Machine Breaks Research Articles

Strategic data augmentation with CTGAN for smart manufacturing: Enhancing ML predictions of paper breaks in pulp-and-paper production

This article addresses the significant challenge posed by the rare occurrence of paper breaks in the pulp-and-paper industry, which, despite their infrequency during production, have considerable economic consequences. We analyze operational data from a paper manufacturing machine, focusing on the rare instances of paper breaks (124 out of 18,398 cases) identified through a quality assurance protocol. This scarcity presents a challenge for machine learning-based predictive models. To overcome this, we introduce a novel data augmentation strategy using Conditional Generative Adversarial Networks (CTGAN) and Synthetic Minority Oversampling Technique (SMOTE), aimed at generating synthetic data that not only reflects the real operational data’s distribution but also improves the predictive models’ performance metrics. We assess the impact of this data augmentation on three machine learning algorithms—Decision Trees (DT), Random Forest (RF), and Logistic Regression (LR)—both before and after augmentation. The use of a CTGAN-enhanced dataset led to notable enhancements in predictive maintenance metrics. Specifically, the ability of the models to detect machine breaks (Class 1) increased significantly: over 30% for Decision Trees, 20% for Random Forest, and nearly 90% for Logistic Regression. This methodological progress offers valuable contributions to the fields of industrial quality control and maintenance scheduling by improving the prediction of rare events in manufacturing processes.

Two-stage learning scatter search algorithm for the distributed hybrid flow shop scheduling problem with machine breakdown

The distributed hybrid flow shop scheduling problem with machine breakdown is investigated to reduce the negative impact on real production caused by machine breakdown events. (DHFSPMB). DHFSPMB comprises two subproblems: the maintenance problem with machine breakdown and the distributed hybrid flow shop scheduling problem (DHFSP). A rescheduling method is designed to address the maintenance problem. Subsequently, a two-stage learning scatter search (TLSS) algorithm is proposed for optimizing the DHFSP when the machines break down. Firstly, a mixed integer programming model for DHFSPMB is constructed. Secondly, TLSS employs an improved reinforcement learning approach to enhance the capability of exploration by guiding the direction of global search. A two-stage approach is designed to address the lack of knowledge in the early periods of learning. Finally, a hybrid search strategy is devised to enhance the development capability of TLSS. The experimental results demonstrate that the TLSS algorithm outperforms the comparison algorithms in effectively addressing the DHFSPMB.

Design and experiment of physical-chemical synergy sleep breaking machine for sainfoin seeds

Design and experiment of physical-chemical synergy sleep breaking machine for sainfoin seeds

Penataan Penjadwalan Preventive Maintenance Semua Mesin Milling Wheat Menggunakan Metode TPM (Total Productive Maintenance)

PT X is a factory that processes wheat into flour with roll mill as the main equipment. The wheat used is a blend of Indian wheat and Australian wheat. Indian wheat has a hard texture that can cause the roll grinding to become damaged or dull, increased working amperes,bearing jams, broken belts and motor overload which causes downtime. When a machine or component breaks down, the production process in the company will be disrupted and may come to a halt, so the target is not achieved and endangers to the company. To keep production machines and equipment working, maintenance processes are carried out properly and regularly. Additionally, the company can implement preventive maintenance steps to prevent and reduce machine downtime. Preventive maintenance is a planned maintenance strategy to prevent potential breakdowns. To reduce the high machine downtime, preventive maintenance is solution . The method chosen in this research is Total productive Maintenance. Based on research results, the overall equipment effectiveness (OEE) values were 85.8% in January, 87.18% in May, 86.69% in June, 85.25% in November, and 85.51% in December. The OEE values that did not meet the standard occurred in February (81.92%), March (81.34%), April (84.73%), July (83.77%), August (79.03%), September (77.05%), and October (81.72%). The biggest factor that causing losses of overall equipment effectiveness is caused by the high value of the six big losses, particularly the reduced speed losses, which stand at 9%.

Scheduling maintenance activities subject to stochastic job-dependent machine deterioration

This paper considers a maintenance scheduling problem on a single machine with a fixed job sequence involving job-dependent, stochastic deterioration. If the machine breaks down, then a time-consuming emergency maintenance activity needs to be conducted. Instead, planned maintenance activities can be conducted between jobs in order to improve the machine’s state and, thus, prevent the machine from breaking down. We distinguish two types of machines differing in the flexibility regarding the point of time when the maintenance activities need to be scheduled. The goal is to minimize the total expected completion time of jobs. We formalize two optimization problems, analyze their computational complexities, develop exact solution approaches, and conduct a computational study. Here, we show that our approaches can solve large instances to optimality within short run times and we analyze the advantage gained by planning maintenance activities depending on the actual state of the machine.

A method for determining the spectral relaxation functions of polymers under single stretching of micro samples

The principles of designing products made of the latest complex-structured polymer composite materials necessitate the need to take into account the large-scale structural effects determined by processes at the supramolecular and molecular levels of the polymer: relaxation, kinetic (breaking and recombination of chemical bonds), recrystallization of supramolecular structures, etc. The development of these processes is described by relaxation functions, which, in turn, can be calculated using the functions of relaxation time spectra. The purpose of the work was to develop a specialized equipment for testing micro-samples with a variable working part for uniaxial stretching along with the experimental technique and computational algorithms for processing the obtained measurement data, and experimental approbation of the developed approach to determining spectral relaxation functions. A method is proposed for estimating relaxation functions not at fixed stress levels within linear elasticity, at secant points of deformation diagrams, at fixed values of the linear elasticity modulus, but within an extended range of the sample deformation up to pre-rupture states. A set of test equipment designed for tensile tests of micro-samples with a thickness of the working part of 0.2 – 1.2 mm has been developed. The tooling can be installed on modern high-precision breaking machines. Tensile tests of polyethylene terephthalate micro-samples with a thickness of 50 and 175 μm were carried out taking into account the scale factor. A tensile test of micro-samples that are technologically stabilized by paper frames of a special shape is described. Diagrams illustrating the kinetics of changes in the spectral relaxation functions of oriented polyethylene terephthalate (PET) are constructed proceeding from the data of testing micro-samples with a constant strain rate. A method for using these diagrams in calculations of empirical relaxation time spectra is described. The results of testing micro-samples of polyethylene terephthalate are presented. Illustrative deformation diagrams of the studied polymer samples and calculated diagrams of functions of relaxation time spectra calculated according to the described method are given.

Knowledge and source type influence children’s skepticism of misinformation

ABSTRACT Three-year-olds often respond to lies as if they were true or with no clear rationale. Individual differences influence children’s processing of misinformation. Here, we explore how two contextual cues (children’s conflicting first-hand knowledge and different information sources) affect their ability to correctly interpret and respond to misinformation. 133 three-year-olds from the northeastern United States searched for a hidden object after it had traveled down one of two criss-crossing tubes. Children played this game by themselves (baseline), with a deceptive human (intentionally incorrect about the location of the object), a broken human (unintentionally incorrect), or a broken machine (incapable of intentions and incorrect). Half of the children could see the object as it traveled down the tubes (knowledgeable group), and the other half could not (no-knowledge group). With this first-hand knowledge, children were more likely to search correctly when playing by themselves. Information source further impacted children’s responses. Responding to a deceptive human was the most challenging: knowledgeable children searched randomly; unknowledgeable children inappropriately deferred to the deceptive experimenter. But when knowledgeable children played with either the broken human or the broken machine, they had as many correct searches as when they played alone. Context may have its limits when it comes to influencing children’s responses to misinformation. Specifically, although first-hand knowledge appears to help 3-year-olds correctly respond to some forms of incorrect information, it may not be enough to help them overcome misinformation from explicitly deceptive sources.

FAILURE ANALYSIS OF A BASE SUPPORT PLATE OF A SEMOLINA PURIFIER MACHINES SUBJECTED TO FATIGUE LOADING

The semolina purifier is a machine used in the production phase in flour factories and is exposed to fatigue loads. In this study, the reason for the damage when a semolina purifier machine breaks during use and the improvements that need to be made in the design are discussed. For this purpose, a finite element model (FEM) was created using ABAQUS software. As a result of the analysis, it was determined that the design of the machine support platform should be improved. A two-stage strengthening alternative is designed. The cyclic loads applied by the twin motors that move the machine screens are applied in the FEM model. The deformations and stresses occurring in the reinforced and existing design machine base plate were compared. The results showed that, the maximum equivalent stress level can be reduced from 86 MPa to 35 MPa by design improvements made on the base plate.

EVALUASI PEMBOROSAN MESIN JUMBO LOOM BERBASIS PENDEKATAN STATISTICAL PROCESS CONTROL

Continuous quality control along the production line is a crucial factor in achieving high productivity. PT. TRZ is a producer of various types of plastic-based products that implement strict quality control standards. However, it is still found that production targets still need to be achieved due to machine damage. This machine breaks. The company needs to be able to fulfill consumer orders on time. This research aims to evaluate product defects resulting from damage to the Jumbo Loom machine. Statistical process control evaluates factors in cutting machine defects, thread splice marks, and sheet shrinkage. The research results show that the company faces problems regarding machine defects, including machine running, thread splice marks, and shriveled sheets. This research aims to reduce defects in machines. The Seven Tools method is used to make repairs. From the processing results on the control chart, there were daily defects that exceeded the control limits. Therefore, it was carried out using a fishbone diagram. The processing results obtained 23 indicators of the causes of the three types of defects.

A genetic algorithm-based approach for flexible job shop rescheduling problem with machine failure interference

Rescheduling is the guarantee to maintain the reliable operation of production system process. In production system, the original scheduling scheme cannot be carried out when machine breaks down. It is necessary to transfer the production tasks in the failure cycle and replan the production path to ensure that the production tasks are completed on time and maintain the stability of production system. To address this issue, in this paper, we studied the event-driven rescheduling policy in dynamic environment, and established the usage rules of right-shift rescheduling and complete rescheduling based on the type of interference events. And then, we proposed the rescheduling decision method based on genetic algorithm for solving flexible job shop scheduling problem with machine fault inter-ference. In addition, we extended the "mk" series of instances by introducing the machine fault interference information. The solution data show that the complete rescheduling method can respond effectively to the rescheduling of flexible job shop scheduling problem with machine failure interference.

A Novel Sensor-Based Label-Smoothing Technique for Machine State Degradation

Due to the rise of Industry 4.0, machinery health prognosis has become one of the primary objectives of machine maintenance. Long-term operating machines gradually age over time, resulting in machine degradation and lower production yields. In general, the entire life cycle of a machine is from health to degradation to fault states. Once a machine breaks down, it may increase production costs and cause serious safety hazards. To prevent the machine from operating in a fault state, a variety of sensors are applied for machine health monitoring. Subsequently, the collected sensor data are fed into a degradation model, which is used to evaluate the machine degradation level. As the machine degradation process changes continuously over time, the features in the transition region between two adjacent condition states are nearly identical. Similar features lead to a poor degradation model performance in the transition region. In this study, a novel label-smoothing method is proposed to improve model performance in the transition region. To enhance the machine degradation model accuracy, the proposed method consists of four major processes: preprocessing, data label smoothing, model training, and postprocessing. The developed model is verified using a bearing run-to-failure dataset and a tool wear dataset, achieving a prediction accuracy of over 90%. The experimental results demonstrate that the proposed method outperforms other existing peer methods, especially in the transition region.

PENERAPAN TOTAL QUALITY MANAGEMENT DALAM MENINGKATKAN KUALITAS PRODUK TEH HITAM (Studi Kasus Pada PT. Xyz, Kabupaten Bandung)

Product quality is an important aspect for consumers that can affect the continuity of the company. PT. XYZ , which is a black tea commodity company with orthodox processing, has strived to always produce quality products. However, in the process there are still product defects. Through the application of total quality management, this study aims to determine the application of product quality management, to determine the factors of product defects, and to determine the sequence of improvements that can be made. This study uses a mix method design with case study research techniques. The first and second objectives were analyzed descriptively using the Statistical Quality Control tool, while the third objective was analyzed using the Analytical Hierarchy Process method. The results showed that quality planning experienced obstacles in the form of budget delays, scarcity of raw materials, and broken machines. Quality control is beyond the control limits due to quality defects of 2.46%. Product quality assurance is carried out through organoleptic testing. Quality improvement has not been implemented comprehensively in both the plantation and processing areas. Improvements that need to be made successively are density due to non-standard inlet temperatures, smallish due to incorrect blend composition settings , powdery due to a strong and repeated pressing process, and smokey due to lack of checking engine condition.

Planning experiments for heat treatment of products from powder steels in electrolytes

The studies used quenching in electrolyte, determined the content of carbon and alloying elements, strength, toughness, hardness, microhardness of structural components, as well as metallographic analysis, X-ray diffraction and X-ray phase analysis. Samples and parts made of powder steels were used as the materials under study. The material in the manufacture of which were powders of the following brands: SP100, SP150, SP150D1,5, SP 100D2,5, SP100N1X1. The porosity of the studied samples ranged from 15 to 20 %. To increase the wear resistance, only the working surface of the part was quenched in electrolyte. By changing the current strength and density, only the surface of the sleeve can be hardened. When an electric current is passed, a rapid heating of the sample occurs, when the current is turned off after heating, the sample is cooled in the same electrolyte. After the heat treatment of the products (bushings), the determination of mechanical properties (bending strength) was carried out in accordance with GOST 26529–85. The test samples have the shape of a hollow cylinder. The sample is destroyed by compression and the maximum load preceding its destruction (σr.s.) is determined on the scale of the testing machine (the maximum stress that occurs at the moment of destruction or the appearance of a crack in it). The bending strength of powder steels was determined using a universal testing machine IR 5047-50 with a measurement error of ± 1 %. Microhardness was measured using a PMT-3 microhardness meter. The hardness was determined by the Brinell method on the installation of the WEB308/111 brand. Tensile and compression tests were carried out in special equipment on the UMM-5 breaking machine. The analysis of the mathematical model of heat treatment in electrolytes is carried out on the example of the regression equation of hardening of steel SP100D2.5H3-1 in NaCl solution.

Performance Analysis of Filling Machine Using Overall Equipment Effectiveness Metric in Beverage Company

The purpose of this study is to measure the machine’s performance in the filling process which often experiences damage to one of the companies engaged in the food sector that produces coffee and goat milk powder sachet packaging. The company targets the production process results on coffee products as much as 15,600 sachets per day. In Filling Line 3 machines, there are often losses caused by machine breaks, so the daily production target is not achieved. The method used is the machine performance measurement method (OEE) which consists of 3 factors, namely Availability, Performance, and Quality. The results of the study were obtained from the Overall Equipment Effectiveness (OEE) value for the period of December 2021 (53.4%), January 2022 (60.6%), February 2022 (61%), and March 2022 (63.3%). The OEE value obtained from the calculation is still too far from the World Class standard (85%). The factors in the Six Big Losses analysis that caused the low OEE value consisted of Equipment Failure (52.7%), and Setup & Adjustment (30.7%). The proposed improvements that can be used to increase the effectiveness value of the machine include that the company must conduct training for employees and add maintenance operators. Making SOPs for workers must also be considered because SOPs are standards passed by the company to be followed. The company must also monitor the engine components used.

A Novel Label Smoothing Technique for Machine Degradation

Due to the rise of Industry 4.0, most factories use fully automated equipment to reduce labor costs and increase production efficiency. These long-running machines gradually age over time, which results in machine degradation and lower product yields. In general, the whole life cycle of a machine is from health state to degradation state to fault state. Once a machine breaks down, it may increase production costs and leads to serious safety hazards. To prevent the machine from running in a fault state, many sensors are applied to monitor the health of the machine. Then, the collected data are fed into the degradation model, which is used to evaluate the degradation level. Because machine degradation is a continuous process, the features in the transition region between adjacent two condition states are nearly identical. Similar features make the degradation model perform poorly in the transition region. In this study, a novel label smoothing method is proposed to improve the model performance in the transition region. The proposed method which is tested on a bearing run-to-failure data dataset has achieved a prediction accuracy of 96.76%. The results of the experimental study demonstrate that the proposed method outperforms the other compared peer methods.

Reduction of Machine Breakdown in the Brewery Manufacturing Company, A Case Study of Brewery “A” in the Eastern Nigeria

In this study, the machine break down pattern in Brewery “A” in Eastern Nigeria situated in Onitsha Anambra state has been considered. In the first step of this study, structured questionnaires were produced and administered to target audience for primary data collection. The brewery has limited newsletters, annual reports and bulletins that were used in addition for the reviews. The machines used in the packaging department and its breakdown data over a period of twelve months were gathered and from this, the frequency of breakdown of the machines were established and the data analyzed. The analysis was done by evaluating bottleneck machine breakdowns for different work stations in the production plant, and the effects of breakdown on system output. As a result of the study, critical rates of machine breakdown, which have affected system output, were determined. The frequency of machine breakdown, downtime and maintenance failure problems were also identified. Data collected were analyzed and model for optimization developed. Root cause analysis tools–fishbone and “5why” were used to eliminate the frequent occurring machine breakdown. Mean Time to Failure (MTBF), Availability, and Mean Time to Repair (MTTR) values for the various production lines were evaluated before and after root cause analysis. The result shows that a percentage increase of 13.66%, 10.62% and decrease of 46.42% respectively were obtained which indicated improved Factory efficiency, machine availability and compliancy to plan. Also, Exponential distribution model was used to calculate the failure rate and reliability of the machines using the reliability measures result obtained after root cause analysis technique was applied to each failure. A reliability of 99.7% was obtained.

Improving the efficiency of welded joints of the “insert pipe-plate” type

The article is devoted to the analysis of the causes of damage formation in the transition zone from the seam metal to the base metal of butt welded joints. A method for increasing fatigue strength and improving the properties of compounds of this type is proposed. The analysis of cases of fatigue failures of welded joints operating under repeated static loads indicates that cracks most often originate in the transition zone from the seam to the base metal. For this reason, the geometric parameters of the zone of maximum stress concentration should be taken into account when predicting performance. To analyze the operability of welded joints, which did biaxial loading on a breaking machine test. The operability of welded joints of the "insert pipe-plate" type in the initial state is approximately 4 times lower than the operability of the base metal by remelting the transition zone without electrode oscillations (samples 5 and 6) make up half of the operability of the base metal. By remelting the transition zone with an oscillating electrode with regulation of the linear energy along the width of the seam (samples 7 and 8) are practically not inferior to the operability of the base metal. 1 The design of the installation, which allows for automatic remelting of the transition zone from the seam to the base metal with transverse arc vibrations, providing a coupling radius R = 4 – 6mm. 2 Reduction of stress concentration and regulation of the zone of thermal influence at the junction of the seam with the base metal made it possible to increase the resistance to the origin and development of destruction of welded joints "weld-sheet" to almost similar characteristics of the base metal.

Development of technological principles of technical control of bus bodies during operation based on passive safety conditions

The object of this study is the permissible limits of aging of bus bodies during operation and the formation of appropriate recommendations to control them based on the conditions of compliance of the body with passive safety rules. According to the current method, the new model of the bus is checked for compliance with passive safety by a destructive method. However, during operation, the physical and mechanical properties of the body deteriorate until the moment of non-compliance with the requirements of passive safety. Therefore, the principles of technical control of bus bodies under the conditions of passive safety by non-destructive methods, the implementation of which became possible during the operation of buses, have been developed. 3 implementation options have been proposed. In the first variant, visual control is complemented by a measuring tool – an ultrasonic thickness gauge for measuring the thickness of the frame pipes. This method has not previously been used in the certification of vehicles. The second option involves checking the mechanical properties during repairs on a breaking machine. It is proved that during the restoration repairs of buses, the endurance limit of the steel elements of the body frame is reduced by 1.14–3.33 times. In the third variant, the methodology for modeling and calculating the stressed-strained state of the body was improved based on the method of finite elements, taking into account the effects of corrosion and fatigue strength of the metal of the frame. When modeling, the deformation of the body racks exceeded the permissible values by 1.5–2.0 times. This non-destructive method makes it possible to check the bus for compliance with passive safety requirements during operation, which was previously impossible. The scope of practical application is the introduction of research results into the real practice of operating buses at the legislative level. The results are suitable for monitoring the technical condition of buses by non-destructive methods during operation

Design And Build A Double Roll Type Pecan Breaking Machine With A Power Of 0.5 Hp

Pecan is one of the spices that become an ingredient in the process of the food and cosmetic industry. The pecan separator machine is made to facilitate and speed up the process of breaking the pecan fruit in order to increase work efficiency in the hope that the machine can achieve high efficiency in the form of good fruit yields. The purpose of this pecan fruit separator machine is to help facilitate the community in processing pecan fruit to the maximum of its production, and the community can also increase the processing productivity of pecan fruit, which can improve the community's economy. The research method applied in this study is an experimental method, namely the initial stage of designing a double roll type pecan breaking machine using Auto CAD. Then build the machine in the workshop based on the design that has been done before. The stages passed are making design drawings in Auto CAD and analyzing the components used in the pecan breaking machine. Such components are the frame, inlet funnel, shaft, breaker roller, bearing and outlet funnel. From the results of the analysis, the motor power is 0.5 HP with a rotation of 1400 rpm. The belt length used from the calculation of the pulley size on the 3" machine and the pulley on the 10 breaking roll is 42". For breaking rollers the outer diameter of the roller = 120 mm, the inner diameter of the roller = 100 mm, and the length of the roller = 190 mm. The shaft on the drive motor is 24 mm in diameter. The shaft isestimated to be of S30C carbon steel with tensile strength = 48 kg/mm².

IMPROVING THE EFFICIENCY OF A ROCK BREAKER HYDRAULIC WORKING SYSTEM BY CHANGING THE STRUCTURE OF THE HYDRAULIC SYSTEM

The amount of energy losses in hydraulic systems, determined directly by the efficiency parameter, becomes one of the basic aspects related to the design of these systems. Recently, reducing the energy consumption of hydraulic drives has become one of the most important factors in, and sometimes even the main reason for, development works focused on hydrostatic drive systems in newly designed and already deployed types of machines. The article presents an approach to improve the efficiency of such a hydraulic system based on the analytical model and also includes a case study of redesigning a hydrostatic drive system in a stationary rock breaking machine. The analysis of the calculation results showed benefits resulting from two different concepts of modifying hydraulic systems with an aim at reducing their energy consumption.