Efficient Cyberattack Detection Methods in Industrial Control Systems.

The article deals with the issue of detecting cyberattacks on control algorithms running in a real Programmable Logic Controller (PLC) and controlling a real laboratory control plant. The vulnerability of the widely used Proportional-Integral-Derivative (PID) controller is investigated. Four effective, easy-to-implement, and relatively robust methods for detecting attacks on the control signal, output variable, and parameters of the PID controller are researched. The first method verifies whether the value of the control signal sent to the control plant in the previous step is the actual value generated by the controller. The second method relies on detecting sudden, unusual changes in output variables, taking into account the inertial nature of dynamic plants. In the third method, a copy of the controller parameters is used to detect an attack on the controller's parameters implemented in the PLC. The fourth method uses the golden run in attack detection.

Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach.

This work has two objectives. Firstly, it describes a novel physics-informed hybrid neural network (PIHNN) model based on the long short-term memory (LSTM) neural network. The presented model structure combines the first-principle process description and data-driven neural sub-models using a specialized data fusion block that relies on fuzzy logic. The second objective of this work is to detail a computationally efficient model predictive control (MPC) algorithm that employs the PIHNN model. The validity of the presented modeling and MPC approaches is demonstrated for a simulated polymerization reactor. It is shown that the PIHNN structure gives very good modeling results, while the MPC controller results in excellent control quality.

The Effect of Nasogastric Feeding after Surgery in Patients with Head and Neck Cancers - Retrospective Single Center Experience.

This study aimed to assess clinical factors that could predict the need for nasogastric feeding after surgery in patients with head and neck cancer (HNC) and evaluate the effect of tube feeding on selected laboratory parameters.This single-center retrospective study included 153 patients who underwent surgery for HNC. Data on patient and tumor characteristics were collected, along with laboratory measurements. Logistic regression was used to identify the predictors of the need for nasogastric feeding. Laboratory parameters were compared between patients who required nasogastric feeding vs those who did not.Nasogastric feeding was required in 90 patients (59%). Significant predictors of nasogastric feeding in HNC patients after surgery, which were revealed by univariate regression analysis, included low body mass index (odds ratio [OR] = 0.84), squamous cell carcinoma histology (OR = 8.05), T2 tumor stage (OR = 2.27), red blood cell count (M/µL) (OR = 0.44), hemoglobin levels (g/dL) (OR = 0.80), and mean corpuscular volume (fL) (OR = 1.10). Multivariate analysis showed that low BMI (OR = 0.87) and red blood cell count (M/µL) (OR = 0.32) were prognostic factors for nasogastric feeding. A significant percentage increase in white blood cell count from admission to discharge was noted in patients who required nasogastric feeding vs those who did not (p = 0.003).Determining factors that predict the need for nasogastric feeding in HNC patients after surgery may support more personalized treatment planning to optimize clinical outcomes.

Forgery Cyber-Attack Supported by LSTM Neural Network: An Experimental Case Study.

This work is concerned with the vulnerability of a network industrial control system to cyber-attacks, which is a critical issue nowadays. This is because an attack on a controlled process can damage or destroy it. These attacks use long short-term memory (LSTM) neural networks, which model dynamical processes. This means that the attacker may not know the physical nature of the process; an LSTM network is sufficient to mislead the process operator. Our experimental studies were conducted in an industrial control network containing a magnetic levitation process. The model training, evaluation, and structure selection are described. The chosen LSTM network very well mimicked the considered process. Finally, based on the obtained results, we formulated possible protection methods against the considered types of cyber-attack.

Digital Twins in the Practice of High-Energy Physics Experiments: A Gas System for the Multipurpose Detector.

The digital twins technology delivers a new degree of freedom into system implementation and maintenance practice. Using this approach, a technological system can be efficiently modeled and simulated. Furthermore, such a twin offline system can be efficiently used to investigate real system issues and improvement opportunities, e.g., improvement of the existing control system or development of a new one. This work describes the development of a control system using the digital twins methodology for a gas system delivering a specific mixture of gases to the time-of-flight (ToF) multipurpose detector (MPD) used during high-energy physics experiments in the Joint Institute for Nuclear Research (Dubna, Russia). The gas system digital twin was built using a test stand and further extended into target full-scale installation planned to be built in the near future. Therefore, conducted simulations are used to validate the existing system and to allow validation of the planned new system. Moreover, the gas system digital twin enables testing of new control opportunities, improving the operation of the target gas system.

LSTM and GRU Neural Networks as Models of Dynamical Processes Used in Predictive Control: A Comparison of Models Developed for Two Chemical Reactors.

This work thoroughly compares the efficiency of Long Short-Term Memory Networks (LSTMs) and Gated Recurrent Unit (GRU) neural networks as models of the dynamical processes used in Model Predictive Control (MPC). Two simulated industrial processes were considered: a polymerisation reactor and a neutralisation (pH) process. First, MPC prediction equations for both types of models were derived. Next, the efficiency of the LSTM and GRU models was compared for a number of model configurations. The influence of the order of dynamics and the number of neurons on the model accuracy was analysed. Finally, the efficiency of the considered models when used in MPC was assessed. The influence of the model structure on different control quality indicators and the calculation time was discussed. It was found that the GRU network, although it had a lower number of parameters than the LSTM one, may be successfully used in MPC without any significant deterioration of control quality.

Fast Real-Time Model Predictive Control for a Ball-on-Plate Process.

This work is concerned with an original ball-on-plate laboratory process. First, a simplified process model based on state-space process description is derived. Next, a fast state-space MPC algorithm is discussed. Its main advantage is computational simplicity: the manipulated variables are found on-line using explicit formulas with parameters calculated off-line; no real-time optimization is necessary. Software and hardware implementation details of the considered MPC algorithm using the STM32 microcontroller are presented. Tuning of the fast MPC algorithm is discussed. To show the efficacy of the MPC algorithm, it is compared with the classical PID and LQR controllers.

Parotid gland tumors. Results of retrospective analysis of 149 patients treated at the Clinical Department of Cranio-Maxillofacial Surgery, Clinic of Otolaryngology and Oncologic Laryngology of Military Institute of Medicine in Warsaw in years 2006-2016.

Wstep: Nowotwory majace swoja etiologie w gruczolach slinowych wystepuja rzadko i stanowia ok. 3-10% wszystkich guzów w obrebie glowy i szyi. Material i metody: W latach 2006-2016 w Klinicznym Oddziale Chirurgii Czaszkowo-Szczekowo-Twarzowej Wojskowego Instytutu Medycznego w Warszawie z powodu nowotworów slinianek przyusznych hospitalizowano i leczono 149 pacjentów. Podstawa do analizy byly historie chorób pacjentów, wyniki badan histopatologicznych oraz protokoly zabiegów operacyjnych. Wyniki: W 126 przypadkach guzy byly lagodne, natomiast w 26 guzy zlosliwe. Analizujac wyniki mozna stwierdzic, ze nowotwory - zarówno lagodne, jak i zlosliwe - czesciej wystepowaly u mezczyzn. Sredni wiek calej grupy badanych wynosil 58,3 lat, dla zmian zlosliwych - 65,5 lat, a dla zmian lagodnych byl nieznacznie nizszy i wynosil 56,9 lat. Wsród pacjentów objetych analiza szczyt zachorowalnosci przypadal na przedzial wiekowy 60-69 lat. Ponadto zwraca uwage, iz przedzial ten byl taki sam dla ogólnej liczby guzów, jak i nowotworów lagodnych, natomiast dla nowotworów zlosliwych byl nieznacznie wyzszy i wynosil 70-79 lat. Z analizy zebranego materialu wynika, ze guzy lagodne wystepowaly znamiennie czesciej, stanowiac 84,56% wszystkich guzów. Najczestszymi rozpoznaniami wsród nowotworów lagodnych byly gruczolak wielopostaciowy (adenoma pleomorphicum) oraz gruczolak limfatyczny (adenolymphoma), które stanowily lacznie 93,66%. Rezultaty badan wskazuja, ze wsród nowotworów zlosliwych dominowaly: gruczolakorak polimorficzny o niskiej zlosliwosci (polymorphous low-grade adenocarcinoma) wystepujacy w 26,07% przypadków, gruczolakorak inaczej nieokreslony (adenocarcinoma NOS) oraz rak zrazikowokomórkowy (acinic cell carcinoma). Kazdy z nich stanowil po 13,04% rozpoznan. Jak wynika z przeprowadzonej analizy najczestsza metoda leczenia bylo leczenie chirurgiczne jako metoda stosowana samodzielnie. Wnioski: Uzyskane z retrospektywnej analizy dane koreluja z pismiennictwem krajowym i swiatowym.