Search

The content of free calcium oxide (f-CaO) in cement clinker is an important index for cement quality. Aiming at the characteristics of strong coupling, time-varying delay and highly non-linearity in cement clinker production, a soft sensor model based on multivariate time series analysis and convolutional neural network (MVTS–CNN) is proposed for the online f-CaO content monitoring. Based on the process industry characteristics, the MVTS–CNN modeling involves the detailed analysis of coupling relationship and time-varying delay in cement production and the application of neural network in multivariate time-series feature extraction. The main researches and contributions are fourfold: First, the strong coupling in the production system is further analyzed, and the proposed model is focused on the data coupling between specific processes, not the control coupling. Second, a multivariate time series analysis method is designed to select the time series that may have direct impacts on the f-CaO content in different production conditions, which is founded on the information on time delay range and longest active duration. Third, a multivariate time series feature extraction method is designed and adopted in the MVTS–CNN model to extract the multivariate time series features, such as active duration difference features, coupling features, nonlinear features and key time series features. Fourth, a new timing matching method, which is combined the rough timing matching of multivariate time series and the detailed timing matching of key features, is proposed to deal with the time-varying delay in various production conditions. Compared with traditional CNN, support vector machines (SVM) and long-short term memory networks (LSTM), the results demonstrate that the MVTS–CNN model has higher accuracy, better generalization ability and superior robustness.

Semantic segmentation has achieved great success with the popularity of convolutional neural networks (CNNs). However, the huge computational burden restricts the application of most existing networks on edge devices with strict inference time constraints. To solve this problem, a weighted factorized-depthwise convolution network (WFDCNet) is presented in this paper, which contains full- dimensional continuous separation convolution (FCS) modules and a lateral asymmetric pyramid fusion (LAPF) module, aiming to obtain high accuracy without damaging inference speed. Specifically, the FCS module enables the calculation of each dimension to be completed independently in a continuous separation process and uses simplified SE (SSE) attention layer to adjust the channels, achieving the extensive extraction of feature information. The LAPF module is able to eliminate semantic divergence and fuse feature maps of three different scales to realize the combination of multiple information from the front-end and the back-end network. WFDCNet shows superior performance on Cityscapes, Camvid, Mapillary Vistas and COCO-Stuff datasets. Especially, the experimental results demonstrate that our network achieves 73.7% mIoU on Cityscapes dataset, with the inference speed of 102.6FPS on a single RTX 2080 Ti GPU, and 17.2FPS on Jetson TX2.

For that there is still a lack of effective methods improving economic performance of the complex process systems in Model Predictive Control (MPC), a design method of multi-variable economic optimization objective function based on interval predictive control is proposed in this paper. The objective function consists of constraint item, control item and economic item, which are separately used to handle the constraint targets, coordinate the operational control and improve the economic indicators. In the process of solving the objective function, the multi-variable economic control optimization strategy is used. Fist, a multi-variable coordination optimization method is used preferentially to satisfy the target set point and constraint interval control of the Controlled Variables (CV s), then the weights of the economic item are adjusted according to the variable priority to achieve optimization of the Manipulated Variables (MV s). The simulation results show that the application of this objective function in MPC is not only able to achieve requirements of the product quality target, but also can significantly increase the economic benefits.

To increase the energy efficiency of sensor nodes and ensure the accuracy of data transmitting, A Trust Degree of node Based on Aware Routing Protocol for Wireless Sensor Networks (TDAR) has been proposed. Based on the energy aware mechanism, TDAR algorithm builds node trust degree function and sets threshold of energy for changing transmitting node, so transmit node with higher link quality and less even no congestion can be chosen, the routing can also dynamic local adjust. Simulation results show that, TDAR can ensure lower end-to-end delay, improve the reliability of data transmitting in networks, and extend the network lifetime significantly.

According to the analysis of the characteristics of time-varying and nonlinear, long delays in industry processes, a fuzzy predictive controller based on the T-S fuzzy model predictive control algorithm is designed for calcining temperature of the rotary cement kiln in this paper. First, a T-S fuzzy model for temperature control system is constructed. The input variables are divided according to the fuzzy C-means clustering algorithm, and the rear parameters of the fuzzy regulation are identified by the least square method. Later the system is locally dynamic linearized at each sampling point. Predictive control is done according to the constructed linear system model in the Generalized Predictive Control (GPC) algorithm. Simulation result shows the good adaptability and high accuracy of the designed controller.

For wireless sensor networks in LEACH algorithm inter-cluster single-hop communication can not meet the requirements of network expansion of the problem, a multi-hop communication routing algorithm called CMRA is proposed. The algorithm uses the node communication energy consumption model derived network optimal cluster number per round under multi-hop communication; by analyzing the network total energy consumption determines the cost of choosing the next jump nodes and establishes a minimum energy path tree to the base station between cluster heads. The simulation results show that the algorithm can make up the lack of single-hop communication in LEACH algorithm, and prolong the network lifetime to a certain extent.

Aiming at problems of communication conflict and network performance degradation resulted from excessive neighbor nodes, we present a degree-optimized LMPT topology control algorithm of wireless sensor networks. The algorithm builds the minimal energy topology based on shortest path theory, simultaneously uses the relative neighborhood graph method to control the number of neighbor nodes. The theoretical analysis proves the connectivity and degree bound of topology derived under our algorithm. The experiment results show that the topology has advantages on node degree and transmission power efficiency, as well as smaller path energy consumption, which can help improve the network performance and prolong the network lifetime.