DeepHow Confidential — prepared for Lear

Lear · Body 2 · 31XX-2 · measured 25 August 2026 · v2, 1-second sampling

Body 2 Work Content

What the line actually does, measured from the cameras already installed — with no reference to the standard work sheet.

Work content varies 2.6× across the twelve stations measured — from 2.2 to 5.6 person-minutes per board, and each station's own load swings three- to eightfold from board to board. Seven stations show operators chasing boards downstream because the work did not fit; two habitually work ahead. The imbalance does not travel down the line, which means it can be fixed one station at a time.

This is v2, rebuilt at 1-second sampling — 80,431 measurements in place of 5,381. Measuring 15 times denser moved no station by more than 0.20 person-minutes and the average station by 0.08, so nothing here overturns the first version. What it does is let these figures be held against your own floor observations, second by second.

Read that 2.6× as an upper bound. Now that every station is confirmed to run two operators, the cameras can be checked against a known crew — and what each one sees ranges from 46% to 130% of expected operator-time. A station whose camera sees less reads lighter, and across the twelve the two track at r = −0.86. So the true spread is narrower than 2.6×: the light end is understated where coverage is poor, and the heavy end overstated where a region admits people who belong to the next station. The chase index below is not affected — it is a share of each station's own appearances, so it survives whatever the camera misses, which is why the two moves rest on it rather than on these magnitudes. Fixing the coverage is the first item on the improvement list.

Work content per board

person-minutes of hands-on work · every board measured, not planned

B2C14
5.64
B2C15
4.26
B2C17
4.17
B2C8
4.14
B2C10
4.12
B2C18
3.96
B2C13
3.63
B2C6
3.63
B2C7
3.35
B2C5
3.23
B2C11
2.64
B2C12
2.19
02.0 4.06.0 8.010.0 5.97 — available now 7.03 at takt
▭ middle 80% of boards (p10–p90) │ median board   ● average ├─┤ lightest to heaviest board ■ work does not fit — operators chase boards downstream ■ spare capacity
Every station is shown as a distribution, not a number. At the line's current speed — a board every 179 seconds — a two-person station has 5.97 person-minutes to finish each board; at takt (211 s) it would have 7.03. Every average sits below both lines, and that is the trap. B2C14 averages 5.64 but runs to 7.50 on its heaviest board, and is over the line on 56% of them. B2C5 averages 3.23 and reaches 8.58. The work fits on average at every station and fails to fit regularly at several. Board-by-board detail: every station, every board, which also carries a second-by-second view for comparing against observations taken on the floor.

Where the work does not fit

chase index against work content · twelve stations · dashed lines are the medians

The line tells you this itself. When an operator cannot finish inside the pitch, they follow the board downstream rather than let it go incomplete. We counted how often that happens at each station — no standard times, no plan, just what the operators did.

2.0 3.0 4.0 5.0 6.0 0 5 10 15 20 cannot finish — but volume is not why overloaded — move work out spare capacity heavy, and coping B2C7 — 3.35 p-min/board, chase index 17.3, left downstream 67 vs upstream 3B2C7 B2C10 — 4.12 p-min/board, chase index 14.8, left downstream 90 vs upstream 5B2C10 B2C5 — 3.23 p-min/board, chase index 14.2, left downstream 97 vs upstream 26B2C5 B2C6 — 3.63 p-min/board, chase index 12.3, left downstream 56 vs upstream 11B2C6 B2C13 — 3.63 p-min/board, chase index 12.1, left downstream 111 vs upstream 46B2C13 B2C18 — 3.96 p-min/board, chase index 12.1, left downstream 73 vs upstream 85B2C18 B2C11 — 2.64 p-min/board, chase index 10.9, left downstream 60 vs upstream 65B2C11 B2C17 — 4.17 p-min/board, chase index 9.2, left downstream 132 vs upstream 82B2C17 B2C14 — 5.64 p-min/board, chase index 6.0, left downstream 38 vs upstream 47B2C14 B2C15 — 4.26 p-min/board, chase index 3.9, left downstream 54 vs upstream 36B2C15 B2C12 — 2.19 p-min/board, chase index 3.9, left downstream 23 vs upstream 54B2C12 B2C8 — 4.14 p-min/board, chase index 2.2, left downstream 12 vs upstream 32B2C8 work content — person-minutes per board → chase index →
The two measurements are independent, and that is the finding. Chase index is the share of a station's own operator-appearances that end with the operator leaving downstream — a comparison between stations, not a count of boards (note 3). It is uncorrelated with work content (r = −0.19), and equally uncorrelated with everything the distribution above shows (note 4). Stations land in all four quadrants: B2C14 carries the most work on the line and copes, while B2C7 carries below-average work and cannot. So a station in trouble is not identified by how much work it holds — adding minutes to a coping station is safe, and taking them off a struggling one may not help if volume was never its problem. Dashed lines are the medians; hover a point for its raw counts.

Two moves to make first

adjacent stations · every measurement agrees

Move work from B2C7 into B2C8

the strongest signal on the line

B2C7 has the highest chase index on the line at 17.3 — its operators followed the board out 67 times against 3 the other way. B2C8, immediately downstream, has the lowest at 2.2 and habitually works ahead. They are adjacent, so the transfer is a work-element move rather than a re-layout. This move rests on behaviour, not on volume — per operator present the two stations are within 1% of each other — which is why it holds whatever the crew numbers turn out to be. Size it carefully all the same: B2C8 is already over the 5.97 line on 15% of boards.

B2C7 · 3.35 p-min
chase 17.3 — cannot finish
→
B2C8 · 4.14 p-min
chase 2.2 — works ahead today

Move work from B2C13 into B2C12

the widest actionable gap — pending crew numbers

B2C12 carries the least work on the line at 2.19 person-minutes per board and spends its spare time working ahead; B2C13 next door carries 3.63 and chases boards at 12.1. Of the gaps between adjacent stations, B2C13 ↔ B2C14 is widest at 2.01, but B2C14 already carries the most work on the line and cannot receive any, and B2C10 ↔ B2C11 at 1.48 involves a camera we do not trust. That leaves this pair, at 1.44, as the widest actionable one.

Check B2C12's camera coverage before acting on this one. Lear has since confirmed every station is crewed with two operators, which settles the capacity line at 5.97 p-min and makes total work content the right basis for comparison — so the 1.66 p-min gap is real as measured. What is not settled is whether B2C12 is genuinely light. Its camera sees an average of 0.93 operators against a crew of two — 46% of expected operator-time, the lowest on the line — and 22% of the engaged work in its own frame falls outside its measured region. Across the twelve stations, unseen operator-time and measured work content correlate at r = −0.86: the stations that look lightest are substantially the ones the cameras see least. B2C12 may be the lightest station on the line, or the least observed one, and the two cannot be told apart from this footage. Reposition that camera and re-measure before moving work into it.

B2C13 · 3.63 p-min
chase 12.1
→
B2C12 · 2.19 p-min
chase 3.9 — least on the line

No cascading-down effect

an overload at one station does not push work onto the next

A reasonable worry with this kind of measurement is that one overloaded station pushes work onto the next, which pushes it onto the next. If that were happening you could not act on any single station without tracing the whole line first.

It is not happening here. Pressure builds over two or three stations and is then absorbed by a station with spare capacity. B2C8 and B2C12 both sit immediately after a run of chasing and act as relief valves.

We also checked whether an operator chasing a board out of one station makes the next station chase too, sweeping every delay from 0 to 300 seconds in 15-second steps — fine enough to catch a whiplash inside a single board cycle. It does not: the transit window sits 4% above chance (note 5), and the effect is the same size in the reverse direction, which a real hand-off could not be. Each station's number is its own, which is why the moves above can be made independently and in either order.

B2C5 ██████████████ chase 14.2 B2C6 ████████████ chase 12.3 absorbed B2C7 █████████████████ chase 17.3 builds B2C8 ██ chase 2.2 absorbed · · · B2C9 — no camera · · · B2C10 ███████████████ chase 14.8 B2C11 ███████████ chase 10.9 absorbed B2C12 ████ chase 3.9 absorbed B2C13 ████████████ chase 12.1 builds B2C14 ██████ chase 6.0 absorbed B2C15 ████ chase 3.9 absorbed · · · B2C16 — no camera · · · B2C17 █████████ chase 9.2 B2C18 ████████████ chase 12.1

What this needs to become routine

from a one-off study to a shift-by-shift measure

Notes on method

  1. What was measured. Operators were detected by a pose model in a region drawn on each station's work area. An operator counts as working when their wrists are low relative to their own shoulders and hips — reaching into the board. Validated against 36 frames scored by hand across 9 stations: mean absolute error 0.28 operators for engagement, 0.39 for presence, within one operator on 97% of frames. Sampled every second in this version: 80,431 measurements across the twelve stations, against 5,381 at the 15-second sampling the first version used. The two agree exactly wherever they share a timestamp (3,134 of 3,134 matched samples identical), so this is the same measurement read more densely, not a new one.
  2. Work content per board = engaged person-minutes per hour ÷ 20.1 boards per hour. Pitch of 179 s was measured three independent ways — board QR tracking, and occupancy rhythm at both 1-second and 15-second sampling — agreeing within 4 seconds. Takt of 211 s was supplied by Lear.
  3. Chase index is the percentage of a station's own operator-appearances that end at the downstream edge. It is deliberately not expressed per board: the tracker fragments a single person into several tracks when they are occluded, which inflates absolute counts by an unknown factor. Dividing by appearances — inflated the same way — largely cancels this. Ranking by raw hourly rate instead gives a materially different order (rank correlation 0.62), and we use the fragmentation-robust version.
  4. Work content and chase index are independent — across the twelve stations r = −0.19. They measure different things: how much work is done, versus how much did not fit in the pitch. The chase index is equally uncorrelated with everything the distribution shows — against the share of boards over the 5.97 line r = −0.28, against a station's spread r = +0.26. Knowing how much work a station carries tells you almost nothing about whether its operators can finish it, which is why both measurements are on this page.
  5. Cascade test. Two passes. At 5-minute resolution, correlation between downstream-exit counts across nine adjacent pairs was +0.14 in the same block and +0.02 one block later. Because station transit is 120 s against a 300 s block, that pass could not rule out a faster whiplash inside a single block, so it was repeated on timestamped tracks at 15-second resolution, sweeping lags 0–300 s. The transit window (90–150 s) came in +4.0% over chance across all nine pairs (p = 0.34); no lag near 120 s rose above noise. Two controls confirm it: the reversed direction shows the same elevation as the forward one (+11% against +12% on the seven pairs excluding B2C11) — and a cascade is directional, so a symmetric effect is not one — while non-adjacent stations show +2.7%. Both nulls preserve the line's own 179 s rhythm, to which every station is phase-locked. This excludes a cascade accounting for more than about 12% of downstream chasing events; it does not exclude a smaller one.
  6. Direction is behaviour, not camera geometry. Correlation between where operators typically stand within a region and which edge they exit by is −0.01. Stations with high chase indices also drift downstream while working (+0.04 to +0.10 of region width); B2C12 drifts upstream.
  7. Cameras do not overlap, so no operator is counted twice. Confirmed three ways: feature matching between adjacent views, visual inspection, and board-ID coincidence — no board appeared in two cameras at the same instant across 14,000 tracked appearances.