Yasser Shaban

Process control based on pattern recognition for routing carbon fiber reinforced polymer

Carbon fiber reinforced polymer (CFRP) is an important composite material. It has many applications in aerospace and automotive fields. The little information available about the machining process of this material, specifically when routing process is considered, makes the process control quite difficult. In this paper, we propose a new process control technique and we apply it to the routing process for that important material. The measured machining conditions are used to evaluate the quality and the geometric profile of the machined part. The machining conditions, whether controllable or uncontrollable are used to control part accuracy and its quality. We present a pattern-based machine learning approach in order to detect the characteristic patterns, and use them to control the quality of a machined part at specific range. The approach is called logical analysis of data (LAD). LAD finds the characteristic patterns which lead to conforming products and those that lead to nonconforming products. As an example, LAD is used for online control of a simulated routing process of CFRP. We introduce the LAD technique, we apply it to the high speed routing of woven carbon fiber reinforced epoxy, and we compare the accuracy of LAD to that of an artificial neural network, since the latter is the most known machine learning technique. By using experimental results, we show how LAD is used to control the routing process by tuning autonomously the routing conditions. We conclude with a discussion of the potential use of LAD in manufacturing.

Predicting the remaining useful life of a cutting tool during turning titanium metal matrix composites

A cutting tool’s remaining useful life is what is left for a tool, at a particular working age, in order to reach a pre-specified level of acceptable performance. The prediction of remaining useful life is crucial in order to decrease the scrapped products or the unnecessary interruption of the machining process in order to replace the tool. Consequently, the accuracy of its estimation affects the cost of machining, particularly when the product’s material is very expensive. In this article, the remaining useful lifes of 25 identical tools are estimated during turning titanium metal matrix composites. These composites are extensively used in aerospace and aviation industries. Accurate estimation of the remaining useful life has positive impact on product quality in terms of producing the required specifications. In this article, experimental data are gathered, and the proportional hazard model are used in order to model the tool’s reliability and hazard functions with EXAKT software and then the remaining useful life curves are developed for different machining conditions, namely, the cutting speed and the feed rate. The use of the proportional hazard model is validated using a normalization process and Kolmogorov–Smirnov test. The proportionality assumption is verified using log minus log plot. The final result is the development of the curves that represent the tools’ reliability and the remaining useful life for different machining conditions of the titanium metal matrix composites.

Survival life analysis applied to tool life estimation with variable cutting conditions when machining titanium metal matrix composites (Ti-MMCs)

Abstract A survival analysis methodology is employed through a novel approach to model the progressive states of tool wear under different cutting conditions during machining of titanium metal matrix composites (Ti-MMCs). A proportional hazards model (PHM) with a Weilbull baseline is developed to estimate the reliability and hazard functions of the cutting inserts. A proper criterion is assigned to each state of tool wear and used to calculate the tool life at the end of each state. Accounting for the machining time and different stages of tool wear, in addition to the effect of cutting parameters, an accurate model is proposed. Investigating the results obtained for different states, it was shown that the evolution of the time-dependent phenomena, such as different tool wear mechanisms, throughout the whole machining process were also reflected in the model. The accuracy and reliability of the predicted tool lives were experimentally validated. The results showed that the model gives very good estimates of tool life and the critical points at which changes of states take place.

Diagnosis of machining outcomes based on machine learning with Logical Analysis of Data

Force is considered to be one of the indicators that best describe the machining process. Measured force can be used to evaluate the quality and geometric profile of the machined part. In this paper, a combinatorial optimization approach is used to characterize the effect of force on the quality of a machined part made of Carbon Fiber Reinforced Polymers (CFRP) material. The approach is called Logical Analysis of Data (LAD) and is based on machine learning and pattern recognition. LAD is used in order to map the machining conditions, in terms of force and torque that lead to conforming products and those which lead to nonconforming products. In this paper, the LAD technique is applied to the drilling of CFRP plates, and the results, based on data obtained experimentally, are reported. A discussion of the potential use of LAD in manufacturing concludes the paper.

Tool Wear Monitoring and Alarm System Based on Pattern Recognition With Logical Analysis of Data

This paper presents a new tool wear monitoring and alarm system that is based on logical analysis of data (LAD). LAD is a data-driven combinatorial optimization technique for knowledge discovery and pattern recognition. The system is a nonintrusive online device that measures the cutting forces and relates them to tool wear through learned patterns. It is developed during turning titanium metal matrix composites (TiMMCs). These are a new generation of materials which have proven to be viable in various industrial fields such as biomedical and aerospace. Since they are quite expensive, our objective is to increase the tool life by giving an alarm at the right moment. The proposed monitoring system is tested by using the experimental results obtained under sequential different machining conditions. External and internal factors that affect the turning process are taken into consideration. The systems alarm limit is validated and is compared to the limit obtained when the statistical proportional hazards model (PHM) is used. The results show that the proposed system that is based on using LAD detects the worn patterns and gives a more accurate alarm for cutting tool replacement.

Optimal replacement times for machining tool during turning titanium metal matrix composites under variable machining conditions

Little practical results are known about the cutting tool optimal replacement time, specifically for machining of composite materials. Due to the fact that tool failure represents about 20% of machine down-time, and due to the high cost of machining, in particular when the work piece’s material is very expensive, optimization of tool replacement time is thus fundamental. Finding the optimal replacement time has also positive impact on product quality in terms of dimensions and surface finish. In this article, two new contributions to research on tool replacement are introduced. First, tool replacement mathematical models are proposed. These models are used in order to find the optimal time to tool replacement when the tool is used under variable machining conditions, namely, the cutting speed and the feed rate. Proportional hazards models are used to find an optimal replacement function. Second, this model is obtained during turning titanium metal matrix composites. These composites are a new generation of materials which have proven to be viable in various industrial fields such as biomedical and aerospace, and they are very expensive. Experimental data are obtained and used in order to develop and to validate the proportional hazards models, which are then used to find the optimal replacement conditions.

Analysis of massive industrial data using MapReduce framework for parallel processing

With the emergence of the ‘Big Data’ paradigm, more and more industrial data are now available for practitioners and professionals. This data is being generated faster due to the advancement of the new information technologies. For reliability and maintenance engineers, ‘Big Data’ is an interesting source of information. If analyzed correctly, it can produce useful knowledge-base to help making decisions in an industrial organization. The availability of ‘Big Data’ is now leading to a new area of researches that are dedicated to the analysis of such data. This paper shows how to analyze massive amount of data generated from an industrial system(s). Those massive data may range from terabytes to petabytes in size; analyzing such sizes cannot be performed on a single commodity computer due to the possibility of memory leakage as the data may not fit into the computers resources, specifically CPUs. Even if it fits, it will take an unacceptable amount of time. For this purpose, processing industrial large size of data requires the involvement of high performance analytical systems running on distributed environments. Different algorithms can be considered to have such analysis done. Cloud Computing models provide the necessary scalable and flexible infrastructure(s) to adapt the standard analytics algorithms in a distributed manner. We introduce a new distributed training technique that combines the newly widely used framework for big dataflow, namely MapReduce, with the traditional structure of machine learning techniques such as matrix multiplication and linear regression. Parallel processing of the aforementioned types is based on different algorithms to be adapted to MapReduce and its framework. Our considered platform is deployed on top of Google Cloud Platform (App Engine and Compute Engine), also taking into consideration Cloud Amazon EMR services to see how we can benefit from the provisioned resources in each one of them, and make the analysis and the extraction of useful information from the massive industrial data goes faster, i.e. in its computational time.

Condition-based reliability prediction based on logical analysis of survival data

This paper presents a novel approach for incorporating condition information based on historical data into the development of reliability curves. The approach uses a variation of Kaplan-Meier (KM) estimator and degradation-based estimators of survival patterns. From a statistical perspective, the use of KM estimator to create a reliability curve of a specific type of equipment, results in a general curve that does not take into consideration the instantaneous condition of each individual equipment. The proposed degradation-based estimator updates the KM estimator in order to capture the actual condition of equipment based on the detected patterns. These patterns identify interactions between condition indicators. The degradation-based reliability curves are obtained by a new methodology called ‘Logical Analysis of Survival Data (LASD). LASD identifies interactions between condition indicators without any prior hypotheses. It generates patterns based on machine learning and pattern recognition technique. Using these set of patterns, survival curves, which can predict the reliability of any device at any time based on its actual condition, are developed. To evaluate the LASD approach, it was applied to experimental results that represent cutting tool degradation during turning TiMMCs with condition monitoring. The performance of the LASD when compared to the traditional Kaplan-Meier based reliability curve improves the reliability prediction.