Yasuhiro Sudo’s research while affiliated with Kanagawa Institute of Technology and other places


Ad

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (17)


Initial Investigation of a Notification System for Indoor Alarm Sounds Using a Neural Network
  • Chapter

June 2019

·

17 Reads

Takeru Kadokura

·

Kohei Watanabe

·

Yoshikaze Yanagiya

·

[...]

·

Many devices can inform the user of everything from a visitor’s arrival at the door to a dangerous gas leak detection. For hearing-impaired people, there are some devices that can notify using light, etc., rather than by sound. However, these are individual devices and are relatively expensive due to their limited production volume. In this paper, a neural network was used as a method to classify alarm sounds of eight types of equipment. Two feature elements such as power spectrum and Mel Frequency Cepstrum Coefficients (MFCC) are taken as feature quantities to enter in this network, and its performance was evaluated. We implemented a neural network learned model on a Raspberry Pi and constructed a system that transmits classification results to a smartphone via Bluetooth. We generated 8 types of alarm sounds, plus indoor environmental sounds and speech sounds, for a total of ten kinds of sounds in the actual use environment of the classification experiment. This produced classification rates of 83.0% and 82.0% in experiments using learned models generated by power spectrum and MFCC. For the 8 alarm sounds, the classification rate was 87.5% by power spectrum and 77.5% by MFCC. It was confirmed that good performance could be obtained if power spectrum is used to determine feature elements in alarm sound classification.


Usage of a Digital Eco-factory for a Printed Circuit Assembly Line

September 2017

·

32 Reads

A concept called digital eco-factory (a collection of software agents that virtually represent the hardware and software facilities involved in a manufacturing system) has been developed to examine the environmental performance, productivity, and manufacturability, simultaneously, of a manufacturing system. This study reports three applications of the digital eco-factory in evaluating a printed circuit assembly (PCA) line. The first application deals with the determination of environmental performance and productivity of a PCA line for various production plans without changing the configuration of the line. The second application deals with the evaluation of the adequacy of the production plans for various PCA lines. The last application deals with the effects of an accident (e.g., machine failures) while running a PCA line. The successful implementation of the proposed digital eco-factory in the above three cases helps identify the general configuration of the digital eco-factory that can be used for other production lines.


Fig. 1. Conceptual structure of the digital eco-factory.
Fig. 2. Major three use cases of the digital eco-factory.
Fig. 3. Agent based construction of the virtual PCA line.  
Fig. 4. Activity diagram for agent of a solder paste printer.  
Fig. 8. Structure of a PCA production plan.

+2

A Multi-agent Based Construction of the Digital Eco-factory for a Printed-circuit Assembly Line
  • Article
  • Full-text available

December 2016

·

344 Reads

·

16 Citations

Procedia CIRP

At present, manufacturing industries are required to consider sustainability of the global environment in addition to minimization of production cost. The digital eco-factory has been proposed for a simultaneous examination of environmental performance, productivity and manufacturability. This paper entertains how to construct the digital eco-factory with high accuracy and usability. In general, the digital eco-factory is constructed on the virtual production line modelling an actual production line and its components. A multi-agent based construction of the digital eco-factory was applied and a trial digital eco-factory has been implemented for a PCA (Printed Circuit Assembly) line. A PCA line consists of a solder paste printer, two or three electronic part mounters, reflow soldering oven and testing machine. In the PCA line, processes for the above machines proceed in sequence, these machines’ capabilities are modelled as individual machine agents. There are several types of printed boards produced, depending on the number of mounted electronic components and the temperature of the solder. When a blank PCB (Printed Circuit Board) is input to a solder paste printing machine, the production process is started. A PCB is modelled as a part agent which is one of the product agents. For some example virtual productions, power consumption of each machine on each line from the environmental view and productivity of each machine and each line are monitored. From the results of the trial implementation, it can be said that all components on the production line could be configured as software agents with required accuracy. These agents are called “machine agents.” In addition to machine agents, manufactured products such as workpiece and parts are also configured as software agents.

Download

Fig. 1. Construction of the digital eco-factory using the e-catalogue library.
Fig. 2. Construction of a machine e-catalogue library.
Table 2 . Power consumption parameters for an electronic part mounter.
Table 3 . Power consumption parameters for a reflow soldering oven.
E-catalogue Library of Machines for Constructing Virtual Printed-circuit Assembly Lines

December 2016

·

518 Reads

·

10 Citations

Procedia CIRP

To easily and smoothly construct a virtual production line for a simulation of environmental performance, productivity and manufacturability, the use of a manufacturing machine e-catalogue library is proposed in this paper. A machine vender such as a machine tool maker and equipment provider registers an e-catalogue of his product to the library using a corresponding template. The designer of a production system constructs a virtual production line by selecting an adequate manufacturing machine's e-catalogue from the library. In this paper, this e-catalogue library concept is applied to the electric-power consumption simulation of a PCA (Printed Circuit Assembly) line. A PCA line consists of a solder paste printing machine, two or three electronic part mounters, reflow furnace and testing machine. Each machine's e-catalogue consists of descriptions not only for specifications but also for computational expressions according to the behavior of the machine. Using experimentally implemented e-catalogues, virtual PCA lines are configured for simulation of electric power consumptions. These virtual lines are configured as a multi agent system of machine agents which are generated based on a selected machine's e-catalogue.


Multi-agent based simulation of electric power consumption based on the production scenario for printed circuit assembly

August 2016

·

6 Reads

·

3 Citations

In this paper, an effective usage method of a multi-agent based simulation system for sustainable production, called a digital eco-factory, is discussed through an electric power consumption simulation for a PCA (Printed Circuit Assembly). A virtual PCA line is constructed as a multi agent system by a solder-paste printer agent, several part-mounter agents and a reflow-soldering oven agent. Each machine agent models a machine's behavior exactly. Electric power consumption is included as a result of machine behavior. Machine behavior is controlled by the produced product, operation and production schedule. These production data are provided to the virtual production line through PCB (Printed Circuit Board) agents. Before the power consumption simulation, the virtual factory which is usually structured from several virtual production lines is constructed as a multi-agent system. Line configuration data and production data are called a production scenario. Various production scenarios can be reviewed by using the proposed multi-agent based simulation.


S1420102 Prototyping of an Agent-Based Digital Eco-Factory

September 2015

·

8 Reads

The Proceedings of Mechanical Engineering Congress Japan

There is a requirement for IT tool to support green production. A digital eco-factory has been proposed by the authors for use in simultaneous examination of environmental performance, productivity and manufacturability. In this paper, the idea of a digital eco-factory is applied to a PCA (Printed Circuit Assembly) line. In the trial implementation of a virtual PCA production line, machines, PCBs and other components on the line were constructed as software agents. Behavior of each machine is described by combination of activities. Virtual PCA lines are implemented on commercially available multi-agent simulator "artisoc." Power consumption of each machine on each production line were monitored from the environmental view and productivity view. This PCA application of a digital eco-factory shows how to construct the digital eco-factory with high accuracy and usability and also shows prominent maneuverability at the usage stage. These results provides the way to a construction of a general digital eco-factory.


Autonomous Assembly Process Planning According to the Production Line Configuration

May 2015

·

6 Reads

·

2 Citations

International Journal of Automation Technology

In this study, a virtual production line is used to present a method for generating assembly process-relational plans for a product according to the configurations of the production line and verify the effectiveness of the proposed method. In an autonomous production system, process-relational plans are generated dynamically by agents based on process-relation graphs. Usually, such process-relation graphs are not determined uniquely and often have some degrees of freedom. Therefore, more practical and efficient assembly process-relational plans would be obtained if process-relation graphs were rewritten according to changes in the configurations of actual production lines. In the proposed method, process-relation graphs are rewritten dynamically by agents using two simple rewriting rules. The results from simulations on a virtual assembly line provided that the progress of the assembly job differs with the quantities of invested jobs and machine layouts. Accordingly, the simulation results prove the usefulness of rewriting process-relation graphs according to the configurations of actual shop floors.


Agent based Manufacturing Simulation for Efficient Assembly Operations

December 2013

·

223 Reads

·

18 Citations

Procedia CIRP

This study experiments with the manufacturing efficiency by layout change of a factory by means of agent-based autonomous production scheduling, using the virtual factory on a multi-agent simulation system. As infrastructure software for agent based simulation, the artisoc(c) is used. In this virtual factory, three types of agents are equipped. Users can alter a configuration such as input new jobs, adjusting a machine setting, etc, with monitoring conditions of agents. As a result, by adjustment of the agent's behavior with shop floor detail, the assembly schedule becomes more effective. The experiment is carried out to show that local negotiations contribute to global optimization when resources in the factory are effectively distributed and shared. In this paper, the effectiveness of job-list cleanup method is shown. In addition, the scheduling influence is simulated by the communication range of agents. A part agent chooses a machine, by the length of a job list and the conveyance cost. But the communication cost between agents increases with the size of the communication range. From experimental results, when extending the communication range simply, the conclusion is reached that optimization did not necessarily result in progress.


Agent Oriented Construction of a Digital Factory for Validation of a Production Scenario

December 2012

·

369 Reads

·

16 Citations

Procedia CIRP

At present, there are various types of manufacturing systems from the traditional centralized system to the autonomous distributed system which has high flexibly for changes in the kinds and/or amounts of products. To support production planning for such a variety and, as a result, to prepare an adequate production scenario which can be well reviewed not only from an economical but also from an environmental view, IT support tools are necessary. In this paper, an agent oriented digital factory is proposed as an IT support tool for production planning. A trial implementation of the digital factory is also reported.


Verification of Scheduling Efficiency of an Autonomous Assembly System Using the Multi-Agent Manufacturing Simulator

June 2012

·

14 Reads

·

4 Citations

This study is an examination of the effect of agent-based autonomous production scheduling, using the virtual factory on multi-agent simulation system. In the autonomous manufacturing system, a production plan is generated autonomously and dynamically, using communication and negotiation between agents that correspond to factory components. As infrastructure software for agent based manufacturing, the artisoc(c) is used as multi-agent simulator system. In this virtual factory, three types of agents are equipped. Users can operate a configuration such as input new jobs, adjusting a machine setting, etc, with monitoring conditions of agents. Additionally, this simulator has capability of input and output files such as assembly process schedules and logs of practical operations. As a result, by adjustment of the agent’s behavior with factory floor detail, the assembly schedule becomes more effective. The experiment was carried out to show that local negotiations contribute to global optimization when resources in the factory are effectively distributed and shared.


Ad

Citations (8)


... Previously, authors proposed a method that is using agents for decentralized autonomous control. This autonomous assembly type system consists of the following: assembly machine agents, product agents and parts agents5678. In addition, it has also discussed the possibility of implementation as a multi-agent system [9]. ...

Reference:

Agent based Manufacturing Simulation for Efficient Assembly Operations
4104 Configuration of the autonomous assembly system using product and machine agents
  • Citing Article
  • July 2008

The Proceedings of Manufacturing Systems Division Conference

... A manufacturing activity unit is also configured as an agent. To obtain more flexibility and autonomy, authors have proposed an event driven configuration [7] [8]. The occurrence of an event means that a workpiece or parts for the product are input to the shop floor. ...

3302 An autonomous decentralized assembly system led by a product part agent
  • Citing Article
  • March 2009

The Proceedings of Manufacturing Systems Division Conference

... This method classifies the energy behaviour of machine components in three modes: fixed (energy behaviour independent of the process and most often used to maintain a specific state of the machine tool), controlled fixed (periodical on/off mode supervised by the programmable logic controller or external devices), and variable (process-dependent). Similarly, the work of Matsuda et al. [109] presents a method for the individual monitoring of machines and creating a catalogue library, the aim of which is to build a virtual factory for production simulation. Mawson and Hughes [110] state in their publication that investing in energy-efficient technologies and implementing smart control technologies can reduce energy consumption by 50% as opposed to operational improvements that can only reduce it by 10-20%. ...

E-catalogue Library of Machines for Constructing Virtual Printed-circuit Assembly Lines

Procedia CIRP

... Integrasi alat komputer yang berbeda memungkinkan manajer dan desainer untuk menyimulasikan kinerja semua aspek sistem produksi (Caggiano, Caiazzo and Teti, 2015). Alat pemodelan memungkinkan analisis perilaku produk, kinerja lini produksi, dan koordinasi jaringan multi situs, sehingga mengarah pada optimalisasi semua proses dan operasi industri (Matsuda, Sudo and Kimura, 2016). ...

A Multi-agent Based Construction of the Digital Eco-factory for a Printed-circuit Assembly Line

Procedia CIRP

... Then, the assembly operation progresses autonomously. Accordingly, transformation of scheduling results from agent's behavior and factory parameter had been further explored141516. In such an agent based system, since there are too many indefinite elements, in order to predict the behaviour of a factory line, the computer simulation is indispensable. ...

Verification of Scheduling Efficiency of an Autonomous Assembly System Using the Multi-Agent Manufacturing Simulator
  • Citing Conference Paper
  • June 2012

... Base resource of reconfigurable plant [12,13] in the new paradigm factories becomes RMS in the cyber-physical systems family, which support flexible technologies, which almost completely exclude humans from the methodology of device manufacturing [14,15]. Reconfigurable plant designer key project problem in this case can be rounded down to justify the interoperability RMS selection and flexible technologies [16,17]. ...

Agent Oriented Construction of a Digital Factory for Validation of a Production Scenario

Procedia CIRP

... DAI, and specifically the Multi-Agent Systems (MASs) paradigm, is a relatively new specialization of distributed artificial intelligence and also one of its subfields which exert autonomous agents' behavior and complexities raised from different agent interactions, including cooperation or competition into the expert systems [26]. There are different problems and areas have been addressed using MAS, including health monitoring systems [42], simulating claims negotiations [38], traveling salesman problem (TSP) [54], and different scheduling schemes comprising manufacturing planning and scheduling [12], dynamic scheduling problem [51], job-shop scheduling problem [8], and project scheduling [14]. However, a few researches are focusing on the DAI application in SCM. ...

Agent based Manufacturing Simulation for Efficient Assembly Operations

Procedia CIRP

... Zhang et al. [36,37] integrated the agent-based methods with RFID technologies and workflow management to develop an event-driven real-time scheduling method in manufacturing systems. Sudo et al. [38] advanced an eventdriven negotiation method among agents for dynamic scheduling in an autonomous decentralized production system using product, parts, and assembly machine agents. Renna et al. [39] proposed a multi-agent coordination strategy for cellular manufacturing systems to react to real-time scheduling in dynamic environments. ...

An Agent Behavior Technique in an Autonomous Decentralized Manufacturing System
  • Citing Article
  • June 2010

Journal of Advanced Mechanical Design Systems and Manufacturing