Wyniki wyszukiwania - BazTech

1

Artificial intelligence-driven internet of things monitoring system towards industry 5.0 – A case study of mold manufacturing process

Patalas-Maliszewska Justyna, Musalekar Dineshkumar, Halikowski Daniel

Advances in Science and Technology. Research Journal

|

2025

|

Vol. 19, no. 8

479--494

EN

Applying Artificial Intelligence (AI) into manufacturing in the context of Industry 5.0 (I5.0) provides for enhancing quality control of processes. This paper employs real life data of mould manufacturing process with the objective of developing a tool for controlling and predicting quality of manufactured highly technically demanding product used for the air conditioning of the high-end cars. Firstly, the parameters that affect the quality level of the manufactured end products, namely compressor were defined. Next, the values of these parameters were collected and pre-processed from IoT-based sensors and the Enterprise Resource Planning (ERP) system during the execution of an order within one month. In total, 9919 real data relating to the die castings process for the selected product was received. Secondly, this study applies Artificial Neural Network (ANN) to develop an AI-based classifier of the quality level of manufactured parts. Finally, AI-driven data analytics model was developed and verified. The accuracy was achieved in the training and testing phases 98.62% and 98.94% respectively. Additionally, this study develops the approach to simulate of process parameter value changes for improving the quality level of manufactured parts. This is a universal AI-driven IoT Monitoring System (AIMS) for industry supporting proactive management.

2

Short-term prediction of power outages in electrical distribution networks

Makungo Pfanelo, Hlalele Tlotlollo, Sumbwanyambe Mbuyu

Archives of Electrical Engineering

|

2024

|

Vol. 73, nr 4

1103--1121

EN

Predictive maintenance and reliability engineering are critical in industrial settings to enhance equipment performance and minimize unplanned downtime. This research, conducted within the machine learning framework, presents innovative solutions to the challenging problem of equipment failure prediction. The study creatively utilizes extensive datasets, including equipment records, weather conditions, and maintenance logs, to develop robust predictive models. Two distinct machine learning models are established for equipment and cables/lines, addressing the intricacies of class imbalances and missing data attributes. Model refinement, feature engineering, and interdisciplinary collaboration enhance predictive accuracy, precision, and recall. Notably, this research highlights the creative application of engineering knowledge and data science techniques, reasoning about complex equipment systems, and the importance of problem decomposition. The outcomes underscore the potential for real-time predictive maintenance in industrial contexts, offering substantial cost savings and improved equipment reliability. This research contributes to the evolving field of predictive maintenance and paves the way for future innovations in reliability engineering.

3

Predictive data mining models in the tests of propelling charges

Ampuła Dariusz

Journal of KONBiN

|

2023

|

Vol. 53, iss. 1

47--58

EN

In the article, in the introduction, the concept of predictive data mining models and was defined and the purpose of the article was specified. Then, the method of building predictive models was characterized and the elements of ammunition were indicated, the test results of which were prepared for the building of models, and the types of ammunition in which the propellant charge is present were indicated. The results of building four data mining models are presented. Predictive models for C&RT, CHAID and exhaustive CHAID decision trees were designed and built. The fourth model analyzed was the SANN model, i.e. the model of neural networks. For each of the tree models, a schema of the designed tree, the rate of false predictions and the parameters of goodness of fit of the built models are shown. For the SANN model, the parameters of the selected neural network were additionally characterized. An analysis of the built models was made and, based on the obtained results, the best designed predictive data mining model was indicated. At the end, the graphical form of the workspace predefined by the GC Advanced Comprehensive Classifiers project is shown.

PL

W artykule we wstępie zdefiniowano pojęcie predykcyjnych modeli data mining oraz określono cel artykułu. Następnie, scharakteryzowano metodę budowy modeli predykcyjnych oraz wskazano elementy amunicji, których wyniki badań zostały przygotowane do budowy modeli a także wskazano rodzaje amunicji w których występuje przedmiotowy ładunek miotający. Przedstawiono wyniki budowy czterech modeli predykcyjnych data mining. Zaprojektowano oraz zbudowano predykcyjne modele dla drzew decyzyjnych typu C&RT, CHAID oraz wyczerpujący CHAID. Czwartym analizowanym modelem był model SANN czyli model sieci neuronowych. Dla każdego z modeli drzew przedstawiono schemat zaprojektowanego drzewa, stopę błędnych przewidywań oraz pokazano parametry dobroci dopasowania zbudowanych modeli. Dla modelu SANN scharakteryzowano dodatkowo parametry wybranej sieci neuronowej. Dokonano analizy zbudowanych modeli oraz na podstawie otrzymanych wyników, wskazano najlepszy zaprojektowany predykcyjny model data mining. Na końcu pokazano graficzną postać przestrzeni roboczej predefiniowaną projektem GC Advanced Comprehensive Classifiers.

4

IoT for the Maritime Industry: Challenges and Emerging Applications

Aslam Sheraz, Herodotou Herodotos, Garro Eduardo, Martínez Romero Álvaro, Angeles Burgos María, Cassera Alessandro, Papas George, Dias Petros, Michaelides Michalis

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

855--858

EN

The Internet of things (IoT) ecosystem provides a platform for the connectivity of interrelated smart devices to automate manual processes and reduce labor costs. IoT has brought significant benefits to all industries, including maritime, as various objects (e.g., ports, ships, agents, etc.) are connected to gather and share information within the maritime ecosystem. The innovative technological aspects of IoT are promoting the effective collaboration between the research community and the maritime industry, for enhancing the performance of maritime transportation systems. Therefore, this study discusses recent advances delivered by the IoT and other emerging technologies, like machine learning and computer vision, for smart maritime transportation systems (SMTSs). In particular, the authors present two specific use cases of SMTSs, namely, predictive maintenance and container damage/seal inspection. Moreover, the key benefits of integrating IoT with machine learning and computer vision are highlighted for the above-mentioned use cases. Finally, a discussion is presented to highlight key opportunities along with foreseeable future challenges in adopting these new technologies by the maritime industry.

5

An empirical method for predicting waterflooding performance in low-permeability porous reservoirs combining static and dynamic data: a case study in Chang 6 formation, Jingan Oilfield, Ordos Basin, China

Jiang Zhihao, Li Gaoren, Zhang Lili, Mao Zhiqiang, Liu Zhidi, Hao Xiaolong, Xia Pei

Acta Geophysica

|

2023

|

Vol. 71, no. 4

1693--1703

EN

After waterflooding, the distribution of the remaining oil in low-permeability porous reservoirs is quite complicated. Strong heterogeneity of formations makes the waterflooding performance more complex. Therefore, accurate prediction and evaluation of the spatial distribution of the remaining oil and the waterflooding performance of low-permeability reservoirs are essential for understanding the waterflooding process and improving oil recovery. In the study, an empirical method is proposed to predict waterflooding performance combined with static and dynamic data for porous reservoirs. Static data, including logging curves, core porosity and permeability data, are adopted to classify the formation into three hydraulic flow units (HFUs). The proportions of the thicknesses of different HFUs (HFUp) are proposed to characterize the remaining oil distribution. In addition, a waterflooding performance prediction method based on the Koval method was built using dynamic production data. The results show that the HFUp plays the key role in predicting the distribution of the remaining oil in the research well group. The K-factor-based waterflooding prediction method is highly correlated with the history matching in low-permeability waterflooded layers. The study also found Type 3 HFUp shows a great effect in predicting the duration of the low water-cut oil production. Therefore, the empirical method can provide a quick and intuitive evaluation of waterflooding performance in space and time of low-permeability waterflooded reservoirs with the local average K-factor and the HFUp results. The empirical method is of great significance to evaluate the remaining oil, infilling of well pattern, and improving oil recovery.

6

Predictive modelling of a rapid stratified bed filter for turbidity removal from surface water

Tejada-Tovar Candelaria N., Villabona-Ortíz Ángel, López-Barbosa David

Journal of Water and Land Development

|

2022

|

no. 53

192--202

EN

The objective of the present work was to evaluate the hydrodynamic behaviour of a stratified bed filtration column consisting of 4 cm of sand and 2 cm of limestone to remove turbidity and measuring the head loss through the filter in several runs. In this study, two types of sand were used as filtering bed material, one fine and one medium. Crushed limestone was also available. These materials were characterized to determine the average particle diameter, porosity, and permeability coefficient. These were respectively 1.7∙10-4 m, 336.96 and 0.68 m∙day-1 for fine sand, 3.3∙10-1 m, 654.24 and 2.59 m∙day-1 for the medium sand and 1.26∙10-3 m, 388.8 and 8.64 m∙day-1 for crushed limestone. Using these materials, hydrodynamic analyses were carried out using clean water under rapid filtration conditions. In these analyses, different filtration rates were determined to be used in each experiment. Once the filtration rates were determined, the filtration analysis was performed with synthetic turbid water prepared at 8 NTU using tap water and bentonite. From the results obtained, a predictive model was developed based on total head losses for the evaluated filter, maintaining the rapid filtration condition. As a result, a turbidity removal efficiency of 97.7% was obtained with a total head loss of 17.8 cm at a filtration rate of 153 m·day-1 . The developed model predicted head loss as a function of operating time, filtration rate, and filter depth to maximise turbidity removal. The model showed excellent prediction accuracy with R2 of 0.9999, which indicates that the model predictions are not biased. It was concluded that, due to the porosity of these materials, a stratified bed of sedimentary rocks has a great potential to be used in surface water filtration processes, which implies that it could be used at the rural community level as a form of water treatment, since the material is a readily available, maintenance is simple and low cost, and installation and operation are effortless.

7

Personality prediction from social media posts using text embedding and statistical features

Majima Seiyu, Markov Konstantin

Annals of Computer Science and Information Systems

|

2022

|

Vol. 30

235--240

EN

Recent advances in deep learning based language models have boosted the performance in many downstream tasks such as sentiment analysis, text summarization, question answering, etc. Personality prediction from text is a relatively new task that has attracted researchers' attention due to the increased interest in personalized services as well as the availability of social media data. In this study, we propose a personality prediction system where text embeddings from large language models such as BERT are combined with multiple statistical features extracted from the input text. For the combination, we use the self-attention mechanism which is a popular choice when several information sources need to be merged together. Our experiments with the Kaggle dataset for MBTI clearly show that adding text statistical features improves the system performance relative to using only BERT embeddings. We also analyze the influence of the personality type words on the overall results.

8

Extending Word2Vec with domain-specific labels

Švaňa Miloš

Annals of Computer Science and Information Systems

|

2022

|

Vol. 30

157--160

EN

Choosing a proper representation of textual data is an important part of natural language processing. One option is using Word2Vec embeddings, i.e., dense vectors whose properties can to a degree capture the “meaning” of each word. One of the main disadvantages of Word2Vec is its inability to distinguish between antonyms. Motivated by this deficiency, this paper presents a Word2Vec extension for incorporating domain-specific labels. The goal is to improve the ability to differentiate between embeddings of words associated with different document labels or classes. This improvement is demonstrated on word embeddings derived from tweets related to a publicly traded company. Each tweet is given a label depending on whether its publication coincides with a stock price increase or decrease. The extended Word2Vec model then takes this label into account. The user can also set the weight of this label in the embedding creation process. Experiment results show that increasing this weight leads to a gradual decrease in cosine similarity between embeddings of words associated with different labels. This decrease in similarity can be interpreted as an improvement of the ability to distinguish between these words.

9

Demand forecasting in the fashion business - an example of customized nearest neighbour and linear mixed model approaches

Henzel Joanna, Wawrowski Łukasz, Kubina Anna, Sikora Marek, Wróbel Łukasz

Annals of Computer Science and Information Systems

|

2022

|

Vol. 30

61--65

EN

The fashion industry is characterised by the need to make demand forecasts in advance and for highly volatile products for which we often have no sales history at the time the forecasts are made. For this reason, it is necessary to propose forecast mechanisms that can cope with the given conditions. Such forecasts can be based on expert predictions for generalized product categories. In this case, the task of machine learning forecasting methods would be to divide the aggregate prediction into forecasts for individual products, in each colour and size. In the paper, we present several approaches to this specific task. We present the use of the naive method, custom nearest neighbour approach, parametric linear mixed model and an ensemble approach. Overall, the best results we obtained for the ensemble method. Our research was based on real data from fashion retail.

10

A combinatorial approach in predicting the outcome of tennis matches

Šarčević Ana, Vranić Mihaela, Pintar Damir

International Journal of Applied Mathematics and Computer Science

|

2021

|

Vol. 31, no. 3

525--538

EN

Tennis, as one of the most popular individual sports in the world, holds an important role in the betting world. There are two main categories of bets: pre-match betting, which is conducted before the match starts, and live betting, which allows placing bets during the sporting event. Betting systems rely on setting sports odds, something historically done by domain experts. Setting odds for live betting represents a challenge due to the need to follow events in real-time and react accordingly. In tennis, hierarchical models often stand out as a popular choice when trying to predict the outcome of the match. These models commonly leverage a recursive approach that aims to predict the winner or the final score starting at any point in the match. However, recursive expressions inherently contain computational complexity which hinders the efficiency of methods relying on them. This paper proposes a more resource-effective alternative in the form of a combinatorial approach based on a binomial distribution. The resulting accuracy of the combinatorial approach is identical to that of the recursive approach while being vastly more efficient when considering the execution time, making it a superior choice for live betting in this domain.

11

Predicting the Relaxation Modulus for the Study of the Delayed Behaviour of Kenaf Fibres in Stress Relaxation

Saïdjo, Ntenga Richard, Mfoumou Etienne, Beda Tibi, Beakou Alexis

Fibres & Textiles in Eastern Europe

|

2021

|

Vol. 29, no. 3 (147)

19--25

EN

Plant fibres (PFs) are preferred reinforcements of bio-composites. Knowledge of their lifespan requires a study of their viscoelastic behaviour. In this paper, a stress relaxation analysis of kenaf fibres was performed at a constant rate of deformation at room temperature. A method for extracting the relaxation modulus in the deferred zone was proposed. This method was compared, using simulation, with the Zapas-Phillips method and experimental data via three predictive models: the stretched exponential function or KWW, the inverse power law of Nutting and the prony series. The results indicate that the relaxation modulus obtained by the method proposed is in good agreement with the experimental modulus. In addition, the estimated error is of the same order of magnitude as in the case of the Zapas-Phillips method. The parameters estimated from the KWW function (β = 0.4) and prony series model showed an important contribution in the study of the delayed response of kenaf fibres. These results can have a significant impact on the use of kenaf fibres in midterm and long-term loading applications.

PL

Włókna roślinne są często stosowane jako wzmocnienia biokompozytów. Znajomość ich trwałości wymaga zbadania ich zachowania lepkosprężystego. W pracy przeprowadzono analizę relaksacji naprężeń włókien kenaf przy stałej szybkości odkształcania w temperaturze pokojowej. Zaproponowano metodę wyodrębniania modułu relaksacji w strefie odroczonej. Metodę tę porównano za pomocą symulacji z metodą Zapas’a-Phillips’a i danymi eksperymentalnymi za pomocą trzech modeli predykcyjnych: rozciągniętej funkcji wykładniczej lub KWW, odwrotnego prawa potęgowego Nutting’a i szeregach Prony’ego. Wyniki wskazały, że moduł relaksacji uzyskany proponowaną metodą jest w dobrej zgodności z modułem eksperymentalnym. Ponadto szacowany błąd jest tego samego rzędu wielkości, co w przypadku metody Zapas’a-Phillips’a. Parametry oszacowane na podstawie funkcji KWW (β = 0.4) i modelu szeregów Prony’ego wykazały istotny wkład w badanie opóźnionej odpowiedzi włókien kenaf. Wyniki te mogą mieć znaczący wpływ na wykorzystanie włókien kenaf w średnioterminowych i długoterminowych zastosowaniach obciążeniowych.

12

Driving comfort assistance system considering two sensors data

Karapetkov Stanimir, Uzunov Hristo, Indrie Liliana, Zlatev Zlatin

Acta Mechanica et Automatica

|

2021

|

Vol. 15, no. 3

164--168

EN

In the present work, a system using data from two sensors located next to the driver and to the mass centre of the bus is proposed. Three degrees of discomfort have been used – comfortable, moderately uncomfortable and very uncomfortable. These levels are set out in the questionnaire. A survey was conducted. Respondents were selected between the ages of 14 and 65 and were divided into three age groups – adults, middle-aged and young. Accelerometer systems with MPU-6500 (TDK InvenSense Corp.) sensors are used. A correlation method (CORR) and sequentially improving estimation methods are used for feature selection, which significantly reduce the number of combinations of features obtained. Selected sensor data is entered into feature vectors. These vectors are reduced by principal component analysis. Predictive models have been created that take into account the age of passengers. The use of data from two sensors and separation of the passengers according their age, leads to an increase in the accuracy of predicting passengers discomfort level (DL) of up to 98%. These results can be used to evaluate and guide the vehicle driver in order to improve his driving style. In addition, the simplified interface does not distract the driver from the road conditions. The results obtained can lead to an improvement in the parameters of the transport process, which covers the interest of the carrier related to the efficient use of vehicles, and hence the reduction of fuel consumption and harmful emissions. However, it should be recommended that, when developing systems to ensure comfort of travel, adjustments should be made to suit the age group of passengers carried on public transport buses.

13

Use of Quantitative and Qualitative Wastewater Monitoring in Water Protection on the Example of Lodz

Brzezińska Agnieszka, Sakson Grażyna

Rocznik Ochrona Środowiska

|

2020

|

Tom 22, cz. 1

431--443

EN

Widely understood protection of water, and in particular surface waters, most exposed to direct pollution, requires many operations carried out both in the catchment area and in sewage systems as well as WWTPs. Due to its character and working conditions, it should be monitored not only in terms of hydraulics, but also in terms of the quality of transported wastewater. During atmospheric precipitation, large volumes of domestic and industrial wastewater as well as rainwater in various proportions flow through the canals, changing not only their quantity but also their composition. In such cases, the issue of monitoring becomes particularly vital. The article presents an analysis of the needs and tasks resulting from the application of quantitative and qualitative monitoring in the assessment of the functioning of sewage systems. Methods and tools used in Lodz that may be useful in water protection are presented. The benefits of using this type of solutions as well as the limitations and difficulties are discussed.

PL

Szeroko rozumiana ochrona wód, a zwłaszcza wód powierzchniowych, najbardziej narażonych na bezpośrednie zanieczyszczenie, wymaga wielu działań przeprowadzanych zarówno w zlewni, jak i w systemach kanalizacyjnych oraz w oczyszczalniach ścieków. Ze względu na swój charakter i warunki pracy system kanalizacji należy monitorować nie tylko pod względem hydraulicznym, ale także pod względem składu transportowanych ścieków. Podczas opadów atmosferycznych przez kanały, w różnych proporcjach, przepływają znaczne ilości ścieków bytowych, przemysłowych oraz deszczowych, zmieniając przy tym także swój skład. W takich przypadkach kwestia monitorowania staje się szczególnie istotna. W artykule przedstawiono analizę potrzeb i zadań wynikających z zastosowania monitorowania ilościowego i jakościowego w ocenie funkcjonowania systemów kanalizacyjnych oraz metody i narzędzia stosowane w Łodzi, które mogą być przydatne w ochronie wód. Omówiono zalety korzystania z tego typu rozwiązań, a także ograniczenia i trudności.

14

Threats to Wastewater Treatment Plant in Combined Sewer System – Analysis of Problems and Possible Solutions on the Example of Lodz

Sakson Grażyna, Brzezińska Agnieszka, Kowalski Krzysztof

Rocznik Ochrona Środowiska

|

2020

|

Tom 22, cz. 2

1132--1144

EN

Municipal WWTP are exposed to the inflow of toxic substances, which may impede their proper functioning, especially of the biological part. In the case of combined or hybrid sewer systems, additionally, in wet weather, there may appear a rapid inflow of a mixture of domestic and industrial sewage, and stormwater in an amount exceeding the capacity of the devices, causing the need to discharge parts of not fully treated wastewater through the bypass channel. In such situations, the receivers are exposed to an inflow of increased amounts of pollutants. The article presents the concept of a monitoring, early warning and sustainable management system for the Lodz wastewater treatment plant, which will allow minimizing pollutant emissions to the aquatic environment.

PL

Miejskie oczyszczalnie ścieków są narażone na napływ substancji toksycznych, które mogą utrudniać ich prawidłowe funkcjonowanie, zwłaszcza części biologicznej. W przypadku ogólnospławnych lub mieszanych systemów kanalizacyjnych dodatkowo w czasie pogody mokrej może pojawić się gwałtowny dopływ mieszaniny ścieków bytowo-gospodarczych i przemysłowych oraz wód opadowych w ilości przekraczającej przepustowość urządzeń, powodując konieczność zrzutu części nie w pełni oczyszczonych ścieków przez kanał ominięcia. W takich sytuacjach odbiorniki są narażone na napływ zwiększonych ilości zanieczyszczeń. W artykule przedstawiono koncepcję systemu monitorowania, wczesnego ostrzegania i zrównoważonego zarządzania łódzką oczyszczalnią ścieków, który pozwoli zminimalizować emisję zanieczyszczeń do środowiska wodnego.

15

Gradient Boosting Application in Forecasting of Performance Indicators Values for Measuring the Efficiency of Promotions in FMCG Retail

Henzel Joanna, Sikora Marek

Annals of Computer Science and Information Systems

|

2020

|

Vol. 21

59--68

EN

In the paper, a problem of forecasting promotion efficiency is raised. The authors propose a new approach, using the gradient boosting method for this task. Six performance indicators are introduced to capture the promotion effect. For each of them, within predefined groups of products, a model was trained. A description of using these models for forecasting and optimising promotion efficiency is provided. Data preparation and hyperparameters tuning processes are also described. The experiments were performed for three groups of products from a large grocery company.

16

Data-based prediction of soot emissions for transient engine operation

Schaub Michèle

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2019

|

T. 9, nr 4

10--13

EN

Global maritime transport is one of the causes of air pollution. Annex VI of the International Maritime Organisation’s (IMO) International Convention for the Prevention of Pollution from Ships (MARPOL) refers to air pollution. Air pollution is mainly caused by the conversion of energy in internal combustion engines, in particular in the case of transient engine operation. The main pollutant is soot. It is an impure carbon substance of various sizes, resulting from incomplete combustion of hydrocarbons. This document concerns data-based modelling of soot emissions – the main component of exhaust particles – in transient engine operation. In a unique manoeuvring aid system, the prediction of exhaust emissions will become a new element. If the navigator knows the consequences of his actions, the human role will be strengthened in relation to the decision making on energy-efficient and emission-poor vessel traffic, in particular during manoeuvres. Thanks to the mathematical model, the soot formation process during stationary engine operation – at constant speed and load – will be mapped first. The model will then be extended to simulate engine operation and soot formation in the transition phase.

PL

Globalny transport morski jest jedną z przyczyn zanieczyszczenia powietrza. Załącznik VI do Międzynarodowej konwencji o zapobieganiu zanieczyszczeniu morza przez statki (MARPOL) Międzynarodowej Organizacji Morskiej (IMO) odnosi się do zanieczyszczeń powietrza. Zanieczyszczenie powietrza jest głównie powodowane przez konwersję energii w silnikach spalinowych, w szczególności w przypadku przejściowej pracy silnika. Głównym zanieczyszczeniem jest sadza. Jest to zanieczyszczona substancja węglowa różnej wielkości, będąca wynikiem niepełnego spalania węglowodorów. Niniejszy dokument dotyczy modelowania emisji sadzy – głównego składnika cząstek spalin, w pracy silnika w warunkach przejściowych w oparciu o dane. W unikalnym systemie wspomagania manewrów, przewidywanie emisji spalin stanie się nowym elementem. Jeżeli nawigator zna konsekwencje swoich działań, to rola człowieka zostanie wzmocniona w odniesieniu do podejmowania decyzji o energooszczędnym i ubogim w emisje spalin ruchu statków, w szczególności podczas manewrów. Dzięki modelowi matematycznemu,w pierwszej kolejności zostanie odwzorowany proces powstawania sadzy podczas stacjonarnej pracy silnika – przy stałych obrotach i obciążeniu. Następnie model ten zostanie tak rozszerzony, aby umożliwić symulację pracy silnika i powstawania sadzy w fazie przejściowej.

17

Use of quantitative and qualitative wastewater monitoring in water protection on the example of Lodz

Brzezińska Agnieszka, Sakson Grażyna

Czasopismo Inżynierii Lądowej, Środowiska i Architektury / Journal of Civil Engineering, Environment and Architecture

|

2019

|

z. 66, nr 2

21--34

EN

Widely understood protection of water, and in particular surface waters, most exposed to direct pollution, requires many operations carried out both in the catchment area and in sewage systems as well as wastewater treatment plants. Due to its character and working conditions, it should be monitored not only in terms of hydraulics, but also in terms of the quality of transported wastewater. During atmospheric precipitation, large volumes of domestic and industrial wastewater as well as rainwater in various proportions flow through the canals, changing not only their quantity but also their composition. In such cases, the issue of monitoring becomes particularly vital. The article presents an analysis of the needs and tasks resulting from the application of quantitative and qualitative monitoring in the assessment of the functioning of sewage systems. Methods and tools used in Lodz that may be useful in water protection are presented. The benefits of using this type of solutions as well as the limitations and difficulties are discussed.

18

Monitoring, early warning and sustainable management system for Lodz wastewater treatment plant as a water protection tool

Sakson Grażyna, Brzezińska Agnieszka, Kowalski Krzysztof

Czasopismo Inżynierii Lądowej, Środowiska i Architektury / Journal of Civil Engineering, Environment and Architecture

|

2019

|

z. 66, nr 3

5--16

EN

Municipal wastewater treatment plants are exposed to the inflow of toxic substances, which may hamper or even preclude their proper functioning, especially of the biological part. In the case of combined or hybrid sewer systems, additionally, in wet weather, there may appear a rapid inflow of a mixture of domestic and industrial sewage, and stormwater in an amount exceeding the capacity of the devices, causing the need to discharge parts of not fully treated wastewater through the bypass channel, which may reduce overall treatment effects. In such situations, the receivers are exposed to an inflow of increased amounts of pollutants, which on the one hand causes a threat to the aquatic environment, on the other, may result in administrative fines for the treatment plant resulting from non-compliance with the conditions of the water permit, as well as costs of removing the effects of failure. The article presents the concept of a monitoring, early warning and sustainable management system for the Lodz wastewater treatment plant, which will allow minimizing pollutant emissions to the aquatic environment. The system will be based on data from the municipal pluviometer network, measurement of flows in combines sewer overflows and newly built sewage quality monitoring stations equipped with on-line probes. The resulting data will allow to predict quantity and quality of inflow to the treatment plant, which will allow for an early warning about the dangers. In consequence decision-making to improve the safety of its operation will be possible.

19

Driving energy management of front-and-rear-motor-drive electric vehicle based on hybrid radial basis function

Sun Binbin, Zhang Tiezhu, Ge Wenqing, Tan Cao, Gao Song

Archives of Transport

|

2019

|

Vol. 49, iss. 1

47--58

EN

This paper presents mathematical methods to develop a high-efficiency and real-time driving energy management for a front-and-rear-motor-drive electric vehicle (FRMDEV), which is equipped with an induction motor (IM) and a permanent magnet synchronous motor (PMSM). First of all, in order to develop motor-loss models for energy optimization, database of with three factors, which are speed, torque and temperature, was created to characterize motor operation based on HALTON sequence method. The response surface model of motor loss, as the function of the motor-operation database, was developed with the use of Gauss radial basis function (RBF). The accuracy of the motor-loss model was verified according to statistical analysis. Then, in order to create a two-factor energy management strategy, the modification models of the torque required by driver (Td) and the torque distribution coefficient (β) were constructed based on the state of charge (SOC) of battery and the motor temperature, respectively. According to the motor-loss models, the fitness function for optimization was designed, where the influence of the non-work on system consumption was analyzed and calculated. The optimal β was confirmed with the use of the off-line particle swarm optimization (PSO). Moreover, to achieve both high accuracy and real-time performance under random vehicle operation, the predictive model of the optimal β was developed based on the hybrid RBF. The modeling and predictive accuracies of the predictive model were analyzed and verified. Finally, a hardware-in-loop (HIL) test platform was developed and the predictive model was tested. Test results show that, the developed predictive model of β based on hybrid RBF can achieve both real-time and economic performances, which is applicable to engineering application. More importantly, in comparison with the original torque distribution based on rule algorithm, the torque distribution based on hybrid RBF is able to reduce driving energy consumption by 9.51% under urban cycle.

20

Detection of wear parameters using existing sensors in the machines environment to reach higher machine precision

Schmitt R. R., Decressin R., Dietrich F., Dröder K.

Journal of Machine Engineering

|

2018

|

Vol. 18, No. 2

85--96

EN

This paper presents methods to plan predictive maintenance for precision assembly tasks. One of the key aspects of this approach is handling the abnormalities during the development phase, i.e. before and during process implementation. The goal is to identify abnormalities which are prone to failure and finding methods to monitor them. To achieve this, an example assembly system is presented. A Failure Mode and Effects Analysis is then applied to this assembly system to show which key elements influence the overall product quality. Methods to monitor these elements are presented. A unique aspect of this approach is exploring additional routines which can be incorporated in the process to identify machine specific problems. As explained within the paper, the Failure Mode and Effects Analysis shows that the resulting quality in a case study from a precision assembly task is dependent on the precision of the rotational axis. Although the rotational axis plays a significant role in the resulting error, it is hard to explicitly find a correlation between its degradation and produced parts. To overcome this, an additional routine is added to the production process, which directly collects information about the rotational axis. In addition to the overall concept, this routine is discussed and its ability to monitor the rotational axis is confirmed in the paper.