Is the feed gradation to my fine crushing stage stable enough?
计算粗粒级给料模数 MCFM，判定是否落在工程最优窗口 4.0–4.5，给出"均匀布料 → 速度均匀化 → 磨损稳定 → 模数恒定"的杠杆调整建议。
| Parameter | Type | Description |
|---|---|---|
cumulative_retained | array | 长度必须为 8 的累积筛余百分比数组，依次对应 最大给料/60/40/20/10/5/2.5mm 与 80% 通过粒级（A1..A8，单位 %）。 |
feed_top_mm | number | 给料最大粒度 mm，用于上下文校验。 |
target_product_mm | number | 目标最终产品粒度 mm。 |
ore_note | string | 矿石名称/硬度/含泥量等备注，原样回显。 |
Run via: local plugin
Input:
{
"cumulative_retained": [
2,
15,
35,
55,
70,
82,
90,
20
]
}
Output (first fields):
| Field | Value |
|---|---|
input_echo.cumulativeRetained | [8 项] [2,15,35,55] |
input_echo.feedTopMm | null |
input_echo.targetProductMm | null |
input_echo.oreNote | null |
mcfm | 2.612 |
optimal_range | [2 项] [4,4.5] |
deviation.level | too_fine |
deviation.deviation | 1.388 |
advice.meaning | 细粒级偏多，料层易于密实化、应力传导失配，破碎腔出现"过粉碎" |
advice.action | 降低细粒级占比：检查预筛分是否失效、筛孔是否磨损超差、是否应该把部分细料提前筛出 |
advice.priority | high |
sieve_slots | [8 项] |
leverage_chain | [6 项] |
assumptions | [2 项] |
warnings | [1 项] ["模数 M=2.612 远低于最优下限 4.0，细粒级过多，须核查预筛分与筛孔磨损"] |
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_mcfm_analysis","arguments":{"cumulative_retained":[2,15,35,55,70,82,90,20]}}}'
Endpoint: https://mackorn.cn/ai/api/mcp.php ·
Registry: cn.mackorn/mackorn-cone-crusher ·
npm: mackorn-cone-crusher
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.