC content in the coating. Some physical and mechanical properties of CGC have been determined without their mechanical pre-treatment, in particular, microhardness and wear resistance. The roughness of Fe-WC compositions was studied in comparison with Fe-Al2O3 coatings.

Decoupling Analysis of Brushless Dual-Mechanical-Port Dual- Electrical-Port Machines

The brushless dual-mechanical-port dual-electrical-port (BLDD) machine has emerged as a promising alternative to the traditional mechanical continuously variable transmission (CVT), due to its gearless and brushless design. In BLDD machines, two sets of windings are placed in the same stator, and care must be taken to avoid strong coupling that may deteriorate the machine performance and reliability. This paper categorizes the topologies of existing BLDD machines into five types and presents a systematic decoupling analysis from the perspective of field-modulation theory. Using the presented method, the conditions to achieve decoupled designs are concluded and the decoupling characteristics of each type of BLDD machine are identified. Besides, a simple indicator is developed to fast identify the coupling type, i.e., decoupled, low or high coupling design, of BLDD machines, enabling an efficient selection of slot-pole combinations. With the aid of finite-element analysis (FEA), the coupling degree of BLDD machines with various slot-pole combinations has been analyzed for verification. Other performances, such as torque density and PM utilization, are also compared among the five types of BLDD machines to provide a more comprehensive view of their characteristics. Finally, a prototype of a BLDD machine is manufactured and tested to validate the analysis.

Systems Reliability and Data Driven Analysis for Marine Machinery Maintenance Planning and Decision Making

Understanding component criticality in machinery performance degradation is important in ensuring the reliability and availability of ship systems, particularly considering the nature of ship operations requiring extended voyage periods, usually traversing regions with multiple climate and environmental conditions. Exposing the machinery system to varying degrees of load and operational conditions could lead to rapid degradation and reduced reliability. This research proposes a tailored solution by identifying critical components, the root causes of maintenance delays, understanding the factors influencing system reliability, and recognising failure-prone components. This paper proposes a hybrid approach using reliability analysis tools and machine learning. It uses dynamic fault tree analysis (DFTA) to determine how reliable and important a system is, as well as Bayesian belief network (BBN) availability analysis to assist with maintenance decisions. Furthermore, we developed an artificial neural network (ANN) fault detection model to identify the faults responsible for system unreliability. We conducted a case study on a ship power generation system, identifying the components critical to maintenance and defects contributing to such failures. Using reliability importance measures and minimal cut sets, we isolated all faults contributing over 40% of subsystem failures and related events. Among the 4 MDGs, the lubricating system had the highest average availability of 67%, while the cooling system had the lowest at 38% using the BBN availability outcome . Therefore, the BBN DSS recommended corrective action and ConMon as maintenance strategies due to the frequent failures of certain critical parts. ANN found overheating when MDG output was above 180 kVA, linking component failure to generator performance. The findings improve ship system reliability and availability by reducing failures and improving maintenance strategies.

Improving the reliability of machine learned potentials for modeling inhomogeneous liquids.

The atomic-scale response of inhomogeneous fluids at interfaces and surrounding solute particles plays a critical role in governing chemical, electrochemical, and biological processes. Classical molecular dynamics simulations have been applied extensively to simulate the response of fluids to inhomogeneities directly, but are limited by the accuracy of the underlying interatomic potentials. Here, we use neural network potentials (NNPs) trained to ab initio simulations to accurately predict the inhomogeneous responses of two distinct fluids: liquid water and molten NaCl. Although NNPs can be readily trained to model complex bulk systems across a range of state points, we show that to appropriately model a fluid's response at an interface, relevant inhomogeneous configurations must be included in the training data. In order to sufficiently sample appropriate configurations of such inhomogeneous fluids, we develop protocols based on molecular dynamics simulations in the presence of external potentials. We demonstrate that NNPs trained on inhomogeneous fluid configurations can more accurately predict several key properties of fluids-including the density response, surface tension and size-dependent cavitation free energies-for liquid water and molten NaCl, compared to both empirical interatomic potentials and NNPs that are not trained on such inhomogeneous configurations. This work therefore provides a first demonstration and framework to extract the response of inhomogeneous fluids from first principles for classical density-functional treatment of fluids free from empirical potentials.

Creation of a Machine Learning-Based Automated System for the Multi-Component Fault Analysis of Industrial Machines

The efficiency and reliability of industrial machines are paramount for ensuring smooth operations and minimizing downtime in manufacturing environments. However, the complexity of these machines and the multitude of components they consist of pose significant challenges in identifying and diagnosing faults promptly. Traditional fault analysis methods often rely on manual inspection or simplistic rule-based systems, which are time-consuming, subjective, and prone to errors. In this study, we propose the development of a novel machine learning-based automated system for the multi-component fault analysis of industrial machines. Leveraging advancements in artificial intelligence and data analytics, our system aims to revolutionize fault detection and diagnosis by efficiently processing vast amounts of sensor data to identify anomalies and pinpoint potential faults across multiple components simultaneously. The proposed system comprises several key components, including data preprocessing techniques to handle noisy sensor data and extract relevant features, machine learning algorithms for fault detection and classification, and a user-friendly interface for visualization and interpretation of results. Additionally, the system will incorporate techniques for model explain ability to enhance trust and understanding of the automated diagnostic process.

Exploring the Potential Application of an Innovative Post-Weld Finishing Method in Butt-Welded Joints of Stainless Steels and Aluminum Alloys.

The prerequisite of the weld bead finishing is intricately linked to the quality of the welded joint. It constitutes the final, yet pivotal, stage in its formation, significantly influencing the reliability of structural components and machines. This article delineates an innovative post-weld surface finishing method, distinguished by the movement of a specialized cutting tool along a butt weld. This method stands out due to its singular approach to machining allowance, wherein the weld bead height is considered and eradicated in a single pass of the cutting tool. Test samples were made of AISI 304L, AISI 316L stainless steels and EN AW-5058 H321, EN AW-7075 T651 aluminum alloys butt-welded with TIG methods. Following the welding process, the weld bead was finished in accordance with the innovative method to flush the bead and the base metal's surface. For the quality control of welded joints before and after the weld finishing, two non-destructive testing methods were chosen: Penetrant Testing (PT) and Radiographic Testing (RT). This article provides results from the examination of 2D profile parameters and 3D stereometric characteristics of surface roughness using the optical method. Additionally, metallographic results are presented to assess changes in the microstructure, the microhardness, and the degree of hardening within the surface layer induced by the application of the innovative post-weld finishing method.

CMMS- Streamlining Maintenance management for Food and Beverage Industry to capture breakdowns

CMMS stands for Computerized Maintenance Management System. In today’s world, when technology is advancing each day at an astonishing rate, any organization must have a detailed knowledge and understanding of its current state of machinery, the number of resources spent on the production floor to maintain equipment reliability, and resource allocation. CMMS is a critical and powerful tool that assists and helps any manufacturing industry to make full use of its capabilities, manage or direct workforce, improve the machine reliability, find innovative ways to improve productivity, stay in compliance with food and dietary regulatory standards as per the safe quality foods (SQF) and national sanitation foundation (NSF) standards and achieve series of goal and benefits the organization overall. Today, the food and beverage industry has grown tremendously and is the backbone of the manufacturing industry. Every company looks at creative ways to help them excel by selecting a reliable CMMS that suits their operations and processes to make educated decisions by monitoring their KPIs. This theoretical study aims to provide a building framework to set up plant maintenance modules to manage work orders, including emergency breakdowns and scheduled maintenance repairs in the food and beverage industry.

Fuzzy reliability evaluation and machine learning-based fault prediction of wind turbines

The swift growth of the wind power industry necessitates comprehensive evaluation and efficient fault prediction of wind turbines. Given the challenges of integration and optimization of reliability evaluation and fault prediction models, a systematic method of reliability fuzzy evaluation and fault prediction based on the Supervisory Control and Data Acquisition (SCADA) data is proposed. A mid-to-long-term reliability fuzzy evaluation model is constructed using Fuzzy Comprehensive Evaluation (FCE). The mid-term evaluation results in ten failure modes reveal that the model's hazard ranking results match the situation better than the RPN method. And the long-term evaluation results of 5 years in the operating mode show that the model effectively gathers the evaluation information each year and provides a clear and accurate reflection of reliability. Meanwhile, fault prediction is studied using alarm logs because they are better at expressing the status of wind turbines than monitoring data. And the tree-based algorithms and unsupervised statistical learning methods are used to mine the mapping relationship between input variables and predefined tags. The fault prediction achieves both accuracy and recall of 0.784 and saves over 163k Euros based on local wind turbine maintenance expenditures. Overall, the reliability evaluation and fault prediction complement each other, which may either affect future wind farm management or prevent unnecessary maintenance costs.

Abstract 2344: Federated image quality assessment of prostate MRI scans in a multi-institutional setting

Abstract Introduction: Reliability of machine and deep learning models on medical images can be compromised by the presence of image artifacts of variability in image acquisition. This is further exacerbated when validating model performance across multiple institutions, where multiple acquisition protocols and scanner equipment may result in significant numbers of outlier scans. We developed a privacy-preserving outlier identification algorithm via federated MR imaging quality evaluation of a distributed multi-institutional cohort of prostate MRI scans. Methods: This retrospective study utilized T2-weighted prostate MRI scans from 1 public collection (used as a template) and 3 federated institutions. An open-source MR image quality evaluation tool (MRQy) was implemented via Docker within the RhinoHealth Federated Computing Platform (FCP). This enabled remote extraction of 9 specific metadata values and remote computation of 15 quality measurements from each scan, while ensuring confidentiality of patient data by avoiding direct access to patient images and information. Centralized analysis of extracted image quality attributes utilized a rule-based classifier to determine whether individual metadata or measurement values for a given MRI scan fell within or outside predefined bounds: (i) ±20% of template metadata values, (ii) 5th - 95th percentile range of template measurement values. Scans were considered outliers if more than 60% of their image quality attributes fell outside predefined bounds. Results: In total, 630 MRI scans from 3 institutions were analyzed in a federated manner. 344 MRI scans from 1 public collection formed a benchmark cohort to calibrate the rule-based classifier and determine predefined bounds for outlier detection. Centralized analysis of federated image quality attributes showed marked differences in the number of outliers per institution (3%, 19%, 79% for Institutions 1, 2, 3, respectively). Further analysis of Institution 3 determined significant intensity and resolution differences compared to other institutions, requiring extensive post-processing prior to downstream analysis. Conclusion: Federated image quality assessment can allow for distributed, privacy preserving analysis of outliers and thus curate multi-institutional cohorts of consistent quality for downstream machine learning tasks. Further analysis of the impact of quality-based curation on federated machine learning applications is currently underway. Citation Format: Mohsen Hariri, Prathyush Chirra, Malhar Patel, Tal Tiano Einat, Ittai Dayan, Alex Tonetti, Yuval Baror, Tristan Barrett, Nikita Sushentsev, Joshua D. Kaggie, Shuaiyu Yuan, Dufan Wu, Baihui Yu, Zhiliang Lyu, Cheyu Hsu, Weichung Wang, Smitha Krishnamurthi, Satish E. Viswanath. Federated image quality assessment of prostate MRI scans in a multi-institutional setting [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2344.

Enhancing Heat Transfer Efficiency in Permanent Magnet Machines through Innovative Thermal Design of Stator Windings

This paper investigates innovative methods for enhancing heat transfer efficiency in high-power permanent magnet electrical machines. The objectives are to quantify the effects of increasing the air speed, increasing the turbulence intensity, and introducing the spacing between windings on cooling performance. The cooling of stator windings is studied through experimental wind tunnel testing and Computational Fluid Dynamics (CFD) modelling. The CFD model is validated against wind tunnel measurements to within 4 Kelvin (K). The results demonstrate that each enhancement method significantly improves the cooling capability. Increasing the air speed from 10 m/s to 40 m/s reduces the winding hotspot temperature by 34%. Introducing a high turbulence intensity of 40% leads to a 21% lower hotspot temperature compared to 0.5% turbulence intensity. Creating a 1.5 mm spacing between coils also substantially improves convection and conduction heat transfer. Overall, combining these optimised design parameters yields over a 40% reduction in hotspot temperature compared to the original design. This research provides practical guidance for maximising heat transfer efficiency in high-power permanent magnet machines, without increasing complexity. The findings will lead to higher machine efficiency, reliability, and longevity for aerospace and other applications.

Applying the MIMO BP Neural Network and Cloud-Based Monitoring of Thermal Behavior for High-Speed Motorized Spindle Units

Understanding the temperature–working condition relationship is crucial for optimizing machining processes to ensure dimensional accuracy, surface finish quality, and overall spindle longevity. Monitoring and controlling spindle temperature through appropriate cooling systems and operational parameters are essential for efficient and reliable machining operations. This paper presents an in-depth analysis of the thermal equilibrium and deformation characteristics of a high-speed motorized spindle unit utilized in grinding machine tools. Through a series of thermal equilibrium experiments and meticulous data acquisition, the study investigates the nuanced influence of various working conditions, including spindle speeds, coolant types, and coolant flow rates, on spindle temperatures and thermal deformations. Leveraging the power of Artificial Neural Networks (ANNs), predictive models are meticulously developed to accurately forecast spindle behavior. Subsequently, the models are seamlessly transitioned to a cloud computing infrastructure to ensure remote accessibility and scalability, facilitating real-time monitoring and forecasting of spindle performance. The validity and reliability of the predictive models are rigorously assessed through comparison with experimental data, demonstrating excellent agreement and high accuracy in forecasting spindle thermal behavior. Furthermore, the study underscores the critical role of key working condition variables as precise predictors of spindle temperature and thermal deformation, emphasizing their significance in optimizing overall spindle efficiency and performance. This comprehensive analysis offers valuable insights and practical implications for enhancing spindle operation and advancing the field of grinding machine tools.

Effect of the stochastic weibull parameters on the reliability of the dialysis machine

Effect of the stochastic weibull parameters on the reliability of the dialysis machine

Improving the Efficiency of the Drive of the Test Bench of Rotary Hydraulic Machines

Volumetric hydraulic drive systems are quite widespread in many industrial sectors. To determine the degree of reliability of hydraulic machines, it is necessary to conduct resource tests. The main requirement for such tests is the compliance of the load level with the operating mode of the hydraulic machine. Analysis of existing methods of creating such a load showed a significant drawback of bench tests—the lack of useful work. Therefore, a number of authors suggest the use of stands with a regenerative drive system. One peculiarity of the work of such stands is the possibility of returning part of the spent energy back to the test system. However, such systems are insufficiently studied and have significant drawbacks. The purpose of this work is to increase the efficiency of the regenerative drive system of the test bench of volumetric hydraulic machines of rotational action by improving the theory and methodology of its calculation and design. This article describes the principle of operation of the circuit of the regenerative drive of the test bench of rotary hydraulic machines. A model of the elastic-dissipative state of the sections of the elements of the hydro-mechanical drive system of the stand is also proposed, which allows for the calculation of the structural and energy parameters of the regenerative hydro-mechanical system. The main structural and functional parameters affecting the operational performance of the system as a whole are also identified. A “test efficiency coefficient” is proposed, which allows for evaluation of the energy efficiency of the test process.

Nonlinear vibrations of a linkage mechanism: theory and experiment

Linkage mechanisms have a wide range of applications in truck-mounted cranes, folding mechanical arms of transport vehicles and so on due to their simple and effective design. Vibration problems in the linkage mechanisms seriously affect the stability and reliability of crane machines or transport vehicles. Therefore, in this study, an effective nonlinear dynamic model of a linkage mechanism with spring-damping systems is developed and experimentally validated to explore the nonlinear vibration properties. The geometric nonlinearity of the linkage mechanism is considered and the Lagrange equation is employed to establish the nonlinear dynamic equations. Based on the harmonic balance method (HBM), the nonlinear vibration properties of the structural system are analyzed. The nonlinear primary resonance response of the linkage mechanism calculated from the HBM is compared with those of the Runge–Kutta method and the experimental result, which validates the effectiveness and accuracy of the proposed nonlinear dynamic model. The influences of some parameters, such as the spring stiffness, the lengths of connecting rods, and the installation positions of the spring-damping system, on the nonlinear vibration characteristic of the linkage mechanism are analyzed. Based on the numerical results, the folding mechanical arms or truck-mounted cranes can be conveniently designed to avoid irreparable damage to the structure caused by nonlinear primary resonance and instability phenomena, which provides new insight into the stability analysis and design of various linkage mechanisms required in engineering applications.