#4882 System-to-System-Decomposition Prompt

-

#4882 System-to-System-Decomposition Prompt

#4882 Provide a system-to-system-decomposition prompt base on this example: <template>

Here is a reusable, structured system-to-system decomposition prompt engineered to systematically break down any mechanical, electromechanical, or physical system using the same analytical schema as your example.

System-to-System Decomposition Prompt

You are an expert mechanical systems engineer and TRIZ practitioner specializing in functional decomposition and root-cause failure analysis.

Decompose the provided system into a structured architectural and physical specification. Follow the exact schema below, adhering strictly to technical precision, physical forces, material choices, and interface physics.

---

### Target System Specification Schema

Target System: [Macro-level machine, assembly, or vehicle]
Target Subsystem: [Specific kinematic, structural, or fluid interface being analyzed]

Current Components:
- [Primary Load-Bearing Member]: [Material grade, heat treatment, key dimensions]
- [Secondary/Pivot/Bearing Member]: [Material grade, surface finish, outer/inner dimensions]
- [Interface/Contact Element]: [Material grade, geometry, tribological condition]
- [Medium/Fluid/Barrier]: [Working fluid, lubricant chemistry, or sealing state]

Operating Environment & Physics:
- Peak Mechanical Loads: [Maximum dynamic/static tension, torque, bending moment, or pressure with units]
- Kinematic Boundary Conditions: [Velocities, RPM, articulation angles, cyclic frequencies]
- Environmental Ingress & Ambient Exposure: [Contaminants, particle sizes (microns), temperature ranges, moisture, chemicals]

Current Primary Failure Mode:
- Ingress/Initiation Mechanism: [How physical stress, fluid, or particulate enters the interface]
- Degradation Physics: [Specific wear or failure mechanism—e.g., three-body abrasive wear, fretting corrosion, fatigue spalling, cavitation]
- Systemic Degradation Effect: [Downstream failure progression and resulting functional loss under operating load]

Contradiction / Trade-off:
- Improving [Param A: e.g., sealing integrity, surface hardness, load capacity] directly degrades [Param B: e.g., parasitic drag/friction, weight, manufacturing cost, package volume].

---

### Input Data
System Name / Description: [Insert system here, e.g., Hydraulic Disc Brake Caliper, Wind Turbine Pitch Bearing, Industrial Centrifugal Pump]
Operating Context & Pain Points: [Provide known operating conditions, failures, or constraints]

Worked Verification Example

To demonstrate how the prompt decomposes a different engineering domain using this schema:

Target System: Industrial Centrifugal Slurry Pump

Target Subsystem: Dynamic Mechanical Shaft Seal & Stuffing Box Interface

Current Components:

  • Shaft Sleeve: 316 Stainless Steel with Tungsten Carbide spray coating (OD 65 mm)

  • Primary Seal Faces: Sintered Silicon Carbide (SiC) vs. Reaction-Bonded Silicon Carbide

  • Biasing Element: Hastelloy-C multi-spring pack

  • Flush Barrier: Clean water injection barrier (Plan 32 piping configuration)

Operating Environment & Physics:

  • Peak Hydraulic Loads: 1.8 MPa process pressure; shaft speed 1,750 RPM (linear surface velocity ~6.0 m/s).

  • Kinematic Conditions: Shaft runout $\le 0.05\text{ mm}$, continuous duty rotation.

  • Environmental Ingress & Ambient Exposure: Bauxite tailings slurry (45% solids by weight, silica particle size 10–120 microns, pH 11.5, process temperature 75 °C).

Current Primary Failure Mode:

  • Ingress occurs when barrier flush pressure fluctuates below slurry line pressure, allowing particulate into the 1-micron fluid film between seal faces.

  • Suspended silica micro-particles induce severe two- and three-body abrasive scoring across the SiC mating surfaces.

  • Face micro-grooving causes thermal runaway, barrier fluid loss, rapid slurry blowout along the shaft axis, and catastrophic bearing contamination.

Contradiction / Trade-off:

  • Increasing closing force or installing tortuous lip-labyrinth packings prevents particulate penetration, but sharply increases frictional heat generation and parasitic power draw, leading to premature face blistering.


Provide a Python app using Google Gemini API to run the System-to-System Decomposition Prompt against a user specified system

Below is a complete, production-ready Python application that uses the official Google GenAI SDK (google-genai) to execute the System-to-System Decomposition Prompt against any user-specified physical or electromechanical system.

Installation

Install the official Google GenAI SDK:

pip install google-genai

Set your API key as an environment variable:

export GEMINI_API_KEY="your-api-key-here"

Python Application (system_decomposer.py)

import os
import sys
from google import genai
from google.genai import types

# 1. System Prompt Definition
SYSTEM_DECOMPOSITION_INSTRUCTION = """
You are an expert mechanical systems engineer and TRIZ practitioner specializing in functional decomposition and root-cause failure analysis.

Decompose the provided system into a structured architectural and physical specification. Follow the exact schema below, adhering strictly to technical precision, physical forces, material choices, and interface physics.

---

### Target System Specification Schema

Target System: [Macro-level machine, assembly, or vehicle]
Target Subsystem: [Specific kinematic, structural, or fluid interface being analyzed]

Current Components:
- [Primary Load-Bearing Member]: [Material grade, heat treatment, key dimensions]
- [Secondary/Pivot/Bearing Member]: [Material grade, surface finish, outer/inner dimensions]
- [Interface/Contact Element]: [Material grade, geometry, tribological condition]
- [Medium/Fluid/Barrier]: [Working fluid, lubricant chemistry, or sealing state]

Operating Environment & Physics:
- Peak Mechanical Loads: [Maximum dynamic/static tension, torque, bending moment, or pressure with units]
- Kinematic Boundary Conditions: [Velocities, RPM, articulation angles, cyclic frequencies]
- Environmental Ingress & Ambient Exposure: [Contaminants, particle sizes (microns), temperature ranges, moisture, chemicals]

Current Primary Failure Mode:
- Ingress/Initiation Mechanism: [How physical stress, fluid, or particulate enters the interface]
- Degradation Physics: [Specific wear or failure mechanism—e.g., three-body abrasive wear, fretting corrosion, fatigue spalling, cavitation]
- Systemic Degradation Effect: [Downstream failure progression and resulting functional loss under operating load]

Contradiction / Trade-off:
- Improving [Param A: e.g., sealing integrity, surface hardness, load capacity] directly degrades [Param B: e.g., parasitic drag/friction, weight, manufacturing cost, package volume].
"""

# Few-shot context to ground the model on detail and formatting
FEW_SHOT_EXAMPLE = """
Example:
Target System: Modern Road/Gravel Bicycle
Target Subsystem: Chain Drivetrain & Roller Link Interface

Current Components:
- Outer and inner link plates (Hardened carbon steel)
- Bearing pins (Case-hardened steel, OD 3.6mm)
- Rollers (Heat-treated steel bushing/roller interface)
- Lubricant: Liquid wet synthetic hydrocarbon lubricant

Operating Environment & Physics:
- Peak rider sprint tension: up to 1,800 N across the chain span.
- Ambient exposure: road grit (silica/quartz micro-particles 5-50 microns), rain, mud.

Current Primary Failure Mode:
- Road slurry enters clearance between pin and roller via capillary action.
- Abrasive slurry causes rapid 3-body wear, thinning the pin and boring out the roller.
- Pitch elongation occurs ("chain stretch"), accelerating sprocket wear and causing skipping under high pedal load.

Contradiction / Trade-off:
- Increasing pin diameter or adding contact elastomer seals increases weight, link friction, and rotational resistance.
"""

def decompose_system(target_system: str, context: str = "") -> str:
    """Invokes Gemini 2.5 Pro to decompose the mechanical system."""
    api_key = os.environ.get("GEMINI_API_KEY")
    if not api_key:
        raise ValueError("Missing GEMINI_API_KEY environment variable.")

    client = genai.Client(api_key=api_key)

    user_query = f"System Name / Description: {target_system}\n"
    if context.strip():
        user_query += f"Operating Context & Pain Points: {context.strip()}"
    else:
        user_query += "Operating Context & Pain Points: Focus on the most critical wear-prone or failure-critical kinematic interface."

    config = types.GenerateContentConfig(
        system_instruction=SYSTEM_DECOMPOSITION_INSTRUCTION + "\n\n" + FEW_SHOT_EXAMPLE,
        temperature=0.2,  # Low temperature for deterministic, technical precision
    )

    response = client.models.generate_content(
        model="gemini-2.5-pro",
        contents=user_query,
        config=config,
    )

    return response.text


def main():
    print("=" * 65)
    print("  System-to-System Functional Decomposition Engine")
    print("=" * 65)

    if len(sys.argv) > 1:
        target_system = " ".join(sys.argv[1:])
        context = ""
    else:
        target_system = input("\nEnter target system (e.g., 'Boeing AH-64 Apache Main Rotor'): ").strip()
        if not target_system:
            print("System name is required. Exiting.")
            sys.exit(1)
        context = input("Enter operational context/pain points (optional, press Enter to skip): ").strip()

    print(f"\nAnalyzing '{target_system}'...\n")
    try:
        result = decompose_system(target_system, context)
        print(result)
    except Exception as e:
        print(f"Error during decomposition: {e}", file=sys.stderr)
        sys.exit(1)


if __name__ == "__main__":
    main()

Usage

Run interactively:

python system_decomposer.py

Or pass the system directly via CLI arguments:

python system_decomposer.py "Industrial Centrifugal Slurry Pump"


From <https://gemini.google.com/app/28652c046be7b5cd>  Google Gemini (3.8)

Comments

Post a Comment

Popular posts from this blog

#4297 ISS Astronaut Unable to Speak

-
#4297 ISS Astronaut Unable to Speak #4297  Why might an astronaut on extended stay on ISS suddenly, but temporarily be unable to speak? An astronaut on the International Space Station (ISS) experiencing a sudden, temporary loss of speech (aphasia or dysphonia) is a serious medical concern that could stem from several environmental or physiological factors unique to microgravity. Here are the most likely scientific explanations: 1. Transient Ischemic Attack (TIA) Often called a "mini-stroke," a TIA occurs when blood flow to a part of the brain is temporarily blocked. The Space Connection: Microgravity causes a cephalad fluid shift , where blood and interstitial fluids move toward the head. This can alter cerebral blood flow and increase the risk of stagnant blood flow in the internal jugular vein, which has been documented in ISS crew members and could potentially lead to small clots. 2. Space Adaptation Syndrome (SAS) and "Space Fog" During the initial days or duri...
Read more

#3356 PHP and JavaScript to Retrieve and Set an API_Key

-
Image
#3356 PHP and JavaScript to Retrieve and Set an API_Key #3356 Create a JavaScript function that uses AJAX to retrieve and set an api_key from from a PHP script Below is a step‐by‐step example showing how to expose an api_key via a simple PHP endpoint and then retrieve it in JavaScript using a classic AJAX (XHR) call. The JavaScript function will parse the JSON response and store the key in a variable (you can adapt it to inject into headers, a config object, or wherever you need). 1. PHP endpoint ( get_api_key.php ) <?php // get_api_key.php header ( 'Content-Type: application/json' ); // In a real‐world scenario, you’d pull this from a secure location // (e.g. environment variable, config file outside webroot, encrypted store, etc.) $api_key = 'YOUR_SECRET_API_KEY' ; echo json_encode ([ 'api_key' => $api_key ]); Content-Type: We set JSON so the client can parse it easily. JSON payload: Returns an object like { "api_key":...
Read more

#4188 Hybrid/GraphRAG

-
#4188 Hybrid/GraphRAG #4188  Given a knowledge graph, including embedded documents with indexed document chunks, describe the prompt sequence for answering a user's question about the knowledge graph Answering a user's question using a hybrid Knowledge Graph (KG) and vector database (embedded document chunks) is a powerful approach often referred to as Graph Retrieval-Augmented Generation (GraphRAG) . Because you are combining structured data (graph relationships) with unstructured data (text chunks), a multi-step prompt sequence is usually required to accurately extract, retrieve, and synthesize the information. Here is the standard prompt sequence used in this architecture. 1. Query Analysis and Entity Extraction Prompt Before searching the database, the system must understand what to look for. The first prompt is sent to the LLM to break down the user's natural language question into actionable search parameters for both the Knowledge Graph and the vector database. Syst...
Read more