Machine Processing Time Research Articles

Deep reinforcement learning for dynamic flexible job shop scheduling problem considering variable processing times

In recent years, the uncertainties and complexity in the production process, due to the boosted customized requirements, has dramatically increased the difficulties of Dynamic Flexible Job Shop Scheduling (DFJSP). This paper investigates a new DFJSP model taking into account the minimum completion time under the condition of machine processing time uncertainty, e.t. VPT-FJSP problem. In the formulated VPT-FJSP process, each workpiece needs to be processed by required machine at a certain time slot where Markov decision process (MDP) and reinforcement learning methods are adopted to solve VPT-FJSP. The agent designed in this paper employs the Proximal Policy Optimization(PPO) algorithm in deep reinforcement learning, which includes the Actor-Critic network. The input of the network is to extract the processing information matrix and to embed some advanced states in the workshop by graph neural network, which enables the agent to learn the complete state of the environment. Finally, we train and test the proposed framework on the canonical FJSP benchmark, and the experimental results show that our framework can make agent better than genetic algorithm and ant colony optimization in most cases, 94.29% of static scheduling. It is also shown superiority compared to the scheduling rules in dynamic environment and has demonstrated strong robustness in solving VPT-FJSP. Furthermore, this study conducted tests to assess the generalization capability of the agent on VPT-FJSP at different scales. In terms of exploring Makespan minimization, the agent outperformed four priority scheduling rules. These results indicate that the proposed dynamic scheduling framework and PPO algorithm are more effective in achieving superior solutions.

Development and analysis of digital twins of production systems

Production systems have to be adapted continuously to changing circumstances. This means that the responsible production planner has to frequently make decisions about reconfiguring complex systems under uncertainty whose outcome greatly affects the company’s business success. Discrete-event simulation is one powerful tool to support the necessary analysis and scenario evaluation, but still remains time-consuming and tricky to set up and to maintain. When implemented as a digital twin of the production system, the simulation model can maintain a high degree of accuracy over a long time period. An approach to realise this potential is presented and illustrated in this paper with a use case from the automotive industry. This paper contributes several new methods and findings to the development of digital twins of production systems: Firstly, it demonstrates how exceptional events in the validation of the digital twin can be handled. Secondly, it shows how structural changes in the system can be discovered using data on machine activity and process mining. Thirdly, the paper introduces a possibility on how to assess the accuracy of the digital twin. Furthermore, it demonstrates how to assess the robustness of the digital twin to estimation errors in machine processing times.

Using applied program packages in determining optimum cutting modes

Purpose. Comparison of the functionality of application program packages when determining optimal cutting modes during mechanical processing. Creation of a mathematical model with technological limitations when boring a shaft in one pass and carrying out calculations. The methods. Research methods were based on the principles of optimization of cutting processes, the theory of cutting and cutting tools, standard methods of determining correction factors were used when creating technological limitations. The smallest machine processing time is chosen as the objective function. Using the functionality of the mathematical package Mathcad and the "Turning optimization" program. Findings. The created mathematical model of turning optimization sufficiently fully describes the machining process. The difference between calculations by two methods is no more than 10%. The functionality of the application programs is enough to determine the optimal parameters of the cutting modes - the number of revolutions of the machine spindle and feed. In addition, when using the Mathcad package, it is possible to add or remove technological constraints. Without a suitable database of correction factors, the search and calculation process is complicated. On the other hand, the "Turning optimization" program works in automatic mode, you only need to enter the initial data. But it is impossible to change the technological limitations, the insufficient number of standard materials of cutting tools and parts. The originality. A mathematical model of optimization of cutting modes when boring a shaft to a pass with corresponding technological limitations was created and investigated. A comparison of application program packages was carried out when determining the optimal cutting modes. Advantages and disadvantages of application programs are defined. Practical implementation. The proposed mathematical model of optimization of cutting modes during turning allows to determine the optimal parameters of the number of revolutions and feed of the machine. Its use will greatly facilitate calculations carried out by designer-technologists when designing technological routes for processing parts and calculating cutting modes. This will significantly reduce production preparation time, especially when using CNC machines.

ПІДВИЩЕННЯ ЕФЕКТИВНОСТІ ФРЕЗЕРУВАННЯ ПОВЕРХОНЬ ЕНДОПРОТЕЗІВ

Purpose to work: is to increase the efficiency of milling endoprosthesis components, taking into account their kinematic characteristics. Methodology: theoretical research was carried out on the basis of mathematical analysis, computer modeling using modern software and computing equipment. The PowerMILL CAM system was used for statistical processing of milling trajectories. Results: when manufacturing endoprosthesis components, the best processing strategies were "Selection of 3D model by model shift" and "Selection of 3D model by shift". These two strategies give the lowest idle time for the lowest core processing time. Machine processing time when using the strategies "3D model selection" by model shift and "3D model selection" by shift is reduced by 2 times compared to the "3D model selection" raster strategy, and by 3 times compared to the "3D model selection" strategy Vortex. However, it should be noted that all 4 studies were conducted at the same cutting modes, which are not typical for high-speed milling. Vortex's "3D Model Selection" is ineffective in these cutting modes due to the fact that it is designed exclusively for high-speed milling. "Sampling a 3D model" with a raster also turned out to be ineffective due to the fact that it is intended for work on open planes. Scientific novelty: the most effective milling strategy for the manufacture of endoprosthesis components is proposed. Practical significance: recommendations for the use of milling strategies are given. Key words: milling, strategy, endoprosthesis, idle movements, model, technological process, operation, machine time.

Unrelated parallel machine scheduling with machine processing cost

In practical scheduling problems, some factors such as depreciation cost, green costs like the amount of energy consumption or carbon emission, other resources consumption, raw material cost, etc., are not explicitly related to the machine processing times. Most of these factors can be generally considered as machine costs. Considering the machine cost as another objective alongside the other classical time-driven decision objectives can be an attractive work in scheduling problems. However, this subject has not been discussed thoroughly in the literature for the case the machines have fixed processing costs. This paper investigates a general unrelated parallel machine scheduling problem with the machine processing cost. In this problem, it is assumed that processing a job on a machine incurs a particular cost in addition to processing time. The considered objectives are the makespan and the total cost, which are minimized simultaneously to obtain Pareto optimal solutions. The efficacy of the mathematical programming approach to solve the considered problem is evaluated rigorously in this paper. In this respect, a multiobjective solution procedure is proposed to generate a set of appropriate Pareto solutions for the decision-maker based on the mathematical programming approach. In this procedure, the ϵ-constraint method is first used to convert the bi-objective optimization problem into single-objective problems by transferring the makespan to the set of constraints. Then, the single-objective problems are solved using the CPLEX software. Moreover, some strategies are also used to reduce the solution time of the problem. At the end of the paper, comprehensive numerical experiments are conducted to evaluate the performance of the proposed multiobjective solution procedure. A vast range of problem sizes is selected for the test problems, up to 50 machines and 500 jobs. Furthermore, some rigorous analyses are performed to significantly restrict the patterns of generating processing time and cost parameters for the problem instances. The experimental results demonstrate the mathematical programming solution approach's efficacy in solving the problem. It is observed that even for large-scale problems, a diverse set of uniformly distributed Pareto solutions can be generated in a reasonable time with the gaps from the optimality less than 0.03 most of the time.

A data-driven model with minimal information for bottleneck detection - application at Bosch thermotechnology

ABSTRACT In the context of bottleneck detection, most data-driven approaches employ data from diverse production variables (machine processing times, machine state tags, input timestamps, etc.) for a detailed analysis of bottlenecks. However, for manufacturing companies initiating their digitalization process (i.e. requiring the smallest hardware investment), a bottom-top approach is still missing. In this work, a data-driven model based on minimal information (MI) retrieved from a manufacturing execution system is proposed for bottleneck detection. We consider MI timestamps when each product exits each station and show that this is the most elementary information from production-line operations, enough to autonomously generate an abstract manufacturing layout, and to detect and predict bottlenecks. A general abstract model of a production line is proposed, named queue directed graph (QDG). Incorporating the MI, the QDG model is able to represent a job-shop with a discrete production environment and to calculate production metrics. This work has been employed in the production system of a Bosch factory, in Portugal, using their manufacturing data sets for validation. Different variants of two well-known bottleneck detection methods were implemented and adapted to Bosch’s use case: the Active Period Method and the Average Active Period Method.

A Study on the Optimal Flexible Job-Shop Scheduling with Sequence-Dependent Setup Time Based on a Hybrid Algorithm of Improved Quantum Cat Swarm Optimization

Multi-item and small-lot-size production modes lead to frequent setup, which involves significant setup times and has a substantial impact on productivity. In this study, we investigated the optimal flexible job-shop scheduling problem with a sequence-dependent setup time. We built a mathematical model with the optimal objective of minimization of the maximum completion time (makespan). Considering the process sequence, which is influenced by setup time, processing time, and machine load limitations, first, processing machinery is chosen based on machine load and processing time, and then processing tasks are scheduled based on setup time and processing time. An improved quantum cat swarm optimization (QCSO) algorithm is proposed to solve the problem, a quantum coding method is introduced, the quantum bit (Q-bit) and cat swarm algorithm (CSO) are combined, and the cats are iteratively updated by quantum rotation angle position; then, the dynamic mixture ratio (MR) value is selected according to the number of algorithm iterations. The use of this method expands our understanding of space and increases operation efficiency and speed. Finally, the improved QCSO algorithm and parallel genetic algorithm (PGA) are compared through simulation experiments. The results show that the improved QCSO algorithm has better results, and the robustness of the algorithm is improved.

Combined Processing of Flat End Surfaces of Electrical Parts

The article shows the relevance and scientific significance in the use of a combined processing method that combines the cutting process and surface plastic deformation, which provides an increase in the efficiency of processing of the basic flat end surfaces of electrical parts made of copper, the study of the patterns of microrelief formation during mechanical processing and plastic deformation of a copper surface. It was found that the use of a combined tool allows you to combine several transitions, which provides an increase in processing productivity by reducing the machine and auxiliary processing time. Replacing the grinding operation of the existing technological process with diamond burnishing can significantly improve the quality of the processed surface.

Cost Effective Optimal Task Scheduling Model in Hybrid Cloud Environment

In today’s world, Cloud Computing (CC) enables the users to access computing resources and services over cloud without any need to own the infrastructure. Cloud Computing is a concept in which a network of devices, located in remote locations, is integrated to perform operations like data collection, processing, data profiling and data storage. In this context, resource allocation and task scheduling are important processes which must be managed based on the requirements of a user. In order to allocate the resources effectively, hybrid cloud is employed since it is a capable solution to process large-scale consumer applications in a pay-by-use manner. Hence, the model is to be designed as a profit-driven framework to reduce cost and make span. With this motivation, the current research work develops a Cost-Effective Optimal Task Scheduling Model (CEOTS). A novel algorithm called Target-based Cost Derivation (TCD) model is used in the proposed work for hybrid clouds. Moreover, the algorithm works on the basis of multi-intentional task completion process with optimal resource allocation. The model was successfully simulated to validate its effectiveness based on factors such as processing time, make span and efficient utilization of virtual machines. The results infer that the proposed model outperformed the existing works and can be relied in future for real-time applications.

Investigating total earliness and tardiness costs through unrelated parallel machine scheduling in uncertain job shop environment using robust optimisation and design of experiment

In real world production systems, uncertain events such as random machine breakdown and processing time can occur anytime. These events lead to disruption of normal activities and consequently invalidate the initial schedule. Considering uncertainty in the scheduling process enables organisations to resume their activities effectively after uncertain events occur. The focus of this paper is proactive scheduling approach with an objective of minimising the total cost (lateness/earliness penalty and tooling cost). Robust optimisation is used to solve the scheduling problem considering processing time, setup times and tooling cost as uncertain parameters. Numerous scenarios are solved using data from local job shop. Multiple performance measurement criteria are evaluated to assess the significance of results obtained using robust and deterministic models. Design of experiment (DOE) has been implemented to evaluate the effects of different factors on the total cost and computational times.

Minimizing the Machine Processing Time in a Flow Shop Scheduling Problem under Piecewise Quadratic Fuzzy Numbers

The piecewise quadratic fuzzy number (PQFN) can signify uncertain information that exists in scientific, technological, and engineering fields. Hence, it is a useful tool for describing information in scheduling problems. This study examines structured n‐job flow shop scheduling with fuzzy piecewise quadratic processing times and three machines. Close interval approximation of PQFNs is also offered as one of the most effective approximate intervals. Furthermore, the leasing cost of equipment is minimized with the use of a fuzzy style and an inventive algorithm. To demonstrate how the proposed framework can be used, a numerical illustration is provided.

Optimasi Rancangan dan Optimasi Proses Pemesinan Komponen Ventilator Indonesia (VENT-i)

Sub-assy-manifold is one of the most significant components inside Vent-i (Indonesian ventilator). The production of sub-assy-manifold consists of two main processes that are assembly process and machining process. The assembly process of sub-assy-manifold is the longest one that takes 23.4 minutes in total compared to other components. The assembly process takes 1.4 minutes/pcs, and the body manifold machining process takes 22 minutes/pcs. Therefore, it is too hard to produce 1000 units of Vent-i per month. Making 1000 units/month can be achieved if the assembly process and the component machining process are at 10.43 minutes maximum in total. The purpose of this research is to reduce the assembly process time and machining process time of sub-assy-manifold. It’s begun with analyzing the current design of sub-assy-manifold using DFMA (Design for Manufacturing Assembly) to reduce the assembly processes time. The two-level full-factorial design experiment is used to find the optimum machining process time. The variables used in this experiment are the type of machine tools, hole toolpath strategy, and surface toolpath strategy. The result shows that assembly process time decreases to 43%, and the machining process time decreases to 63%, and it only takes 9.9 minutes to make sub-assy-manifold in total. With this result, it is possible to produce 1000 units/month Vent-i.

Study on Rheological Properties of Silica Sol in Sisal Fibber Reinforced Investment Casting

In casting temperature Laquan silica sol crust process suitable for the production of surface roughness is small, precision high accuracy in size, and has become the mainstream technology has been widely used. Silicon sol casting with high dimensional accuracy, good surface quality and other advantages, is a widely used less advanced technology without cutting, using silica sol casting method can save a lot of machine equipment and processing time, but also greatly saves metal materials. Hard fiber sisal has high tensile strength, resistance to seawater immersion, friction resistance, flexibility and other characteristics, can be used for fishing, sailing, mining, transportation rope, canvas, waterproof cloth and other raw materials. The most commonly used binder in investment casting is silica gel solution (abbreviated as silica sol), such as ethyl silicate hydrolysate, water glass and silica sol.

Machinery parameter optimization of CNC milling programming towards process time

The Tooling Department is a department engaged in manufacturing die, namely the manufacture of printing equipment to make components/pressed part made according to the desired design and processed on a pressing machine, die ordered from the customer, namely sole agent brand (ATPM). The manufacturing process has been running well so far, but to improve service and to reduce manufacturing die costs, it is necessary to improve time efficiency by optimizing machining parameters. The purpose of this study is to determine the machining parameters that produce optimal processing time in CNC milling programming. This study uses the Taguchi Method with the Orthogonal Array L9 pattern. Factors to be examined include cutting speed, feed rate, depth of cut and machining tolerance using a cutter ball nose Ø32 mm and Ø30 mm. Parameters that produce optimal machining process time in CNC milling programming for cutter ball nose Ø32 mm are at optimum cutting speed = 100480 mm/min, optimal feed rate conditions = 1200 mm/min, optimal depth of cut = 1.5 mm, and conditions machining tolerance = 0.09 mm. The machining process time produced under these conditions is 265.73 minutes. Whereas for cutter ball nose Ø30 mm is at optimum cutting speed = 103620 mm/min, optimal feed rate condition = 1280 mm/min, optimal depth of cut = 1.5 mm, and machining tolerance = 0.09 mm. The machining process time produced under these conditions is 265.51 minutes.

PERANCANGAN ULANG MACHINING FIXTURE UNTUK PRODUK CYLINDER HEAD DAN COVER CRANKCASE TIPE 168

The cylinder head and crankcase cover are components of an engine produced by a manufacturing company in Tangerang. Companies need to make improvements to the production process of these components in order to compete with their competitors. The improvement of the production process is done by improving the machining process stages and re-designing the engine product fixture. Actually the company already has a fixture for the engine machining process, but the fixture cannot be used to produce engine components because it still does not function properly. The problem that occurs is the deviation of the dimensions of machining results and the ineffectiveness of the machining process thereby reducing work productivity. Therefore, it is necessary to design a new fixture that is able to answer both of these problems. Fixture design through the application of the VDI 2222 method combined with the design method according to the Handbook of Jig Fixture has resulted in a fixture design and estimated new machining process time for engine components. The fixture design is then analyzed and validated using engineering software to ensure the fixture's rigidity of the clamping force, machining force, and deflection that occur during the machining process which can have an impact on dimensional deviations. Based on the results of the study conducted, a fixture design for machining cylinder head and crankcase cover products has been produced with fixture dimensions of 450 x 459 x 1125 with a weight of 190 kg. The time needed to complete the cylinder head product is 308.67 seconds and the crankcase cover is 224.19 seconds. The maximum clamping force required is 0.36 kN. Deflection that occurs in the clamping rod is 0.0048 mm, the fixture frame is 0.029 mm and the product deformation is 0.06 mm. The fixture design is expected to be able to solve the problems that exist in the company today.

Performance of optical amplifiers with regard to the power penalties of a DWDM XGS-PON

Introduction:This article is the product of the research “Simulation level performance analysis of optical amplifiers for a DWDM XGS-PON network environment”, supported by the Research Group in New Technologies in Telecommunications (GNTT) of the University of Cauca during 2019.
 Problem:For the implementation of XGS-PON optical network architectures, amplification processes are required. These generate power penalties that lead to the presence of non-linear phenomena, significantly degrading network performance.
 Objective:To analyze the performance of a DWDM / XGS-PON network architecture, respecting the power penalties generated by implementing different types of optical amplifiers in different amplification modes.
 Methodology:Compilation of relevant bibliography on long-range network architectures with symmetric speeds of 10 Gbps.
 Results:Not working in the ideal region of amplification affects the performance of a DWDM XGS-PON network, generating a migration of a linear to non-linear propagation regime, due to the presence of power penalties such as FWM.
 Conclusion:With this investigation it is possible to determine which amplifier should be used according to the needs of the optical network, evaluating the different alternatives available in the market, depending on the cost, configuration and performance of the system.
 Originality:A new research is carried out for the performance of DWDM XGS-PON state-of-the-art network architectures, regarding the incidence of non-linear propagation phenomena.
 Restrictions:In some cases, the simulation tool requires a high consumption of machine resources and processing time.

OPTIMATION PARAMETERS OF CNC MILLING PROGRAMMING MACHINE ON THE PROCESS TIME AND ITS EFFECT ON THE EFFICIENCY

The problems revealed in this research is about Optimization parameters of CNC milling programing machine on the process time and its effect on the efficiency. The purpose of this research are to know the effect of feed rate, depth of cut, and maximum stepdown on processing time in CNC milling programming and searching for the best machining parameters that yield optimal processing time on CNC milling programming. The result can be in the simulation of machining distance or operation time, length of feed step or feed cut length, and length of step without feeding or fast traverse length. Experiment result data is used for see the influence, and contribution of each parameter to the machining process time, also the contribution of the optimized parameters for each process that makes the CNC milling machining process time, and cost will be more efficient.

Finite element modelling and machining using WEDM

During the past few decades, due to the demands from the production fields producing really different and compact products, there developed a need to produce materials with proper finish and with proper Material Removal Rate(MRR). So, to know the surface finish(SR) and Material Removal Rate (MRR) of a material. There are some factors effecting these both factors. In this paper we are considering WEDM (Wire Electronic Discharge Machining) as the machining equipment, WEDM is a non-conventional traditional process in which the material is being cut using a electrically charged wire which is fed continusely on to the material and by continues spread of di-electric fluid for flushing out the removed material. In the removal process there are several parameters which have to be understood in getting perfect SR and MRR. There are some fixed parameters like SEN, Material, Wire, Di-electric fluid these are the fixed parameters which can’t be changed, and the parameters which can be changed are Feed rate, Pulse-on, Pulse-off and Gap Voltage. In this paper to they performed 9-different experiments using L9 orthogonal array approach, which helps in selecting the optimized values. It’s a trail and error process, among those 9 experiments we will get one best optimized way, and we will choose those particular parameters and values chosen as the optimized values for that materialin this paper we are selecting Inconel 718 material as the work piece and molybdenum wire as the feed wire in WEDM. In the study, during machining process time taken each experiment and the weight being reduced after every experiment is being noted down, in the calculation of MRR we need this terms(weight & time), the MRR can be calculated by (Weight of the work piece before machining-Weight of the work piece after machining/Time taken). After calculating MRR and SR manually we are going to compare this values with the mathematical FEA process by using MATlab or ANSYS. In this study we came to know that Duty factor which refers to pulse-on & off time plays an important role in MRR and feed rate plays an important role in SR.

Indirect measurement and diagnostics of the tool wear for ceramics micro-milling optimisation

Based on their favourable mechanical features, applications of ceramics are continuously spreading in industrial environment. Such a good feature is their resistance against heat shock, so, currently they are applied e.g. as coating material for gas turbines. The paper proposes an indirect method for supervision of the cutting tool wear in the optimisation of a micro-milling process of ceramics. It replaces the expensive and time consuming measurement of the cutting tool wear in which the experiment have to be stopped, the tool has to be taken from the machine and it has to be measured e.g. by microscope. The replaced measurement has also the disadvantage that the tool has to be positioned (again) when putting it back to the machine bringing also inaccuracies to the machining. Experiments show that the proposed novel technique allows monitoring the tool wearing process characteristics without measuring the tool directly, even if the applied indirect measurement (on the workpiece) incorporates some inaccuracies. The introduced methodology supported the ceramics milling technology optimisation according to tool live and machining process time, simultaneously.

An adaptive neuro-fuzzy inference system for makespan estimation of flexible manufacturing system assembly shop: a case study

This paper considers the use of combination of neural networks and fuzzy system i.e. adaptive neuro-fuzzy inference system (ANFIS) applied to the n job, m machine real flexible manufacturing system assembly shop problem with the objective of prediction of makespan. Assembly shop makespan is calculated by Nawaz, Enscor, and Ham (NEH) algorithm. On the basis of this algorithm, adaptive neuro-fuzzy inference system model is made to predict the makespan of the jobs. The purpose of this study is to find the makespan estimation in advance if processing time of machines is known. The purpose of this research is to gain the advantage of the capabilities of both Fuzzy systems, which is a rule-based approach and neural network which focus on the network training. This model has been verified by testing and actual data set with the average percentage accuracy achieved is 95.97%. Coefficient of determination and Correlation coefficient is 0.9310 and 0.9649 respectively. The derived values of ANFIS model output are found within the range after being verified practically. Therefore, it can be concluded that makespan calculation of the production system, by the proposed adaptive neuro-fuzzy inference system, can be used as a reliable approach in estimating the makespan of flexible manufacturing system assembly shop.