A Cloud Computing-Based Approach for Efficient Processing of Massive Machine Tool Diagnosis Data

2021 ◽  
pp. 2150297
Author(s):  
Heng Li ◽  
Xiaoyang Zhang ◽  
Shuyin Tao
Keyword(s):  
Cloud Computing ◽  
Tool Wear ◽  
Data Processing ◽  
Machine Tool ◽  
Execution Time ◽  
Machine Tools ◽  
Visual Detection ◽  
Detection Method ◽  
Image Block ◽  
Local Threshold

This paper proposes a cloud computing-based approach to efficiently process the massive data produced in intelligent machine tool diagnosis flow. By collecting and extracting the vibration, power and other useful system signals during the machining operation of machine tools, the cutting process samples and cutting gap samples of machine tools can be accurately segmented, in order to construct a set of signal samples that can effectively and completely characterize the level of tool wear. We propose a visual detection method that relies on local threshold segmentation to predict tool wear status. The machine tool image is divided into several small blocks, and each image block is segmented to obtain the segmentation threshold, which is defined as the local threshold of each block. Then, the detection method scans the whole image based on the maximum local threshold among all blocks. Considering the complicated flow of visual detection and the high volume of machine tool diagnosis data, we further propose a big data processing approach which is implemented on a cloud computing architecture. By modeling the workflow of the proposed visual detection method as a directed acyclic graph, we develop a scheduling model that aims at minimizing the execution time of massive tool diagnosis data processing with available cloud computing resources. A effective metaheuristic based on search strategy of artificial bee colony is developed to solve the formulation scheduling problem. Experimental results on a cloud-based system demonstrate that, the visual detection method enhances the accuracy of tool wear detection, and the cloud-based approach significantly reduces the execution time of tool diagnosis flow by means of distributed computing.

scholarly journals Recurrent neural networks with long term temporal dependencies in machine tool wear diagnosis and prognosis

2021 ◽  
Vol 3 (4) ◽  
Author(s):  
Jianlei Zhang ◽  
Yukun Zeng ◽  
Binil Starly
Keyword(s):  
Neural Network ◽  
Tool Wear ◽  
Machine Tool ◽  
Recurrent Neural Network ◽  
Machine Tools ◽  
Prediction Performance ◽  
Sequential Data ◽  
Diagnosis And Prognosis ◽  
Proposed Model

AbstractData-driven approaches for machine tool wear diagnosis and prognosis are gaining attention in the past few years. The goal of our study is to advance the adaptability, flexibility, prediction performance, and prediction horizon for online monitoring and prediction. This paper proposes the use of a recent deep learning method, based on Gated Recurrent Neural Network architecture, including Long Short Term Memory (LSTM), which try to captures long-term dependencies than regular Recurrent Neural Network method for modeling sequential data, and also the mechanism to realize the online diagnosis and prognosis and remaining useful life (RUL) prediction with indirect measurement collected during the manufacturing process. Existing models are usually tool-specific and can hardly be generalized to other scenarios such as for different tools or operating environments. Different from current methods, the proposed model requires no prior knowledge about the system and thus can be generalized to different scenarios and machine tools. With inherent memory units, the proposed model can also capture long-term dependencies while learning from sequential data such as those collected by condition monitoring sensors, which means it can be accommodated to machine tools with varying life and increase the prediction performance. To prove the validity of the proposed approach, we conducted multiple experiments on a milling machine cutting tool and applied the model for online diagnosis and RUL prediction. Without loss of generality, we incorporate a system transition function and system observation function into the neural net and trained it with signal data from a minimally intrusive vibration sensor. The experiment results showed that our LSTM-based model achieved the best overall accuracy among other methods, with a minimal Mean Square Error (MSE) for tool wear prediction and RUL prediction respectively.

scholarly journals Active vibration control for a CNC milling machine

2013 ◽  
Vol 228 (2) ◽  
pp. 230-245 ◽  
Author(s):  
DG Ford ◽  
A Myers ◽  
F Haase ◽  
S Lockwood ◽  
A Longstaff
Keyword(s):  
Control System ◽  
Tool Wear ◽  
Machine Tool ◽  
Vibration Control ◽  
Surface Finish ◽  
Machine Tools ◽  
Active Vibration Control ◽  
Milling Machine ◽  
Cnc Machine ◽  
Active Vibration

There is a requirement for improved three-dimensional surface characterisation and reduced tool wear when modern computer numerical control (CNC) machine tools are operating at high cutting velocities, spindle speeds and feed rates. For large depths of cut and large material removal rates, there is a tendency for machines to chatter caused by self-excited vibration in the machine tools leading to precision errors, poor surface finish quality, tool wear and possible machine damage. This study illustrates a method for improving machine tool performance by understanding and adaptively controlling the machine structural vibration. The first step taken is to measure and interpret machine tool vibration and produce a structural model. As a consequence, appropriate sensors need to be selected and/or designed and then integrated to measure all self-excited vibrations. The vibrations of the machine under investigation need to be clearly understood by analysis of sensor signals and surface finish measurement. The active vibration control system has been implemented on a CNC machine tool and validated under controlled conditions by compensating for machine tool vibrations on time-varying multi-point cutting operations for a vertical milling machine. The design of the adaptive control system using modelling, filtering, active vibration platform and sensor feedback techniques has been demonstrated to be successful.

scholarly journals A Study on Proposal of Flank Wear Criterion by Using a Built-in Current Sensor when Manufacturing the Mold Materials in a Smart Machine Tool

2018 ◽  
Vol 207 ◽  
pp. 03007
Author(s):  
Seung-Yub Baek ◽  
Sung-Taek Jung ◽  
Dae-Yu Park
Keyword(s):  
Tool Wear ◽  
Machine Tool ◽  
Machine Tools ◽  
High Efficiency ◽  
Flank Wear ◽  
Acoustic Emissions ◽  
Measuring Method ◽  
Current Signal ◽  
Flank Face ◽  
Smart Machine

Recently, it has been increased with respect to the safe and reliable operations in industry of machine tools and intelligent of the machine tool has consistently been developing in term of an unmanned manufacturing. For such realization, diagnosis monitoring of machining must be carried out while being processed in real-time. When tool wear is reached to criteria of flank wear and crater wear, the tools must be changed to new tools for improving the manless rate of operation. However, time of tool change was when spark generated because of wear about 0.3 mm on a flank face during manufacturing in the field. So, built-in sensor system in a smart machine tool must be necessary for high efficiency unmanned of manufacturing. As mentioned earlier, the various technique for measuring the tool wear was already defined such as sensing of acoustic emissions, vibrations, sounds, currents, cutting force, and other. The representative one of measuring method is current signal, which is used as a representative index of tool state. In this study, we carried out the proposal of tool wear criterion by using built-in wireless current signal system when manufacturing the mold materials of KP-4M and it was investigated via smart machine tools.

Application of Ubiquitous Sensor Network in Collection and Analysis of CNC Machine Tool Processing Status Information

2010 ◽  
Vol 455 ◽  
pp. 621-624
Author(s):  
X. Li ◽  
Y.Y. Yu
Keyword(s):  
Machine Tool ◽  
Sensor Network ◽  
Machine Tools ◽  
Thermal Error ◽  
Development Trend ◽  
Cnc Machine Tools ◽  
Cnc Machine Tool ◽  
Cnc Machine ◽  
Status Information ◽  
The Development Trend

Because of the practical requirement of real-time collection and analysis of CNC machine tool processing status information, we discuss the necessity and feasibility of applying ubiquitous sensor network(USN) in CNC machine tools by analyzing the characteristics of ubiquitous sensor network and the development trend of CNC machine tools, and application of machine tool thermal error compensation based on USN is presented.

Efficiency Improvement of Metal Lathing by Using of an Evaluation Technique of Assembly Machine Tools Quality

2016 ◽  
Vol 684 ◽  
pp. 421-428 ◽  
Author(s):  
D.S. Vasilega ◽  
M.S. Ostapenko
Keyword(s):  
Machine Tool ◽  
Machine Tools ◽  
Quality Evaluation ◽  
Composite Index ◽  
Production Operation ◽  
Evaluation Technique ◽  
Efficiency Improvement ◽  
Index Of Quality

They defined conditions of use, calculated a composite index of quality for different tools, chose a machine tool according to its quality evaluation, calculated efficiency of processing by tools with different parameters for a certain production operation.

A conceptual framework for product service system design for machine tools

2016 ◽  
Vol 23 (5) ◽  
pp. 1227-1248 ◽  
Author(s):  
Pankaj U. Zine ◽  
Makarand S Kulkarni ◽  
Arun K. Ray ◽  
Rakesh Chawla
Keyword(s):  
Machine Tool ◽  
Conceptual Framework ◽  
Machine Tools ◽  
Business Models ◽  
Service System ◽  
Product Service System ◽  
Content Type ◽  
Business Context ◽  
Product Service ◽  
Key Issues

Purpose – The purpose of this paper is to propose a conceptual framework for product service system (PSS) design for machine tools and discuss the PSS implementation issues focusing on the Indian machine tool business sector. Design/methodology/approach – The paper opted for an exploratory survey conducted in the Indian machine tool sector including 39 in-depth interviews with employees of different organizations representing middle and senior management having decision-making authority. It also involves proposing a framework to address the stakeholder’s requirements for services that offers foundation for PSS designers. Findings – The paper helps get an insights about key issues for PSS implementation by the Indian machine tool sector. The hybrid PSS model proposed in the paper can address the stakeholder’s requirements for flexibility in business models through different business phases. Practical implications – The paper offers suggestions for the development of PSS for machine tools for designers and identify issues to be considered particularly in Indian machine tools business context. Originality/value – This paper provides an insight to judge the feasibility of PSS concept for machine tools in Indian context and offers framework for PSS designers.

Sign in / Sign up

Export Citation Format

Share Document