Engineering lab / Interactive technical portfolio
Synthetic demonstrationContinuous improvement & experiments
Investigate a loss. Test the mechanism. Propose a verifiable change.
Factory and quality workspaces
All records below are fictional; no employer or customer engagement is implied.
Can process settings improve dimensional margin without excessive cycle time or energy?
Eligible study settings
2 / 8
All three response bounds must meet the selected limits.
Fastest eligible setting
S8
70.1 s per cut; confirmation required.
Selected mean error
22.8 µm
95% mean interval: 16.6 to 28.9 µm.
Selected cut energy
32.8 Wh
95% mean interval: 32.3 to 33.4 Wh per cut.
SYN-CI-OBS-01 / fixed 8-skid window
Loss register
Same denominator: person-minutes per eight-skid teaching window, normalized per skid. Travel uses a time assumption; the other entries are synthetic event logs. These exposures do not establish causes or throughput.
CI-E04 / 45.00 person-min / 8 skids
- SYN-RWK-01–03: 18, 12 and 15 attended person-minutes for three fictional repair events.
- Inspection notes raise dimensional consistency as a hypothesis. No causal attribution, scrap count or link to existing SPC lots is established.
Use the randomized machining experiment to test the setting mechanism. Confirm on new parts before claiming any reduction in historical rework.
SYN-VS25 / M1 / SYN-MC-01
Controlled machining experiment
Three factors × two levels × four independent replications = 32 cuts. The study tests dimensional margin, cut time and cut energy on new fictional blanks. It does not directly estimate the loss-register rework minutes.
- A / Feed
- 0.12 → 0.20 mm/rev
- B / Cutting speed
- 120 → 180 m/min
- C / Coolant flow
- 6 → 10 L/min
Drawing limits remain 24.90–25.10 mm. The editable mean-error guard is a tighter study assumption around 25.00 mm, not a revised drawing tolerance.
Design controls and evidence limits
- Same fictional material grade, blank geometry, fixture, tool type and calibrated measurement method.
- One independent blank and a reset/stabilized setup per run; four replications of all eight settings.
- Completely randomized run order; no tool-wear trend, carryover, blocks or nuisance drift in this generator.
- Cycle response is cut-only elapsed seconds; energy is machine-plus-coolant Wh during that cut.
Historical associations suggest questions. Randomized setting comparisons estimate effects only within this controlled synthetic mechanism.
Select → inspect → propose
Compare settings under engineering constraints
A setting is eligible when its entire 95% mean-error interval fits the guard, its single-cut prediction interval fits the drawing, and the cycle/energy mean upper bounds meet their limits. Intervals are pointwise, not simultaneous guarantees after selection. Fastest eligible means lowest mean cut time among these eight tested settings.
S8 / Eligible for confirmation
Feed 0.20 mm/rev · Speed 180 m/min · Coolant 10 L/min
Single-cut diameter-error prediction: 9.0 to 36.5 µm.
| Setting / A,B,C | Diameter error | Cut cycle | Cut energy | Study screen |
|---|---|---|---|---|
− / − / − | -23.4 [-29.6 to -17.3] | 97.8 [96.5 to 99.0] | 37.1 [36.5 to 37.7] | Cycle mean upper bound exceeds limit; Energy mean upper bound exceeds limit |
+ / − / − | 28.8 [22.6 to 34.9] | 76.3 [75.0 to 77.5] | 31.2 [30.6 to 31.8] | Eligible for confirmation |
− / + / − | 3.3 [-2.8 to 9.5] | 81.0 [79.8 to 82.3] | 29.5 [28.9 to 30.0] | Cycle mean upper bound exceeds limit |
+ / + / − | 97.9 [91.8 to 104.1] | 66.2 [65.0 to 67.5] | 27.1 [26.5 to 27.7] | Mean-error interval outside guard band; Single-cut prediction interval outside drawing limits |
− / − / + | 1.2 [-5.0 to 7.3] | 102.4 [101.1 to 103.7] | 43.2 [42.7 to 43.8] | Cycle mean upper bound exceeds limit; Energy mean upper bound exceeds limit |
+ / − / + | -21.2 [-27.3 to -15.0] | 79.5 [78.3 to 80.8] | 37.1 [36.5 to 37.7] | Cycle mean upper bound exceeds limit; Energy mean upper bound exceeds limit |
− / + / + | -22.6 [-28.8 to -16.4] | 84.8 [83.6 to 86.1] | 34.2 [33.6 to 34.8] | Cycle mean upper bound exceeds limit |
+ / + / + | 22.8 [16.6 to 28.9] | 70.1 [68.8 to 71.4] | 32.8 [32.3 to 33.4] | Eligible for confirmation |
SYN-DOE-M01 Rev A / seed 41973
Inspect the randomized runs
SYN-DOE-01 · SYN-EXP-V001 · S6 · replicate 1
24.9785 mm · 80.4 s/cut · 36.0 Wh/cut
Each dot is an independent cut. Randomized order is not a time-series process trend. Inspection nonconformances: 2 / 32 experimental blanks; not a production defect rate.
All 32 run records
| Order / blank | Setting / replicate | Diameter / mm | Cycle / s | Energy / Wh |
|---|---|---|---|---|
| 1 / SYN-EXP-V001 | S6 / 1 | 24.9785 | 80.4 | 36.0 |
| 2 / SYN-EXP-V002 | S3 / 4 | 24.9967 | 79.2 | 29.7 |
| 3 / SYN-EXP-V003 | S2 / 2 | 25.0327 | 75.8 | 30.3 |
| 4 / SYN-EXP-V004 | S5 / 2 | 24.9994 | 102.1 | 43.5 |
| 5 / SYN-EXP-V005 | S6 / 3 | 24.9745 | 79.9 | 37.0 |
| 6 / SYN-EXP-V006 | S1 / 4 | 24.9723 | 98.2 | 37.2 |
| 7 / SYN-EXP-V007 | S8 / 2 | 25.0123 | 70.0 | 33.1 |
| 8 / SYN-EXP-V008 | S4 / 3 | 25.1017 | 65.8 | 27.6 |
| 9 / SYN-EXP-V009 | S5 / 3 | 25.0070 | 103.3 | 42.4 |
| 10 / SYN-EXP-V010 | S8 / 4 | 25.0295 | 71.7 | 32.9 |
| 11 / SYN-EXP-V011 | S1 / 2 | 24.9707 | 98.3 | 37.4 |
| 12 / SYN-EXP-V012 | S4 / 2 | 25.0948 | 63.6 | 26.4 |
| 13 / SYN-EXP-V013 | S7 / 2 | 24.9793 | 84.0 | 34.5 |
| 14 / SYN-EXP-V014 | S8 / 3 | 25.0263 | 70.0 | 32.4 |
| 15 / SYN-EXP-V015 | S2 / 1 | 25.0158 | 75.7 | 31.3 |
| 16 / SYN-EXP-V016 | S6 / 2 | 24.9789 | 80.8 | 37.6 |
| 17 / SYN-EXP-V017 | S4 / 4 | 25.0920 | 68.6 | 27.1 |
| 18 / SYN-EXP-V018 | S8 / 1 | 25.0229 | 68.8 | 32.9 |
| 19 / SYN-EXP-V019 | S3 / 2 | 25.0032 | 81.5 | 29.7 |
| 20 / SYN-EXP-V020 | S7 / 1 | 24.9805 | 84.7 | 34.2 |
| 21 / SYN-EXP-V021 | S7 / 3 | 24.9758 | 85.4 | 33.6 |
| 22 / SYN-EXP-V022 | S1 / 1 | 24.9832 | 97.8 | 37.3 |
| 23 / SYN-EXP-V023 | S6 / 4 | 24.9835 | 77.1 | 37.9 |
| 24 / SYN-EXP-V024 | S5 / 4 | 24.9927 | 101.7 | 44.0 |
| 25 / SYN-EXP-V025 | S3 / 1 | 25.0078 | 81.9 | 29.6 |
| 26 / SYN-EXP-V026 | S2 / 3 | 25.0328 | 76.2 | 31.2 |
| 27 / SYN-EXP-V027 | S2 / 4 | 25.0338 | 77.3 | 32.1 |
| 28 / SYN-EXP-V028 | S7 / 4 | 24.9740 | 85.2 | 34.4 |
| 29 / SYN-EXP-V029 | S3 / 3 | 25.0058 | 81.5 | 28.8 |
| 30 / SYN-EXP-V030 | S1 / 3 | 24.9801 | 96.8 | 36.4 |
| 31 / SYN-EXP-V031 | S4 / 1 | 25.1033 | 67.0 | 27.3 |
| 32 / SYN-EXP-V032 | S5 / 1 | 25.0056 | 102.4 | 43.1 |
A = feed / B = speed / C = coolant
Separate main effects and interactions
High-minus-low contrasts; all seven factorial terms are estimated. Replication supplies pure-error variance with 24 degrees of freedom. Whiskers show pointwise 95% intervals, not a causal claim about the historical loss register.
Effect estimates and calculation
| Term | Effect | 95% interval |
|---|---|---|
| A | 42.4 | 38.1 to 46.8 |
| B | 29.0 | 24.7 to 33.4 |
| C | -31.6 | -36.0 to -27.3 |
| AB | 27.5 | 23.2 to 31.9 |
| AC | -30.9 | -35.3 to -26.6 |
| BC | -18.9 | -23.3 to -14.6 |
| ABC | 6.3 | 2.0 to 10.7 |
Average over the third factor
Investigate a two-factor interaction
Each point averages eight cuts over both levels of the third factor. Nonparallel slopes indicate an interaction; a main effect alone can hide the tradeoff. The fitted model also includes the three-factor interaction.
| Second factor | First factor low | First factor high |
|---|---|---|
| Low / solid | -10.0 | 63.4 |
| High / dashed | -10.7 | 0.8 |
Study selection is not implementation
Propose the countermeasure and verification
S1 → S8: estimated cut-time reduction 27.6 s/cut; energy reduction 4.2 Wh/cut. These are study mean differences, not realized savings or factory capacity.
Checkmarks record review of a future verification plan. They do not create test evidence, execute trials or approve a change.
Verify gauge resolution/bias, fixture, tool condition, material and stabilized coolant. Record actual setup and calibration evidence.
Execution: not run · Evidence: none
Run 12 new blanks at the proposed setting, across three fresh setups. Check every diameter against 24.90–25.10 mm; compare mean error, cut time and cut energy against the saved study limits. Investigate any failure; no automatic approval.
Execution: not run · Evidence: none
Collect at least 100 subsequent individual measurements across representative tool life and shifts. Assess stability before estimating capability or revising control limits; define a hold/investigate response to signals.
Execution: not run · Evidence: none
Propose SYN-SW-M01 Rev B and SYN-CP-M01 Rev B with settings, setup checks, first-off inspection, reaction plan and traceable change approval. Keep current work and quality holds until reviewed.
Execution: not run · Evidence: none
The existing SPC history SYN-RUN-01 is unchanged and supplies no confirmation evidence for this experiment. Use its investigation pattern when planning new monitoring records.
Method, responsibility, assumptions and lessons
This independently authored synthetic study demonstrates loss framing, experimental design, reproducible calculations and a reviewable change record. The decision is whether a tested setting warrants confirmation. Randomization supports controlled comparisons; independent confirmation, measurement validity and sustained stability remain necessary.
- Synthetic equations encode the mechanism. Experimental effects describe this generator, not validated real machining physics.
- Only eight tested corners are compared; no interpolation, global optimum, production capability or machine recommendation.
- Pointwise 95% intervals assume independent normal errors and equal variance within each response. They are not simultaneous selection guarantees.
- No real implementation, confirmation trials, cost savings, customer results or approval evidence exists.
- Cut seconds cannot replace the factory's six-minute machining-and-inspection work assumption or establish capacity.
The statistical basis follows the NIST/SEMATECH handbook. Manufacturing settings, limits, losses and responses are teaching assumptions.
Factory planning scenario and reset
factory-1.0 · Synthetic operation
Plan: 8 skids / 54.8 h assumed work. Baseline: 8 skids / 54.8 h.
This tab retains your scenario and demo reviews. Reset factory restores the original state.
One connected perspective
Physical requirements become data. Data becomes evidence. Evidence informs an operational decision. These demonstrations connect my manufacturing and quality foundation with the systems thinking used in enterprise transformation and product engineering.
Professional context
Explore my documented manufacturing experience, SAP readiness work and data and product development. The synthetic lab is separate from those professional records.
Download technical README