Coupled Multimodal Emotional Feature Analysis Based on Broad-Deep Fusion Networks in Human-Robot Interaction.

A coupled multimodal emotional feature analysis (CMEFA) method based on broad-deep fusion networks, which divide multimodal emotion recognition into two layers, is proposed. First, facial emotional features and gesture emotional features are extracted using the broad and deep learning fusion network (BDFN). Considering that the bi-modal emotion is not completely independent of each other, canonical correlation analysis (CCA) is used to analyze and extract the correlation between the emotion features, and a coupling network is established for emotion recognition of the extracted bi-modal features. Both simulation and application experiments are completed. According to the simulation experiments completed on the bimodal face and body gesture database (FABO), the recognition rate of the proposed method has increased by 1.15% compared to that of the support vector machine recursive feature elimination (SVMRFE) (without considering the unbalanced contribution of features). Moreover, by using the proposed method, the multimodal recognition rate is 21.22%, 2.65%, 1.61%, 1.54%, and 0.20% higher than those of the fuzzy deep neural network with sparse autoencoder (FDNNSA), ResNet-101 + GFK, C3D + MCB + DBN, the hierarchical classification fusion strategy (HCFS), and cross-channel convolutional neural network (CCCNN), respectively. In addition, preliminary application experiments are carried out on our developed emotional social robot system, where emotional robot recognizes the emotions of eight volunteers based on their facial expressions and body gestures.

A robust integrated control design for weight-on-bit fluctuation suppression in drilling process subject to fractured formations.

Fractured formations lead to insufficient contact or loss of contact between the drill bit and rocks, which subsequently causes notable fluctuation in weight-on-bit due to flexible drill strings. This paper presents a robust integrated control design to suppress weight-on-bit fluctuation. First, a finite element drill-string longitudinal model is employed as the basis of control design, which has been verified using actual run data. The integrated controller contains a proportional-integral (PI) controller and a dynamic output feedback controller, dealing with the system's first-order and high-order dynamics. The dynamic output feedback controller only needs to focus on the system's high-order dynamics since the controller synthesis is based on the pre-designed PI controller. The controller decreases the flexible mode amplitude from disturbance to the output channel through H-infinity loop shaping, making the closed-loop system less flexible. The numerical results demonstrate that the developed approach can effectively suppress weight-on-bit fluctuation due to drill-string flexibility when drilling in fractured formations.

Weighted Kernel Fuzzy C-Means-Based Broad Learning Model for Time-Series Prediction of Carbon Efficiency in Iron Ore Sintering Process.

A key energy consumption in steel metallurgy comes from an iron ore sintering process. Enhancing carbon utilization in this process is important for green manufacturing and energy saving and its prerequisite is a time-series prediction of carbon efficiency. The existing carbon efficiency models usually have a complex structure, leading to a time-consuming training process. In addition, a complete retraining process will be encountered if the models are inaccurate or data change. Analyzing the complex characteristics of the sintering process, we develop an original prediction framework, that is, a weighted kernel-based fuzzy C-means (WKFCM)-based broad learning model (BLM), to achieve fast and effective carbon efficiency modeling. First, sintering parameters affecting carbon efficiency are determined, following the sintering process mechanism. Next, WKFCM clustering is first presented for the identification of multiple operating conditions to better reflect the system dynamics of this process. Then, the BLM is built under each operating condition. Finally, a nearest neighbor criterion is used to determine which BLM is invoked for the time-series prediction of carbon efficiency. Experimental results using actual run data exhibit that, compared with other prediction models, the developed model can more accurately and efficiently achieve the time-series prediction of carbon efficiency. Furthermore, the developed model can also be used for the efficient and effective modeling of other industrial processes due to its flexible structure.

Operating Performance Improvement Based on Prediction and Grade Assessment for Sintering Process.

Sintering is the preproduction process of ironmaking, whose products are the basis of ironmaking. How to improve the operating performance of the iron ore sintering process has always been a problem that operators are committed to solve. An operating performance improvement method based on prediction and grade assessment is presented in this article. First, considering the data distribution characteristics of the process, a performance index prediction model based on the Gaussian process regression is built, in which the mutual information analysis method is used to select the inputs of the performance index prediction model. Then, the operating performance grade is assessed by a threshold division method. Next, the operating performance grade guides the control of the burn-through point to improve the operating performance. Finally, experimental verification is performed based on the actual running data. The results show that the proposed method has high prediction accuracy, and it is also significant in improving the operating performance. Therefore, this approach provides an effective solution to predict and improve operating performance.

Equivalent-input-disturbance-based robust control of drilling trajectory with weight-on-bit uncertainty in directional drilling.

Weight-on-Bit is of vital importance to the drilling trajectory orientation in directional drilling. This paper concerns robust control of drilling trajectory with weight-on-bit uncertainty for the directional drilling process. The objective is to develop an equivalent-input-disturbance-based trajectory control scheme such that the drilling trajectory is precisely controlled by suppressing the fluctuations of weight-on-bit. The motion orientation of both the drill bit and a series of stabilizers is used to describe the evolution process of the drilling trajectory. A state-space model with weight-on-bit uncertainty is derived from the evolution equation through a variable transformation. An equivalent-input-disturbance-based trajectory control system is designed, and two control loops are to track and control the trajectory inclination and azimuth, respectively. Two internal models track the trajectory inclination and azimuth respectively to elevate the control accuracy in the trajectory system. Two observer models combined with two low-pass filters estimate the trajectory inclination and azimuth by measuring the bottom hole assembly's inclination and azimuth. Some sufficient conditions are derived using linear-matrix-inequalities to obtain the control parameters by considering a reasonable fluctuation range of weight-on-bit. Finally, the control effects in the build-up and horizontal section of the drilling trajectory illustrate the proposed approach's validity.

A deviation correction strategy based on particle filtering and improved model predictive control for vertical drilling.

This paper is concerned with the correction of trajectory deviation in vertical drilling. Note that the accuracy of correction control will be reduced significantly by measurement and process noises, which finally leads to that the inclination angle exceeds beyond a tolerable limit. To deal with such noises and take into account practical constraints, a deviation correction strategy is developed for vertical drilling based on particle filtering and improved model predictive control in this paper. Firstly, the distributions and characters of the measurement and process noises in vertical drilling process are analyzed, and their approximate prior probability distributions are obtained. Based on the analysis, the structure of the deviation correction strategy is provided, including a particle filter and an improved model predictive controller which introduces a flexible constraint and an adjustable weight. The particle filter is effective to reject the measurement noises, and the improved model predictive controller plays an important role in achieving a small inclination of the drilling trajectory. Finally, two groups of simulations are carried out to illustrate the effectiveness of the proposed correction strategy.