Lean Six Sigma

Six Sigma is a quality improvement methodology focused on reducing product or service failure rates to a level of perfection. Structured, data driven approaches are used to eliminate the number of defects across all business areas, such as management, supply chain, design, manufacturing, and customer satisfaction. The overall goal is to produce better products and services more efficiently and effectively, while reducing costs.

Implement the DMAIC (Define-Measure-Analyze-Improve-Control) approach to keep projects organized, on time, and on point. The DMAIC process will assist in defining the problem and scope of the project and ensure that these objectives are accounted for throughout the study.

The concept of Lean centers on the continuous elimination of waste in processes, thereby increasing customer satisfaction while reducing the total costs required to produce the same goods or services.

Analysis and Control of Production Systems

Forecasting – the use of historical data to predict/project future values.

Qualitative Forecasting – When historical data is unavailable, subject matter experts provide opinions in an iterative process with the goal of converging to the “correct” forecasting values. Common qualitative forecasting methods include expert opinion, sales force polling, the Delphi Method, and customer surveys.

Quantitative Forecasting – The historical pattern of the data, i.e. random fluctuations, trends, shifts, and seasonality, is used to forecast future values. Common quantitative forecasting methods include simple linear regression, multiple linear regression, nonlinear regression, moving-average methods, simple exponential smoothing, Holt’s model (with trend), and Winter’s model (with trend and seasonality).

Inventory Theory – Scientific inventory management is used to assist companies to determine how much of a product should be ordered, or produced, and when the order should be placed so the total inventory costs are minimized. Common inventory models include the Economic Order Quantity (EOQ) model, the Economic Production Quantity (EPQ) model, Aggregation models, and Quantity discount models.

Aggregate Production Planning – Consists of efforts to plan a desired output over a longer range by adjusting the production rate, employment, inventory, and other controllable variables. Common pure strategies include varying workforce size to fulfill demand by employment only, to maintain a stable workforce but permit overtime, maintain a stable workforce but carry inventory, implement a backorder strategy, or implement a subcontracting strategy.

Material Requirements Planning (MRP) – Uses the Master Production Schedule (MPS) to create schedules that identify parts and subcomponents needed to produce an end product, the quantity of the parts and subcomponents needed, and the dates when the materials need to be ordered.

Just-In-Time (JIT) – A pull system with the goal of reducing the work-in-process to a minimum by only moving items when requested by a higher level in the production process.

Production Planning and Scheduling – Project management is a strategic component that involves planning, organizing, staffing, controlling, and monitoring a project in an efficient and effective manner, thus relating the project results to a business objective. Projects can be achieved optimally by using the Critical Path Method (CPM) and the Program Evaluation and Review Technique (PERT).

Job Sequencing and Operations Scheduling – Job sequencing focuses on determining the schedule for machine process jobs such that a specific measure of performance, e.g. time, is optimized. Assembly Line Balancing (ALB) analyzes assembly operations such that workstations are assigned in an order to achieve equal balance between stations and increase the overall efficiency and effectiveness of the assembly line.

Markov Chain Analysis – A descriptive technique that provides probabilistic information about a decision situation. Analyzes systems that exhibit probabilistic movement from one state, or condition, to another over time.

Queueing Theory – A descriptive modeling technique that describes a solution to allow for analysis of concepts such as the expected number of entities, e.g. people, in the queue and the expected waiting time of the entities in the queue.

Optimization

Linear Programming – An optimization problem for which the goal is to maximize, or minimize, a linear objective function with respect to a set of linear constraints. Linear programming is used throughout several industries typically with the primary goal of maximizing a profit function or minimizing a cost function. Common linear programming applications include work-scheduling, budgeting, financial planning, transportation, transshipment, and network models.

Integer Programming – A linear program for which some or all of the variables are required to be non-negative integers. Note that nonlinear integer programming is an optimization problem such that the objective function and/or the constraints are composed of nonlinear variables where some or all of the variables are required to be integers. Common integer programming applications include investment decision making, facility location, and machine scheduling problems.

Nonlinear Programming – An optimization problem where the objective function and/or constraints are not linear. Types of nonlinear programming include quadratic, convex, non-convex, geometric, and fractional programming.

Multiple Criteria Decision Making – An optimization problem for which several conflicting criteria are simultaneously optimized. An example of multiple criteria decision making is goal programming, which chooses one of the multiple criteria as the primary criterion and use it as the objective function to be optimized. The remaining criteria are assigned acceptable values and treated as constraints. The criteria are treated as targets with the goal of producing a solution as close as possible to the targets based on priorities.

Heuristic Techniques – When it is difficult, time consuming, or costly to solve an optimization problem, heuristic algorithms are used to find a “good” solution in a much more cost-effective manner. Heuristic algorithms are used in many applications, but one common area of application are network analysis models.

Financial Analysis and Decision Making

Cost-Benefit Analysis – Evaluate several alternatives strengths and weaknesses with respect to business objectives. Use advanced techniques, such as quality function deployment (QFD), analytical hierarchy process (AHP), and the technique for order preference for similarity to ideal solution (TOPSIS), to integrate qualitative and quantitative data into the overall decision making and evaluation process.

Analysis of Alternatives – Evaluate several alternatives in terms of effectiveness with respect to process objectives. Thoroughly analyze the impacts that each course of action will have with respect to defined output performance parameters.

Economics – Analyze cash flows, life cycle cost estimates, and utility functions to determine the fiscal viability of investments and decisions.

Product Development

Market Research – Develop surveys and data collection plans to capture the wants and needs of customers when developing a product. It is critical to have a customer oriented point of view when developing the requirements for a new product and determining ways to meet the requirements so the end product is salable.

Product Design – Use statistical techniques to prioritize the wants and needs of the customer and translate their desires into affordable designs. Creating a linked chain from customer needs to the final product will help ensure that the end product will correlate with the market research.