LIVEdataset aec-bench@releasetasks 552models 18disciplines 5last submission … · built …

electricalwith-tool

Cv Liquid Incompressible

Sizes control valves for incompressible liquid service by computing the required flow coefficient Cv from the ISA-75.01.01 equation Kv = Q * sqrt(SG / deltaP_eff), with Cv = 1.156 * Kv. Checks for choked (cavitating) flow using the liquid pressure recovery factor FL and critical pressure ratio factor FF, essential for process control and piping system design.

with-tool: The model is given an executable Python calculator script.

Standards

IEC 60534-2-1 ISA-75.01.01

How this task is generated

One template produces many comparable benchmark tasks while keeping the scoring contract fixed.

01
Template
The reusable contract shown on this page.
02
Scenario
An archetype and site context are sampled.
03
Difficulty tier
Inputs may be hidden at harder tiers.
04
Task prompt
The model responds with the declared outputs.

Parameters

Inputs the model receives, and the outputs it is scored on.

Inputs

7 inputs

Always given

Included directly in every task prompt.

Flow rate
flow_rate_m3_h
Volumetric flow rate through the valve
0.5 – 500 m³/h
Upstream pressure
upstream_pressure_bar
Upstream pressure (P1) at valve inlet
1 – 100 bar
Downstream pressure
downstream_pressure_bar
Downstream pressure (P2) at valve outlet
0.5 – 99 bar

Derived from scenario

Sampled from the scenario and inferable from its description.

Fluid specific gravity
fluid_specific_gravity
Fluid specific gravity relative to water at 15°C
Derived from the archetype scenario. Hidden at hard difficulty.
0.5 – 2
Fluid vapor pressure
fluid_vapor_pressure_bar
Fluid vapor pressure at operating temperature
Derived from the archetype scenario. Hidden at hard difficulty.
0.01 – 50 bar
Fluid critical pressure
fluid_critical_pressure_bar
Fluid thermodynamic critical pressure
Derived from the archetype scenario. Hidden at hard difficulty.
10 – 250 bar
Fl recovery factor
fl_recovery_factor
Liquid pressure recovery factor FL of the valve
Derived from the archetype scenario. Hidden at hard difficulty.
0.5 – 1

Scored outputs

4 outputs

Pressure drop bar

pressure_drop_bar

Actual pressure drop across the valve (bar)

Scores if within ±3% of the reference value.

Cv required

cv_required

Required valve flow coefficient Cv

Scores if within ±3% of the reference value.

Choked pressure drop bar

choked_pressure_drop_bar

Choked (limiting) pressure drop (bar)

Scores if within ±3% of the reference value.

Is choked

is_choked

Choked flow indicator (1.0 = choked, 0.0 = not choked)

Scores if within ±1% of the reference value.

Difficulty

Each template is sampled at three tiers. Harder tiers may hide inputs, forcing the model to infer them from the scenario description.

easy

All inputs given

Water service, moderate pressures, all parameters given, non-choked conditions

Fl recovery factor restricted to: {'min': 0.85, 'max': 0.95}

medium

All inputs given

Any fluid type and pressure range, all parameters given

hard

Some inputs hidden

Fluid properties and valve FL hidden, agent must infer from process context

Hidden inputs

Fluid specific gravityfluid_specific_gravity
Fluid vapor pressure barfluid_vapor_pressure_bar
Fluid critical pressure barfluid_critical_pressure_bar
Fl recovery factorfl_recovery_factor

Prompt replacement text

The process involves {{ archetype.description }} at a {{ archetype.site_context }} facility

Task bundle

The exact instruction and parameter contract used to generate this task, pinned to the published library source.

/workspace

instruction.md
cv-liquid-incompressible_calc.py

Teal lines show Jinja input conditions, not task visibility policy. A line renders only when that input or tool is visible.

1You are a senior instrumentation and controls engineer specializing in control valve sizing for process plants.2 3## Problem4 5Calculate the required flow coefficient (Cv) for a control valve in incompressible liquid service using the ISA-75.01.01 / IEC 60534-2-1 sizing method. Determine whether the flow is choked (cavitating).6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Volumetric flow rate (Q) | {{ flow_rate_m3_h }} | m³/h |12| Upstream pressure (P1) | {{ upstream_pressure_bar }} | bar |13| Downstream pressure (P2) | {{ downstream_pressure_bar }} | bar |14{% if fluid_specific_gravity is defined %}15| Fluid specific gravity (SG) | {{ fluid_specific_gravity }} | - |16{% endif %}17{% if fluid_vapor_pressure_bar is defined %}18| Fluid vapor pressure (Pv) | {{ fluid_vapor_pressure_bar }} | bar |19{% endif %}20{% if fluid_critical_pressure_bar is defined %}21| Fluid critical pressure (Pc) | {{ fluid_critical_pressure_bar }} | bar |22{% endif %}23{% if fl_recovery_factor is defined %}24| Liquid pressure recovery factor (FL) | {{ fl_recovery_factor }} | - |25{% endif %}26{% if archetype_description is defined %}27 28### Process Context29 30{{ archetype_description }}31{% endif %}32 33{% if tool_available %}34## Available Tool35 36A control valve sizing tool is available at `/workspace/cv-liquid-incompressible_calc.py`. Run it with:37 38```bash39python3 /workspace/cv-liquid-incompressible_calc.py --help40```41 42You may use this tool to verify your calculations or compute values directly.43{% endif %}44 45## Required46 47Calculate the following:48 491. Actual pressure drop across the valve (bar)502. Required valve flow coefficient Cv513. Choked (limiting) pressure drop (bar)524. Whether the flow is choked (1.0 = choked, 0.0 = not choked)53 54## Applicable Standards55 56- ISA-75.01.01 — Industrial-Process Control Valves, Flow capacity sizing equations57- IEC 60534-2-1 — Industrial-process control valves, Part 2-1: Flow capacity58 59## Constraints60 61- No internet access is available. Work from engineering knowledge and the provided tool.62- Use the ISA-75.01.01 sizing method for incompressible liquids without attached fittings (Fp = 1):63  - **Actual pressure drop:** deltaP = P1 - P264  - **Critical pressure ratio factor:** FF = 0.96 - 0.28 * sqrt(Pv / Pc)65  - **Choked pressure drop:** deltaP_choked = FL² × (P1 - FF × Pv)66  - **Effective pressure drop:** deltaP_eff = min(deltaP, deltaP_choked)67  - **Choked flow check:** if deltaP >= deltaP_choked, the flow is choked68  - **Metric flow coefficient:** Kv = Q × sqrt(SG / deltaP_eff), where Q in m³/h, deltaP_eff in bar69  - **US flow coefficient:** Cv = 1.156 × Kv70- All pressures are absolute (bar). Specific gravity is dimensionless relative to water at 15°C.71 72## Output Format73 74Show your step-by-step working in Markdown, including the choked flow check, effective pressure drop selection, and Cv calculation. At the end of your solution, include a JSON block with your final answers in exactly this format:75 76```json77{78  "pressure_drop_bar": <numeric_value>,79  "cv_required": <numeric_value>,80  "choked_pressure_drop_bar": <numeric_value>,81  "is_choked": <1.0_or_0.0>82}83```84 85Write your complete solution to `/workspace/output.md`.86

Scenario archetypes

Each generated task is drawn from one of these realistic scenario bands.

Site contexts ground each scenario in a real locale the model can use to infer hidden values.

Water utility

water_utility

Water utility service — clean water, low pressure

municipal-water-treatmentpumping-station-transfer

Parameter ranges

flow_rate_m3_h: 5 – 100
upstream_pressure_bar: 3 – 10
downstream_pressure_bar: 1 – 6
fluid_specific_gravity: 0.99 – 1.01
fluid_vapor_pressure_bar: 0.02 – 0.05
fluid_critical_pressure_bar: 220 – 221
fl_recovery_factor: 0.8 – 0.95

Petrochemical light

petrochemical_light

Petrochemical light hydrocarbon liquid service

refinery-distillation-unitpetrochemical-transfer-line

Parameter ranges

flow_rate_m3_h: 10 – 200
upstream_pressure_bar: 5 – 40
downstream_pressure_bar: 2 – 30
fluid_specific_gravity: 0.65 – 0.85
fluid_vapor_pressure_bar: 0.5 – 10
fluid_critical_pressure_bar: 30 – 50
fl_recovery_factor: 0.6 – 0.9

Chemical process

chemical_process

Chemical process — moderate-density process liquid

chemical-plant-reactor-feedsolvent-blending-unit

Parameter ranges

flow_rate_m3_h: 1 – 80
upstream_pressure_bar: 3 – 25
downstream_pressure_bar: 1 – 15
fluid_specific_gravity: 0.9 – 1.5
fluid_vapor_pressure_bar: 0.05 – 5
fluid_critical_pressure_bar: 40 – 100
fl_recovery_factor: 0.7 – 0.95

High pressure oil

high_pressure_oil

High-pressure oil or heavy hydrocarbon service

offshore-production-platformcrude-oil-pipeline-terminal

Parameter ranges

flow_rate_m3_h: 20 – 500
upstream_pressure_bar: 20 – 100
downstream_pressure_bar: 5 – 60
fluid_specific_gravity: 0.82 – 1.1
fluid_vapor_pressure_bar: 0.01 – 2
fluid_critical_pressure_bar: 30 – 80
fl_recovery_factor: 0.5 – 0.85

Example task

refinery-distillation-unit-petrochemical-light-preview — hard difficulty, some inputs hidden.

Petrochemical light hydrocarbon liquid service. refinery-distillation-unit. Required outputs: pressure_drop_bar, cv_required, choked_pressure_drop_bar, is_choked

The model sees

Scenario context and visible inputs.

flow_rate_m3_h: 10 to 200 m³/h
upstream_pressure_bar: 5 to 40 bar
downstream_pressure_bar: 2 to 30 bar

Executable tool: cv-liquid-incompressible_calc.py

The model must infer

Inputs withheld at this difficulty.

Fluid specific gravity
fluid_specific_gravity
Fluid vapor pressure bar
fluid_vapor_pressure_bar
Fluid critical pressure bar
fluid_critical_pressure_bar
Fl recovery factor
fl_recovery_factor

Stand-in text in the prompt

The process involves {{ archetype.description }} at a {{ archetype.site_context }} facility

The model must produce

The scored JSON answer schema.

{
  "pressure_drop_bar": <number>,
  "cv_required": <number>,
  "choked_pressure_drop_bar": <number>,
  "is_choked": <number>
}

pressure_drop_bar · scored within ±3%
cv_required · scored within ±3%
choked_pressure_drop_bar · scored within ±3%
is_choked · scored within ±1%

Cv Liquid Incompressible

How this task is generated

Template

Scenario

Difficulty tier

Task prompt

Parameters

Inputs

Scored outputs

Pressure drop bar

Cv required

Choked pressure drop bar

Is choked

Difficulty

easy

medium

hard

Task bundle

Scenario archetypes

Water utility

Petrochemical light

Chemical process

High pressure oil

Example task

The model sees

The model must infer

The model must produce