scholarly journals Improved Control Scheduling Based on Learning to Prediction Mechanism for Efficient Machine Maintenance in Smart Factory

Actuators ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 27
Author(s):  
Sehrish Malik ◽  
DoHyeun Kim
Keyword(s):  
Smart Factory ◽  
Prediction Algorithm ◽  
Utilization Rate ◽  
Task Management ◽  
Management Mechanism ◽  
Machine Maintenance ◽  
Machine Utilization ◽  
And Performance ◽  
Artificial Neural Network Ann ◽  
Prediction Mechanism

The prediction mechanism is very crucial in a smart factory as they widely help in improving the product quality and customer’s experience based on learnings from past trends. The implementation of analytics tools to predict the production and consumer patterns plays a vital rule. In this paper, we put our efforts to find integrated solutions for smart factory concerns by proposing an efficient task management mechanism based on learning to scheduling in a smart factory. The learning to prediction mechanism aims to predict the machine utilization for machines involved in the smart factory, in order to efficiently use the machine resources. The prediction algorithm used is artificial neural network (ANN) and the learning to prediction algorithm used is particle swarm optimization (PSO). The proposed task management mechanism is evaluated based on multiple scenario simulations and performance analysis. The comparisons analysis shows that proposed task management system significantly improves the machine utilization rate and drastically drops the tasks instances missing rate and tasks starvation rate.

scholarly journals Machine Rate Estimates and Equipment Utilization

2021 ◽  
Vol 42 (3) ◽  
Author(s):  
John Sessions ◽  
Michael Berry ◽  
Han Sup-Han
Keyword(s):  
Traditional Method ◽  
Utilization Rate ◽  
Forest Operations ◽  
Equipment Replacement ◽  
Machine Maintenance ◽  
Modified Method ◽  
Rate Calculation ◽  
Machine Utilization ◽  
Equipment Utilization ◽  
Productive Time

As mechanization increases, the percentage of the total cost of the logging operation due to equipment purchase and operation increases. This makes assumptions about machine life, machine maintenance costs, and fuel consumption more critical in understanding the costs of logging operations. For many years machine rate calculations have followed a fixed format based on the concept of scheduled and productive machine hours. When equipment utilization is less than 100%, the traditional machine rate calculation assumes that the machine continues to depreciate and machine wear occurs during the non-productive time at the same rate as during the productive time. This can lead to overestimates of the hourly cost of machine operation by effectively shortening the machine lifetime productive hours as the utilization decreases. The use of inflated machine rates can distort comparisons of logging systems, logging strategies, equipment replacement strategies, and perhaps the viability of a logging operation. We propose adjusting the life of the machine to account for non-productive time: machine life in years should be increased with a decrease in machine utilization, while cumulative machine life in hours remains the same. Once the life has been adjusted, the traditional machine rate calculation procedure can be carried out as is normally done. We provided an example that shows the traditional method at 50% utilization yielded a machine rate per productive hour nearly 30% higher than our modified method. Our sample analysis showed the traditional method consistently provided overestimates for any utilization rate less than 100%, with lower utilization rates yielding progressively increasing overestimates. We believe that our modified approach yields more accurate estimates of machine costs that would contribute to an improved understanding of the machine costs of forest operations.

Mycielski Based 2d-Predictive Image Coding Algorithm

2016 ◽  
Vol 850 ◽  
pp. 144-151 ◽  
Author(s):  
Mehmet Fidan ◽  
Ömer Nezih Gerek
Keyword(s):  
Image Coding ◽  
Predictive Coding ◽  
Prediction Method ◽  
Physical Distance ◽  
Prediction Algorithm ◽  
Two Dimensional ◽  
Two Dimensional Image ◽  
Past Data ◽  
And Performance ◽  
Definition Of

The Mycielski method is a prospering prediction algorithm which is based on searching and finding largest repeated binary patterns. It uses infinite-past data to devise a rule based prediction method on a time series. In this work, a novel two-dimensional (image processing) version of the Mycielski algorithm is proposed. Since the dimensionality definition of “past” data increases in two-dimensional signals, the proposed algorithm also needs to handle how the boundaries of the pixel cliques are iteratively extended in the neighborhood of a current pixel. The clique extension invokes novel similarity search strategies that depend on the chosen physical distance metric. The proposed prediction algorithm is used for predictive image compression and performance comparisons with other predictive coding methods are presented.

scholarly journals Neuron Blockchain Algorithm for Legal Problems in Inheritance of Legacy

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1595
Author(s):  
Seong-Kyu Kim ◽  
Jun-Ho Huh
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Non Fiction ◽  
Legal Problems ◽  
Artificial Neurons ◽  
The Will ◽  
Artificial Neural ◽  
And Performance ◽  
Artificial Neural Network Ann ◽  
Artificial Network

This paper discusses the worldwide trend of aging as the lifespan of humans increases. Nonetheless, most people do not write wills, which results in many legal problems after their death. There are many reasons for this including the problem of the validity of their heritage possibly not being legally certified. Wills can be divided into two categories, i.e., testimony and documents. A lawyer in the middle should notarize them, however, instead of providing these notarized services, we propose more transparent algorithms, blockchain shading, and smart country functions. Architectures are designed based on a neural network, the blockchain deep neural network (DNN), and deep neural network-based units are built with a necessary artificial neural network (ANN) base. A heritage inherited blockchain architecture is designed to communicate between nodes based on the minimum distance algorithm and multichannel protocol. In addition, neurons refer to the nerve cells that make up the nervous system of an organism, and artificial neurons are an abstraction of the functions of dendrite, soma, and axon that constitute the neurons of an organism. Similar to the neurons in organisms, artificial neural algorithms such as the depth-first search (DFS) algorithm are expressed in pseudocode. In addition, all blockchain nodes are equipped with verified nodes. A research model is proposed for an artificial network blockchain that is needed for this purpose. The experimental environment builds the server and network environments based on deep neural networks that require verification. Weights are also set for the required verification and performance. This paper verifies the blockchain algorithm equipped with this non-fiction preprocessor function. We also study the blockchain neuron engine that can safely construct a block node for a suicide blockchain. After empirical testing of the will system with artificial intelligence and blockchain, the values are close to 2 and 10 and the distribution is good. The blockchain node also tested 50 nodes more than 150 times, and we concluded that it was suitable for actual testing by completing a demonstration test with 4500 TPS.

A Hybrid Multiple Parallel Queuing Model to Enhance QoS in Cloud Computing

2020 ◽  
Vol 12 (1) ◽  
pp. 18-34 ◽  
Author(s):  
Shahbaz Afzal ◽  
G. Kavitha
Keyword(s):  
Cloud Computing ◽  
Response Time ◽  
Waiting Time ◽  
Queue Length ◽  
Utilization Rate ◽  
Queuing Model ◽  
Total Response Time ◽  
Proposed Model ◽  
Mathematical Equations ◽  
And Performance

Among the different QoS metrics and parameters considered in cloud computing are the waiting time of cloud tasks, execution time of tasks in VM's, and the utilization rate of servers. The proposed model was developed to overcome some of the pitfalls in the existing systems among which are sub-optimal markdown in the queue length, waiting time, response time, and server utilization rate. The proposed model contemplates on the enhancement of these metrics using a Hybrid Multiple Parallel Queuing approach with a joint implementation of M/M/1: ∞ and M/M/s: N/FCFS to achieve the desired objectives. A neoteric set of mathematical equations have been formulated to validate the efficiency and performance of the hybrid queuing model. The results have been validated with reference to the workload traces of Bit Brains infrastructure provider. The results obtained indicate the significant reduction in the queue length by 60.93 percent, waiting time in the queue by 73.85 percent, and total response time by 97.51%.

scholarly journals Sustainable Scheduling of an Automatic Pallet Changer System by Multi-Objective Evolutionary Algorithm with First Piece Inspection

2019 ◽  
Vol 11 (5) ◽  
pp. 1498
Author(s):  
Qingmiao Liao ◽  
Jianjun Yang ◽  
Yong Zhou
Keyword(s):  
Evolutionary Algorithm ◽  
Pass Rate ◽  
Utilization Rate ◽  
Manufacturing Execution System ◽  
Solution Quality ◽  
Multi Objective ◽  
Machining Center ◽  
Dynamic Factors ◽  
Industry Practice ◽  
Machine Utilization

In this study, the machining center with the Automated Pallet Changer (APC) scheduling problem considering the disturbance of the first piece inspection is presented. The APC is frequently used in industry practice; it is useful in terms of sustainability and robustness because it increases the machine utilization rate and enhances the responsiveness to uncertainties in dynamic environments. An enhanced evolutionary algorithm for APC scheduling (APCEA) is developed by combining the multi-objective evolutionary algorithm with APC simulation. The dynamic factors in the simulation model include the pass rate of the first piece inspection (FPI) and the adjusted time when the FPI is unpassed. The proposed APCEA defines the non-robust gene based on the risk combination of the first piece inspection, and screens the non-robust gene in the genetic operation, thus improving the solution quality under the same computation times. Compared with the other three multi-objective evolutionary algorithms (MOEAs), it is demonstrated that the proposed APCEA produces the best result among the four methods. The proposed APCEA has been embedded into the manufacturing execution system (MES) and successfully applied in a manufacturing plant. The application value of the proposed method is verified by a practical example.

scholarly journals Cooperative Multiagent System for Parking Availability Prediction Based on Time Varying Dynamic Markov Chains

2017 ◽  
Vol 2017 ◽  
pp. 1-14 ◽  
Author(s):  
Surafel Luleseged Tilahun ◽  
Giovanna Di Marzo Serugendo
Keyword(s):  
Traffic Congestion ◽  
Shopping Mall ◽  
Time Varying ◽  
Dynamic Prediction ◽  
Long Term Changes ◽  
Parking Lot ◽  
And Performance ◽  
Prediction Mechanism ◽  
Parking Place

Traffic congestion is one of the main issues in the study of transportation planning and management. It creates different problems including environmental pollution and health problem and incurs a cost which is increasing through years. One-third of this congestion is created by cars searching for parking places. Drivers may be aware that parking places are fully occupied but will drive around hoping that a parking place may become vacant. Opportunistic services, involving learning, predicting, and exploiting Internet of Things scenarios, are able to adapt to dynamic unforeseen situations and have the potential to ease parking search issues. Hence, in this paper, a cooperative dynamic prediction mechanism between multiple agents for parking space availability in the neighborhood, integrating foreseen and unforeseen events and adapting for long-term changes, is proposed. An agent in each parking place will use a dynamic and time varying Markov chain to predict the parking availability and these agents will communicate to produce the parking availability prediction in the whole neighborhood. Furthermore, a learning approach is proposed where the system can adapt to different changes in the parking demand including long-term changes. Simulation results, using synthesized data based on an actual parking lot data from a shopping mall in Geneva, show that the proposed model is promising based on the learning accuracy with service adaptation and performance in different cases.

scholarly journals Neural Network Prediction for Efficient Waste Management in Malaysia

2018 ◽  
Vol 12 (2) ◽  
pp. 738
Author(s):  
Siti Hajar Yusoff ◽  
Ummi Nur Kamilah Abdullah Din ◽  
Hasmah Mansor ◽  
Nur Shahida Midi ◽  
Syasya Azra Zaini
Keyword(s):  
Neural Network ◽  
Waste Management ◽  
Solid Waste ◽  
Solid Waste Management ◽  
Prediction Algorithm ◽  
Municipal Solid Waste Management ◽  
Neural Network Prediction ◽  
Solid Waste Generation ◽  
The Government ◽  
Artificial Neural Network Ann

<span lang="EN-MY">Maintaining current municipal solid waste management (MSWM) for the next ten years would not be efficient anymore as it has brought many environmental issues such as air pollution. This project has proposed Artificial Neural Network (ANN) based prediction algorithm that can forecast Solid Waste Generation (SWG) based on population growth factor. This study uses Malaysian population as sample size and the data for weight is acquired via authorized Malaysia statistics’ websites. All data will be normalized in the pre-processing stage before proceeding to the prediction using Visual Gene Developer. This project evaluated the performance using R<sup>2</sup> value. Two hidden layers with ten and five nodes were used respectively. The result portrayed that there will be an increase of 29.03 percent of SWG in year 2031 compared to 2012. The limitation to this study is that the data was not based on real time as it was restricted by the government.</span>

scholarly journals Design and Performance Analysis of 4-bit Nano-processor Design for Low Area, Low Power and Minimum Delay Using 32nm FinFET Technology

2021 ◽  
Vol 12 ◽  
pp. 1-8
Author(s):  
Sujata A. A ◽  
Lalitha. Y. S
Keyword(s):  
Power Consumption ◽  
High Speed ◽  
Software Tool ◽  
Cmos Technology ◽  
Effective Control ◽  
Low Area ◽  
Area Reduction ◽  
And Performance ◽  
Artificial Neural Network Ann ◽  
Universal Gates

The recent technologies in VLSI Chips have grown in terms of scaling of transistor and device parameters but still, there is challenging task for controlling current between the source and drain terminals. For effective control of device current, the FinFET transistors have come into VLSI chip, through which current can be controlled effectively. This paper is to address the issues present in CMOS technology and majorly concentrated on the proposed 4-bit Nano processor using FinFET 32nm technology by using the Cadence Virtuoso software tool. In the proposed Nano processor, the first part is to design using 4bit ALU which includes all basic and universal gates, efficient and high-speed adder, multiplier, and multiplexer. The Carry Save Adder (CSA) and multiplier are the major subcomponents which can optimize the power consumption and area reduction. The second part of the proposed Nano processor is 4-bit 6T SRAM and Encoder and decoder and also Artificial Neural Network (ANN). All these subcomponents are designed at analog transistors (Schematic level) through which the Graphic Data System (GDS-II) is generated through mask layout design. Finally, the verification and validation are done using DRC and LVS, at the last chip-level circuit is generated for chip fabrication. The ALU is designed by using CMOS inverters and the designed ALU schematic is simulated through 32nm FinFET technological library and compared with CMOS technology which is simulated through 32nm CMOS library (without FinFET). The power consumption of AND, OR, XOR, NOT, NAND gates, SRAM, Encoder, Decoder and ANN are 36.09nW, 64.970nW, 61.13nW, 33.31nW, 37.45nW, 32.5% optimization in power dissipation and 47% optimization in leakage current, 2.68uW, 1.98uW and 7.5% improvement in power consumption and 0.5% information loses compressed subsequently respectively. The basic gates and universal gates, CSA, subtraction, and MUX are integrated for 4-bit ALU design, and its delay, power consumption, and area are 0.104nsec, 314.4uW, and 56.8usqm respectively

scholarly journals Kinetics and Performance of Biological Activated Carbon Reactor for Advanced Treatment of Textile Dye Wastewater

Processes ◽  
2022 ◽  
Vol 10 (1) ◽  
pp. 129
Author(s):  
Yen-Hui Lin ◽  
Bing-Han Ho
Keyword(s):  
Experimental Data ◽  
Activated Carbon ◽  
Removal Efficiency ◽  
Utilization Rate ◽  
Textile Dye ◽  
Yield Coefficient ◽  
Dye Wastewater ◽  
Monod Kinetics ◽  
Biological Activated Carbon ◽  
And Performance

The kinetics and performance of a biological activated carbon (BAC) reactor were evaluated to validate the proposed kinetic model. The Freundlich adsorption capacity (Ka) and adsorption intensity constants (n) obtained from the batch experiments were 1.023 ± 0.134 (mg/g) (L/mg)1/n and 2.036 ± 0.785, respectively. The effective diffusivity (Ds) of the substrate within the activated carbon was determined by comparing the adsorption model value with the experimental data to find the best fit value (4.3 × 10–4 cm2/d). The batch tests revealed that the yield coefficient (Y) was 0.18 mg VSS/mg COD. Monod and Haldane kinetics were applied to fit the experimental data and determine the biokinetic constants, such as the maximum specific utilization rate (k), half-saturation constant (KS), inhibition constant (Ki), and biomass death rate coefficient (kd). The results revealed that the Haldane kinetics fit the experimental data better than the Monod kinetics. The values of k, KS, Ki, and kdwere 3.52 mg COD/mg VSS-d, 71.7 mg COD/L, 81.63 mg COD/L, and 4.9 × 10−3 1/d, respectively. The BAC reactor had a high COD removal efficiency of 94.45% at a steady state. The average influent color was found to be 62 ± 22 ADMI color units, and the color removal efficiency was 73‒100% (average 92.3 ± 10.2%). The removal efficiency for ammonium was 73.9 ± 24.4%, while the residual concentration of ammonium in the effluent was 1.91 ± 2.04 mg/L. The effluent quality from the BAC reactor could meet the discharge standard and satisfy the reuse requirements of textile dye wastewater.

Sign in / Sign up

Export Citation Format

Share Document