Your Reliability Engineering Professional Development Site
A listing in reverse chronological order of articles by:
Learn how to use Claude AI to perform a full Statistical Process Control (SPC) and Process Capability analysis — from raw data to a formatted Excel report — in a single conversation.
In this 9-minute tutorial, we work through a real PCB (Printed Circuit Board) thickness dataset and cover every step of a professional SPC study.
[Read more…]The best way to predict the future is to create it. Peter Drucker
One of the most consequential topics facing the FMEA community today is how to effectively use Artificial Intelligence (AI) to support FMEA activities. Do it wrong, and the results could be missed opportunities, or potentially catastrophic outcomes. Do it right, and the benefits are immense.
Quality, Reliability, and Six Sigma professionals are increasingly exploring how Artificial Intelligence can support data analysis and interpretation. Using the Claude AI engine, I analysed field-failure life data for a camshaft, which is a component used in internal combustion engines. The objective was to assess whether an AI model can perform this type of analysis effectively—and whether the insights align with results from established statistical software.
I’m sharing a short video demonstrating this approach: A Case Study in Performing Life Data Analysis using the Claude AI model. I hope you find it useful, and I look forward to experimenting further with AI-assisted methods for reliability and quality analytics.
[Read more…]We want to let subscribers know that the recent spate of past Inside FMEA articles that were sent from “Fred at Accendo Reliability” to the full subscriber list were not planned to be sent. Fred let me know that this was inadvertently caused by AccendoReliablity.com website updates that allowed the release of some of the old articles. We are sorry for any inconvenience you experienced from loading your email with older articles. Fred says the problem is resolved, and should not recur.
Of course, you are always welcome to peruse and read any past articles. You can find Inside FMEA past articles by clicking this link, for the most recent articles first, or this link for past articles grouped by category.
Meanwhile, I will resume writing new articles next month, as part of the Inside FMEA series. So, stay tuned.
Carl
This article is adapted from Chapter 9 of my book, Measuring Manufacturing Effectiveness.
The book examines how manufacturing organizations define and apply performance metrics, and how those choices influence decisions, priorities, and outcomes across operations. While the chapters collectively form a structured framework, each chapter is written to address a specific dimension of manufacturing effectiveness and can be read independently.
Quality loss is often discussed in terms of defects and scrap. While those outcomes matter, they represent only the most visible expressions of a deeper issue: the ability of a manufacturing system to produce stable, predictable, and usable output.
Chapter 9 reframes quality loss through the lenses of yield, stability, and usable output. Rather than treating quality as a pass/fail condition, this chapter examines how variation influences what portion of production can actually be counted as usable output.
By viewing quality loss as a system property rather than a simple defect rate, this chapter aims to clarify why many quality metrics fail to reflect real operational performance, and why improving quality often requires changes beyond the quality function itself.
[Read more…]What if there’s no lifetime data? Periodic product ships or sales data and returns (complaints, failures, repairs, or spares sales) contain reliability information. Neutrosophic statistics provide a way to make nonparametric estimates of products’ or parts’ reliability without lifetime data.
This article is adapted from Chapter 8 of my book, Measuring Manufacturing Effectiveness.
The book explores how manufacturing organizations define and use performance metrics, and how those definitions influence operational decisions, improvement efforts, and management behavior. While the chapters form a connected framework, each is written to address a specific aspect of manufacturing effectiveness and can be read independently.
Performance loss is often described in overly simple terms—the equipment is running slower than it should. While speed is certainly part of the story, this narrow view hides a much broader set of losses that affect output, flow, and stability.
Chapter 8 expands the discussion of performance loss beyond basic speed shortfalls. It examines how interruptions, minor stops, micro-downtime, variability, and operating practices contribute to lost performance—even when equipment appears to be running continuously.
By broadening how performance loss is defined and observed, this chapter aims to improve how organizations diagnose problems and select effective improvement actions.
[Read more…]
Dear friends, I am happy to release my 106th technical video. In this video, I have explained how to use the open source JASP software to create and analyse Full Factorial Experiment. I have illustrated this with an application example of how to maximize fatigue strength of a crankshaft. Crankshaft is a critical component used in internal combustion engines.
[Read more…]
Message to “Inside FMEA” readers. This is a reprint of a message that went out earlier this week as part of the Accendo Weekly Update. I wanted to be sure to reach any “Inside FMEA” readers who may have missed the original request.
My new eBook is in draft form and ready for review. I am very excited to introduce this project, as it is the culmination of a career in reliability engineering and FMEA. The title is Achieving Effective FMEAs: Simple Principles for Realizing the Full Potential of Failure Mode and Effects Analysis. It summarizes and simplifies articles I’ve written over the years as part of the Inside FMEA Series, with added emphasis on principles, examples, exercises and case studies. Each chapter has a section called “Potential AI Application” which shares where AI is useful, and where human involvement is essential. [Read more…]
This article is adapted from Chapter 8 of my book, Measuring Manufacturing Effectiveness.
The book explores how manufacturing organizations define and use performance metrics, and how those definitions influence operational decisions, improvement efforts, and management behavior. While the chapters form a connected framework, each is written to address a specific aspect of manufacturing effectiveness and can be read independently.
Performance loss is often described in overly simple terms—the equipment is running slower than it should. While speed is certainly part of the story, this narrow view hides a much broader set of losses that affect output, flow, and stability.
Chapter 8 expands the discussion of performance loss beyond basic speed shortfalls. It examines how interruptions, minor stops, micro-downtime, variability, and operating practices contribute to lost performance—even when equipment appears to be running continuously.
By broadening how performance loss is defined and observed, this chapter aims to improve how organizations diagnose problems and select effective improvement actions.
[Read more…]This article is adapted from Chapter 6 of my book, Measuring Manufacturing Effectiveness.
The book examines how manufacturing organizations define and use performance metrics, and how those measurement choices influence decisions, priorities, and behavior on the shop floor and in management. While the chapters are organized as a cohesive framework, each one is written to address a specific aspect of manufacturing effectiveness and can be read independently.
Chapter 6 focuses on a critical but often oversimplified topic: downtime.
Most organizations track downtime in some form, but far fewer distinguish meaningfully between how often downtime occurs and how long it lasts. These two dimensions — frequency and duration — are frequently combined, averaged, or summarized in ways that mask important operational realities.
This chapter explores why separating downtime frequency from downtime duration matters, how each dimension points to different underlying causes, and how failing to distinguish between them can lead to ineffective or misdirected improvement efforts.
[Read more…]
Broom” charts are reliability function estimates from different or successive production cohorts. Their differences may contain actionable information. How to quantify and use that information? This article provides an alternative to traditional Duane, AMSAA, and Crow reliability growth models, based on Cox’ proportional hazards model for test or field reliability data. This article provides:
Suppose successive test samples or production cohorts have reliability growth or deterioration, caused by TAAF (Test, Analyze And Fix), configuration, environment, stress, or vendor changes, or ??? Suppose product cohorts have “proportional hazard” functions.
[Read more…]
Time is the scarcest resource, and unless it is managed, nothing else can be managed. Peter Drucker
Achieving high-quality FMEAs requires support from the right FMEA team. Getting the team to show up and participate to the fullest extent is critical to success.
My new book titled Measuring Manufacturing Effectiveness develops a practical framework for understanding manufacturing effectiveness through the lens of performance metrics including how they are defined, how they are interpreted, and how they influence real operational behavior.
Chapter 5 turns attention to the first of the three components of Overall Equipment Effectiveness (OEE): Availability.
Availability addresses a deceptively simple question: Can the equipment run when it is scheduled to run?
Behind that question sits a wide range of losses related to downtime, changeovers, failures, maintenance practices, and scheduling decisions.
This article is adapted from Chapter 4 of my book, Measuring Manufacturing Effectiveness.
The book is organized as a structured, multi-chapter examination of how manufacturing organizations define, measure, and interpret “effectiveness.” Rather than focusing on isolated metrics or individual tools, it treats measurement as a system, one that directly influences operational decisions, improvement priorities, and management behavior across manufacturing organizations.
Each chapter is written to stand on its own, while also contributing to a larger, integrated framework for understanding manufacturing performance.
Chapter 4 introduces the core components that make up Overall Equipment Effectiveness (OEE). While OEE is often presented as a single number, it is actually the product of three distinct elements, each representing a different category of loss and a different dimension of system performance.
This chapter provides an orientation to those components, explains what each is intended to capture, and establishes the conceptual foundation needed before OEE can be used meaningfully as a measurement or improvement tool.
[Read more…]
