Dragan Djurdjanovic

Sustainability in manufacturing: Recovery of resources in product and material cycles

Global Framework.- Life Cycle Engineering and Management.- Product Development.- Processes and Tools for Disassembly.- Planning for Remanufacturing and Recycling.- Enabling for Sustainability in Engineering.- Roadmap.

Maintenance scheduling in manufacturing systems based on predicted machine degradation

In this paper, we propose a new method for scheduling of maintenance operations in a manufacturing system using the continuous assessment and prediction of the level of performance degradation of manufacturing equipment, as well as the complex interaction between the production process and maintenance operations. Effects of any maintenance schedule are evaluated through a discrete-event simulation that utilizes predicted probabilities of machine failures in the manufacturing system, where predicted probabilities of failure are assumed to be available either from historical equipment reliability information or based on the newly available predictive algorithms. A Genetic Algorithm based optimization procedure is used to search for the most cost-effective maintenance schedule, considering both production gains and maintenance expenses. The algorithm is implemented in a simulated environment and benchmarked against several traditional maintenance strategies, such as corrective maintenance, scheduled maintenance and condition-based maintenance. In all cases that were studied, application of the newly proposed maintenance scheduling tool resulted in a noticeable increase in the cost-benefits, which indicates that the use of predictive information about equipment performance through the newly proposed maintenance scheduling method could result in significant gains obtained by optimal maintenance scheduling.

Similarity based method for manufacturing process performance prediction and diagnosis

Full realization of all the potentials of predictive maintenance highly depends on the accuracy of long-term predictions of the remaining useful life of manufacturing equipments. In this paper, we propose a new method that is capable of achieving high long-term prediction accuracy by comparing signatures from any two degradation processes using measures of similarity that form a match matrix (MM). Through this concept, we can effectively include large amounts of historical information into the prediction of the current degradation process. Similarities with historical records are used to generate possible future distributions of features indicative of process performance, which are then used to predict the probabilities of failure over time by evaluating overlaps between predicted feature distributions and feature distributions related to unacceptable equipment behavior. The analysis of experimental results shows that the proposed method can yield a noticeable improvement of long-term prediction accuracy in terms of mean prediction errors over the Elman Recurrent Neural Network (ERNN) based prediction, which was shown in the past literature to predict well behavior of highly non-linear and non-stationary time series.

Dimensional errors of fixtures, locating and measurement datum features in the stream of variation modeling in machining

Machining processes are usually multi-station processes involving a large number of operations and several locating datum changes. Machining errors are thus introduced, transformed and accumulated as the workpiece is being machined. This paper introduces procedures for expressing the influence of errors in fixtures, locating datum features and measurement datum features on dimensional errors in machining. These procedures are essential in the derivation of the Stream of Variation model of dimensional machining errors using the CAD/CAPP parameters of the machining process. The linear state space form of the Stream of Variation model allows for advanced control theory achievements to be employed in formal solutions to problems in multi-station machining. Modeling procedures presented in this paper were experimentally verified in machining of an automotive cylinder head.

Time-Frequency Based Sensor Fusion in the Assessment and Monitoring of Machine Performance Degradation

Machines degrade as a result of aging and wear, which decreases their performance reliability and increases the potential for faults and failures. In contemporary manufacturing it becomes increasingly important to predict and prevent machine failures, rather than allowing the machine to fail and then fixing the failure. In this paper, methods of time-frequency signal analysis will be used to capture information from multiple machine sensors. This information could be used to assess machine performance degradation and subsequently take appropriate action. Signals emanating from three different sensors were collected when a sharp and a worn tool have been mounted on a CNC lathe machine. Several combinations of sensors and signal features have been tried in order to demonstrate the ability to use the information from multiple sensors and increase sensitivity to tool wear.© 2002 ASME

Maintenance Priority Assignment Utilizing On-line Production Information

Maintenance management has a direct influence on production performance. Existing works have not systematically taken the on-line production information into consideration in determining maintenance work-order priority, which is often assigned either through an ad hoc approach or using largely heuristic and static methods. In this paper, we first present a metric that can be used to quantitatively evaluate the effects of different maintenance priorities. Based on this index, one can employ a search algorithm to obtain maintenance work-order priorities that will lead to improved productivity within the optimization horizon. These concepts and methods are validated through simulation experiments and implementation in a real industrial facility. The results show that the effective utilization of on-line production data in dynamic maintenance scheduling can yield visible production benefit through maintenance priority optimization.

Multisensor process performance assessment through use of autoregressive modeling and feature maps

This paper presents an algorithm for quantitative assessment of process or machine performance. The algorithm is based on the fusion of multiple sensor inputs and matching of the currently observed system signatures against those observed during its normal behavior. In contrast to traditional monitoring techniques, neither faulty data nor historical data are needed for the performance assessment to be made. This quantitative information about process performance can be used to take appropriate maintenance action in a timely manner. Effectiveness of the methods presented in this paper was experimentally demonstrated in multisensor welding process assessment.

Measurement Scheme Synthesis in Multi-Station Machining Systems

Different sets of measurements carry different amounts of information about the root causes of quality problems in machining. The selection of measurements in multi-station machining systems is currently a slow and error-prone process based on expert human knowledge. In this paper, we propose systematic procedures for synthesizing measurement schemes that carry the most information about the root causes of dimensional machining errors. The amount of root cause information conveyed by a given set of measurements was assessed using the recently introduced formal methods for quantitative characterization of measurement schemes in multi-station machining systems. The newly proposed measurement scheme synthesis procedures were applied to devising measurement schemes in an automotive cylinder head machining process. It was observed that the measurement scheme synthesis procedure based on a genetic algorithm robustly outperformed the synthesis procedures based on the heuristics of successive measurement removal.

Quality and Inspection of Machining Operations: CMM Integration to the Machine Tool

Dimensional measurement feedback in manufacturing systems is critical in order to consistently produce quality parts. Considering this, methods and techniques by which to accomplish this feedback have been the focus of numerous studies in recent years. More-over, with the rapid advances in computing technology the complexity and computational overhead that can be feasibly incorporated in any developed technique have dramatically improved. Thus, techniques that would have been impractical for implementation just a few years ago can now be realistically applied. This rapid growth has resulted in a wealth of new capabilities for improving part and process quality and reliability. In this paper, overviews of recent advances that apply to machining are presented. More specifically, research publications pertaining to the use of coordinate measurement machines to improve the machining process are discussed.

Quality and Inspection of Machining Operations: Tool Condition Monitoring

Tool condition monitoring (TCM) is an important aspect of condition based maintenance (CBM) in all manufacturing processes. Recent work on TCM has generated significant successes for a variety of cutting operations. In particular, lower cost and on-board sensors in conjunction with enhanced signal processing capabilities and improved networking has permitted significant enhancements to TCM capabilities. This paper presents an overview of TCM for drilling, turning, milling, and grinding. The focus of this paper is on the hardware and algorithms that have demonstrated success in TCM for these processes. While a variety of initial successes are reported, significantly more research is possible to extend the capabilities of TCM for the reported cutting processes as well as for many other manufacturing processes. Furthermore, no single unifying approach has been identified for TCM. Such an approach will enable the rapid expansion of TCM into other processes and a tighter integration of TCM into CBM for a wide variety of manufacturing processes and production systems.