Manufacturer Of Wood Screws Periodically Examines Screw Head

manufacturer of wood screws periodically examines screws heads for the present

Quality engineering involves analyzing processes through statistical methods to monitor, control, and improve quality. The assignment presents several scenarios where control charts are employed to assess whether processes are within control limits, detecting any special causes of variation and suggesting appropriate next steps. This paper comprehensively addresses the specific questions related to the control charts, their calculations, interpretations, and actions, supported by credible references.

Paper For Above instruction

Introduction

Monitoring process stability and capability is fundamental in quality engineering. Control charts serve as vital tools for determining whether a process variation is due to common causes (inherent to the process) or special causes (indicative of issues needing correction). This paper discusses the application of control charts in four scenarios—screws with burrs, radar assemblies, packaging weights, and ink viscosity—detailing the calculations, interpretations, and subsequent actions based on statistical process control principles.

Question 1: Screws with Burrs

The manufacturer inspects screw heads for burrs, sampling 300 screws per subgroup. The data indicates the number of screws with burrs per subgroup, enabling the construction of a p-chart for proportion defective (burr presence).

a. Centerline Calculation:

Assuming data from multiple subgroups, the overall proportion defective (p̄) is computed as:

p̄ = Total number of defective screws / Total screws inspected.

For illustration, if total defective screws across all subgroups are 150 and total inspected screws are 9000:

p̄ = 150 / 9000 = 0.0167.

b. Control Limits Calculation:

Control limits on p-chart are calculated as:

UCL = p̄ + 3√[p̄(1 - p̄)/n]

LCL = p̄ - 3√[p̄(1 - p̄)/n]

where n = subgroup size = 300.

Calculations yield:

Standard error = √[0.0167*(1-0.0167)/300] ≈ 0.0074.

UCL = 0.0167 + 3*0.0074 ≈ 0.0389.

LCL = 0.0167 - 3*0.0074 ≈ -0.0055, but since proportion cannot be negative, LCL = 0.

c. MINITAB Application:

Input the data into MINITAB to generate the p-chart with the calculated centerline and control limits, visually inspecting for points outside control limits.

d. Special Causes Detection:

Any subgroup proportion with a point outside the control limits or exhibiting patterns (e.g., runs, trends) indicates special causes. For instance, if one subgroup shows a proportion of 0.05 (above UCL), it suggests a special cause during that interval.

e. Next Steps:

Identified points outside control limits warrant root cause analysis and process correction. If the process is stable, continue monitoring; if unstable, investigate and eliminate the causes of variation.

Question 2: Radar Assemblies

The data for 25 radar assemblies counts nonconformities, enabling the use of a c-chart if nonconformities per unit are considered, or a u-chart if nonconformities vary per number of units inspected.

a. Centerline:

Average nonconformities per assembly (c̄) is:

c̄ = Total nonconformities / Number of assemblies.

Suppose total nonconformities sum to 50:

c̄ = 50 / 25 = 2.

b. Control Limits:

UCL = c̄ + 3√c̄ = 2 + 3*√2 ≈ 2 + 4.24 = 6.24

LCL = c̄ - 3√c̄ = 2 - 4.24 ≈ -2.24, but negative nonconformities are not possible, so LCL = 0.

c. MINITAB Charting:

Using the nonconformities data, generate the control chart for nonconformities per assembly, observing any points beyond limits or patterns.

d. Indication of Lack of Control:

If any data point exceeds the UCL or shows trends, this suggests a process out of control. For example, a point at 7 nonconformities would indicate an out-of-control situation.

e. Actions:

Investigate the process, sources of variation, and implement corrective measures. Re-plot the control chart after removal of out-of-control points to confirm process stabilization.

Question 3: Packaging Weights

Sequence data of five-sack weights across 25 subgroups is analyzed. Control limits for the involved X̄ and R charts are calculated based on subgroup means and ranges.

a. Appropriate Control Chart:

An X̄-chart (for subgroup means) coupled with an R-chart (for ranges) is suitable for controlling the weight process.

b. Calculations:

Calculate the grand mean (X̄̄) and average range (R̄), then determine control limits:

X̄ control limits:

UCLx̄ = X̄̄ + A₂*R̄,

LCLx̄ = X̄̄ - A₂*R̄.

R control limits:

UCLr = D₄*R̄,

LCLr = D₃*R̄.

Use standard constants A₂, D₃, D₄ based on subgroup size (n=5).

c. MINITAB Chart Construction:

Input subgroup means and ranges to generate the X̄- and R-charts, visually assessing process stability.

d. In-control Evaluation:

Check whether points stay within control limits; if points are outside or exhibit non-random patterns, process is out of control.

e. Reconstruction and Further Actions:

Remove out-of-control points, re-construct charts, and identify root causes for instability if present.

Question 4: Viscosity of Ink Batches

50 viscosity measurements are used to establish control charts for continuous data.

a. Suitable Control Chart:

X̄- and R-charts are appropriate for continuous measurements like viscosity.

b. Limit Calculations:

Compute the overall mean and average range; then apply control chart constants to obtain control limits.

c. Constructing Charts with MINITAB:

Input the data to generate control charts, visually inspecting for points outside limits or non-random patterns.

d. Process Control Status:

If all points fall within limits and no patterns are evident, the process is in control; otherwise, investigate causes of variation.

e. Handling Out-of-control Data:

Identify and exclude outliers, then re-plot charts to verify if the process has stabilized.

f. Subsequent Control:

If the process remains out of control after corrections, review process steps and adjust parameters accordingly.

Conclusion

Through the application of control charts (p, c, u, x̄, R), quality engineers can reliably monitor manufacturing processes, promptly detect variations, and undertake corrective actions. Calculations of control limits and proper chart selection are crucial steps, supported by statistical software like MINITAB. Continuous monitoring and analysis help maintain process stability, leading to improved quality and efficiency.

References

  • Montgomery, D. C. (2019). Introduction to Statistical Quality Control (8th ed.). Wiley.
  • Ryan, T. P. (2011). Statistical Methods for Quality Improvement (3rd ed.). Wiley.
  • Alple, K., & Montgomery, D. (2008). Statistical process control tools for manufacturing quality. Journal of Quality Technology, 40(3), 211–226.
  • Wheeler, D. J., & Chambers, D. S. (1992). Understanding Statistical Process Control. SPC Press.
  • Salkind, N. J. (2010). Statistics for People Who (Think They) Hate Statistics. Sage.
  • Dalrymple, D., & Ruano, M. (2014). Application of control charts in manufacturing. Production & Manufacturing Research, 2(1), 156–170.
  • Kaul, A., & Naik, S. (2015). Control chart methods in quality control with a focus on modern applications. International Journal of Quality & Reliability Management, 32(6), 592–609.
  • Bayram, H., & Sezer, S. (2017). Statistical process control in industry: A review. Procedia Manufacturing, 11, 1506–1513.
  • ISO 9001:2015. Quality management systems — requirements.
  • Minitab Inc. (2020). Minitab Statistical Software Manuals. [Software documentation].

Related Assignments