Machine Failure Research Articles

Analysis Riplle Mill Machine Damage Analysis Using the FMEA Method at the PT Argo Sinergi Nusantara Palm Oil Factory

PT Agro Sinergi Nusantara (ASN), one of the industries engaged in the Palm Oil Mill (PKS) industry, is located in Teunom, Aceh Jaya Regency. The Ripple Mill machine is one of the important machines used in Palm Head Mills which functions as a separator or splitter of kernel kernels and palm shells by utilizing centrifugal force to produce Palm Kernel Oil. From the initial analysis, it is known that the use of Ripple Mill machines in the industry today often experiences donwtime or damage. The purpose of this study is to analyze the damage of the Ripple Mill machine at PT ASN's Palm Oil Mill using the Failure Mode and Effects Analysis (FMEA) method and Fishbone diagram. The results of the study obtained damage to the Ripple Mill machine in the identification of 5 (five) malfunctions or failure modes that occurred. using the FMEA method, it is known that the most dominant Ripple Mill machine failure mode occurs is the fracture of rotor bar components due to the entry of hard objects with the Risk Priority Number (RPN) which is 384 and using the fishbone diagram method, it is known that there are (four) influencing factors, namely human, machine, environmental and method factors.

Fast Schedule Recovery Method for Semiconductor Packaging Lines With Machine Failures and Constrained Time Windows

Fast Schedule Recovery Method for Semiconductor Packaging Lines With Machine Failures and Constrained Time Windows

Predicting machine failures using machine learning and deep learning algorithms

Industry 4.0 emphasizes real-time data analysis for understanding and optimizing physical processes. This study leverages a Predictive Maintenance Dataset from the UCI repository to predict machine failures and categorize them. This study covers two objectives namely, to compare the performance of machine learning algorithms in classifying machine failures, and to assess the effectiveness of deep learning techniques for improved prediction accuracy. The study explores various machine learning algorithms and finds the XG Boost Classifier to be the most effective among them. Long Short-Term Memory (LSTM), a deep learning algorithm, demonstrates its superior accuracy in predicting machine failures compared to both traditional machine learning and Artificial Neural Networks (ANN). The novelty of this study is the application and comparison of machine learning and deep learning models to an unbalanced dataset. Findings of this study hold significant implications for industrial management and research. The study demonstrates the effectiveness of machine learning and deep learning algorithms in predictive maintenance, enabling proactive maintenance interventions and resource optimization.

Interactions between planners’ and PPC systems: Derivation of simulation scenarios with consideration of cognitive bias and disruptions

Despite an increase in the availability of digital solutions, planners’ remain at the center of the production planning and control (PPC) decision-making process and have to make numerous decisions involving different information. Due to the inherent complexities, planners’ are supported by PPC systems to fulfil their tasks. Research has shown that humans are influenced by cognitive bias when making decisions, especially in uncertain and complex environments and when disruptions such as machine failures occur. Researchers have therefore proposed debiasing methods to reduce human errors in decision-making. However, there is currently no environment within this research to test these proposed methods. In this study, we aimed to take the first step toward closing this research gap. We combined existing PPC research with a systematic literature review on disruptions in production as well as perspectives from practice through interviews with 12 experts. We investigated the interactions between planners’ and PPC systems with consideration of different cognitive biases and disturbances to derive relevant simulation uses cases.

Natural Language Processing Approaches in Industrial Maintenance: A Systematic Literature Review

Industrial maintenance plays a crucial role in manufacturing by significantly reducing machine failure time and minimizing costs, especially in the revolution of Industry 4.0. Consequently, researchers and industrial engineers have continuously focused on this area. Manufacturing companies possess extensive maintenance reports or logs containing valuable textual information, which offers a new avenue for exploring effective industrial maintenance methods. Natural Language Processing (NLP), a subfield of Artificial Intelligence, has demonstrated remarkable potential in analyzing maintenance reports and achieving promising results in various tasks. This paper presents a comprehensive systematic literature review that specifically concentrates on the applications of NLP approaches employed in the field of industrial maintenance. Additionally, this review analyzed the datasets utilized in previous studies and the evaluation measures adopted, which can serve as a valuable resource for other researchers seeking potential solutions in maintenance. Furthermore, the paper discusses the challenges encountered in applying NLP to industrial maintenance and outlines future research directions in this domain. By conducting this systematic literature review, we provide a comprehensive understanding of the current state of NLP applications in industrial maintenance, identify gaps in the existing literature, and guide future research efforts in leveraging NLP techniques for enhanced maintenance practices.

Lean manufacturing practices in an educational institution to improve the operational efficiency of a machine shop

The lean manufacturing approach is employed across several sectors to minimise waste and extend its ideas to institutional settings. The objective of this work is to provide instruction to aspiring engineers regarding the implementation and utilisation of lean tools. The machine shop of an engineering college utilised several tools, including 5S, standard work, and machine maintenance. The students were educated on the difficulties and achievements associated with the implementation of lean ideas across several tiers within the machine shop. The findings indicate that it is imperative to remove non-value-added operations, commonly referred to as Muda, in any manifestation inside the shop. A sequence of 5S audits was carried out to facilitate the enhancement of KAIZEN initiatives and uphold the shop's commitment to lean principles. The determination and assessment of the influence of lean tools on the Machine Shop were conducted through the utilisation of a questionnaire employing a five-point Likert scale. Following the implementation of lean principles, there has been a notable enhancement in several aspects. Specifically, there has been a 6.6% improvement in space utilisation, a substantial 95.12% increase in safety measures, a significant reduction of 83.3% in machine failure occurrences, and a noteworthy decrease of 80.2% in the time required for tool search.

Reliability analysis and ANFIS computation for multi-server redundant machining system with the generalized triadic policy

The intent of this research is to have discussions about the transient behavior of a multi-server redundant machining system with a generalized Triadic control policy. Furthermore, the system facilitates a multiple working vacation policy for servers. The relevant rates of the associated birth-death process are chosen in order to frame the differential-difference equations for the system. Using the fourth order Runge-Kutta technique, time-dependent probabilities of the states are derived. Some performance metrics of system such as the average number of failed machines, average waiting time of failed machines, and reliability function are established using the states probabilities. Graphical and tabular representations demonstrate the behavior of these metrics with respect to a variety of system characteristics. Statistical hypothesis testing has been employed to compare the outcomes presented in tabular format. Beside these, numerical findings of the Runge-Kutta method are compared to those delivered by an adaptive neuro-fuzzy inference system (ANFIS) technique.

Diagnosis of localized defects in floating bush bearings through time-frequency domain analysis

Bearings play a crucial role in the functionality of rotating machinery, and any defects in these components can result in machine failure. Detecting, diagnosing, and prognosing bearing faults are crucial steps in machine failure diagnostics to prevent malfunctions and breakdowns. While various methods exist for fault detection, including acoustic emission analysis, visual inspection, thermography, ultrasonic, motor current analysis, wear-debris analysis, oil analysis, and vibration analysis, the latter stands out as a popular non-destructive method. This paper focuses on time and frequency domain vibration analysis techniques for detecting faults in floating bush bearings. Particularly beneficial for online monitoring, remote and non-human intervention areas, and hazardous locations, the time-frequency domain approach enhances diagnostic capabilities. The vibration data collected during these experiments has been rigorously analyzed using data acquisition system and applied a comprehensive approach that includes evaluating the data in both the time and frequency domains, as well as utilizing advanced signal processing techniques, notably the high-frequency resonance technique. Test results underscore the effectiveness of specific parameters in identifying defects: waveform, form factor, parameter K, and cepstrum excel in pinpointing external defects, while kurtosis, crest factor, and skewness prove adept at identifying internal faults. In the frequency domain, the enveloped spectrum emerges as a robust method for comprehensive defect detection. The vibration data presented in this paper will prove to be an invaluable resource for professionals engaged in the field of vibration measurement and analysis.

디지털 트윈 기반의 도메인 독립 회전 기계 고장 진단 시스템

디지털 트윈 기반의 도메인 독립 회전 기계 고장 진단 시스템

A genetic algorithm for cost optimization in queueing models of machining systems with multiple working vacation and generalized triadic policy

This study presents a generalized approach for implementing the Triadic control policy in queueing modeling of a redundant machining system with multiple servers. The machining system further integrates a policy for servers that allows for multiple working vacations. The fluctuation of active servers is based on the count of accumulated failed machines in the system. This alteration occurs individually at every stage of service completion or the arrival of a failed machine. The recursive approach is employed to generate analytical closed-form solutions of the system in terms of steady-state probabilities. The performance metrics of the system are determined, and their response to varying system parameters is demonstrated through tables and graphs. A cost function is proposed for the system and subsequently examined with different configurations. A Genetic Algorithm technique is used to acquire the most optimal input parameters to minimize the cost function.

Automatic Feature Extraction Based on Envelope Analysis and its Application in Rolling-Element Bearing Fault Detection

Bearing fault diagnosis is essential for the maintenance, durability, and reliability of rotating machines. It can minimize economic losses by removing unplanned downtime in the industry due to the failure of rotary machines. In bearing fault detection, developing fault features extraction techniques that can successfully applicable for various fault severity and different operating conditions is still a critical issue. In the current work, the feature extraction technique is a combination between pre-processing algorithms and envelope analysis method. In the pre-processing stage, the autoregressive (AR) model is used to filter the original signal and remove the deterministic vibration sources, as well as maintain the signal representing the condition of the bearing without contaminating noises. Then, the most suitable frequency band is selected based on the spectral kurtosis (SK) analysis. This band contains the signature frequencies of the roller bearing. After that, envelope analysis is employed for detecting faults at different severity. Finally, the features represented the peaks at fundamental fault frequencies are automatically selected from the envelope spectrum. By analyzing all diagnoses results, it is found that the presented method effectively extracts the features at calculated resonance bearing frequencies and proves the significance of the enhancements in a pre-filtering stage in the overall detection performance. Also, it can benefit from these features in the fault classification fields at different speeds because it is independent of speed variation.

Analisis Efektivitas Gas Turbine Generator pada PT Mitra Energi Batam

PT Mitra Energi Batam is one of the Gas Power Plants (PLTG) and regulates the electricity supply of Batam city with PT PLN-Batam. According to the tabulation of PT Mitra Energi Batam's production data from September 2022 to September 2023, the rolls-royce Gas Turbine Generator production engine has a downtime value of 805.60 hours. The purpose of the study is to find out the factors that cause high downtime and know how to minimize it. Using the proposed Overall Equipment Effectiveness method as a way to measure Losses due to production disruptions by taking six big loss and Fishbone diagrams to find the cause and effect of Losses that cause failure of machine or equipment operations. The results of the study of the highest OEE value in August 2023 were 98.54%, the lowest OEE value was in April 2023 which was 0%, the cause was severe damage to the power turbine blade which required engine replacement, but was constrained by the time of the engine spare delivery process. The six big Losses factor that contributed the most to the OEE value was idling minor stoppage with an average value of 8.83% and equipment failure Losses with an average value of 8.81%.

A comprehensive survey on load balancing techniques for virtual machines

Cloud computing is an emerging technique with remarkable features such as scalability, high flexibility, and reliability. Since this field is growing exponentially, more users are attracted to fast and better service. Virtual Machine (VM) allocation plays a crucial role in cloud computing optimization; hence, resource distribution is not impacted by machine failure and is migrated with no downtime. Therefore, effective management of virtual machines is necessary for increasing profit, energy-saving, etc. However, it could utilize the virtual machine resources more efficiently because of the increased load, so load balancing is more concentrated. The predominant purpose of load balancing is to balance the available load equally among the nodes to avoid overloading or underloading problems. The present study conducted an extensive survey on virtual machine placement to describe the application of prediction algorithms and to provide more efficient, reliable, high response, and low overhead VM placement. Furthermore, the survey attempted to overview the challenges in load balancing in VM placement and various ideas of state-of-the-art techniques to resolve the issues.

Graph Multi-Scale Permutation Entropy for Bearing Fault Diagnosis.

Bearing faults are one kind of primary failure in rotatory machines. To avoid economic loss and casualties, it is important to diagnose bearing faults accurately. Vibration-based monitoring technology is widely used to detect bearing faults. Graph signal processing methods promising for the extraction of the fault features of bearings. In this work, graph multi-scale permutation entropy (MPEG) is proposed for bearing fault diagnosis. In the proposed method, the vibration signal is first transformed into a visibility graph. Secondly, a graph coarsening method is used to generate coarse graphs with different reduced sizes. Thirdly, the graph's permutation entropy is calculated to obtain bearing fault features. Finally, a support vector machine (SVM) is applied for fault feature classification. To verify the effectiveness of the proposed method, open-source and laboratory data are used to compare conventional entropies and other graph entropies. Experimental results show that the proposed method has higher accuracy and better robustness and de-noising ability.

Unavailability-aware allocation of backup resources considering failures of virtual and physical machines

Cloud service providers widely use virtual machines and bring various benefits for customers and themselves. The unavailability of virtual machines is a crucial performance indicator for cloud service quality. However, no previous works studied the unavailability-aware backup allocation considering the failures of both virtual and physical machines. This paper proposes a backup allocation model considering these failures to minimize the maximum unavailability among virtual machines. We use a Markov chain and analyze the state transitions of the proposed model. We establish how to analytically compute the unavailability in the proposed model by solving the equilibrium-state equations formulated from the state transitions. We introduce a heuristic algorithm to solve the optimization problem of backup allocation. Numerical results show that the proposed model reduces the maximum unavailability by 7.5–28.2% compared to baseline models. Our study establishes a fundamental analytical way to calculate unavailability in the proposed model, which handles the failures of both virtual and physical machines.

INTRODUCTION OF THE «PREDICTIVE MAINTENANCE» CONCEPT TO INCREASE RELIABILITY AND PREDICTABILITY OF REPAIRS

This research article discusses the importance of implementing the Predictive Maintenance concept in the context of rocket and artillery weapons to improve the reliability and predictability of repair work. The article discusses key aspects of this concept, including its basic principles and methods, including the use of data analytics and artificial intelligence. The authors analyze the benefits of Predictive Maintenance in the military context, pointing to reduced repair costs, increased availability of military equipment, and extended equipment life. In addition, the article examines the challenges that arise when implementing this concept and provides recommendations on how to overcome them. Modern military equipment requires a high level of reliability and combat readiness. The introduction of the Predictive Maintenance concept is becoming extremely important to ensure the efficiency and safety of military equipment. This research article is devoted to the study and discussion of the possibilities of implementing Predictive Maintenance in the context of rocket and artillery weapons in order to increase the reliability and predictability of repair work. In conclusion, the article emphasizes the importance of implementing Predictive Maintenance as a strategic tool to ensure optimal performance and readiness of missile and artillery weapons in the modern military environment. Keywords: Implementation, concept, Predictive Maintenance, reliability, predictability, repair work, data analytics, artificial intelligence, monitoring systems, machine learning algorithms, sensors, failure prediction, planning, efficiency, readiness, rocket and artillery weapons.

Analisis Preventive Maintenance pada Mesin Injection Molding dengan Metode Mean Time Between Failure dan Mean Time to Repair di PT. XZY

A series of predictable preventive activities to overcome machine failure during operation is very important because it produces good and stable spare parts. This research was carried out with the aim of preventing machine damage due to short circuits that occur in injection molding machines used for the sudden production of automotive component spare parts. The research was carried out using the Mean Time Between Failure (MTBF) and Mean Time To Repair (MTTR) approaches to calculate the time between the machine breaking down and the time it was repaired. The MTBF calculation results in this research were 72.9 hours or less than 4 days the engine would experience damage or every 72.9 hours the engine would experience damage again. The MTTR value obtained is 2 hours, where in 2 hours the work to overcome the damage can be done.

Learning from machines: How negative feedback from machines improves learning between humans

Prior studies on learning from failure primarily focus on how individuals learn from failure feedback given by other individuals. It is unclear whether and how the advent of machine feedback may influence individuals’ learning from failures. We suggest that failure feedback provided by machines facilitates learning in two ways. First, it focuses individuals’ attention on their failures, leading them to learn from these failures. Second, it serves as a catalyzer, motivating individuals to learn more from failure feedback given to them by other individuals as well. In addition, this catalyzing effect is stronger if the failure feedback from machines and by other individuals pertain to related tasks. Using a dataset of 1.5 million observations from an online programming contest community, we find support for our predictions. We contribute to the learning literature by demonstrating both the direct effect and the catalyzing effect of machine failure feedback on individuals’ learning.

Evaluation of stochastic flow lines with provisioning of auxiliary material

Flow lines are often used to perform assembly operations in multi-stage processes. During these assembly operations, components that are relatively small, compared to the work pieces travelling down the flow line, are mounted to the work pieces at a given stage. Those components, or more generally, any kind of auxiliary material, are provisioned to the corresponding production stage in a repetitive but not necessarily deterministic manner using a certain delivery frequency, each time filling the local storage up to a predetermined order-up-to level. Just like random processing times, machine failures, and repairs, the randomness of the provisioning process can impact the long-term throughput of such a flow line. In this paper, we develop a fast and accurate analytical performance evaluation method to estimate the long-term throughput of a Markovian flow line of this type for the practically important case of limited buffer capacities between the production stages. We first give an exact characterization of a two-machine line of that type and show how to determine system state probabilities and aggregate performance measures. Furthermore, we show how to use this two-machine model as the building block of an approximate decomposition approach for longer flow lines. As opposed to previous decomposition approaches, even the state space of the two-machine lines can become so large that an exact solution of the Markov chains can become impractical. We hence show how to set up, train, and use an artificial neural network to replace the Markov chain solver embedded in the decomposition approach, which then leads to an accurate and extremely fast flow line evaluation tool. The proposed methodology is evaluated by a comparison with simulation results and used to characterize the structural patterns describing the behaviour of flow lines of this type. The method can be used to systematically consider the combined impact of the delivery frequency and the local order-up-to levels for the auxiliary material when designing a flow line of this type.

Realization of the Online System for Consumption Monitoring and Power Quality Control in the Gruner Serbian Ltd Company

The paper presents the realization of the system for consumption monitoring and the system for power quality control in the hall 4 of the company GRUNER Serbian d.o.o. in Vlasotince, Serbia. The motivation for the establishment of the mentioned systems are machine failures within the warranty period for which the machine suppliers refuse to recognize the warranty, due to poor voltage conditions and frequent power sags within the industrial plant. Power quality problems are caused by external influences coming from the power supply network. For these reasons, a system of power etwork analysers was designed and implemented by the company Conseko d.o.o., Belgrade. This system monitors and records all relevant parameters of power quality (voltages, currents, active and reactive power, power factor, harmonic content, THD, etc.) in key parts of the hall 4 (molding, air conditioning, tool room, dining room, laboratory, etc.). In addition to this, the monitoring system provides complete insight into consumption and distribution of consumption at a given time interval, which represents an exceptional convenience for optimal distribution of internal consumption and financial calculation of power consumption of each subsystem, which directly affects to the economic profit. The Cloud subsystem is also installed in the system, so that all relevant parameters can be monitored in real time via a remote computer or through an application on a mobile phone.