Nowadays the industrial Internet of things (IIoT) has been successfully utilized in smart manufacturing. The massive data in IIoT promotes the development of deep learning-based health monitoring for industrial equipment. Since monitoring data for mechanical fault diagnosis collected on different working conditions or equipment have domain mismatch, models trained with training data may not work in practical applications. Therefore, it is essential to study fault diagnosis methods with domain adaptation ability. In this paper, we propose an intelligent fault diagnosis method based on an improved domain adaptation method. Specifically, two feature extractors concerning feature space distance and domain mismatch are trained using maximum mean discrepancy (MMD) and domain adversarial training respectively to enhance feature representation. Since separate classifiers are trained for feature extractors, ensemble learning is further utilized to obtain final results. Experimental results indicate that the proposed method is effective and applicable in diagnosing faults with domain mismatch.

Massive industrial data collected from industrial Internet of things (IIoT) assets improves data-driven methods for prognostics and health management (PHM) systems. As an important role in PHM, remaining useful life (RUL) prediction is essential to maintain the reliability and safety of industrial manufacture. However, recent data-driven approaches for bearing RUL prediction do not weight the contributions of data from different sensors and time steps, which decreases the efficiency in the big data era. In this context, we present a deep learning-based RUL prediction method with attention mechanism to weight sequence data’s representations. Specifically, the proposed method weights different industrial sensors and time steps respectively based on distributed attention mechanism. Then temporal convolution modules with the shared weights are used for feature extraction of time series. Finally, performance of the proposed method is verified using a popular dataset C-MAPSS. Experimental results reveal that the proposed method has high accuracy and is efficient in practical applications.

With the detailed load data provided by smart meter, the learning of electricity usage behavior for individual household short-term load forecasting has become a hot research topic. The existing methods generally ignore the relation among multiple households and fail to obtain enough information from the limited household load data, resulting in accuracy reduction. To solve this problem, a novel hybrid Multitask Multi-information Fusion Deep Learning Framework (MFDL) considering both recent and long-term regular behaviors is proposed by integrating long short-term memory (LSTM), and convolutional neural network (CNN) to predict the multiple individual household short-term electricity consumptions. A multitask framework with two levels of information extraction is developed considering multiple household short-term load forecasting. In the low-level information extraction stage, the data structure including long and short datasets with different time scales is presented to learn the recent electricity usage behavior by LSTM and the long-term regular electricity behavior features by CNN. Then the multiple time-scale information is fused and further extracted in the high-level stage to complete the multiple individual short-term household load forecasting. The developed framework is implemented on one real-world load datasets and the results show the proposed method outperforms the state-of-the-art methods in common metrics.

Industrial internet of things (IIoT) obtains big data from industrial facilities. Based on these data, health conditions for facilities can be predicted using machine learning methods, which in turn improves the trustworthiness of IIoT. Intelligent fault diagnosis is developing with this process. Since machine damages always happen under different circumstances, the designed intelligent fault diagnosis methods should have domain adaption ability. In this paper, a data-driven fault diagnosis method called domain adaption network (DAN) is present, in which the difference between training and testing data can be minimized while the maximum training accuracy can be maintained. First, DAN uses a combined loss for consistent feature learning and optimum training classification performance. Then a DAN retraining (DAN-R) strategy is employed based on weighted pseudo-labeled testing dataset. Finally, three experiments are performed on two fault diagnosis datasets. The results reveal that DAN-R is applicable and has outstanding domain adaption ability.

Providing real-time bus arrival information can help to improve the service quality of a transit system and enhance its competitiveness among other transportation modes. Taking the city of Jinan, China, as an example, this study proposes two artificial neural network (ANN) models to predict the real-time bus arrivals, based on historical global positioning system (GPS) data and automatic fare collection (AFC) system data. Also, to contend with the difficulty in capturing the traffic fluctuations over different time periods and account for the impact of signalized intersections, this study also subdivides the collected dataset into a bunch of clusters. Sub-ANN models are then developed for each cluster and further integrated into a hierarchical ANN model. To validate the proposed models, six scenarios with respect to different time periods and route lengths are tested. The results reveal that both proposed ANN models can outperform the Kalman filter model. Particularly, with several selected performance indices, it has been found that the hierarchical ANN model clearly outperforms the other two models in most scenarios.

Bearing faults are among the most common causes of machine failures. Therefore, bearing fault diagnosis should be performed reliably and rapidly. Currently, many types of modal data for monitoring the running state of bearings are available. They include data from different kinds of sensors and various domains (such as time and frequency domains). However, obtaining fault features with high quality from single-modal data is difficult because of the complex working conditions. Therefore, extracting and integrating complementary fault features from multimodal monitoring data are problems that remain to be solved. To address these issues, this study considers vibration and torque signals and proposes a novel three-stage feature fusion method of multimodal data for the fault diagnosis of bearings. The method is called attention-based multidimensional concatenated convolutional neural network. The attention mechanism can learn global information and assign different weights to feature maps to highlight important features. The fused features are then used in fault classification via softmax regression. The effectiveness of the proposed method is verified through the Paderborn data set. Results show that diagnostic accuracy is significantly improved from 96.4% to 99.8%.