Abstract In the coming era of big data, many advances and attempts have been witnessed in deep learning based remaining useful life (RUL) prediction methods which can construct the mapping relation between the massive information and the RUL. Existing studies leverage advanced deep networks for RUL prediction mainly generating the point estimates for the RUL while the prognostic uncertainty quantification is often difficult. However, it is well admitted that such prognostic uncertainty quantification is important and cannot be neglected for health management of degrading products. The purpose of this paper is to develop an adaptive prognostic method towards both the massive data and prognostics uncertainty by leveraging the advantages of deep learning methods in processing massive data and stochastic methods in the uncertainty representation. To do so, a continuous deep belief network (CDBN) is first utilized to extract the deep hidden features behind the massive information, and then, we determine the health index via the self-organizing map (SOM) neural network based on the extracted features. Next, the diffusion process is applied to construct the health index evolving model. The parameters in the diffusion process are estimated online by combining Bayesian method and Expectation Maximization (EM) algorithm. Consequently, the probability density function (PDF) of the RUL can be obtained and updated adaptively. Finally, a practical case study for bearings is provided to substantiate the effectiveness and superiority of the proposed method. Experimental results indicate that the proposed method can provide more accurate RUL predictions.

中文翻译：

---

融合CDBN和扩散过程的自适应预测方法：在轴承数据中的应用

摘要 在即将到来的大数据时代，基于深度学习的剩余使用寿命（RUL）预测方法出现了许多进展和尝试，可以构建海量信息与RUL之间的映射关系。现有研究利用先进的深度网络进行 RUL 预测，主要生成 RUL 的点估计，而预后不确定性量化通常很困难。然而，众所周知，这种预测不确定性量化很重要，对于降解产品的健康管理不容忽视。本文的目的是利用深度学习方法在处理海量数据和随机方法在不确定性表示中的优势，开发一种针对海量数据和预测不确定性的自适应预测方法。为此，首先利用连续深度信念网络（CDBN）提取海量信息背后的深层隐藏特征，然后根据提取的特征通过自组织图（SOM）神经网络确定健康指数. 接下来，应用扩散过程构建健康指数演化模型。通过结合贝叶斯方法和期望最大化（EM）算法在线估计扩散过程中的参数。因此，可以自适应地获取和更新 RUL 的概率密度函数 (PDF)。最后，提供了轴承的实际案例研究，以证实所提出方法的有效性和优越性。实验结果表明，所提出的方法可以提供更准确的 RUL 预测。首先利用连续深度信念网络（CDBN）提取海量信息背后的深层隐藏特征，然后根据提取的特征通过自组织图（SOM）神经网络确定健康指数。接下来，应用扩散过程构建健康指数演化模型。通过结合贝叶斯方法和期望最大化（EM）算法在线估计扩散过程中的参数。因此，可以自适应地获取和更新 RUL 的概率密度函数 (PDF)。最后，提供了轴承的实际案例研究，以证实所提出方法的有效性和优越性。实验结果表明，所提出的方法可以提供更准确的 RUL 预测。首先利用连续深度信念网络（CDBN）提取海量信息背后的深层隐藏特征，然后根据提取的特征通过自组织图（SOM）神经网络确定健康指数。接下来，应用扩散过程构建健康指数演化模型。通过结合贝叶斯方法和期望最大化（EM）算法在线估计扩散过程中的参数。因此，可以自适应地获取和更新 RUL 的概率密度函数 (PDF)。最后，提供了轴承的实际案例研究，以证实所提出方法的有效性和优越性。实验结果表明，所提出的方法可以提供更准确的 RUL 预测。