Improving Walking Economy With an Ankle Exoskeleton Prior to Human-in-the-Loop Optimization

Lower limb robotic exoskeletons have shown the capability to enhance human locomotion for healthy individuals or to assist motion rehabilitation and daily activities for patients. Recent advances in human-in-the-loop optimization that allowed for assistance customization have demonstrated great potential for performance improvement of exoskeletons. In the optimization process, subjects need to experience multiple types of assistance patterns, thus, leading to a long evaluation time. Besides, some patterns may be uncomfortable for the wearers, thereby resulting in unpleasant optimization experiences and inaccurate outcomes. In this study, we investigated the effectiveness of a series of ankle exoskeleton assistance patterns on improving walking economy prior to optimization. We conducted experiments to systematically evaluate the wearers' biomechanical and physiological responses to different assistance patterns on a lightweight cable-driven ankle exoskeleton during walking. We designed nine patterns in the optimization parameters range which varied peak torque magnitude and peak torque timing independently. Results showed that metabolic cost of walking was reduced by 17.1 ± 7.6% under one assistance pattern. Meanwhile, soleus (SOL) muscle activity was reduced by 40.9 ± 19.8% with that pattern. Exoskeleton assistance changed maximum ankle dorsiflexion and plantarflexion angle and reduced biological ankle moment. Assistance pattern with 48% peak torque timing and 0.75 N·m·kg−1 peak torque magnitude was effective in improving walking economy and can be selected as an initial pattern in the optimization procedure. Our results provided a preliminary understanding of how humans respond to different assistances and can be used to guide the initial assistance pattern selection in the optimization.

Accurate Digital Marketing Communication Based on Intelligent Data Analysis

In digital marketing, the core advantages of scientific and technological means such as artificial intelligence and big data analysis gradually appear and pay attention to them. This paper studies the accuracy of digital marketing and proposes an intelligent algorithm based on data analysis, which improves the effect of marketing communication. Through the combination of intelligent algorithms and big data analysis, the data are convincing. Through the comparison and improvement of intelligent algorithm logistic regression and XGBoost, this paper puts forward an improved algorithm of XGBoost based on Bayesian optimization parameters, which can improve the efficiency of digital marketing communication and enhance the social influence of digital marketing.

Determining the optimal location of an urban transport interchange hub

Several possible options for the location of Pyatiletka transport interchange hub in the Samara city district are considered. In order to determine the optimal option, the hub location is compared by several parameters. Such values as passenger traffic, existing routes of urban public transport, priority directions of passenger traffic, and capital investments in construction are selected as optimization parameters. To determine the values of passenger traffic, an analysis of the existing passenger traffic was performed, with its allocation by capacity and routing. The unevenness of passenger traffic by days of the week and periods of the day is determined, the minimum and maximum values of passenger traffic are revealed, as well as its fluctuations over the considered periods. The construction of public urban transport routes allowed to identify the busiest routes and the availability of transport for different variants of the transport interchange hub location. The options of organizing the possible arrival/departure of urban public transport to/from the transport interchange hub are considered. Using the obtained data, a SWOT analysis was performed to determine the strengths and weaknesses of each hub placement option and the optimal variant was selected.

STRUCTURAL AND PARAMETRIC OPTIMIZATION OF GAS-HYDRODYNAMIC MEASURING TRANSDUCERS OF PHYSICAL AND MECHANICAL PARAMETERS OF FLUIDS

The article is devoted to improving the methods for building throttle diagrams of gas-hydrodynamic measuring transducers of physical and mechanical parameters of fluids. The authors reviewed modern throttle transducers of various parameters, built on different diagrams, with different numbers and types of throttle elements, with different output signals. We established that the goodness of the measuring transducer is determined both by the structural diagram and the design characteristics of the throttle elements of a specific measuring diagram. The article proposes using structural synthesis with parametric optimization to achieve the specified characteristics of the gas-hydrodynamic transducers. The aim is to develop an effective method for building throttle diagrams of gas-hydrodynamic measuring transducers of physical and mechanical parameters of fluids using structural optimization of diagrams and to evaluate each dia-gram using parametric optimization methods with the appropriate criterion that quantifies the goodness of the measur-ing transducer. To achieve this goal, the authors analyzed the criteria and resources of structural and parametric optimization of gas-hydrodynamic transducers. In particular, the following resources of structural synthesis of measuring transducers’ dia-grams are analyzed: diagram order and throttle arrangement, type of throttles, output signals, supply mode of the transducer. Approaches to parametric optimization of throttle diagrams are offered: based on the mathematical model, one defines the objective function, forms restrictions on variable and fixed values, substantiates optimization parameters, chooses the optimization method. As a result of the research, the authors developed a technique for structural and parametric optimization of gas-hydrodynamic measuring transducers, making it possible to synthesize throttle diagrams and build mathematical models of transducers of specific parameters of the fluid with optimal characteristics.

Study of Microscale Meniscus Confined Electrodeposition Based on COMSOL

The rate and quality of microscale meniscus confined electrodeposition represent the key to micromanipulation based on electrochemistry and are extremely susceptible to the ambient relative humidity, electrolyte concentration, and applied voltage. To solve this problem, based on a neural network and genetic algorithm approach, this paper optimizes the process parameters of the microscale meniscus confined electrodeposition to achieve high-efficiency and -quality deposition. First, with the COMSOL Multiphysics, the influence factors of electrodeposition were analyzed and the range of high efficiency and quality electrodeposition parameters were discovered. Second, based on the back propagation (BP) neural network, the relationships between influence factors and the rate of microscale meniscus confined electrodeposition were established. Then, in order to achieve effective electrodeposition, the determined electrodeposition rate of 5*10−8 m/s was set as the target value, and the genetic algorithm was used to optimize each parameter. Finally, based on the optimization parameters obtained, we proceeded with simulations and experiments. The results indicate that the deposition rate maximum error is only 2.0% in experiments. The feasibility and accuracy of the method proposed in this paper were verified.

Optimization of layering technique and secondary structure analysis during the formulation of nanoparticles containing lysozyme by quality by design approach

In our study, core-shell nanoparticles containing lysozyme were formulated with precipitation and layering self-assembly. Factorial design (DoE) was applied by setting the process parameters during the preparation with Quality by Design (QbD) approach. The factors were the concentration of lysozyme and sodium alginate, and pH. Our aim was to understand the effect of process parameters through the determination of mathematical equations, based on which the optimization parameters can be predicted under different process parameters. The optimization parameters were encapsulation efficiency, particle size, enzyme activity and the amount of α-helix structure. The nanoparticles were analysed with transmission electron microscopy (TEM), Fourier-transform infrared spectroscopy (FTIR) and circular dichroism (CD) spectroscopy. Based on our results, we found that pH was the most important factor and pH 10 was recommended during the formulation. Enzyme activity and α-helix content correlated with each other very well, and particle size and encapsulation efficiency also showed very good correlation with each other. The results of the α-helix content of FTIR and CD measurements were very similar for the precipitated lysozyme due to the solid state of lysozyme. The mixing time had the best influence on the encapsulation efficiency and the particle size, which leads to the conclusion that a mixing time of 1 h is recommended. The novelty in our study is the presentation of a mathematical model with which the secondary structure of the protein and other optimization parameters can be controlled in the future during development of nanoparticle based on the process parameters.

Selection of the Optimal Structural Design of a Spar Composite Wing

This paper describes a method for optimizing the design of a spar-type composite aircraft wing structure based on multi-criterion approach. Two types of composite wing structures such as two-spar and three-spar ones were considered. The optimal design of a wing frame was determined by the Pareto method basing on three criteria: minimal weight, minimal wing deflection, maximal safety factor and minimal weight. Positions of wing frame parts, i.e. spars and ribs, were considered as optimization parameters. As a result, an optimal design of a composite spar-type wing was proposed. All the calculations necessary to select the optimal structural and design of the spar composite wing were performed using nonlinear static finite element analysis in the FEMAP with NX Nastran software package.

Optimum control of purpose activities in the area of quality based on a linear model of dynamics in state space

The paper considers the optimization problem formulation at goal-setting in the field of quality on the basis of a dynamics verified linear model in the state space using stepwise and linear laws of enterprise activity management. The classical quadratic functional to find optimal solutions for goal-setting was used. The direct connection of these functional components with the Taguchi loss function for product quality indicators has been substantiated, and the function scope application on the managing purposeful activities process has been expanded. The optimization parameters are determined, which are the amplification factors of the control actions. These actions ensure the actual attainability of the set goals in the field of quality during the time planned period. The optimal solutions search was carried out on the example of the textile and light industry CJSC “Salyut” (St. Petersburg). The functional minimum value in case of stepwise control law is more than 14 times greater than with a linear law. This fact found under the condition of equal unit costs for quality losses and control caused by their deviations from the nominal values. The results obtained can be used for a reasonable choice of the enterprise management law in the goal-setting in the field of quality.

Information-extreme machine training of on-board recognition system with optimization of RGB-component digital images

The research increases the recognition reliability of ground natural and infrastructural objects by use of an autonomous onboard unmanned aerial vehicle (UAV). An information-extreme machine learning method of an autonomous onboard recognition system with the optimization of RGB components of a digital image of ground objects is proposed. The method is developed within the framework of the functional approach to modeling cognitive processes of natural intelligence at the formation and acceptance of classification decisions. This approach, in contrast to the known methods of data mining, including neuro-like structures, provides the recognition system with the properties of adaptability to arbitrary initial conditions of image formation and flexibility in retraining the system. The idea of the proposed method is to maximize the information capacity of the recognition system in the machine learning process. As a criterion for optimizing machine learning parameters, a modified Kullback information measure was used, this informational criterion is the functionality of exact characteristics. As optimization parameters, the geometric parameters of hyperspherical containers of recognition classes and control tolerances for recognition signs were considered, which played the role of input data quantization levels when transforming the input Euclidean training matrix into a working binary training matrix using admissible transformations of a working training matrix the offered machine learning method allows to adapt the input mathematical description of recognition system to the maximum full probability of the correct classification decision acceptance. To increase the depth of information-extreme machine learning, optimization was conducted according to the information criterion of the weight coefficients of the RGB components of the brightness spectrum of ground object images. The results of physical modeling on the example the recognition of terrestrial natural and infrastructural objects confirm the increase in functional efficiency of information-extreme machine learning of on-board system at optimum in information understanding weight coefficients of RGB-components of terrestrial objects image brightness.

Optimization of PEMFC Model Parameters Using Meta-Heuristics

The present study introduces an economical–functional design for a polymer electrolyte membrane fuel cell system. To do so, after introducing the optimization problem and solving the problem based on the presented equations in the fuel cell, a cost model is presented. The final design is employed for minimizing the construction cost of a 50 kW fuel cell stack, along with the costs of accessories regarding the current density, stoichiometric coefficient of the hydrogen and air, and pressure of the system as well as the temperature of the system as optimization parameters. The functional–economic model is developed for the studied system in which all components of the system are modeled economically as well as electrochemically–mechanically. The objective function is solved by a newly improved metaheuristic technique, called converged collective animal behavior (CCAB) optimizer. The final results of the method are compared with the standard CAB optimizer and genetic algorithm as a popular technique. The results show that the best optimal cost with 0.1061 $/kWh is achieved by the CCAB. Finally, a sensitivity analysis is provided for analyzing the consistency of the method.