CHAPTER 3: Data collection methods

Survey and questionnaires in engineering

Surveys and questionnaires are commonly used in engineering to gather data,
assess user needs, validate design decisions, and evaluate system performance.
Here's a brief overview of their purpose, design, and application in engineering
contexts:

1. Purpose in Engineering

 User Requirement Gathering: Understanding what end users need from a

system or product.
 Design Validation: Checking if a prototype or solution meets user
expectations.
 Performance Feedback: Assessing system performance or satisfaction after
deployment.
 Quality Control: Collecting feedback on processes, products, or services.
 Safety and Compliance: Ensuring systems meet regulatory or safety
standards based on stakeholder input.

2. Questionnaire Design Principles

 Clarity: Use simple, direct language to avoid misunderstandings.

 Relevance: Ask questions that are directly tied to the engineering objective.
 Brevity: Keep it concise to avoid respondent fatigue.
 Balance: Use both open-ended and closed-ended questions as needed.
 Scaling: Employ Likert scales (e.g., 1–5 ratings) for quantifiable feedback.

3. Types of Questions

 Closed-ended: Yes/no, multiple choice, or rating scale (good for

quantitative analysis).
 Open-ended: Free text responses (useful for qualitative insights).
 Ranking or Rating: Useful in comparing design features or system
priorities.

4. Applications in Engineering Fields

  Civil Engineering: Public surveys on infrastructure usability or urban
planning.
 Mechanical Engineering: Usability feedback on product ergonomics or
durability.
 Software Engineering: User experience (UX) and functionality testing.
 Electrical Engineering: Evaluation of device interfaces or control systems.
 Industrial Engineering: Workflow analysis and process improvement
studies.

5. Tools Commonly Used

 Google Forms / Microsoft Forms – Easy to use, free.

 SurveyMonkey / Qualtrics – Advanced analytics and customization.
 MATLAB / Python (with libraries like pandas, matplotlib) – For custom
survey data analysis.

Experimental methods and design of experiments

Experimental Methods and Design of Experiments (DoE) are core tools in
engineering used to systematically investigate the behavior of systems, optimize
processes, and make data-driven decisions. Here's a structured overview:

1. Experimental Methods in Engineering

These are systematic procedures used to test hypotheses, validate models, or

analyze systems under controlled conditions.

Key Components:

 Independent Variables (Factors): What you manipulate.

 Dependent Variables (Responses): What you measure.
 Control Variables: Conditions kept constant to isolate effects.
 Replication: Repeating experiments to assess variability and reliability.

Types:

 Laboratory Experiments: Controlled, repeatable, high precision.

 Field Experiments: Real-world conditions, more variability.
 Computational Experiments: Simulations or modeling (e.g., finite element
analysis).
2. Design of Experiments (DoE)

DoE is a structured, statistical approach to planning experiments to obtain valid

and objective conclusions with minimal trials.

Benefits:

 Identifies cause-effect relationships.

 Optimizes processes and designs.
 Reduces time and cost of experimentation.

Common DoE Techniques:

Technique Description Use Case
Tests all possible combinations Small number of
Full Factorial Design
of factors variables
Screen important
Fractional Factorial Design Tests a subset of combinations
variables
Randomized Design Random order to reduce bias All experiments
Response Surface Models and optimizes complex
Process optimization
Methodology (RSM) responses

3. Steps in Designing an Experiment

1. Define Objective: What are you trying to learn or improve?

2. Select Factors and Levels: Variables to manipulate and their ranges.
3. Choose a Design: E.g., 2^k factorial, Latin square, RSM.
4. Conduct the Experiment: Randomize to reduce bias, replicate for
reliability.
5. Analyze Data: Use ANOVA, regression, or other statistical tools.
6. Draw Conclusions and Optimize: Interpret results, refine design or
process.

4. Tools & Software

 Minitab / JMP / Design-Expert: Specialized for DoE.

 Excel: Basic designs and analysis.
  MATLAB / Python (SciPy, statsmodels): For custom analysis and
scripting.

Case studies and their relivance to engineering investigations

Case studies are detailed, contextual analyses of specific instances, projects, or

problems. In engineering, they serve as valuable tools for learning, problem-
solving, and decision-making. Here's how they fit into engineering investigations:

1. What is a Case Study in Engineering?

A case study is a real-world example used to explore how engineering principles

were applied to solve a problem, develop a system, or optimize a process. It
includes context, challenges, solutions, and outcomes.

2. Relevance to Engineering Investigations

 Understanding Complex Systems

Case studies provide insight into how theoretical knowledge applies to real, often
messy systems, where multiple variables interact.

 Learning from Success and Failure

They allow engineers to study what worked and what didn’t, helping improve
future designs or avoid repeat mistakes.

 Application of Experimental Methods

They often illustrate how tools like Design of Experiments (DoE), simulations,
or surveys were applied in practice.

 Interdisciplinary Insight

Engineering problems are rarely isolated. Case studies show the integration of
technical, social, economic, and environmental factors.

 Decision-Making Support
In design or troubleshooting, engineers refer to case studies as evidence-based
references to justify design decisions or process changes.

3. Common Case Study Types in Engineering

Type Example Relevance

Tacoma Narrows Bridge Teaches structural dynamics and
Failure Analysis
collapse design oversight
Design Redesign of a jet engine Shows iterative testing and material
Optimization blade analysis
Process Lean manufacturing in Demonstrates workflow
Improvement automotive enhancement using data
Environmental Oil spill containment Balances engineering with
Impact design ecological responsibility
Innovation Smart grid Combines electrical, software, and
Deployment implementation systems engineering

4. Where Case Studies Are Used

 Academia: Teaching problem-solving and critical thinking.

 Industry: Documenting best practices and lessons learned.
 Research: Supporting or contrasting experimental results.
 Certification & Auditing: Validating engineering processes and standards.

Use of sensors, data acquisition systems and instrumentation

in engineering research
The use of sensors, data acquisition systems (DAQ), and instrumentation is
fundamental in engineering research, enabling precise measurement, monitoring,
and analysis of physical phenomena. Here’s an overview of how each component
plays a role:

1. Sensors in Engineering Research

Sensors convert physical quantities into measurable electrical signals. They are
essential for monitoring variables in experiments or systems.

Common Sensor Types and Uses:

Sensor Type Measured Variable Example Application
Thermocouple / Heat transfer studies, combustion
Temperature
RTD analysis
Structural testing of bridges,
Strain Gauge Deformation / Stress
materials
Seismic analysis, vehicle crash
Accelerometer Vibration / Motion
testing
Fluid dynamics, aerodynamics
Pressure Sensor Pressure
research
Proximity Sensor Distance / Presence Robotics, automation
Light Intensity /
Optical Sensor Laser systems, spectroscopy
Wavelength

2. Data Acquisition Systems (DAQ)

A DAQ system collects, digitizes, and stores sensor data for analysis. It typically
includes:

 Sensors and transducers

 Signal conditioning units (amplifiers, filters)
 Analog-to-digital converters (ADC)
 Computer interface (e.g., USB, PCIe)

Key Functions:

 Real-time data monitoring

 High-speed sampling
 Synchronization of multiple sensors
 Data logging for later analysis

3. Instrumentation in Engineering
Instrumentation refers to the complete setup of measurement tools and control
systems used in experiments.

Applications:

 Control systems: Feedback loops in robotics, automation.

 Testing rigs: Wind tunnels, vibration tables, tensile testers.
 Embedded systems: Sensor networks in IoT-based research.
 Calibration: Ensuring measurement accuracy and repeatability.

4. Integration in Engineering Research

 Experimental Validation

Sensors and DAQs are used to validate theoretical models (e.g., testing fluid flow
models with real velocity/pressure data).

 Monitoring and Control

In real-time experiments, data from sensors can be used to trigger events or adjust
parameters dynamically.

 Big Data & Analytics

Sensor networks generate large datasets for advanced analysis using machine
learning, particularly in fields like structural health monitoring or smart
manufacturing.

 Interdisciplinary Use

These tools bridge fields like mechanical, electrical, civil, chemical, and
biomedical engineering.

5. Tools & Platforms

 LabVIEW, MATLAB, Simulink: For DAQ and control.

 Arduino, Raspberry Pi, NI DAQ, dSPACE: Hardware for custom
experimentation.
 Python (PyDAQmx, pandas, NumPy): Open-source data handling and
processing.