Machine Maintenance Research Articles

Preventive Maintenance Policy to Improve the Effectiveness of XYZ Machine

PT ABC which is a manufacturing company that produces steel pipes. The last period there was an XYZ machine that often downtime and disrupted the production process. The breakdowns indicate the ineffectiveness of machine. It was necessary to identify and analyze the problems that occurred and the factors that caused the problem. Measurement of machine effectiveness dan it caused is carried out using the OEE method. To avoid the recurrence of machine ineffectiveness, machine maintenance is carried out in a preventive manner according to the spare parts classification (there are 3 classifications of spare parts based on price, namely A under Rp.250,000, B between Rp.250,000 -Rp.500,000 and C above Rp.500,000). The results obtained for the average value of OEE for 1 year is 68%, which shows a value below the ideal OEE standard (85%) and needs to be evaluated. From the calculation of the largest losses value is in the reduce speed losses factor of 67%, it is necessary to minimize the difference in ideal cycle time with actual time (operation time). The best scheduling results is using the preventive maintenance policy method with the schedule of maintenance are: for classification A spare parts the maintenance every 3 months, class B every 5 months, and class C every 6 months.

Machine learning models for condition-based maintenance with regular truncated signals

Condition-based maintenance (CBM) of industrial machines depends on the continuous, real-time monitoring of the machine’s operational condition via smart sensors attached to different components on the machine. The problem of regularly spaced missing data, which can occur due to a variety of hardware or software issues, is one that is often overlooked in the literature surrounding CBM in industrial machines. Such missing data can cause issues in interpreting the true operational state of the machine, which can reduce the effectiveness of CBM processes. In this paper, we examine the capabilities of five data imputation techniques for handling this regular missing data and examine the impact these techniques have on machine learning (ML) classification algorithms for machine fault diagnosis. We examine the following techniques: simple mean imputation, mean imputation with outliers removed, best and worst-case imputation, and previous day imputation. Each of these methods is configured with the specific parameters that they will only consider data from the previous 24 hours, to ensure that the data is recent, and adequately represents the current status of the machine. The efficacy of each method at accurately reconstructing the missing data and the impact they have on ML classification is recorded in the results. The models are evaluated on a real-world dataset and are evaluated on a variety of common performance metrics.

ВКЛАД АКАДЕМИКА ВАСХНИЛ А.И. СЕЛИВАНОВА В ПОДГОТОВКУ НАУЧНО-ПЕДАГОГИЧЕСКИХ И АГРОИНЖЕНЕРНЫХ КАДРОВ РОССИИ

The development of engineering education in Russia plays an important role in the creation of future technologies, the development of new inventions. (Research purpose) The research purpose is forming a patriotic attitude to engineering education in Russia on the example of the activities of a prominent scientist in the field of mechanization and electrification of agriculture, Doctor of Technical Sciences, Professor, academician of the VASHNIL Aleksandr Ivanovich Selivanov. (Materials and methods) The analysis of literary sources was carried out by applying the historical and analytical method. Modern and historical literary sources, conference materials, scientific manuscripts, military-historical materials, original scientific works of A.I. Selivanov were used as materials. (Results and discussion) They outlined the life and creative path of A.I. Selivanov. After graduating from the Faculty of Industrial Agriculture of the Leningrad Polytechnic Institute, A.I. Selivanov worked his way up from an engineer, head of a laboratory, to deputy director for scientific work of VIM, GOSNITI, Siberian Research Institute of Mechanization and Electrification of Agriculture. (Conclusions) A significant cycle of his work is aimed at developing maintenance and repair systems for machines and the rational organization of the repair base. A.I. Selivanov is the founder of the theory of aging of machines, co-author of the textbook "Theoretical foundations of repair and reliability of agricultural machinery." Under his leadership and with his direct participation, a standard tractor and combine repair technology was developed, which served for many years as the main technical document for all repair enterprises. A.I. Selivanov made a huge contribution to the training of scientific, pedagogical and agroengineering personnel in Russia. His diligence, courage, bravery, heroism, perseverance and many other qualities that are necessary for our younger generation serve as a real example for many people.

Technical support system for energy-installed agricultural equipment in the agricultural industry

Agricultural production in Russia solves the most important national problems - food security and import substitution. The conducted research substantiates the need to improve the engineering service of the agro-industrial complex through the introduction of modern innovative technologies. The article outlines the basic principles and technical means that determine the system of maintenance and repair of machines in the agro-industrial complex, as well as the mechanism of relations between manufacturers and consumers of technical means. Current issues of individual subsystems of the repair and maintenance base in the engineering service of the agro-industrial complex and the main groups of repair and maintenance impacts on domestic agricultural machinery were considered, and a relationship was established for foreign-made machines with all elements of maintenance, repair, modernization and disposal. Information is presented on depreciation rates and recommended distributions of the volume of repair and maintenance work by facility.

Development of an AR-based application for assembly assistance and servicing

Recent advancements in the field of digital manufacturing, especially the adoption of fast connectivity through 5G, Digital Twins and Extended Reality (XR) in manufacturing, offer new possibilities for innovative and effective design of production workflows. Augmented Reality (AR) can assist in speeding up the assembly and maintenance processes by facilitating the operators to perform these processes without dealing with detailed paper manuals. AR-based interactive user interfaces can support operators to be more productive by visualizing certain product and component 3D models dynamically, in addition to assembly steps along the corresponding manufacturing process. Likewise, AR-based applications can facilitate the setup and maintenance service of a machine by providing advanced machine visualization and digitalized information. This paper presents a conceptual model and case-based demo applications adopting AR technology for the maintenance of an industrial machine and supporting operators during the assembly process of a specific product. The goal is to improve productivity by reducing the processing time and minimize the operator training time. Moreover, the proposed AR application is integrated with the non-conformance reporting feature which helps to address the quality related issues quickly and efficiently, leading to a reduction in the number of nonconformities. Two case studies demonstrate the relevance of the proposed conceptual model and testing of the applications.

Exact Solution to a Machine Maintenance Problem with Multiple Unobservable States

Exact Solution to a Machine Maintenance Problem with Multiple Unobservable States

Flexible Job Shop Scheduling Problem Considering Upper Bounds for the Amount of Interruptions Between Operations and Machines Maintenance Activities

Flexible Job Shop Scheduling Problem Considering Upper Bounds for the Amount of Interruptions Between Operations and Machines Maintenance Activities

Roles of IoT, Big Data Analytics, and Cyber-Physical Systems in a Sustainable Manufacturing

The convergence of big data analytics, cyber-physical systems (CPS), and the Internet of Things (IoT) is causing a fascinating revolution in the manufacturing sector. The convergence known as "Industry 4.0" is expected to bring about a symphony of sustainability, adaptability, and efficiency where machines move in time with real-time data. The maestro at this point is big data analytics, which translates these tunes to improve the whole thing from inventory control to machine maintenance. By permitting machines to separately adjust settings, act to fluctuating circumstances, and cooperate with one another, CPS bridge the gap amid the digital and physical worlds. This materializes into an astonishing ballet of intelligent automation. But regardless of this fascinating music, there are trials waiting in the shadows. Robust cybersecurity procedures are essential to address worries about data security and privacy, and continuous research and development is compulsory to manage the multifaceted integration and standardization of several technologies. Cautious planning and oversight are also compulsory due to ethical worries about algorithmic prejudice and job movement. The manufacturing industry is full of potential for invention and sustainability, even in the face of these dark clouds. Let us not be overwhelmed by the hindrances in the way of this uprising, but relatively use them to our benefit to generate a harmonious prearrangement of responsible solutions. Industry 4.0 will be protected to dance not just with data but also with beliefs, safety, and sustainability by means of continuing research, transparent communication, and investments in labor force development. This will pave the way for a upcoming in which humans and robots work collectively for an improved tomorrow. The main concepts of Industry 4.0 are outlined in this paper, along with its prospects, complications, and condition for an all-encompassing strategy.

Minimize inventory deviations in the Konimex technical warehouse through the implementation of the DMAIC concept

PT Konimex is a manufacturing company that focuses on the pharmaceutical sector and is supported by an Engineering warehouse for machine maintenance during operation. However, during its run, there were problems in the form of discrepancies between the stock stored in the warehouse and those recorded in the company’s system which had a negative impact in the form of losses for the company. Therefore, a step-by-step analysis is carried out to provide solutions that are in accompanying circumstances using the DMAIC (define-measurement-analyze-improve-control) concept. The data collection method carried out is carried out directly and produces data in the form of primary data and indirect data collection, which uses the company’s historical data and produces secondary data. Data processing using the DMAIC concept then obtained the root of the problem and improvement solutions in the form of container redesign and the application of 5S as well as the addition of warehouse personnel which is expected to reduce the company’s stock-taking discrepancies.

Smart manufacturing system based on industrial internet of things

The primary challenge in the manufacturing industry today is the subpar productivity and efficiency in production processes. This predicament can be attributed to the widespread utilization of suboptimal production systems and the underutilization of advanced technology in manufacturing. Furthermore, the lack of accurate production data, limited employee involvement in production processes, and the high costs associated with production and machine maintenance have emerged as significant concerns in the contemporary manufacturing landscape. In response to these challenges, the adoption of Smart Manufacturing Systems (SMS) based on the Industrial Internet of Things (IIoT) has become crucial to address these issues andenhance overall production quality and efficiency. The SMS IIoT system empowers companies to gather real-time data from various industrial devices and machines. This data is subsequently analyzed to optimize production processes, resulting in increased efficiency and productivity. With this system in place, companies can closely monitor production processes in real-time and promptly detect and address defective or non-compliant products at the onset of production. The research results show an availability value of 88%, indicating that the machine operates 88% of the scheduled time. A Performance value of 100% indicates that the engine is operating at the desired maximum speed. OEE is calculated as the product of Availability, Performance, and Quality of Rate. With a value of 88%, OEE reflects the overall level of effectiveness of the machine in the production process. This paper highlights the significance of IIoT-based Smart Manufacturing Systems in addressing the prevailing challenges encountered by the manufacturing industry.

ANALYSIS OF WORK RISK LEVEL WITH SUITABILITY OF SAFETY SIGN AT PT. AIR MANCUR KARANGANYAR

Production activities that use machines pose a risk of danger to workers. The maintenance and repair of machines in the production process also has many potential hazards. So the purpose of this study was to analyze the effect of the level of occupational risk on the suitability of the safety sign at PT. Air Mancur Karanganyar. Hazard Identification Risk Assessment Determinant Control (HIRADC) method is a way of identifying hazards, risks and determining control of hazards. This study used a cross sectional quantitative, the sampling technique used was Porportionate Statified Random Sampling is if the population had members or elements that had proportional strata with the samples being 38 people. The inclusion criteria for this study were workers in engineering rooms, Solid External Medicines (OLP), and cosmetics at PT. Air Mancur Karanganyar. Data analysis of a spearmen correlation test. The results that there is a significant influence between the Level of Occupational Risk on the Compliance of the Safety Sign at PT. Air Mancur Karanganyar with a significance value of 0.012. The recommendations is are the placement of safety signs such as the Caution for Pinched Hands sign, routine socialization twice a week, and review HIRADC once a year

Cake Breaker Conveyor Machine Maintenance System Analysis Using the Reliability-Centered Maintenance (RCM) Method

Machine maintenance plays a vital role in the production activities of a company, which concerns the smooth and bottleneck of production. This research was conducted in a company engaged in palm oil processing. The company often suffers from machine breakdowns and has not found a suitable solution. Reliability Maintenance is one of the methods used to determine the appropriate maintenance actions for each critical component on the Cake Breaker Conveyor (CBC) machine, based on analysis using Failure Mode and Effect Analysis (FMEA) by looking at the highest RPN value of each component, 4 critical elements are obtained from the 11 main features of the Cake Breaker Conveyor (CBC) machine, namely bearing parts, Universal Joint, Rod Clutch and Pen. Determine the maintenance schedule of critical components at the seed separation station. Taking damage, lognormal distribution, proposed replacement schedule 461.5 (hours), pen damage, normal distribution, proposed replacement schedule 587.29 (hours), universal joint damage, normal distribution, proposed replacement schedule 536.46 (hours), clutch rod damage, normal distribution, proposed replacement schedule 581.6 (hours), and axle damage, normal distribution, proposed replacement schedule 586.6 (hours).

LEAN SIX SIGMA APPROACH TO IMPROVE THE PRODUCTION PROCESS IN THE GARMENT COMPANY: A CASE STUDY

PT “X” is a company engaged in the garment industry. The company is facing problems that inhibit the production process. These problems comprise an excess of product defects beyond the specified limits, a considerable rate of product returns, delays in product shipment, and disorderly arrangements in storing raw material. This study aims to determine the root causes of problems in the PT “X” and provide recommendations for improvement using the concept of lean six sigma. The waste assessment model is used to identify the dominant waste, while the value stream analysis tools is a method used to analyze the causes of the dominant waste. From the research results, four dominant wastes are identified, namely waste defects, unnecessary inventory, waiting and unnecessary motion, with percentages of 27.02%, 15.92%, 14.32% and 14.0% respectively. The results of the analysis using mapping tools show the details of waste in each dominant waste. Proposed recommendations for improvement are made using the failure mode and effect analysis based on the highest risk priority number for each dominant waste. The recommendations proposed by the researchers include implementing a standard operating procedure and work instruction for the sewing process; scheduling machine maintenance using reliability centered maintenance II; planning and scheduling materials using material requirement planning; implementing line balancing; and designing name tags, visual displays, and storage rack layout.

Assessment of Maintenance Performance Using the Maintenance Scorecard Method and Prioritization of Problem Control Strategies with the USG Method

Measuring the performance of machine maintenance becomes very important, serves as a monitoring tool, and triggers increased performance in the production section. Losses due to engine damage will impact the company's profit, which is less than optimal because maintenance can contribute as much as 20-50% of the cost composition of the company's operational costs. This study aimed to measure performance in the maintenance section using the maintenance scorecard (MS) and determine the priority of the performance control strategy using the Urgency, Seriousness, and Growth Method (USG). The research was conducted through case studies on chemical manufacturing companies located in Indonesia. The performance assessment results with the maintenance scorecard method show that the total scorecard maintenance value is in the category of need improvement, which is 63.35. There are 3 KPIs in the very bad category: maintenance costs from a cost-efficiency perspective, work completed from a quality perspective, and self-audit from a learning perspective. The first and foremost strategy that can be done based on USG's priority is to implement reliability-centered maintenance (RCM) to reduce time loss and increase the knowledge and competence of employees. This priority is useful when a company encounters a constraint so that it cannot carry out all strategies simultaneously or can only carry out some strategies while still getting optimal benefits from continuous improvement.

A bibliometric analysis on condition monitoring of machinery using IR Thermography

In order to extend the life of machinery, condition monitoring of equipment has become crucial in every industry or power plant. IR Thermography is a strong tool for condition monitoring since it can detect flaws earlier than other techniques. The most important technique for condition monitoring is infrared thermography. Machine condition monitoring has evolved along with machine maintenance, from manual maintenance through approaches involving the use of sensors to the now under discussion methods and techniques centered on shared automation, data processing, and exchange. The purpose of this paper is to give a brief summary of the academic work that has been done on using IR thermography to monitor the status of machinery. In order to present an up-to-date, content-based analysis that includes bibliometric performance analysis and systematic literature evaluation, this paper evaluates the body of current literature. The writers may concentrate on identifying the most important researchers, journals, and publications, as well as the most significant and influential researchers, thanks to the mix of literature review methodologies used. These conclusions have prompted the authors to outline research trends pertinent to the studied domain and, in addition, to identify potential future research goals from engineering viewpoints.

IIoT System for Intelligent Detection of Bottleneck in Manufacturing Lines

Production lines face numerous challenges to meet market demands, including constant changes in products that require continuous adjustments. Efficient and rapid reconfiguration and adaptation of production processes are crucial. In cases of inadequate adaptation, bottlenecks can arise due to human errors or incorrect configurations, often introducing complexity in pinpointing the root cause and resulting in financial losses. Furthermore, improper machine maintenance contributes to this situation as well. This article seeks to establish a framework grounded in the contemporary smart factory, the IIoT, the Industry 4.0 paradigm, and Big Data. The proposed system places emphasis on leveraging real-time data analysis for predicting risks, while concurrently conducting a thorough analysis of historical data to monitor trends and enhance bottleneck identification. The defined architecture operates across multiple levels, acquiring real-time information and generating historical data for training and continuous optimization. Predictive results contribute to decision-making and assist in mitigating bottlenecks in manufacturing lines.

Perhitungan Waktu Baku Proses Preventive Maintenance Mesin CNC Router

An efficient preventive maintenance requires scheduling process. The first step of this process is to calculate the standard time for each maintenance activity. This research aims to calculate the standard time for preventive maintenance activities for CNC Router machines at PT X through three stages: (1) Interviews and direct observation with the relevant machine operators to obtain a list of maintenance activities, (2) measure the cycle time of each maintenance activities, (3) Calculate Standard time based on cycle time measurement data. The research results show that it takes a total of 100 minutes to carry out the daily maintenance process, 95 minutes for the weekly maintenance process, 790 minutes for the maintenance process after 2000 hours, and 1140 minutes for the maintenance process after 4000 hours. This result can be used as input for the scheduling process for CNC Router machines maintenance at PT. X.

Current-Signal-Based Fault Diagnosis of Railway Point Machines Using Machine Learning

The majority of railway operators still implement conventional maintenance for railway point machines (RPMs), which is one of the most vital pieces of equipment for ensuring the safety of train operation. The conventional maintenance method lacks accuracy, is less efficient, and has high labor costs. This study developed a cost-effective and accurate fault diagnosis (FD) method based on current data to increase the overall efficiency of RPM maintenance. The FD method for RPM equipment discussed in this paper consists of three working conditions: normal, working, and failure. The method was proposed based on time-series current signals, which were gathered when the RPM was in operation. Time-series data were extracted and filtered using time-domain feature extraction based on scalable hypothesis testing. The selected features became the datasets for machine learning modeling. Six machine learning algorithms were compared in order to find the algorithm with the best FD accuracy. The results showed 100% accuracy for the Decision Tree and Random Forest algorithms in the FD method. The results of the FD method could be important for maintenance teams in determining suitable maintenance activities based on RPM working conditions.

Analysis of the Potential Hazards of Work Accidents Department of Production Using Failure Mode Effect Analysis (FMEA) and Fault Tree Analysis (FTA) Methods in PT. XYZ

PT. XYZ is a company engaged in the business of white crystal sugar with raw sugar cane in Jombang. As the industrial world develops, companies are required to produce products both in terms of quality and quantity. Therefore, the production process has the potential to experience work accidents. To minimize this from happening, this research identified the potential hazards of work accidents in the production division. The methods used are the Failure Mode Effect Analysis (FMEA) and Fault Tree Analysis (FTA) methods. Using the FMEA method produced 3 potential hazards with the highest RPN values namely potential for exposed hot ashes at the boiler station with an RPN of 33,716. In second place is the potential collapse of the crane at the mill station with RPN 27,192. Then in third place is the potential Explosion of pipes and tanks at the evaporation station with an RPN value of 23.549. With the FTA method, the 3 potential hazards that have been obtained are used as top events and an analysis is carried out to find out the root causes of the potential accidents that occur. The analysis is grouped from human, equipment, and environmental aspects. From the human factor, it is known that the cause was workers who were not concentrating, were negligent, and did not comply with SOPs. The equipment factor comes from the age of the old tool and lack of maintenance. As well as environmental factors, namely high temperature pressure and humidity which can have an impact on corrosion of iron equipment. So that the suggestions that can be given to companies are imposing sanctions on employees who do not comply with the rules, providing job training according to their respective fields, and scheduling regular machine maintenance.

Цифровизация системы организации рабочих процессов лесозаготовительных машин: оценка эффективности на примере «Ponsse», «Komatsu» и «John Deerе»

When organizing the work of logging machines, it is necessary to take into account not only their technical characteristics, but also their adaptation into a single digital space. In the absence of synchronization, the ability to control the volume of harvested wood, optimize sorting plans for maximum benefit, remotely monitor the technical condition of the tires, organize their effective maintenance and repair is reduced. The software used by the manufacturers of logging equipment "Ponsse", "Komatsu", "John Deere" was evaluated according to fourteen criteria for parameter control, machine maintenance management, personnel training using the method of intergroup relations (Jacquard measure), and visualized with a cluster diagram. The basis of digital systems is software solutions that allow integrating machines of only one brand into a single information space of the company, which narrows the field of their activity, and therefore reduces the effectiveness of their application. The existing models of digital ecosystems of the companies under consideration lack a module related to logging planning, which does not allow to effectively link the required amount of equipment (harvesters, forwarders, loaders, skidders) with the planned volumes of timber harvesting, as well as to coordinate their work and productivity with maintenance and repair. The imbalance of output volumes by different machines used in logging leads to downtime of the most productive (head) machines and a decrease in the total volume of their output to a minimum at one of the main operations.