Apostolos Tsagaris

Data monitoring system for supervising the performance assessment of a photovoltaic park

Industrial process measurement and control systems are used in many industrial sectors in order to achieve production improvement, process optimization and accuracy of measurements. The increasing tendency in the construction of photovoltaic (PV) parks suggests the use of PLC and SCADA systems for the efficient operation. This paper proposes an intelligent automation system for supervising the performance assessment of a photovoltaic park. It is a data acquisition system based on PLC technology with the use of an OPC server and a high level program language for the front end. The front end (Graphical User Interface) is implemented in Visual Basic™. The PV Park has a total capacity of aprox. 17 kWp and consists of fixed and tracking units. There are 13 different types of PV modules installed, of which four are mounted on fixed as well as on tracking systems. The proposed data monitoring and acquisition system is able to record various parameters of the PV park performance.

Intelligent invariance techniques for music gesture recognition based on skin modelling

A computer vision methodology for the recognition of finger gestures performed on a music instrument has been recently developed and implemented in the PianOrasis system. PianOrasis recognises the gestures of all the five fingers simultaneously, but not in real-time. In this paper, an optimisation of the above methodology is presented, implying the recognition of finger musical gestures performed in space. Scale and rotation invariance techniques are integrated into the system increasing the recognition quality and reducing the processing time. Scale invariance rests on the deterministic modelling of the number of skin pixels in the image. The proposed modelling enable three different sets of filtering parameters for the hand segmentation process, overcoming a long and manual preliminary analysis. More flexible finger gestures, performed in space without music instrument, can be recognised because of the integration of the rotation invariance.

Design for Skin and Shape: An Innovative Design Approach

Although all aspects of a product design are demanding and need several resources to be completed, Design for X (DfX) represents a series of formal methodologies used to optimize a specific aspect of the product design under consideration. Those DfX tools deal with different stages of the product design and there is considerable gap concerning the package design cycle. The proposed methodology Design for Skin and Shape (DfS&S) is focused on the package design industry and offers significant advantage towards its success. It helps the designers to be focused on shapes that are easily recognized by the customers and then create appropriate graphics for them. Following this approach, it is easier to create an innovative optical identity for the product and its packaging during the conceptual stage. The methodology can reduce the development time of the package, while designers have in mind, from the beginning of the design process, the shape which will guide them to its completion. Following the proposed methodology different packaging designs are presented.

Optimal control of storage system based on intelligent techniques.

In order to obtain high productivity industrial automatic storage systems should complete the storage tasks in minimum of time with the maximum of performance. Optimization is the key point of this problem. This paper proposes a method for intelligent storage system, which optimizes the storing process by deciding the optimum slot that an object will occupy in a warehouse. Depending on the weight, each object has to be stored in a different space. The method is based on genetic algorithm. Genetic algorithms are used in order to optimise the allocation of storage slots at the shortest time. The duration of storage is monitored and used as feedback to the system so as to optimize the algorithm. The system is integrated with PLC and custom SCADA system which gathered the necessary information from the PLC via an OPC server. Any delay of the system is taken into account using feedback of the completion time, so that the operation error is introduced in the application, which is trained to improve its operation in the next loop. The proposed framework improves the placement of objects in specific warehouse slots.

Off-line Robot Optimization with Hybrid Algorithm

Having developed a hybrid optimization methodology for mechatronics system movements in space, the task is to efficiently control of robotic system with 6 degrees of freedom. In this work, hybrid methodology is compared with a simple genetic algorithm. It is applied in a simulation environment of a 6-degrees of freedom robotic arm and the results are compared with the mathematical model developed to support this methodology. The results of the research show that the optimization with the hybrid method compared to the simple GA, which is calculated by the mathematical model, is confirmed by more than 90% of the robotic arm simulation model examples.

Hand finger gesture modeling in advanced CAD system

ABSTRACTThe current paper presents a system for the dynamic simulation of the human hand. The simulation of the human hand offers the capability to acquire handshapes that correspond to letters of the finger alphabet, enabling an integrated representation of words and sentences. The hand model is designed using the Autodesk InventorTM and Autodesk AutoCadTM design environments. The user is able to type words or sentences which are dynamically translated into postures according to the finger alphabet. The system is based on the physiometric characteristics of an average human hand. High precision design is utilized in every part through integration of all the necessary functionalities needed to perform the movements required. The system has been tested on more than 500 words with a letter representation success rate in the range of 95–97%.

Machine learning via multimodal signal processing

This paper proposes a methodology for recognition of vocal music (Byzantine music) via multi-modal signals processing. A sequence of multi-modal signals is captured from the experts (teacher) and students hymns performances, respectively. The machine learning system is trained using the values of particular features which are extracted from the captured multi-modal signals. After the system is being trained then it becomes able to recognize any hymn performance from the corpus. Training and recognition takes place in real time by utilizing machine learning techniques. The evaluation of the system was carried out with the cross - validation statistical method Jackknife, giving promising results.

Fingers gestures early-recognition with a unified framework for RGB or depth camera

This paper presents a unified framework computer vision approach for finger gesture early recognition and interaction that can be applied on sequences of either RGB or depth images without any supervised skeleton extraction. Either RGB or time-of-flight cameras can be used to capture finger motions. The hand detection is based on a skin color model for color images or distance slicing for depth images. A unique hand model is used for the finger detection and identification. Static (fingerings) and dynamic (sequence and/or combination of fingerings) patterns can be early-recognized based on one-shot learning approach using a modified Hidden Markov Models approach. The recognition accuracy is evaluated in two different applications: musical and robotic interaction. In the first case standardized basic piano-like finger gestures (ascending/descending scales, ascending/descending arpeggio) are used to evaluate the performance of the system. In the second case, both standardized and user-defined gestures (driving, waypoints etc.) are recognized and used to interactively control an automated guided vehicle.

Error prooving and sensorimotor feedback for singing voice

This paper presents a sensorimotor system for Byzantine Music. The main goal of this research is to detect some pre-defined errors in singing performance. After error-detection, the system uses a pre-defined error-dictionary in order to feedback. Through these feedbacks the potential chanter is being able to correct his performance. The system is being trained via experts MFCC features from a corpus of anthems. The recognition also takes place via MFCC but form student. The developed system is being able to evaluate in real time the pitch distance and furthermore the duration of two musicians performances, expert and student. The system may also evaluate the distance between two sequential musical gestures by which we may find the tempo of the hymn. After the pitch of these two hymns are being compared any identified errors will cause a feedback action to the student. This feedback corresponds to an error dictionary.

Improving the Tensile Strength of a Novel Double Hook Design Manufactured by Nanosilica Epoxy Reinforced Aramid/Carbon Composites

This paper presents the novel design of a double hook manufactured with advanced composite materials and nanomaterials. For the preparation of the composite materials an epoxy resin was used while the fiber reinforcement was in the form of hybrid aramid/carbon twill fabric. The nanoparticles were silica nanospheres dispersed in the epoxy matrix. The nanospheres were in the form of a colloidal silica-sol and they were added in the epoxy resin so to form a carefully prepared masterbatch. A series of tensile and fracture toughness tests were performed in order to evaluate the effect of the nanosilica concentration as well as the strength of the hybrid aramid/carbon composites. Upon the design and the manufacture of the innovative geometry of the double hook, comparative uniaxial tensile tests were performed. The results proved that the use of the silica nanoparticles significantly increase the strength of the hook, while affect considerably its tensile fracture behavior.