Abstract

In this article, we consider the organizational issues of monitoring the thermal conditions of melting and casting alloys at foundries. It is noted that the least reliable method is when the measuring and fixing the temperature are assigned to the worker. On the other hand, a fully automatic approach is not always available for small foundries. In this regard, the expediency of using an automated approach is shown, in which the measurement is assigned to the worker, while the values are recorded automatically. This method assumes an algorithm implementation for automatic classification of temperature measurements based on an end-to-end array of data obtained in production series. This task solution is divided into three stages. Preparing of raw data for the classification process is provided in the first stage. In the second stage, the task of measurement classification is solved by using principles of artificial neural networks. Analysis of the artificial neural network results has shown its high efficiency and degree of correspondence with the actual situation at the work site. It is also noted that the application of artificial neural networks principles makes the classification process flexible due to the ability to easily supplement the process with new parameters and neurons. The final stage is analysis of the results. Correctly performed data classification provides an opportunity not only to assess agreements with technological efficiency at the site, but also to improve the process of identifying the causes of casting defects. Application of the proposed approach allows us to reduce the influence of human factor in the analysis of thermal conditions of melting and casting alloys with minimal costs for melting monitoring.

中文翻译：

---

神经网络在合金熔铸过程中温度测量值的分析和分类

摘要

在本文中，我们考虑了监视铸造厂的熔融和铸造合金热状况的组织问题。注意，最不可靠的方法是将温度的测量和固定分配给工人。另一方面，对于小型铸造厂，并非总是可以使用全自动方法。在这方面，显示了使用自动方法的便利性，其中将测量值分配给工人，同时自动记录值。该方法假设基于在生产系列中获得的数据的端对端数组对温度测量值进行自动分类的算法实现。此任务解决方案分为三个阶段。在第一阶段提供了用于分类过程的原始数据的准备。在第二阶段 利用人工神经网络原理解决了测量分类的任务。对人工神经网络结果的分析表明，它具有很高的效率，并且与工作现场的实际情况相符。还应注意的是，人工神经网络原理的应用使分类过程具有灵活性，因为它能够轻松地用新的参数和神经元补充过程。最后阶段是结果分析。正确执行的数据分类不仅为评估现场技术效率的协议提供了机会，而且还为改进确定铸件缺陷原因的过程提供了机会。