This paper investigates the adaptive sliding mode security control (ASMSC) problem of rotary inverted pendulum against randomly occurring false data injection attacks (ROFDIAs). To accomplish the control objectives for both swing-up and stabilization stages, this study proposes an adaptive backstepping nonlinear control method and an ASMSC method, respectively. These approaches distinctly differ from conventional strategies such as energy-based swing-up control methods, linear quadratic regulators, or adaptive sliding mode control techniques. Besides, note that the existing control methods are proposed in the normal network environment, once the network is malicious attacks, these methods will be invalid. Based on this, a novel ASMSC method is proposed of rotating inverted pendulum against ROFDIAs. Meanwhile, the validity of the proposed method is proved by two comparative experiments on the hardware-in-the-loop simulation platform.

Froth image features serve as crucial reference indicators for optimizing productivity under complex flotation process conditions. However, due to the instability of the production environment, calculating the size distribution and froth velocity of froth images proves challenging. This article investigates a feature extraction method based on segment anything model (SAM), a visual foundation model, to address issues of low accuracy and time-intensive froth image feature extraction. Leveraging the instance segmentation performance of the SAM model, the low-rank adaptation fine-tuning method is employed to enhance SAM’s feature modeling capability for froth images. A mask-prompt generator is designed to guide SAM in froth segmentation. Subsequently, a froth velocity calculation method based on SAM’s instance segmentation results is proposed. Only a small amount of training data is required to achieve the desired level of model performance. Ultimately, this article implements a unified algorithmic framework for froth image feature extraction.

In the context of Pharma 4.0, i.e., the pharmaceutical version of Industry 4.0, pharmaceutical quality control (PQC) for a pharmaceutical cyber-physical system (PCPS) plays a critical role in ensuring the quality of drug products during pharmaceutical development. However, drug customization through Pharma 4.0 also introduces uncertainty embodied in ever-changing critical material attributes, which presents new challenges related to development costs and efficiency in PQC compared to traditional control modes. Although we have proposed a data-driven methodology to tackle these challenges, it ignores some visible or potential process knowledge that also contains much additional information reflecting the laws and trends governing pharmaceutical process operations. This not only sacrifices the opportunity to use this knowledge to make up for insufficiencies in the information provided by the data but also goes against the core ideology of future intelligent manufacturing. In this article, we introduce the idea of a data- and knowledge-driven approach into PQC for the first time by proposing a general data- and knowledge-driven adaptive PQC framework for a PCPS-based two phases—PQC by direct data- and knowledge-driven adaptive iterative learning control and PQC by learning from primitive data and knowledge. Next, a case study is presented to preliminarily investigate the application of the proposed framework in a simulated pharmaceutical spray fluidized bed granulation process. Finally, a series of simulation experiments are designed to verify the feasibility and effectiveness of the proposed framework.

This article investigates the adaptive fuzzy sliding exact tracking control problem of a class of high-order nonlinear systems with full-state constraints and mismatched external disturbances. To achieve exact tracking control, the upper bound of a composite polynomial is estimated, which is composed of approximation error, mismatched disturbance, and virtual control law and its upper bound estimated information is employed in the controller design. In this way, once the tracking error deviates from the origin, the corresponding adaptive fuzzy sliding exact tracking control mechanism will be activated to force it to slide along the origin, and then exact tracking control is achieved. Meanwhile, high-order log-type time-varying barrier Lyapunov functions are introduced to ensure that the full-state constraint is not violated. A 2-D high-order nonlinear system and an underactuated nonlinear benchmark system with weak coupling are considered to illustrate the characteristics of the control mechanism in simulation.

In this article, the main contribution is to introduce the adaptive backstepping technique into nonlinear cyber–physical systems against randomly occurring false data injection (ROFDI) attacks. And a new defense strategy based on nonlinear disturbance observer (NDO) is developed, which can not only effectively estimate the external compound disturbance in the presence of the attack, but also improve the robustness of the controlled system. Different from FDI attacks, it is a special case of ROFDI attacks, and the proposed method can deal with ROFDI attacks injected by attackers. Meanwhile, multiple Nussbaum functions are introduced, which overcomes the design difficulty of unknown control directions caused by ROFDI attacks. Furthermore, the approximation of the unknown nonlinear function and the exponential growth problem in the traditional backstepping calculation process are handled by radial basis function neural network and dynamic surface control, respectively. Finally, a new adaptive neural control method based on NDO is proposed to make all signals bounded. Meanwhile, tracking errors and disturbance estimation errors converge on the neighborhood of zero. Numerical and practical examples further illustrate the rationality of the method.

In this article, the problem of disturbance-observer-based adaptive fuzzy control is investigated for a class of strict-feedback switched nonlinear systems under arbitrary switching. Compared with existing results, a main contribution of this article is to design a piecewise switched nonlinear disturbance observer (NDO) for arbitrary switching systems to estimate unknown compound disturbances, which consist of external disturbances and approximate errors. Different from the common adaptive laws, the piecewise switched adaptive laws are designed, which reduces the conservativeness of controller design. In order to solve the difficulties caused by input delay and computational complexity, the Padé approximation and dynamic surface control technology are introduced, respectively. By utilizing the adaptive backstepping technique and the Lyapunov stability theorem, a novel controller based on the piecewise switched NDO is developed. It is proved that all the signals of the closed-loop systems are semiglobally uniformly ultimately bounded. The disturbance estimation errors and the tracking errors converge on a small neighborhood of the origin. Simulation results are provided to demonstrate the effectiveness of the proposed method.

Pharmaceutical quality control (PQC) holds a critical position in quality by design-based pharmaceutical development, but development costs are seldom considered due to the overly important role of drugs. Furthermore, in the context of the Made in China 2025 and Industry 4.0 strategies, drug customization brings about uncertainty embodied as frequently changing critical material attributes, which presents new challenges related to development cost and efficiency in PQC compared to traditional model-based control. The pursuit of optimal cost and efficiency while ensuring high quality will always be a hot topic of discussion because it is an eternal theme of technological revolutions. In this article, we first introduce the idea of a cyber-physical system into pharmaceutical development to propose the concept of a cyber-pharmaceutical-development system (CPDS) for the first time, and then we present a general data-driven adaptive PQC framework for the CPDS. Next, a case study is presented to preliminarily apply the proposed framework in a simulated pharmaceutical granulation-tabletting process. Finally, a series of simulation experiments are designed to verify the feasibility and effectiveness of the simulation modeling and the proposed PQC framework.

The operational variables used to adjust the control level of the copper cleaner flotation process have a noticeable impact on the object variables, e.g., the copper concentrate grade. Currently, due to the complexity of the flotation process, the operational variables, which are controlled by operators, are often not adjusted properly in time. Hence, this article investigates an intelligent operational adjustment framework based on a hybrid Bayesian network (BN). The offline BN model structure and the parameters are established based on process knowledge and real industrial data, respectively. After receiving the expected value of the copper concentrate grade as evidence, an operational adjustment can be obtained online by BN reasoning. To ensure its credibility, the copper concentrate grade after operational adjustment is further predicted. According to the predicted value, the operators can determine whether to implement the operational adjustment or not. Finally, the experimental results show the effectiveness and practical significance of the proposed method.

This paper proposes a new coal quality exploration method that detects coal quality in coal mining areas and explores and monitors the distribution and change of coal through remote sensing images. First, we collected a large number of coal and noncoal samples such as sandstones, shales, and coal gangues. Second, we measured the actual spectral data of these samples using a spectrometer. For coal mines, we used the chemical analysis method to quantify coal's fixed carbon and categorize the coal mines into three types based on the fixed carbon content present in coal. Third, we collected satellite remote sensing images of coal mining areas and established spectral data relations between the measured spectral data of the samples and the remote sensing images. Fourth, we proposed an incremental multilayer learning machine algorithm and used the algorithm combined with spectral data to build a coal quality classification model to identify coal quality in remote sensing images. Finally, the model accurately described the distribution map of coal quality. Compared with traditional coal exploration methods, this method has the advantages of high speed, high accuracy, and low price.