As the torrential rains continue to descend, I stand in my basement staring at the crack in my foundation that I had sealed last summer. The oozing brown liquid dripping into my basement mocks my efforts at foundation repair. Last summer I braved the 90-degree weather to crawl under my deck armed with my short-handled shovel and heavy-duty power drill. For several hours I labored to inch my way through solid, concrete-like clay to dig a hole deep enough to access the exterior of the foundation to seal the culprit.
Because I am an engineer, my mind turns to probabilities. What is the probability that this crack would have leaked again? What is the probability that it would rain this much? What is the probability that the local weather forecaster is ever right? I mean, they have to predict the weather while trying to factor in temperature, humidity, precipitation, cloud cover, wind speed, wind direction, jet streams, cold fronts, warm fronts, and more. These seemingly random factors combine to cause weather (and my leaky basement).
Making Sense of ChaosMany years ago, one of my systems engineering professors, discussing chaos theory, described how systems, like the weather system, are sensitive to and dependent on initial conditions, i.e., what happens first. He told us about the “butterfly effect” in which a small change in the state of a system can result in differences in a later state. For example, the flapping of the wings of a butterfly in China can affect the weather thousands of miles away in New York a few weeks later. Really? What’s the probability that a butterfly flapping its wings could influence weather thousands of miles away?
Bayesian NetworksGood news, there’s an engineering concept for that! Thomas Bayes to the rescue. Thomas Bayes was an English statistician, philosopher, and Presbyterian minister who lived in the early 1700s and is known for formulating the theorem that bears his name. A Bayesian network is a model, just like a weather model. It represents a set of random variables like those that affect weather. Not only does it capture a set of random variables, but it also describes their conditional dependencies on one another.
Thomas Bayes Source CDC website
For example, given the conditions that there is complete cloud cover and the humidity is 100%, what is the probability that it will precipitate? This probability is based on conditions and is called conditional probability. Bayes translated a set of complex relationships or dependencies into an intuitive, mathematic model. Bayesian network models incorporate uncertainty and work in the face of missing or inconsistent data – sounds like a weatherman’s dream to me! Not only do weathermen use Bayesian networks, but Engility uses them, too. Engility’s robust systems engineering is often underpinned by mathematical methods. Recently I was part of a team that developed a method to probabilistically determine integration readiness in complex systems using a Bayesian Network model. Read an abstract of the paper on page 67 here.
Our method may not save me a call to the handyman, but chances are my next engineering job will have a lot less risk.
Posted by Don York
As a Principal Technical Expert for System Development Metrics, I serve as an integral part of a team of subject matter experts invited to work with the Government Accountability Office (GAO) to develop their government-wide Technology Readiness Assessment (TRA) Best Practice Guide, reviewing and helping to write the section on systems readiness metrics. The Guide will be published in 2019.
I have co-authored, published and presented a number of articles related to this blog. These include Mitigating Integration Risks in Complex Systems at the 28th INCOSE International Symposium (IS) in July of this year, Applying Bayesian Networks to TRL Assessments – Innovation in Systems Engineering at the 27th INCOSE IS, and Using Bayesian Networks to Validate Technology Readiness Assessments of Systems at the 15th Annual Conference on Systems Engineering Research (CSER) in March of 2017. Read more here.