Michał Grochowski

Analysis and design of softly switched model predictive control

Abstract This paper presents a new approach to soft switching between two model predictive controllers. The motivation for this work comes from the control of large scale hierarchical systems where different operating scenario asking for different control objective makes a single model predictive controller (MPC) unsuitable. The proposed soft switching approach shows much better switching performance both in system output and control input than the traditional hard switching. The stability of the designed soft switching process is analysed and sufficient conditions for stability are derived. Numerical examples with simulation results show that the proposed approach can be useful in practical applications.

Data-driven models for fault detection using kernel PCA

Kernel Principal Component Analysis (KPCA), an example of machine learning, can be considered a non-linear extension of the PCA method. While various applications of KPCA are known, this paper explores the possibility to use it for building a data-driven model of a non-linear system-the water distribution system of the Chojnice town (Poland). This model is utilised for fault detection with the emphasis on water leakage detection. A systematic description of the system’s framework is followed by evaluation of its performance. Simulations prove that the presented approach is both flexible and efficient.

Intelligent Control Structure for Control of Integrated Wastewater Systems

Abstract The paper proposes an approach to design a structure for control of integrated wastewater treatment plant-sewer system under full range of disturbance inputs. The control activities are hierarchically structured into a multilevel-multilayer form. A newly developed robust Model Predictive Control method for uncertain and output constrained dynamic systems is a key control technology employed at Optimising Control Level. This level is further decomposed into control layers operating at different time scales: slow, medium and fast. Appropriate models for control purposes is described Needed data are delivered by measuring system and Extended Kaiman Filter. A Supervisory Control Level is located at a top of the control hierarchy.

Softly Switched Model Predictive Control for Control of Integrated Wastewater Treatment Systems at Medium Time Scale

Abstract Difficulties occur when one universal control strategy attempts controlling a plant that is under wide range of operating conditions. In order to best adopt the control strategy to existing conditions three operational states: normal, disturbed and emergency are distinguished and the corresponding control strategies are designed. Appearance of different control strategies at hand enforces finding a mechanism to switch between them. It can be done in a hard or a soft manner. In case of wastewater systems the second solution is preferable. The paper describes two methods of soft switching between control strategies based on Model Predictive Control (MPC) as a control technology Supervisory Control Level (SuCL) mounted at the top of hierarchical multilevel-multilayer control structure is responsible for the conducting the switching process. The switching instants, switching time and way of switching are parameters to be selected by the SuCL. The soft switching concepts were examined based on wastewater system in Kartuzy, Poland.

Kernel PCA in application to leakage detection in drinking water distribution system

Monitoring plays an important role in advanced control of complex dynamic systems. Precise information about systems behaviour, including faults detection, enables efficient control. Proposed method- Kernel Principal Component Analysis (KPCA), a representative of machine learning, skilfully takes full advantage of the well known PCA method and extends its application to nonlinear case. The paper explains the general idea of KPCA and provides an example of how to utilize it for fault detection problem. The efficiency of described method is presented for application of leakage detection in drinking water systems, representing a complex and distributed dynamic system of a large scale. Simulations for Chojnice town show promising results of detecting and even localising the leakages, using limited number of measuring points.

Use of Neural Networks in Diagnostics of Rolling-Element Bearing of the Induction Motor

Bearing defect is statistically the most frequent cause of an induction motor fault. The research described in the paper utilized the phenomenon of the current change in the induction motor with bearing defect. Methods based on the analysis of the supplying current are particularly useful when it is impossible to install diagnostic devices directly on the motor. The presented method of rolling-element bearing diagnostics used indirect transformation, namely Clark transformation. It determines the vector of the spatial stator current based on instantaneous current measurements of the induction motor supply phases current. The analysis of the processed measurement data used multilayered, one-directional neural networks, which are particularly attractive due to their nonlinear structure and ability to learn. During the research 40 bearings: undamaged, with damages of three types and various degrees of fault extent, were used. The conducted research proves the efficiency of neural networks for detection and recognition of faults in induction motor bearings. In case of tests of the unknown state bearings, an efficiency approach to failure detection equaled 77%.

Pipeline system for heat transportation from nuclear power plant — An optimizing approach

Over the last few years heat piping insulation technology and pump systems efficiency have been significantly improved. Reduced thermal losses encourage heat transportation over long distances. It provides an opportunity for increasing thermodynamic efficiency of Nuclear Power Plants (NPPs) that are often located in rural areas because of safety issues. It can be achieved by Combined Heat and Power (CHP) generation, as heat produced in cogeneration mode can now by effectively used for distant District Heating (DH). Methodology for optimal design of Heat Transportation System (HTS) between NPP and DH network is investigated. Static model of HTS has been proposed and used in multi-criteria, hybrid, nonlinear and constrained optimization task in order to minimize construction and operation costs of HTS. These costs are minimized over presumed system lifetime and under variation of annual heat demand within DH area. Moreover, the issues of: terrain elevation profile, variability of ground temperature and insulation aging are taken into account. The methodology was tested on case study example of intended NPP located in Northern Poland.

Intelligent system supporting diagnosis of malignant melanoma

Malignant melanomas are the most deadly type of skin cancers. Early diagnosis is a key for successful treatment and survival. The paper presents the system for supporting the process of diagnosis of skin lesions in order to detect a malignant melanoma. The paper describes the development process of an intelligent system purposed for the diagnosis of malignant melanoma. Presented system can be used as a decision support system for primary care physicians and as a system capable of self-examination of the skin with usage of dermatoscope. The system utilizes computational intelligence methods for proper classification of the dermoscopic features extracted from the medical images. The paper also proposes the extension of the well know ABCD method used for malignant melanoma diagnosis. The proposed system is tested on 126 and trained on 80 skin moles and the obtained results are very promising.

Supervised model predictive control of wastewater treatment plant

An optimizing control of a wastewater treatment plant (WWTP), allowing for cost savings over long time period and fulfilling effluent discharge limits at the same time, requires application of advanced control techniques. Model Predictive Control (MPC) is a very suitable control technology for a synthesis of such a truly multivariable controller that can handle constraints and accommodate model-based knowledge combined with hard measurements. As it is impossible to efficiently control the plant by one universal control strategy under all possible influent conditions, it is proposed in the paper to on-line adapt the nonlinear MPC control strategy in order to best adapt the control actions to actual and predicted WWTP conditions. Adjusting the MPC control strategy is carried out by suitable manipulating the components of performance index and constraints. This process is supervised by Mamdani reasoning system. The supervised MPC controller performance was tested by simulations within large range of plant operating conditions and then compared with classic MPC without such mechanism. The simulation model of the benchmark WWTP utilizes ASM2d model.

Computed aided system for separation and classification of the abnormal erythrocytes in human blood

The human peripheral blood consists of cells (red cells, white cells, and platelets) suspended in plasma. In the following research the team assessed an influence of nanodiamond particles on blood elements over various periods of time. The material used in the study consisted of samples taken from ten healthy humans of various age, different blood types and both sexes. The markings were leaded by adding to the blood unmodified diamonds and oxidation modified. The blood was put under an impact of two diamond concentrations: 20μl and 100μl. The amount of abnormal cells increased with time. The percentage of echinocytes as a result of interaction with nanodiamonds in various time intervals for individual specimens was scarce. The impact of the two diamond types had no clinical importance on red blood cells. It is supposed that as a result of longlasting exposure a dehydratation of red cells takes place, because of the function of the cells. The analysis of an influence of nanodiamond particles on blood elements was supported by computer system designed for automatic counting and classification of the Red Blood Cells (RBC). The system utilizes advanced image processing methods for RBCs separation and counting and Eigenfaces method coupled with the neural networks for RBCs classification into normal and abnormal cells purposes.