How do I call this tool?

POST a JSON-RPC 2.29 tools/call request to https://mackorn.cn/ai/api/mcp.php with name "mackorn_simulate_flowsheet". No installation is required.

Is the model based on published literature?

Yes. The particle-size and flow models are independently implemented from Whiten (1972) and Bond (1952); the implementation is MIT-licensed and auditable. Vendor data comes from MACKORN parameter tables. Every number carries its source; unknown values return null rather than an estimate.

mackorn_simulate_flowsheet — What is the final product size of a multi-stage crushing circuit, and what is the circulating load?

What it answers

多段破碎 + 筛分 + 闭路流程模拟：逐段算产品粒度与循环负荷，用群体平衡迭代到稳态，输出各段入料/出料 P80、破碎比、筛下率与最终产品 P80。

Input parameters

Parameter	Type	Description
`feed_p80_mm`	number	新鲜给料 P80 mm（必填）。
`feed_n`	number	Rosin-Rammler 均匀性指数 n（默认 1.1）。
`stages`	array	段定义数组，按顺序。破碎段 {type:"crusher", name, css_mm, throw_mm}；筛分段 {type:"screen", name, aperture_mm, recirculate_to}（recirculate_to 为返回的破碎段下标，不填则返回上一破碎段）。
`bond_wi`	number	邦德功指数 kWh/t。
`ore`	string	矿石种类。
`max_iter`	integer	最大迭代次数（默认 200）。

Worked example (real output, not a mock-up)

Run via: local plugin

Input:

{
  "feed_p80_mm": 500,
  "stages": [
    {
      "type": "crusher",
      "name": "secondary",
      "css_mm": 40
    },
    {
      "type": "screen",
      "name": "check",
      "aperture_mm": 20
    },
    {
      "type": "crusher",
      "name": "tertiary",
      "css_mm": 12
    }
  ]
}

Output (first fields):

Field	Value
`uncertainty.method`	流程级确定性区间传播（扰动全部破碎段的待标定参数，重跑整条流程）
`uncertainty.calibrated`	false
`uncertainty.level`	flowsheet（含闭路循环放大效应）
`uncertainty.crusher_stages`	2
`uncertainty.point_estimate_mm`	12.76
`uncertainty.interval_mm`	[2 项] [10.96,14.56]
`uncertainty.half_width_mm`	1.8
`uncertainty.sigma_pct`	14.1
`uncertainty.confidence_grade`	B
`uncertainty.grade_note`	流程级区间中等（±10~25%），可用于初步方案
`uncertainty.contributions`	[4 项]
`uncertainty.caveats`	[3 项] ["区间为流程级 1σ 合成估计（各参数独立假设）。闭路循环会放大扰动，故流程级区间通常大于单机区间。","本次计算使用【文献典型参数】，未经现场实测标定 —— 区间反映参数不确定度，不是模型误差。","要收窄区间，须提供各段的实测给料/产品筛析数据做标定（工具 mackorn_calibrate）。"]
`feed_p80_mm`	275.701
`final_p80_mm`	12.762
`overall_reduction_ratio`	21.6
`iterations`	28
`converged`	true
`circulating_load_ratio`	0

How to call it

POST a JSON-RPC 2.0 request to the public MCP endpoint — no installation, no API key:

curl -s https://mackorn.cn/ai/api/mcp.php \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"mackorn_simulate_flowsheet","arguments":{"feed_p80_mm":500,"stages":[{"type":"crusher","name":"secondary","css_mm":40},{"type":"screen","name":"check","aperture_mm":20},{"type":"crusher","name":"tertiary","css_mm":12}]}}}'

Endpoint: https://mackorn.cn/ai/api/mcp.php · Registry: cn.mackorn/mackorn-cone-crusher · npm: mackorn-cone-crusher

Data sources and limits

Particle-size and flow models are independently implemented from published literature (Whiten 1972; Bond 1952). Vendor parameters come from MACKORN NH/NS tables. Every output carries assumptions[] and warnings[]; unknown values are returned as null, never estimated. Literature parameters must be calibrated against on-site sieve data before use in a formal proposal.

A hydraulic cone crusher is a secondary/tertiary machine: feed above roughly 350 mm is refused.