IL3.3A - SPPF High-Accuracy Spare-Parts Forecasting Platform

A Docker microservices platform for forecasting spare-parts consumption. It includes a forecast database, REST API, periodic hyperparameter retraining and theoretical components validated in international scientific publications, and is fed by SAP/Bosch APIs.

  • Main Gain(s): Spare-parts demand forecasting, Periodic model retraining, REST API integration, Support for long-term performance monitoring

  • Use Case(s): SAP/Bosch spare-parts consumption time series and real-time data feeds via APIs

  • Start TRL: TRL 5

  • Final TRL: TRL 8

  • Main Contributions: Universidade de Aveiro (coord. Prof. Eugénio Rocha; support Diogo Costa) with Bosch Termotecnologia, S.A. (coord. Eng. Nelson Ferreira)

Main Features

    </th>
    <th class="px-3 py-3 text-center font-semibold">Batch Data</th>
    <th class="px-3 py-3 text-center font-semibold">Web App</th>
    <th class="px-3 py-3 text-center font-semibold">Real-Time Data</th>
    <th class="px-3 py-3 text-center font-semibold">Control Tower Integration</th>
    <th class="px-3 py-3 text-center font-semibold">REST API</th>
    <th class="px-3 py-3 text-center font-semibold">Containerized Application</th>
    <th class="px-3 py-3 text-center font-semibold">Extensible</th>
  </tr>
</thead>

<tbody class="divide-y divide-slate-100">

  <!-- Optional second row example -->
  <tr class="transition hover:bg-slate-50">
    <td class="sticky left-0 z-10 bg-white px-4 py-3 font-medium text-slate-900">
      Product Capabilities
    </td>

    <td class="px-3 py-3 text-center">
      <span class="inline-flex h-6 w-6 items-center justify-center rounded-full bg-rose-100 text-rose-700">X</span>
    </td>

    <td class="px-3 py-3 text-center">
      <span class="inline-flex h-6 w-6 items-center justify-center rounded-full bg-amber-100 text-amber-700">~</span>
    </td>

    <td class="px-3 py-3 text-center">
      <span class="inline-flex h-6 w-6 items-center justify-center rounded-full bg-emerald-100 text-emerald-700">✓</span>
    </td>

    <td class="px-3 py-3 text-center">
      <span class="inline-flex h-6 w-6 items-center justify-center rounded-full bg-emerald-100 text-emerald-700">✓</span>
    </td>

    <td class="px-3 py-3 text-center">
      <span class="inline-flex h-6 w-6 items-center justify-center rounded-full bg-rose-100 text-rose-700">X</span>
    </td>

    <td class="px-3 py-3 text-center">
      <span class="inline-flex h-6 w-6 items-center justify-center rounded-full bg-emerald-100 text-emerald-700">✓</span>
    </td>

    <td class="px-3 py-3 text-center">
      <span class="inline-flex h-6 w-6 items-center justify-center rounded-full bg-emerald-100 text-emerald-700">✓</span>
    </td>
  </tr>
</tbody>
  • Docker-based microservices platform in production
  • Forecast database and REST API for integration
  • Periodic hyperparameter retraining
  • Models for sparse and non-periodic time series with many zero values
  • News-extraction and sentiment-analysis enrichment using local LLaMA workflows
  • Integration into the Project 3 Control Tower