Erica Klampfl

Application of intelligent methods to automotive assembly planning

The automotive manufacturing process is one of the most complex processes in industry today. The rapid changes in the marketplace and introduction of new technologies require that the underlying manufacturing processes keep pace. The use of intelligent systems for this environment is quickly becoming a necessity. In this paper, we describe how some of these intelligent methods are used at Ford Motor Company in the automotive assembly planning domain. The following applications of intelligent systems will be described: knowledge-based labor management, ergonomics analysis, and workcell layout optimization. We will also discuss how natural language processing can assist in understanding unstructured textual data. All of these examples show how computational intelligence can be successfully applied in an industrial setting.

Bayesian Rule Sets for Interpretable Classification

A Rule Set model consists of a small number of short rules for interpretable classification, where an instance is classified as positive if it satisfies at least one of the rules. The rule set provides reasons for predictions, and also descriptions of a particular class. We present a Bayesian framework for learning Rule Set models, with prior parameters that the user can set to encourage the model to have a desired size and shape in order to conform with a domain-specific definition of interpretability. We use an efficient inference approach for searching for the MAP solution and provide theoretical bounds to reduce computation. We apply Rule Set models to ten UCI data sets and compare the performance with other interpretable and non-interpretable models.

Scheduling Crash Tests at Ford Motor Company

We consider the problem of scheduling crash tests for new vehicle programs at Ford. We describe the development of a comprehensive web-based system that automates time-consuming scheduling analyses through mathematical optimization, while also institutionalizing expert knowledge about the engineering complexities of crash testing. We present a novel integer programming model and a corresponding solution algorithm that quickly generates efficient schedules. The system’s user interface enables engineers to specify key program data and consider multiple scheduling scenarios, while using the underlying optimization model and solution algorithms as a black box.

Ford Uses Analytics to Help Fleet Customers Buy More Sustainable Vehicles

We developed an innovative technology that uses analytics to promote sustainability as a central purchase consideration for organizations with large fleets of vehicles. Working with Ford’s fleet customers over the past several years, we witnessed their strong and increasing desire to adopt greener vehicle technologies, and their unmet need to financially justify the higher initial investment costs associated with adopting those more fuel-efficient technologies. We responded by developing the Ford Fleet Purchase Planner™—a set of tools that begin with simple calculators and gradually transition to highly precise full-fleet optimization tools. These tools enable fleet customers to invest strategically in greener vehicles.

JEDI: Just-in-time execution and distribution information support system for automotive stamping operations

Stamping is one of the most complex operations in the automotive supply chain, providing over 400 end items to dozens of assembly plants and service facilities. This operation consists of a complex network of blankers, presses, and subassemblies. Stamping is affected by much variability, such as unexpected machine and tool down time, quality concerns, and customer requirement fluctuations. These facilities typically run a tight schedule, and supply chain visibility is a critical factor in efficient operations. The data pertaining to operations is distributed across several systems including material requirements planning (MRP), plant floor automation, and logistics management. As a result, decision makers are faced with too much data and not enough information. This leads to time loss and effort spent in consolidating and comprehending the data. This chapter describes the Just-in-time Execution and Distribution Information (JEDI) system that collects and integrates relevant data from a set of disparate systems and generates a set of spreadsheet models that represent the stamping production and supply chain status. JEDI not only presents the information in an intuitive way, but also provides what-if analysis capability and decision support for scheduling and distribution.

Ford Uses OR to Make Urgent Sourcing Decisions in a Distressed Supplier Environment

Ford Motor Company used operations research methodology to aid in determining the best sourcing footprint for its

Emotive Driver Advisor System (EDAS)

1.5 billion Automotive Components Holdings, LLC (ACH) Interiors business, saving approximately

Integrated process planning and supply chain configuration for commodity assemblies using petri nets

40 million in upfront investment over the previously preferred alternative. This extensive undertaking required a complete reengineering of the supply footprint of 42 high-volume product lines over 26 major manufacturing processes and more than 50 potential supplier sites. Under extreme time constraints (two months), we developed a decision-support tool and a novel approach to solve the underlying large-scale mixed-integer nonlinear program. We reformulated a complex real-life problem into a manageable model that provided practical insights in a timely fashion. The proposed algorithms scale well and account for nonlinearities arising from supplier facility cost structures. The new tool provided a state-of-the-art, data-driven, quantitative basis for sourcing decisions in an area of strategic importance to the company and enabled Ford to make faster and better decisions on how to restructure its ACH Interiors business.

Do labeled versus unlabeled treatments of alternatives' names influence stated choice outputs? Results from a mode choice study.

This paper describes the Emotive Driver Advisory System (EDAS), Ford Research & Advanced Engineering’s project on next generation driver assistance. EDAS integrates several emerging technologies, focusing on personalization and adaptive and intelligent behavior. We will provide a high-level overview of the EDAS architecture, focusing on novel consumer-facing features, such as the emotive spoken dialogue system and an Avatar as an automotive human machine interface. Furthermore, we will discuss the benefits of cloud-based vehicle infotainment and decision support and how this can be integrated in a vehicle environment. The system concept was revealed at the 2009 Consumer Electronics Show and the 2009 North American International Auto Show.

Dynamic Modeling of Operator Overload Conditions in Mixed Model Automotive Assembly

We present a methodology for integrated process planning and supply chain configuration for commodity assemblies. Although the supply chain configuration problem for commodity assemblies is relatively straightforward using math programming, developing a commodity-dependent math program with precedence constraints can be a very daunting and time-consuming process. We use Petri net techniques to support the development of such a math program. Our modeling approach is based on a series of stepwise Petri net transformations that transform the Petri net model of the assembly process into a supply chain configuration representation. We use the matrix representation as a basis for the integer program formulation. We present a small example commodity from the automotive industry to illustrate the proposed methodology.