11-CS-4 Engineering Law and Professional Liability · December 2013
Nivaar worked solution (AI-drafted; not reviewed by a licensed engineer)
Question text not reproduced: the examination questions are © Engineers and Geoscientists BC. Open the official past paper (linked at the top of this page) to read the question, then follow the worked solution below.
Trend analysis is the systematic study of historical data to identify the underlying direction and rate of change in a variable over time, so that management can anticipate future conditions rather than merely react to them. Its purpose is to support planning decisions—capacity, staffing, product development, and investment—by distinguishing genuine long-run movement from short-term noise and seasonal fluctuation. In an engineering-management context, trend analysis informs when a technology will mature, when demand will justify new capacity, and when a product will require replacement. The major forces that influence trends are economic (growth cycles, interest rates, disposable income), technological (innovation, obsolescence, automation), social and demographic (population change, values, lifestyle), political and regulatory (legislation, trade policy, environmental rules), and competitive (rival strategies, market entry and exit). A sound analysis recognizes that these forces interact, so a trend is rarely explained by a single cause.
(a) Time-series models forecast a variable purely from the historical pattern of its own past values, decomposing the series into trend, seasonal, cyclical, and irregular (random) components. They assume that the patterns of the past will continue, which makes them powerful for stable processes but weak at anticipating structural breaks. (b) The moving-average model smooths a series by averaging the most recent n observations, dropping the oldest as each new one arrives; a longer window smooths more heavily and responds more slowly, while a shorter window is more responsive but noisier. It is simple and transparent but lags behind turning points and weights all included periods equally. (c) Exponential smoothing refines this idea by applying exponentially decreasing weights to older observations through a smoothing constant α between 0 and 1: the new forecast equals α times the latest actual plus (1−α) times the previous forecast. A high α makes the forecast responsive to recent change, a low α makes it stable; extensions (Holt, Holt–Winters) add trend and seasonal terms.
A technology assessment audits the organization's technological position and the impact of adopting or retaining a technology. The questions typically asked are: What technologies do we currently use, and how do they compare with best available practice? Where is each technology on its life cycle (emerging, growth, mature, or declining)? What is the technology's impact on cost, quality, and capability? What are the risks—obsolescence, dependence on a single supplier, safety, or regulatory exposure? What competitive advantage does it confer, and are competitors ahead? What investment is required to upgrade or replace it, and what is the return? And what are the wider environmental, social, and legal consequences of the technology?
A manufacturer of industrial pumps would use time-series decomposition on ten years of order data to separate a modest upward trend from strong seasonality, apply Holt–Winters exponential smoothing (with a moderate α) to generate the next year's monthly forecast, and feed that into capacity planning. In parallel, a technology audit would reveal that its casting process is mature and energy-intensive relative to a competitor's near-net-shape method, prompting a business case for re-investment.
