MIYOQA
Contact Request a demonstration

MIYOQA / Engines

Calculation engines, one standard of evidence.

Statistical process control, capability, measurement systems, risk, geometry and process flow. Each engine is versioned, and each result is kept with its inputs.

Calculation engines

Statistics you can defend in an audit.

Figures come from named, versioned engines that follow published reference methods, and each result is kept with the record of how it was calculated.

Statistical process control

  • Variables, attribute and median charts
  • EWMA, CUSUM and moving average
  • Hotelling T² for related characteristics
  • Run rules with their expected false-alarm rate shown
  • Phase I limits locked for Phase II

Capability and measurement

  • Cp, Cpk, Pp and Ppk with confidence intervals
  • Stability check before capability is reported
  • Non-normal data handled, not ignored
  • Gauge R&R by ANOVA, AIAG MSA 4th edition
  • Type 1 study, attribute agreement, uncertainty

Risk and reliability

  • AIAG-VDA action priority, full table
  • Fault tree with minimal cut sets
  • System FMEA and FMEDA
  • Weibull analysis
  • Hypothesis tests, DOE and regression

Geometry and process

  • True position with bonus tolerance
  • Stack-up, worst case and RSS
  • Monte Carlo simulation, labelled as a model
  • Line balance, takt and bottleneck
  • Plant layout feasibility

Kept with its inputs

Each result records the engine, its version and the exact inputs it used.

Readings never overwritten

A measurement, once recorded, is kept. A correction is a new entry.

Checked a second way

Engines can recompute a result by an independent method and flag any disagreement.

In the product

An engine reports what the data supports, and no more.

These results were calculated by MIYOQA's engines from the demonstration programme that ships with the product: an electric coolant pump, flow rate at 20 kPa, and a bore diameter gauge study.

A process capability report for flow rate at 20 kPa: 125 readings between limits of 18 and 22 litres per minute, Pp 2.066, Ppk 2.026, Cp 2.086 and Cpk 2.045 with 95 percent confidence intervals, a normality test, and the verdict Not assessable because the process is not in statistical control.
Capability. Ppk 2.03 clears the 1.67 requirement, yet the engine marks the result Not assessable and blocks release: the process is not in statistical control, so the index cannot be interpreted. Each index carries its 95% confidence interval.
An X-bar and R control chart of flow rate at 20 kPa over 16 subgroups of five, with an event over subgroups 11 to 16 where tests 1, 3 and 5 fail, each test named in full with its suggested cause.
Control chart. Sixteen subgroups of five. The engine names each failed test in full (a point beyond 3 sigma, a six-point trend, two of three beyond 2 sigma), states the subgroups and suggests the likely cause. The rule set's expected false-alarm run length is shown with it.
A gauge R and R study for bore diameter: total gauge R and R 8.49 percent of study variation, repeatability 7.14 percent, reproducibility 4.59 percent, part-to-part 99.64 percent, verdict acceptable, with the analysis model stated.
Gauge R&R. Total 8.49% of study variation, so the gauge may be used. Both the standard-deviation and variance shares are shown, with the analysis model in force stated beside the verdict.

Review your own part on MIYOQA.

Bring one part's BOM, PFMEA and control plan. We will show what is connected and what is missing.

Request a demonstrationcontact@miyoqa.com