Deep learning frameworks to learn prediction and simulation focused control system models

Deep learning (DL) methods have brought world-shattering breakthroughs, especially in computer vision and classification problems. Yet, the design and deployment of DL methods in time series prediction and nonlinear system identification applications still need more progress. In this paper, we present DL frameworks that are developed to provide novel approaches as solutions to the aforementioned engineering problems. The proposed DL frameworks leverage the advantages of autoencoders and long-short term memory network, which are known being data compression and recurrent structures, respectively, to design Deep Neural Networks (DNN) for modeling time series and nonlinear systems with high performance. We provide recommendations on how deep AEs and LSTMs should be utilized to end up with efficient Prediction-focused (Pf) and Simulation-focused (Sf) DNNs for time series and system identification problems. We present systematic learning methods for the DL frameworks that allow straightforward learning of Pf-DNN and Sf-DNN models in detail. To demonstrate the efficiency of the developed DNNs, we present various comparative results conducted on the benchmark and real-world datasets in comparison with their conventional, shallow, and deep neural network counterparts. The results clearly show that the deployment of the proposed DL frameworks results with DNNs that have high accuracy, even with a low dimensional feature vector.

     

The comprehensive investigation of the room temperature ionic liquid additives in PVC based polymer inclusion membrane for Cr(VI) transport

This study is to perform the comprehensive investigation of PVC based ionic plasticized membrane (IPM) production by using room temperature ionic liquid (RTIL)‐based additives and the membrane application of selective Cr(VI) removal. Some significant parameters related to membrane structures that are membrane thickness, plasticizer rate, and type, RTILs rate, and type, the average molecular weight of PVC were studied to define the excellent polymeric membrane film composition. After that, the PVC based polymeric film used in the Cr(VI) transport and initial mass transfer coefficient (J_o) were about 3.57 × 10^?7 mol s^?1 m^?2 by decyl substituted RTIL as an additive. Also, optimized membrane transport process has been considered as selective enough for Cr(VI) in the presence of the other heavy metal ions. Surface characterizations of the membranes have been performed to clarify the structural and the morphological assessment of IPMs at initial and end of Cr(VI) transport by SEM‐EDX, AFM, contact angle measurement and found a good relationship between the molecular structure of RTIL additive and membrane morphology. As we know that lots of researchers are still trying to find environmentally friendly, inexpensive and straightforward processes to remove toxic substances from industrial effluents or natural sources. At that point, our results can open a gate for cheap, novel and environmentally friendly Cr(VI) removal by PVC based membrane. J. VINYL ADDIT. TECHNOL., 25:E107–E119, 2019. © 2018 Society of Plastics Engineers     

Correction to: Deep learning frameworks to learn prediction and simulation focused control system models

Applied Intelligence - A Correction to this paper has been published: https://doi.org/10.1007/10489.1573-7497     

Type-2 fuzzy model based controller design for neutralization processes

In this study, an inverse controller based on a type-2 fuzzy model control design strategy is introduced and this main controller is embedded within an internal model control structure. Then, the overall proposed control structure is implemented in a pH neutralization experimental setup. The inverse fuzzy control signal generation is handled as an optimization problem and solved at each sampling time in an online manner. Although, inverse fuzzy model controllers may produce perfect control in perfect model match case and/or non-existence of disturbances, this open loop control would not be sufficient in the case of modeling mismatches or disturbances. Therefore, an internal model control structure is proposed to compensate these errors in order to overcome this deficiency where the basic controller is an inverse type-2 fuzzy model. This feature improves the closed-loop performance to disturbance rejection as shown through the real-time control of the pH neutralization process. Experimental results demonstrate the superiority of the inverse type-2 fuzzy model controller structure compared to the inverse type-1 fuzzy model controller and conventional control structures.     

The cell-surface heparan sulfate proteoglycan glypican-1 regulates growth factor action in pancreatic carcinoma cells and is overexpressed in human pancreatic cancer

Heparan sulfate proteoglycans (HSPGs) play diverse roles in cell recognition, growth, and adhesion. In vitro studies suggest that cell-surface HSPGs act as coreceptors for heparin-binding mitogenic growth factors. Here we show that the glycosylphosphatidylinositol- (GPI-) anchored HSPG glypican-1 is strongly expressed in human pancreatic cancer, both by the cancer cells and the adjacent fibroblasts, whereas expression of glypican-1 is low in the normal pancreas and in chronic pancreatitis. Treatment of two pancreatic cancer cell lines, which express glypican-1, with the enzyme phosphoinositide-specific phospholipase-C (PI-PLC) abrogated their mitogenic responses to two heparin-binding growth factors that are commonly overexpressed in pancreatic cancer: fibroblast growth factor 2 (FGF2) and heparin-binding EGF-like growth factor (HB-EGF). PI-PLC did not alter the response to the non-heparin-binding growth factors EGF and IGF-1. Stable expression of a form of glypican-1 engineered to possess a transmembrane domain instead of a GPI anchor conferred resistance to the inhibitory effects of PI-PLC on growth factor responsiveness. Furthermore, transfection of a glypican-1 antisense construct attenuated glypican-1 protein levels and the mitogenic response to FGF2 and HB-EGF. We propose that glypican-1 plays an essential role in the responses of pancreatic cancer cells to certain mitogenic stimuli, that it is relatively unique in relation to other HSPGs, and that its expression by pancreatic cancer cells may be of importance in the pathobiology of this disorder.     

Optimal PID Control of Spatial Inverted Pendulum With Big Bang – Big Crunch Optimization

As the extension of the linear inverted pendulum (LIP) and planar inverted pendulum (PIP), this paper proposes a novel spatial inverted pendulum (SIP). The SIP is the most general inverted pendulum (IP) than any existing IP. The model of the SIP is presented for the first time. The SIP inherits all the characteristics of the LIP and the PIP, which is a nonlinear, unstable and underactuated system. The SIP has five degrees of motion freedom and three control forces. Thus, it is a multiple-input and multiple-output (MIMO) system with nonlinear dynamics. To realize the spatial trajectory tracking of the SIP, the control structure with five PID controllers will be designed. The parameter tuning of the multiple PIDs is a challenging work for the proposed SIP model. To alleviate the difficulties of the parameter tuning for the multiple PID controllers, optimal PIDs can be achieved with the help of Big Bang-Big Crunch (BBBC) optimization. The BBBC algorithm can successfully optimize the parameters of the multiple PID controllers with high convergence speed. The optimization performance index of the BBBC algorithm is compared with that of the particle swarm optimization (PSO). Simulation results certify the rightness and effectiveness of the proposed control and optimization methods.      

A framework for designing cognitive trajectory controllers using genetically evolved interval type-2 fuzzy cognitive maps

In this paper, we provide a complete framework for the design of genetically evolved cognitive tracking controller based on interval type-2 (IT2) fuzzy cognitive map (FCM). We construct the cognitive controller based on a nonlinear controller by transforming its representation into a FCM. This representation gives the opportunity to prove the stability of the cognitive controller in the framework of nonlinear control theory. Moreover, with the deployment of IT2-fuzzy sets which are known to be capable to handle high level of uncertainty, the proposed cognitive controller has the ability to deal with uncertainty that are encountered in real-time world applications. To accomplish the design of the cognitive controller, we present a systematic approach based on genetic algorithm to optimize its parameters and learn fuzzy rules by extracting them from model space (e.g., a set of rules). Within the paper, all steps in constructing and designing the IT2-FCM-based cognitive controller are presented. We first show the performance improvements of the proposed IT2-FCM-based tracking controller with extensive and comparative simulation results and then with experimental results that were collected on real-world mobile robot. The results clearly show the superiority of proposed cognitive control systems when compared to its conventional and fuzzy controller counterparts. We believe that the proposed genetically evolved design approach of the IT2-FCM-based cognitive controller will provide a bridge between the well-developed cognitive sciences and control theory.     

Selective separation of nickel from cobalt in ammoniacal solutions by emulsion type liquid membranes using 8-hydroxyquinoline (8-HQ) as mobile carrier

The selective separation and concentration of nickel from ammoniacal solutions containing nickel and cobalt by an emulsion liquid membrane (ELM) technique using 8-hydroxyquinoline (8-HQ) as carrier has been examined. The emulsion liquid membrane consists of a diluent (kerosene), a surfactant (ECA 4360J), a carrier (8-HQ), and a stripping solution (0.025 M EDTA solution, buffered at pH 4.0). Cobalt (II) in the 6 M ammonia feed solution was oxidised to cobalt (III) by adding H₂O₂ and the pH adjusted to 10 with hydrochloric acid (HCl). The important variables were found to be membrane composition, ammonia concentration, diluent type, surfactant concentration, extractant concentration, EDTA concentration in the stripping solution, pH of the feed and the stripping solutions, phase ratio, and treatment ratio. It was possible to selectively extract 96.5 to 99.0% of nickel from a mixture of nickel and cobalt.     

Selective extraction of nickel from ammoniacal solutions containing nickel and cobalt by emulsion liquid membrane using 5,7-dibromo-8-hydroxyquinoline (DBHQ) as extractant

The selective extraction and concentration of nickel from ammoniacal solutions containing nickel and cobalt by an emulsion liquid membrane (ELM) technique using 5,7-dibromo-8-hydroxyquinoline (DBHQ) as extractant has been presented. ELM consists of a diluent (kerosene), a surfactant (Span 80), an extractant (DBHQ), a modifier (tributyl phosphate), and a stripping solution (very dilute sulfuric acid solution containing EDTA as complexing agent, buffered at pH 4.25). Cobalt (II) in feed solution with 6 mol/L ammonia was oxidised to Cobalt (III) by H₂O₂ and pH of this ammoniacal solution was adjusted to 10.0 with the addition of hydrochloric acid (HCl). The important variables governing the permeation of nickel and their effect on the separation process have been studied. These variables were membrane composition, ammonia concentration in the feed solution, mixing speed, surfactant concentration, extractant concentration, pH of the feed and the stripping solutions, complexing agent concentration in the stripping solution, and phase ratio. After the optimum conditions had been determined, it was possible to selectively extract 99% of nickel from the ammoniacal solutions containing Ni and Co. The separation factors of nickel with respect to cobalt, based on initial feed concentration, have experimentally found to be of as high as 88.1 for about equimolar Co–Ni feed solutions.     

Extraction of cadmium from solutions containing various heavy metal ions by Amberlite LA-2

In present study, selective extraction of cadmium from acidic leach solutions, containing various heavy metal ions, by emulsion liquid membrane (ELM) is studied. For this reason, the zinc plant copper cake was leached with sulfuric acid and main acidic leach solution containing Zn(II), Cu(II), Fe(II), Cd(II), Co(II) and Ni(II) ions was obtained. After Zn(II), Cu(II), Fe(II) and Cd(II) ions in the acidic leach solution were separated, the important parameters influencing the extent of cadmium extraction were investigated and optimum conditions were determined. Cadmium extraction was influenced by number of parameters like initial metal ion concentration, mixing speed, phase ratio, extractant concentration, surfactant concentration, the stripping solution type and concentration, and the feed solution acid concentration. The optimum values of parameter above mentioned were used and cadmium in the acidic leach solution containing 650 mg Cd/L, 365 mg Co/L, 535 mg Ni/L, and 1260 mg Zn/L was almost completely extracted within 10 min. The results showed that it is possible to extract 99% of cadmium after 10 min contact time by using ELM from aqueous solutions, containing Fe(II), Al(III), Cu(II), Zn(II), Pb(II), Co(II) and Ni(II) ions, at the optimum operating conditions.