mackorn_beneficiation_selection

What does mackorn_beneficiation_selection do?

What it answers

(Multilingual triggers / 多语言触发词: beneficiation, mineral processing, flotation, gravity separation, ore sorting, sensor-based sorting, magnetic separation, recovery, concentrate grade, liberation, 选矿, 选别, 浮选, 重选, 光电选, 光选, 激光选矿, 图像选矿, 磁选, 回收率, 精矿品位, 解离粒度, 矿泥 | beneficio, flotación, gravedad, separación magnética | Aufbereitung, Flotation, Schwerkraftscheidung, Magnetscheidung | обогащение, флотация, гравитация, магнитная сепарация | enrichissement, flottation, gravité, séparation magnétique | beneficiamento, flotação, gravidade, separação magnética | 選鉱, 浮選, 比重選別, 磁選 | anrikning, flotation, gravimetrisk | oparbejdning, flotation, gravitation | rikastus, vaahdotus, painovoima | معالجة المعادن, تعويم, فصل بالجاذبية | pengolahan mineral, flotasi, gravitasi, pemisahan magnetik) MACKORN 选矿方法推荐工具(全价值链第 4 段):按矿石类型/目标矿物/解离粒度,推荐选矿方法(浮选 / 重选 / 光电选 / 磁选),给适用条件、预期回收率区间、能耗区间、关键限制,并主动拦截:解离粒度过细(<10μm)或过粗(>200μm)告警、矿泥 >15% 强制提示脱泥、光电选必须做工业试验的强制告警。 用于回答:这个矿该用什么选别方法、预期回收率多少、有什么坑。 【适用边界】本工具只管【选矿方法选择】;磨矿请用 grinding_selection,破碎请用 cone_selection / plant_design。不含药剂制度、设备型号、经济指标;实际方案必须做选矿试验。

Input parameters

ParameterTypeDescription
orestring矿石类型/名称(如 硫化铜矿石 / 磁铁矿 / 金矿 / 石灰石)。
target_mineralstring目标矿物或元素(如 铜 / 金 / 铁 / 钨)。
liberation_umnumber解离粒度 μm(磨到多细才解离)。低于 10μm 或高于 200μm 会告警。
feed_p80_mmnumber磨矿给料 P80 mm(用于判断是否需要预选抛废)。
target_tphnumber处理量 t/h。
slime_pctnumber矿泥(-10μm)占比 %。>15% 会强制提示脱泥。
modestring只查目录或只做推荐。

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

Run via: local plugin

Input:

{}

Output (first fields):

FieldValue
request.orenull
request.targetMineralnull
request.feedP80Mmnull
request.liberationUmnull
request.targetTphnull
request.slimePctnull
errorinsufficient_input
message至少需要 ore(矿石类型)或 targetMineral(目标矿物),否则无法推荐选矿方法
recommended_methods[0 项]
assumptions[0 项]
warnings[1 项] ["输入不足:既没给矿石类型也没给目标矿物。选矿方法选择高度依赖这两项,不能猜。"]
basisNO_CALCULATION

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_beneficiation_selection","arguments":{}}}'

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.