Many machining monitoring systems based on artificial intelligence (AI) process models have been successfully developed in the past for optimising, predicting or controlling machining processes. In general, these monitoring systems present important differences among them, and there are no clear guidelines for their implementation. In order to present a generic view of machining monitoring systems and facilitate their implementation, this paper reviews six key issues involved in the development of intelligent machining systems: (1) the different sensor systems applied to monitor machining processes, (2) the most effective signal processing techniques, (3) the most frequent sensory features applied in modelling machining processes, (4) the sensory feature selection and extraction methods for using relevant sensory information, (5) the design of experiments required to model a machining operation with the minimum amount of experimental data and (6) the main characteristics of several artificial intelligence techniques to facilitate their application/selection.

A review of machining monitoring systems based on artificial intelligence process models

Machining is one of the most important and widely used manufacturing processes. Due to complexity and uncertainty of the machining processes, of late, soft computing techniques are being preferred to physics-based models for predicting the performance of the machining processes and optimizing them. Major soft computing tools applied for this purpose are neural networks, fuzzy sets, genetic algorithms, simulated annealing, ant colony optimization, and particle swarm optimization. The present paper reviews the application of these tools to four machining processes—turning, milling, drilling, and grinding. The paper highlights the progress made in this area and discusses the issues that need to be addressed.

Application of soft computing techniques in machining performance prediction and optimization: a literature review

In automated flexible manufacturing systems the detection of tool wear during the cutting process is one of the most important considerations. This study presents a comparison between several architectures of the multi-layer feed-forward neural network with a back propagation training algorithm for tool condition monitoring (TCM) of twist drill wear. The algorithm utilizes vibration signature analysis as the main and only source of information from the machining process. The objective of the proposed study is to produce a TCM system that will lead to a more efficient and economical drilling tool usage. Five different drill wear conditions were artificially introduced to the neural network for prediction and classification. The experimental procedure for acquiring vibration data and extracting features in both the time and frequency domains to train and test the neural network models is detailed. It was found that the frequency domain features, such as the averaged harmonic wavelet coefficients and the maximum entropy spectrum peaks, are more efficient in training the neural network than the time domain statistical moments. The results demonstrate the effectiveness and robustness of using the vibration signals in a supervised neural network for drill wear detection and classification.

Drilling wear detection and classification using vibration signals and artificial neural network

Fuzzy logic, neural networks, and evolutionary computation are the core methodologies of soft computing (SC). SC is causing a paradigm shift in engineering and science fields since it can solve problems that have not been able to be solved by traditional analytic methods. In addition, SC yields rich knowledge representation, flexible knowledge acquisition, and flexible knowledge processing, which enable intelligent systems to be constructed at low cost. This paper reviews applications of SC in several industrial fields to show the various innovations by TR, HMIQ, and low cost in industries that have been made possible by the use of SC. Our paper intends to remove the gap between theory and practice and attempts to learn how to apply soft computing practically to industrial systems from examples/analogy, reviewing many application papers.

/pdf/industrial-applications-of-soft-computing-a-review-45ao4h93ry.pdf

Industrial applications of soft computing: a review

This paper addresses the challenges inherent in root cause diagnosis of process variations in a production machining environment. We develop and present a process monitoring and diagnosis approach based on a Bayesian belief network for incorporating multiple process metrics from multiple sensor sources in sequential machining operations to identify the root cause of process variations and provide a probabilistic confidence level of the diagnosis. The vast majority of previous work in machining process monitoring has focused on single-operation tool wear monitoring. The focus of the present work is to develop a methodology for diagnosing the root cause of process variations that are often confounded in process monitoring systems, namely workpiece hardness, stock size, and tool wear variations. To achieve this goal, multiple sensor metrics have been identified with statistical correlations to the process faults of interest. Data from multiple sensors on sequential machining operations are then combined through a causal belief network framework to provide a probabilistic diagnosis of the root cause of the process variation.

A Bayesian network approach to root cause diagnosis of process variations

Tool wear condition monitoring has the potential to play a critical role in ensuring the dimensional accuracy of the workpiece and prevention of damage to cutting equipment. It could also help in automating cutting processes. In this paper, the feed cutting force estimated with the aid of an inexpensive current sensor installed on the AC servomotor of a computerized numerical control tuning center is used to monitor tool wear condition. To achieve this, the feed drive system is modeled, using neuro-fuzzy techniques, to provide the framework for estimating the feed cutting force based on the feed motor current measured. Functional dependence of the feed cutting force on tool wear and cutting parameters are then expressed in the form of a difference equation relating variation in the feed cutting force to tool wear rate. The computerized system automatically compares successive feed cutting force estimates and determines the onset of accelerated tool wear in order to issue a request for tool replacement. Experimental results show that the tool wear condition monitoring is effective and industrially applicable.

/pdf/current-sensor-based-feed-cutting-force-intelligent-2fk65cqkz5.pdf

Current-sensor-based feed cutting force intelligent estimation and tool wear condition monitoring

In automated manufacturing systems such as flexible manufacturing systems (FMSs), one of the most important issues is the detection of tool wear during the cutting process. This paper presents a hybrid learning method to map the relationship between the features of cutting vibration and the tool wear condition. The experimental results show that it can be used effectively to monitor the tool wear in drilling. First, a neural network model with fuzzy logic (FNN), responding to learning algorithms, is presented. It has many advantageous features, compared to a backpropagation neural network, such as less computation. Secondly, the experimental results show that the frequency distribution of vibration changes as the tool wears, so the r.m.s. of the different frequency bands measured indicates the tool wear condition. Finally, FNN is used to describe the relationship between the characteristics of vibration and the tool wear condition. The experimental results demonstrate the feasibility of using vibration signals to monitor the drill wear condition.

https://lixiaoli.tripod.com/papers/IJAMT001.pdf

Hybrid Learning for Tool Wear Monitoring

It is very important to use reliable and inexpensive sensors to obtain useful information about manufacturing processing, such as cutting force, for monitoring automated machining. In this paper, the feed cutting force is measured using an inexpensive current sensor installed on the a.c. servo motor of a CNC turning centre. The factors that affect a feed drive system are analysed in detail, and a model of the feed drive system for estimating feed cutting force is presented. The feed cutting force is estimated using feed motor current measurement and neuro-fuzzy techniques. Experimental results demonstrate that this method can accurately estimate feed cutting force within an error of 5%.

/pdf/feed-cutting-force-estimation-from-the-current-measurement-857tckgnav.pdf

Feed Cutting Force Estimation from the Current Measurement with Hybrid Learning

A recent model-based approach for predicting the compensation required on the next part to be turned on a CNC machine solely on the basis of three independent measurements conducted at selected locations on a limited set of previously machined parts under a similar cutting set-up is reviewed. A new method of achieving the same objective through the use of the learning capability of an adaptive neuro-fuzzy network is developed and tested against experimental data for cylindrical turning. This method requires only one on-machine measurement per sample. It is conducted by a novel contact sensor that probes with the tool and facilitates automation by providing proximity information as the tool approaches the workpiece.

/pdf/predicting-machining-errors-in-turning-using-hybrid-learning-q1bii3738j.pdf

P.K. Venuvinod

Papers

Current-sensor-based feed cutting force intelligent estimation and tool wear condition monitoring

Hybrid Learning for Tool Wear Monitoring

Feed Cutting Force Estimation from the Current Measurement with Hybrid Learning

Predicting Machining Errors in Turning Using Hybrid Learning