Bruno Agard

Data-mining-based methodology for the design of product families

Companies design and manufacture widely diversified products to satisfy the needs of their customers and markets. Two issues important to achieving this aim are discussed. The first concerns adequate diversity for a particular market. The second concerns the management and manufacture of products within an acceptable lead time and an acceptable cost. The two issues are examined with a methodology for the design of products families. This methodology is based on a data-mining approach and it focuses on the analysis of functional requirements.

MINING PUBLIC TRANSPORT USER BEHAVIOUR FROM SMART CARD DATA

Abstract In urban public transport, smart card data is made of millions of observations of users boarding vehicles over the network across several days. The issue addresses whether data mining techniques can be used to study user behaviour from these observations. This must be done with the help of transportation planning knowledge. Hence, this paper presents a common “transportation planning/data mining” methodology for user behaviour analysis. Experiments were conducted on data from a Canadian transit authority. This experience demonstrates that a combination of planning knowledge and data mining tool allows producing travel behaviours indicators, mainly regarding regularity and daily patterns, from data issued from operational and management system. Results show that the public transport users of this study can rapidly be divided in four major behavioural groups, whatever type of ticket they use..

Design for Cost: Module-Based Mass Customization

The assemble-to-order (ATO) production strategy considers a tradeoff between the size of a product portfolio and the assembly lead time. The concept of modular design is often used in support of the ATO strategy. Modular design impacts the assembly of products and the supply chain, in particular, the storage, transport, and production are affected by the selected modular structure. The demand for products in a product family impacts the cost of the supply chain. Based on the demand patterns, a mix of modules and their stock are determined by solving an integer programming model. This model cannot be optimally solved due to its high computational complexity and, therefore, two heuristic algorithms are proposed. A simulated annealing algorithm improves on the previously generated solutions. The computational results reported in this paper show that significant savings could be realized by optimizing the composition of modules. The best performance is obtained by a simulated annealing combined with a heuristic approach.

Data mining for improvement of product quality

The assemble-to-order strategy delays the final assembly operations of a product until a customer order is received. The modules used in the final assembly operation result in a large product diversity. This production strategy reduces the customer waiting time for the product. As the lead-time is short, any product rework may violate the delivery time. Since quality tests can be performed on the stocked modules without impacting the assembly schedule, the quality of the final assembly operations should be the focus. The data-mining approach presented in this paper uses the production data to determine the sequence of assemblies that minimizes the risk of producing faulty products. The extracted knowledge plays an important role in sequencing modules and forming product families that minimize the cost of production faults. The concepts introduced in the paper are illustrated with numerical examples.

Analysing the Variability of Transit Users Behaviour with Smart Card Data

This paper proposes various measures regarding the variability of travel behaviours of transit users. The analyses are performed with smart card data collected over a ten months period. The variability in terms of boarding per day and new stops frequented with the days of travel on the transit network is examined. Data mining techniques are then used to classify days of travel according to the similarity of the boarding time periods. In this view, the use of two specific smart cards is examined in more details. These experiments first show that the behaviours of regular transit users evolve with time both in terms of transit stops frequented and time of boarding. Hence, variability of behaviours also changes for various user types

Calculation of Transit Performance Measures Using Smartcard Data

This paper illustrates the use of smartcard data to estimate various transit performance measures. Combined with well-established evaluation processes, such measures can help operators monitor their networks in greater detail. The performance of the network supply and the statistics on passenger service can be calculated from these datasets for any spatial or temporal level of resolution, including route and bus stop levels.

Modular design of product families for quality and cost

The purpose of this article is to help managers early in the design of new product families. Based on product structures, sales forecasts, and constraints imposed by the marketplace, like quality and cost, the proposed method selects the product modules that meet customer requirements for the products, while respecting those constraints. The proposal includes a single-level module design formulation that considers quality and cost simultaneously. The method for testing the proposed algorithm is based on a case study of an electro–mechanical assembly device (headlamp). The performance of the algorithm is compared to that of the zero module case, where often the constraint problem cannot be resolved. The main result is a model and an algorithm that optimise quality and cost under the constraints of quality and cost. It shows what modules to manufacture, in what quantities, and in which products to use them. The output also provides the predicted quality and cost, based on improvements made to the modules. To conclude, this research enables the joint optimisation of quality and cost by defining the modules to be manufactured. It provides input for managers seeking modules designed for their supply chain. The algorithm provides key input for managing production ramp-up.

An experimental study for the selection of modules and facilities in a mass customization context

To design an efficient product family, designers have to anticipate the production process and, more generally, the supply chain costs. But this is a difficult problem, and designers often propose a solution which is subsequently evaluated in terms of logistical costs. This paper presents a design problem in which the product and the supply chain design are considered at the same time. It consists in selecting a set of modules that will be manufactured at distant facilities and then shipped to a plant close to the market for final, customized assembly under time constraints. The goal is to obtain the bill of materials for all the items in the product family, each of which is made up of a set of modules, and specifying the location where these modules will be built, in order to minimize the total production costs for the supply chain. The objective of the study is to analyze both, for small instances, the impact of the costs (fixed and variable) on the optimal solutions, and to compare an integrated approach minimizing the total cost in one model with a two-phases approach in which the decisions relating to the design of the products and the allocation of modules to distant sites are made separately.

A new method for evaluating the best product end-of-life strategy during the early design phase

The choice of an appropriate end-of-life (EOL) destination for discarded products is becoming an important issue for most manufactured products, given the current problems of environmental waste impact and landfill saturation. To address these issues, the design of a product must be optimised with a view to incorporating in that product an environmentally sustainable EOL scenario that respects economic and legislative constraints. The new EOL scenario evaluation method (ELSEM) that we propose in this paper takes these fundamental aspects into account, and provides a method for evaluating the various options for the EOL scenario of a product during early design phase. The ELSEM provides a simple and intuitive tool for designers to help them construct arguments for the EOL decision-making process. It is built using the fuzzy technique for order preference by similarity to ideal solution method, a multi-criteria decision process that is highly appropriate in the uncertain and subjective environment in which the designer works during the early stages of product development. Our method is illustrated with a case study involving a vehicle engine.

Data mining for subassembly selection

The paper presents a model and an algorithm for selection of subassemblies based on the analysis of prior orders received from the customers. The parameters of this model are generated using association rules extracted by a data mining algorithm. The extracted knowledge is applied to construct a model for selection of subassemblies for timely delivery from the suppliers to the contractor. The proposed knowledge discovery and optimization framework integrates the concepts from product design and manufacturing efficiency. The ideas introduced in the paper are illustrated with an example and an automotive case study.