Purpose

The prediction of by-product gas is an important guarantee for the full utilization of resources. The purpose of this research is to predict gas consumption to provide a basis for gas dispatch and reduce the production cost of enterprises.

Design/methodology/approach

In this paper, a new method using the ensemble empirical mode decomposition (EEMD) and the back propagation neural network is proposed. Unfortunately, this method does not achieve the ideal prediction. Further, using the advantages of long short-term memory (LSTM) neural network for long-term dependence, a prediction method based on EEMD and LSTM is proposed. In this model, the gas consumption series is decomposed into several intrinsic mode functions and a residual term (r(t)) by EEMD. Second, each component is predicted by LSTM. The predicted values of all components are added together to get the final prediction result.

Findings

The results show that the root mean square error is reduced to 0.35%, the average absolute error is reduced to 1.852 and the R-squared is reached to 0.963.

Originality/value

A new gas consumption prediction method is proposed in this paper. The production data collected in the actual production process is non-linear, unstable and contains a lot of noise. But the EEMD method has the unique superiority in the analysis data aspect and may solve these questions well. The prediction of gas consumption is the result of long-term training and needs a lot of prior knowledge. Relying on LSTM can solve the problem of long-term dependence.

中文翻译：

---

基于EEMD-LSTM深度学习技术的冷轧气体预测

目的

副产气预测是资源充分利用的重要保障。本研究的目的是预测用气量，为用气调度提供依据，降低企业的生产成本。

设计/方法/方法

本文提出了一种使用集成经验模态分解（EEMD）和反向传播神经网络的新方法。不幸的是，这种方法没有达到理想的预测。此外，利用长短期记忆（LSTM）神经网络对长期依赖的优势，提出了一种基于EEMD和LSTM的预测方法。在该模型中，气体消耗序列通过 EEMD 分解为几个固有模式函数和一个残差项 (r(t))。其次，每个组件都由 LSTM 预测。所有分量的预测值相加得到最终的预测结果。

发现

结果表明，均方根误差降低到0.35%，平均绝对误差降低到1.852，R平方达到0.963。

原创性/价值

本文提出了一种新的用气量预测方法。在实际生产过程中采集到的生产数据是非线性的、不稳定的，并且含有大量的噪声。但EEMD方法在分析数据方面具有独特的优势，可以很好地解决这些问题。耗气量的预测是长期训练的结果，需要大量的先验知识。依靠LSTM可以解决长期依赖的问题。