Fig 1 - uploaded by Atsushi Yoshikawa
Content may be subject to copyright.
Source publication
This paper presents a real time workers' behavior analyzing system using wearable sensors which combine Bluetooth low energy beacon (Beacon) and acceleration sensor to measure production progress and work history data in a cellular manufacturing system. It takes a lot of cost to collect those data on the cellular manufacturing line where workers' w...
Contexts in source publication
Context 1
... expertise and takes too much cost. Besides, in sensing workers by a video image analysis, it is difficult to adjust analysis parameters, and it is impossible to measure the data when the worker moves to the blind spot. For these reasons, it is difficult to collect production progress and work history data in a cellular manufacturing system ( Fig. 1) that assembles complicated products by workers, and there are much time and effort to improve production efficiency. This paper presents a real time workers' behavior analyzing system using wearable sensors which combine Bluetooth low energy beacon (Beacon) and acceleration sensors to measure production progress and work history data ...
Context 2
... Exp. 3rd Exp. Production cycle time collection ratio (%) 90.0 78.7 Production cycle time MAE (s) 3.7 9.2 Abnormal work accuracy (%) 67.4 67.4 Total accuracy (%) 60.7 53.0 Sampling rate (data/s) 1.7 1.6 Calculation time (s) 13.54 13.72 Fig. 10 The time series result of one worker in 2nd ...
Context 3
... our system took only approximately 13 s to complete, therefore it is much more effective than the visual method. Figure 10 is a time-series graph of the cycle time of one worker in the second experiment by the visual method and our system. The moving average and the value difference of the cycles are also shown in the graph. ...
Context 4
... a product. Since our system took only approximately 13 s to complete, therefore it is much more effective than the visual method. Figure 10 is a time-series graph of the cycle time of one worker in the second experiment by the visual method and our system. The moving average and the value difference of the cycles are also shown in the graph. In Fig. 10, the worker decreases the cycle time at around the 25th product compared with the production start. Thereafter, the worker manufactured the product almost in the same cycle ...
Context 5
... the other hand, the calculation time has been significantly shortened compared with the conventional visual method, and it seems that it contributes greatly to the efficiency of data collection. It is expected that the merit of this system will be further improved by improving accuracy in the future. Furthermore, in Fig. 10, a decrease of the cycle time seems to indicate the effect of proficiency of the worker. The ability to display such time-series results in real time is an advantage of using our system. Moreover, the motion will be slowed by worker fatigue and the accuracy of the work will be deteriorated [27], [28]. From Fig. 10, in the second half ...
Context 6
... the motion will be slowed by worker fatigue and the accuracy of the work will be deteriorated [27], [28]. From Fig. 10, in the second half of the experiment, the worker manufactured the product almost in the same cycle time. Even other workers, we could not see the cycle time nor the accuracy of the work was deteriorated. ...
Context 7
... of one product. This time included the data loading time, RSSI analysis time, and acceleration analysis time. Our sys- tem can measure them automatically. Thus, the measurement cost is significantly lower than the visual method. However, if it takes a long time to analyze the data, its usefulness will de- crease. The measurement time of the visual method was about 30 s per a product. Since our system took only approximately 13 s to complete, therefore it is much more effective than the visual method. Figure 10 is a time-series graph of the cycle time of one worker in the second experiment by the visual method and our system. The moving average and the value difference of the cycles are also shown in the graph. In Fig. 10, the worker de- creases the cycle time at around the 25th product compared with the production start. Thereafter, the worker manufactured the product almost in the same cycle ...
Context 8
... of one product. This time included the data loading time, RSSI analysis time, and acceleration analysis time. Our sys- tem can measure them automatically. Thus, the measurement cost is significantly lower than the visual method. However, if it takes a long time to analyze the data, its usefulness will de- crease. The measurement time of the visual method was about 30 s per a product. Since our system took only approximately 13 s to complete, therefore it is much more effective than the visual method. Figure 10 is a time-series graph of the cycle time of one worker in the second experiment by the visual method and our system. The moving average and the value difference of the cycles are also shown in the graph. In Fig. 10, the worker de- creases the cycle time at around the 25th product compared with the production start. Thereafter, the worker manufactured the product almost in the same cycle ...
Context 9
... Exp. 3rd Exp. Production cycle time collection ratio (%) 90.0 78.7 Production cycle time MAE (s) 3.7 9.2 Abnormal work accuracy (%) 67.4 67.4 Total accuracy (%) 60.7 53.0 Sampling rate (data/s) 1.7 1.6 Calculation time (s) 13.54 13.72 Fig. 10 The time series result of one worker in 2nd ...
Context 10
... the other hand, the calculation time has been significantly shortened compared with the conventional visual method, and it seems that it contributes greatly to the efficiency of data collec- tion. It is expected that the merit of this system will be further improved by improving accuracy in the future. Furthermore, in Fig. 10, a decrease of the cycle time seems to indicate the effect of proficiency of the worker. The ability to display such time-series results in real time is an advantage of using our sys- tem. Moreover, the motion will be slowed by worker fatigue and the accuracy of the work will be deteriorated [27], [28]. From Fig. 10, in the second half of the experiment, the worker manufactured the product almost in the same cycle time. Even other workers, we could not see the cycle time nor the accuracy of the work was deteriorated. Therefore, the effect of fatigue could not be confirmed in this experiment. However, we be- lieve that it is highly possible to observe the effects of fatigue in real time by collecting the data with our system for a long ...
Context 11
... the other hand, the calculation time has been significantly shortened compared with the conventional visual method, and it seems that it contributes greatly to the efficiency of data collec- tion. It is expected that the merit of this system will be further improved by improving accuracy in the future. Furthermore, in Fig. 10, a decrease of the cycle time seems to indicate the effect of proficiency of the worker. The ability to display such time-series results in real time is an advantage of using our sys- tem. Moreover, the motion will be slowed by worker fatigue and the accuracy of the work will be deteriorated [27], [28]. From Fig. 10, in the second half of the experiment, the worker manufactured the product almost in the same cycle time. Even other workers, we could not see the cycle time nor the accuracy of the work was deteriorated. Therefore, the effect of fatigue could not be confirmed in this experiment. However, we be- lieve that it is highly possible to observe the effects of fatigue in real time by collecting the data with our system for a long ...
Context 12
... kinds of data can be collected at the factory. Among the data, production progress and work history data on a manu- facturing floor are very important because they influence whole production efficiency indices, which are the quality, the cost, and the delivery. To gather these data, it is necessary to sense materials, machines, and workers, which are constituent ele- ments of the manufacturing floor. However, attaching sensors to materials increases the cost directly, and a machine can not measure the process which does not use the machine. Further- more, in sensing workers by an engineer's visual method, it requires expertise and takes too much cost. Besides, in sensing workers by a video image analysis, it is difficult to adjust anal- ysis parameters, and it is impossible to measure the data when the worker moves to the blind spot. For these reasons, it is dif- ficult to collect production progress and work history data in a cellular manufacturing system ( Fig. 1) that assembles compli- cated products by workers, and there are much time and effort to improve production efficiency. This paper presents a real time workers' behavior analyzing system using wearable sensors which combine Bluetooth low energy beacon (Beacon) and acceleration sensors to measure production progress and work history data in cellular manu- facturing systems. Our system has two analyzing methods of workers' behavior, 1) analyzing workers' position from Bea- con's received signal strength index to measure production progress, 2) analyzing workers' movements from acceleration sensor data to measure work history. For that purpose we first built an experimental cellular manufacturing line and collected workers' behavioral data. Next, we developed our system and determined analyzing parameters using the workers' behavioral data. Finally, we built another experimental cellular manufac- turing line, and we measured production progress and work his- tory data from our system. We then compared the result with a conventional visual method using video. The results revealed that our system is able to measure the productivity data in the cellular manufacturing line which does not use a machine, and we were able to gather production progress and work history data more quickly than the conventional visual method. We believe that our system will make it possible to increase the ef- ficiency of the supply chain system, to get a quick feedback in daily production, and to improve ...
Similar publications
This paper describes a dataset acquired on 8 subjects while simulating 13 types of falls and 5 types of Activities of Daily Living (ADL), each repeated 3 times. In details, data includes 4 simulated falls forward (falling on knees ending up lying, ending in lateral position, ending up lying, ending up lying with recovery), 4 backward (falling sitti...
Purpose
We fabricated a wearable patch including a novel patch-type flexible dry electrode based on carbon nanofibers (CNFs) and biocompatible PDMS (MED-6215) for long-term bio-potential monitoring.
Methods
The patch comprises dry electrode parts for recording bio signals and sticky parts for skin mounting. To evaluate electrical characteristics a...
Increased life expectancy coupled with declining birth rates is leading to an aging population structure. Aging-caused changes, such as physical or cognitive decline, could affect people’s quality of life, result in injuries, mental health or the lack of physical activity. Sensor-based human activity recognition (HAR) is one of the most promising a...
The increase of Internet of Things (IoT) means more active user devices on the Internet. IoT devices can be everyday objects from vehicles, smart phones to wearable sensors. Massive amounts of data are generated by IoT devices through the collection and transmission of data needed for the output of useful outcomes and therefore, an efficient way to...
Citations
... Since online decisions must be made as soon as the problems are identified in the system, RTS frameworks are based on real-time input data acquired while the real system is evolving. Kitazawa et al. [29] used RTS to estimate the completion time of a flow shop manual assembly. The data is collected by Bluetooth-based beacons to record the proximity of operators to their workstation. ...
The latest developments in industry have involved the deployment of digital
twins for both long and short term decision-making, such as supply chain
management and production planning and control. The ability to take appropriate
decisions online is strongly based on the assumption that digital models
are properly aligned with the real system at any time. As modern production
environments are frequently subject to disruptions and modifications, the
development of digital twins of manufacturing systems cannot rely solely on
manual efforts. Industry 4.0 has contributed to the rise of new technologies
for data acquisition, storing and communication, allowing for the knowledge
of the shop floor status at anytime. If a model could be generated from the
available data in a manufacturing system, the development phase may be significantly
shortened. However, practical implementations of automated model
generation approaches remain scarce. It is also true that automatically built
representations may be excessively accurate and describe activities that are
not significant for estimating the system performance. Hence, the generation
of models with an appropriate level of detail can avoid useless efforts and long
computation times, while allowing for easier understanding and re-usability.
This research focuses on the development and adoption of automated
model generation techniques for obtaining simulation-based digital models
starting from the data logs of manufacturing systems, together with methods to
adjust the models toward a desired level of detail. The properties and parameters
of the manufacturing system, such as buffer sizes, are estimated from data
through inference algorithms. The system properties are also used in a model
tuning approach, which generates an adjusted model starting from the available
knowledge and the user requirements in terms of complexity (e.g., number
of stations). In addition, a lab-scale environment has been built with the
aim to test decision-making frameworks based on digital twins within a realistic
data infrastructure. The experimental results prove the effectiveness of the
proposed methodology in generating proper digital models that can correctly
estimate the performance of a manufacturing system. The model generation
and tuning method can positively contribute to real-time simulation. Indeed, its application within an online framework of production planning and control allows
for adapting simulation models to the real system, potentially at any time
a modification occurs. This way, decisions taken online are guaranteed to be
referring to the current state of the factory. Thanks to this research, manufacturing
enterprises will be able to reach a higher production flexibility, together
with higher responsiveness to technological changes and market-demand fluctuations.
... Since online decisions must be made as soon as the problems are identified in the system, RTS frameworks are based on real-time input data acquired while the real system is evolving. Kitazawa et al. [16] used RTS to estimate the completion time of a flow shop manual assembly. The data is collected by Bluetooth-based beacons to record the proximity of operators to their workstation. ...
In the last years, the increase of data availability together with enhanced computation capabilities empowered researchers to conceive production planning and control methods with real-time inputs. Literature is rich with techniques for using simulation to take production planning and control decisions online. However, it is generally impractical to test these approaches on real systems , and experiments on digital instances are limited because they do not capture the physical aspects. This work proposes to test Real-time Simulation approaches using lab-scale models of manufacturing system and a software architecture aligned with industrial standards. Such models allow to reproduce material flows and the production control logic of real factory environments. By exploiting this setting to test new approaches and tools, it is possible to increase their own achievable Technology Readiness Level (TRL). The laboratory has been used to set a real-time rescheduling problem on a Flexible Manufacturing System (FMS) model. The test involves simulation models aligned with the current system state for the online identification and implementation of a production scheduling rule that decreases the expected makespan. The results testify that the proposed lab-scale models can be used successfully to test production planning and control approaches.
