Steam sterilizer

Steam kills by temperature. Air in the chamber is what stops it.

A porous-load sterilizer pulls air out, fills the chamber with saturated steam and holds it. Pressure tells you what the temperature should be. The twin checks every cycle for air, tracks the leak test day by day, and times the vacuum pump, so a worn seal or a tired pump is a planned job.

Porous-load steam sterilizer, 600 L chamber, 121–134 °C cycles, vacuum-pulse air removal, clean steam

Built and run to EN 285, ISO 17665

Start with one utility See how we prove results

F0, 121 °C cycle: 20.2
F0, 134 °C cycle: 93
Steam at 134.5 °C: 3.09 bar abs
Leak limit as a hole: 0.37 mm

Anatomy and nameplate

1Chamber temperature and pressure. Pressure gives the saturation temperature. The two must agree.
2Drain temperature. The coldest point in the chamber, where air collects.
3Jacket pressure. Keeps the chamber walls hot so steam does not condense on them.
4Vacuum pump current and ultimate pressure. Pull-down time and the lowest pressure it reaches.
5Door seal pressure. Seal inflation. A tired seal leaks during the vacuum phases.
6Cycle phase. From the controller, so each reading is read in its phase.

Steam sterilizer nameplate
Chamber and cycles
Chamber	600 L, jacketed, pass-through with two doors
Cycles	Porous load at 121 °C (15 min hold) and 134 °C (3.5 min hold)
Air removal	3 vacuum pulses to 70 mbar
F0 at the drain, 121 °C cycle	20.2 (18.5 from the hold)
F0 at the drain, 134 °C cycle	93 (77 from the hold)
Saturation pressure	2.057 bar abs at 121.1 °C, 3.087 bar abs at 134.5 °C
Vacuum and leak test
Vacuum pump	Liquid ring, 90 m³/h, seal water at 15 °C
Pull-down, atmosphere to 70 mbar	70 s with a new pump
Leak test	Hold at 70 mbar, 5 min to settle, 10 min to measure
Leak limit	1.3 mbar/min (EN 285), a hole about 0.37 mm across in this chamber
Steam
Supply	Clean steam from a clean steam generator
Use	About 1,980 cycles a year

The clean utilities behind a batch

Three paths run side by side. Water goes from the still to the hot loop. Steam sterilizes parts, and product moves on to drying and cold storage. Air goes through HEPA filters into the graded rooms.

Water
Air
Steam
Product
Has its own twin page

The physics

The equations behind every curve on this page.

Lethality

F0 = Σ 10^((T − 121.1)/10)·Δt

Minutes at 121.1 °C that would do the same job. Each 10 °C hotter counts ten times as much.

Saturation check

T_measured vs T_sat(p_measured)

A gap means air in the chamber (cooler) or superheated steam (hotter).

Air in the steam

p = p_steam + p_air → T = T_sat(p − p_air)

Air takes part of the pressure and none of the heat.

Leak rate

rate = Δp / Δt ≤ 1.3 mbar/min

Pressure rise during the vacuum hold. EN 285 sets the limit.

Vacuum pull-down

t = (V/S)·ln((p0 − p_u)/(p1 − p_u))

Chamber size over pump speed. Warm seal water raises the lowest pressure the pump can reach.

Where the kill comes from

Lethality builds fastest at the top of the cycle. Air removal and drying add almost nothing.

F0 builds up during the hold

Chamber drain temperature, z = 10 °C, reference 121.1 °C

134 °C cycle, 3.5 min hold
121 °C cycle, 15 min hold

Lethal rate at 134.5 °C: 21.9 per minute
Lethal rate at 122 °C: 1.23 per minute
Lethal rate at 111 °C (pulse peaks): 0.10 per minute

Lethality climbs ten times for every 10 °C. Almost all of it comes from the hold, which is why the hold temperature has to be real steam temperature.

F0 = Σ 10^((T − 121.1)/10)·Δt

Is it really steam?

Saturated steam has one temperature for each pressure. The twin checks every hold against that line.

Measured temperature against saturation temperature for the measured pressure

134 °C cycle

Saturation temperature from chamber pressure
Measured, dry saturated steam
Measured, 5% air in the chamber

Chamber pressure in the hold: 3.087 bar abs
Saturation temperature: 134.50 °C
With 5% air: 132.75 °C (1.75 K low)
121.1 °C needs: 2.057 bar abs

Pressure says what the temperature should be. Air in the chamber adds pressure without adding heat, so the drain runs cold for its pressure. Superheat does the opposite.

T_measured vs T_sat(p) | with air: T = T_sat((1 − x_air)·p)

The leak test, read as a trend

Each daily test passes or fails. Read together, they show a seal wearing out weeks ahead.

Daily vacuum leak test, door seal wearing

600 L chamber held at 70 mbar

Test result
Model from seal leak area

Baseline: 0.32 ± 0.04 mbar/min
Hole that gives 1.3 mbar/min: 0.37 mm across
Warning before a failed test: 55 days

Each test passes until one does not. Read together, the results climb weeks before the limit, so the seal is changed on a planned day.

rate = Δp/Δt | dp/dt = Cd·A·p0·√(k/RT)·(2/(k+1))^((k+1)/(2(k−1)))·R·T / V

Failure modes

What breaks, what it looks like, what the twin does about it.

Failure mode	The physics	Signals that show it	How the twin catches it
Vacuum pump wear	A worn pump moves less gas per second, so each pulse takes longer.	Pull-down time up. Ultimate pressure up. Pump current changes.	Times every pull-down against the pump’s speed. At 60 m³/h instead of 90, each cycle takes 2.5 min longer to evacuate.
Door seal leak	A worn or under-inflated seal lets air in while the chamber is under vacuum.	Leak rate climbing test by test. Seal pressure low.	Trends the daily test and flags the rise 55 days before the 1.3 mbar/min limit.
Steam trap failure	A trap stuck shut leaves condensate in the jacket or drain. Stuck open, it wastes steam.	Drain temperature slow to rise. Jacket pressure unsteady. Steam use up.	Compares heat-up time and drain temperature with past cycles at the same load.
Air or non-condensable gas in the steam	Gas in the steam takes part of the pressure, so the chamber is cooler than its pressure says.	Drain temperature below saturation for the chamber pressure. At 5% air, 1.8 K low at 134.5 °C.	Checks the gap on every hold, and trends it across cycles and steam supply changes.
Drain sensor drift	A drifting sensor looks like a steam problem, or hides one.	Drain and chamber sensors disagree at the hold. Saturation gap shifts on every cycle at once.	Uses chamber pressure as a second reading. A steady offset on every cycle points at the sensor.

What the twin does not do

The sterilizer’s own controller and your release process decide if a load is sterile. The twin watches the equipment trend across cycles.
We do not change a cycle. We recommend. Your change control and QA decide.

How we catch it early

A physics twin and a PINN, working on one steam sterilizer.

The twin is a set of equations for this machine, tuned to its nameplate. Give it the flow, speed and conditions and it returns what every reading should be. It always gives the same answer for the same inputs.

A physics-informed neural network, or PINN, sits on top. It is trained on the plant’s own data and it is penalized whenever it breaks a physics rule. So it can only learn what the equations leave out: wear, fouling, friction. It cannot invent an answer that the machine could never produce.

Step 1
Measure
Flow, pressure, current, temperature, vibration. Whatever the asset already has.
Step 2
Physics twin
The equations of this machine, set to its nameplate. It says what the readings should be right now.
Step 3
Residual
Measured minus expected. Demand, weather and speed are already taken out.
Step 4
PINN
A small neural network that learns the cause of the gap, under the physics rules.
Step 5
Finding
A named cause, a date, and the kWh or hours at stake. An engineer reviews it.

loss = (measured − predicted)² + λ · (physics residual)²

The second term is the rulebook. It is zero when the network obeys the equations.

Why this beats black-box AI

A black-box model learns patterns from history. It needs examples of each failure, and it goes quiet when the pump runs at a point it has not seen. The twin starts from physics, so it works on day one. The PINN adds what physics cannot know about this particular machine.

That is also what makes the savings countable. The baseline is a calculation, not a guess, so the gap between baseline and meter is a number a customer can check.

What the twin checks on this asset

Drain temperature against saturation temperature for chamber pressure, every hold
F0 at the drain against the cycle’s usual value: 20.2 at 121 °C, 93 at 134 °C
Daily leak test as a trend against 1.3 mbar/min
Vacuum pull-down time against pump speed: 70 s to 70 mbar new
Jacket pressure and drain heat-up time against past cycles

	Fixed alarm	Black-box AI	Twin + PINN
Needs failure history to learn	No	Yes, lots	No
Says what is wrong	No	Rarely	Yes, by name
Works at a flow it has never seen	No	Often fails	Yes, the equations still hold
Puts a number on the saving	No	No	Yes, in kWh and dollars
Lead time on slow wear	Late	Varies	Weeks to months
Every number can be traced	Yes	No	Yes, to an equation

What the twin puts a number on

Energy and cost, from the equations.

Tired vacuum pump

+2.5 min a cycle

83 hours of sterilizer time a year at 1,980 cycles

Warm seal water

+1.0 min a cycle

Seal water at 30 °C instead of 15 °C

Seal leak warning

55 days

From the first rise in the daily test to a failed test

Air found in the hold

1.8 K

5% air at 134.5 °C. The twin checks every cycle.

What we do for you

We watch it. We catch it. We prove it.

Our reliability engineers run the twin on your steam sterilizer, review every finding, and help your crew fix it. After the repair we compare the meter to the baseline and write the result in the ledger.

Start with one utility See the 90-day pilot

More assets

More from pharmaceutical, then the lead asset of each other industry.