Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 44

Liczba wyników na stronie
first rewind previous Strona / 3 next fast forward last
Wyniki wyszukiwania
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 3 next fast forward last
EN
The paper presents some aspects of a development project related to Industry 4.0 that was executed at Nemak, a leading manufacturer of the aluminium castings for the automotive industry, in its high pressure die casting foundry in Poland. The developed data analytics system aims at predicting the casting quality basing on the production data. The objective is to use these data for optimizing process parameters to raise the products’ quality as well as to improve the productivity. Characterization of the production data including the recorded process parameters and the role of mechanical properties of the castings as the process outputs is presented. The system incorporates advanced data analytics and computation tools based on the analysis of variance (ANOVA) and applying an MS Excel platform. It enables the foundry engineers and operators finding the most efficient process variables to ensure high mechanical properties of the aluminium engine block castings. The main features of the system are explained and illustrated by appropriate graphs. Chances and threats connected with applications of the data-driven modelling in die casting are discussed.
PL
Metody eksploracji danych mogą przynieść znaczące korzyści w procesach produkcyjnych, przyczyniając się do ułatwienia wykrywania przyczyn problemów w postaci wad wyrobów i innych zakłóceń procesów wytwarzania. Warto zwrócić uwagę, że metody te z założenia wykorzystują istniejące, zarejestrowane w przedsiębiorstwie dane, bez konieczności przeprowadzania kosztownych eksperymentów w warunkach laboratoryjnych lub przemysłowych. Warunkiem pomyślnego ich stosowania jest jednak uświadomienie sobie przez personel inżynieryjny ogromnego potencjału systemów eksploracji danych w przedsiębiorstwach produkcyjnych, których wprowadzenie stanie się niedługo koniecznością.
EN
The paper presents an application of advanced data-driven (soft) models in finding the most probable particular causes of missed ductile iron melts. The proposed methodology was tested using real foundry data set containing 1020 records with contents of 9 chemical elements in the iron as the process input variables and the ductile iron grade as the output. This dependent variable was of discrete (nominal) type with four possible values: ‘400/18’, ‘500/07’, ‘500/07 special’ and ‘non-classified’, i.e. the missed melt. Several types of classification models were built and tested: MLP-type Artificial Neural Network, Support Vector Machine and two versions of Classification Trees. The best accuracy of predictions was achieved by one of the Classification Tree model, which was then used in the simulations leading to conversion of the missed melts to the expected grades. Two strategies of changing the input values (chemical composition) were tried: content of a single element at a time and simultaneous changes of a selected pair of elements. It was found that in the vast majority of the missed melts the changes of single elements concentrations have led to the change from the non-classified iron to its expected grade. In the case of the three remaining melts the simultaneous changes of pairs of the elements’ concentrations appeared to be successful and that those cases were in agreement with foundry staff expertise. It is concluded that utilizing an advanced data-driven process model can significantly facilitate diagnosis of defective products and out-of-control foundry processes.
EN
The aim of this paper is to present an application of the input variable significance analysis to finding probable causes of product defects occurring in continuous casting (CC) of steel. The research was carried out using production data routinely recorded in one of Polish steel plants and basically referred to defective fraction of billets per heat as the process output. The data did not include the cases with zero defects which made the analysis difficult. The process inputs included eight parameters of different nature (physical, organizational and human). For determining which of the process input parameters are crucial for the output and which of them can be easily eliminated in further analyses two different approaches were applied and compared. The basic tool was an MLP-type Artificial Neural Network in which the relative significance was defined as the sum of the absolute weights of the connections from the given input node to all the nodes in the first hidden layer. As a complementary method the one-way analysis of variance (ANOVA) was utilized in which the value of the F-statistics is used as a measure of the input significance. It was found that the both methods indicate that the start-time of the CC process is the factor highly influencing the fraction of defective products. The process physical parameters which are expected to have a large influence on the billet quality, i.e. deviations from nominal casting temperature and deviation from nominal casting speed also appeared to be significant, moreover their variations also highly depend on the start-time of the CC process. The final conclusion is that the direct cause of the defective products are incorrect adjustments of the casting speed occurring mainly in the morning hours, however not correlated with particular operators. This finding can considerably facilitate the identification of the root cause of the defects by the plant engineers. Some recommendations concerning the future work are also given.
PL
Celem niniejszej pracy jest przedstawienie analizy istotności zmiennych wejściowych jako narzędzia pozwalającego na znalezienie prawdopodobnych przyczyn wad wyrobów w procesie ciągłego odlewania stali. Do analizy wykorzystano dane przemysłowe zebrane w jednej z polskich hut stali, dotyczące produkcji kęsów. Skorzystano z zarejestrowanych danych związanych z przebiegiem i parametrami procesu produkcyjnego, według obowiązujących w zakładzie procedur. Podstawowym źródłem danych była baza tzw. wybraku technologicznego rejestrowanego przez zakład produkcyjny, informująca o fakcie pojawienia się braków oraz ich ilości wyrażonej w procentach dla każdego wytopu. Baza ta nie zawierała jednak pełnej informacji o tych wytopach, w których braki nie występowały, co powodowało istotne trudności i ograniczenia prowadzonych badań. Analizie poddano osiem parametrów wejściowych o różnym charakterze: fizycznym, organizacyjnym i ludzkim. W celu określenia, które z parametrów procesu mają największe znaczenie z punktu widzenia pojawiania sic braków, a które z nich mogą być pominięte, zastosowano i porównano dwie metody. Podstawowym narzędziem były sztuczne sieci neuronowe typu MLP, w których istotność względna jest definiowana jako bezwzględna suma wag połączeń między danym wejściem a wszystkimi węzłami w pierwszej warstwie ukrytej. Drugą metoda była jednoczynnikowa analiza wariancji (ANOVA), badająca wpływ poziomu jednego czynnika klasyfikującego na wartości badanej zmiennej zależnej typu rzeczywistego, określany wartością statystyki F. Otrzymane wyniki pozwalają jed¬noznacznie stwierdzić, że parametr wejściowy ‘pora spustu' ma znaczący wpływ na kształtowanie się parametru wyjściowego ‘udział braków’. Podstawowe fizyczne parametry procesu, tj. odchyłka od nominalnej temperatury odlewania i odchyłka od szybkości odlewania, zgodnie z oczekiwaniami wykazały również duże znaczenie, a ponadto duże zróżnicowanie w zależności od wartości parametru ‘pora spustu’. Końcowym wnioskiem wynikającym z przeprowadzonych analiz jest zidentyfikowanie bezpośredniej przyczyny powstawania wadliwych produktów, którą jest niepoprawne dostosowywanie prędkości odlewania do aktualnej temperatury stali, występujące głównie w godzinach porannych, lecz niezwiązane z konkretnymi pracownikami. Poczynione spostrzeżenia mogą w znaczący sposób ułatwić dokonanie ostatecznej identyfikacji źródeł powstawania wad w wyrobach przez personel inżynieryjny zakładu. W pracy zawarto również zalecenia dotyczące przyszłych badań, zarówno przemysłowych jak i związanych z metodyką prowadzenia podobnych badań.
EN
Statistical Process Control (SPC) based on the Shewhart’s type control charts, is widely used in contemporary manufacturing industry, including many foundries. The main steps include process monitoring, detection the out-of-control signals, identification and removal of their causes. Finding the root causes of the process faults is often a difficult task and can be supported by various tools, including data-driven mathematical models. In the present paper a novel approach to statistical control of ductile iron melting process is proposed. It is aimed at development of methodologies suitable for effective finding the causes of the out-of-control signals in the process outputs, defined as ultimate tensile strength (Rm) and elongation (A5), based mainly on chemical composition of the alloy. The methodologies are tested and presented using several real foundry data sets. First, correlations between standard abnormal output patterns (i.e. out-of-control signals) and corresponding inputs patterns are found, basing on the detection of similar patterns and similar shapes of the run charts of the chemical elements contents. It was found that in a significant number of cases there was no clear indication of the correlation, which can be attributed either to the complex, simultaneous action of several chemical elements or to the causes related to other process variables, including melting, inoculation, spheroidization and pouring parameters as well as the human errors. A conception of the methodology based on simulation of the process using advanced input - output regression modelling is presented. The preliminary tests have showed that it can be a useful tool in the process control and is worth further development. The results obtained in the present study may not only be applied to the ductile iron process but they can be also utilized in statistical quality control of a wide range of different discrete processes.
EN
The paper undertakes an important topic of evaluation of effectiveness of SCADA (Supervisory Control and Data Acquisition) systems, used for monitoring and control of selected processing parameters of classic green sands used in foundry. Main focus was put on process studies of properties of so-called 1st generation molding sands in the respect of their preparation process. Possible methods of control of this processing are presented, with consideration of application of fresh raw materials, return sand (regenerate) and water. The studies conducted in one of European foundries were aimed at pointing out how much application of new, automated plant of sand processing incorporating the SCADA systems allows stabilizing results of measurement of selected sand parameters after its mixing. The studies concerned two comparative periods of time, before an implementation of the automated devices for green sands processing (ASMS - Automatic Sand Measurement System and MCM – Main Control Module) and after the implementation. Results of measurement of selected sand properties after implementation of the ASMS were also evaluated and compared with testing studies conducted periodically in laboratory.
EN
The purpose of this paper was testing suitability of the time-series analysis for quality control of the continuous steel casting process in production conditions. The analysis was carried out on industrial data collected in one of Polish steel plants. The production data concerned defective fractions of billets obtained in the process. The procedure of the industrial data preparation is presented. The computations for the time-series analysis were carried out in two ways, both using the authors’ own software. The first one, applied to the real numbers type of the data has a wide range of capabilities, including not only prediction of the future values but also detection of important periodicity in data. In the second approach the data were assumed in a binary (categorical) form, i.e. the every heat(melt) was labeled as ‘Good’ or ‘Defective’. The naïve Bayesian classifier was used for predicting the successive values. The most interesting results of the analysis include good prediction accuracies obtained by both methodologies, the crucial influence of the last preceding point on the predicted result for the real data time-series analysis as well as obtaining an information about the type of misclassification for binary data. The possibility of prediction of the future values can be used by engineering or operational staff with an expert knowledge to decrease fraction of defective products by taking appropriate action when the forthcoming period is identified as critical.
EN
Simulation software can be used not only for checking the correctness of a particular design but also for finding rules which could be used in majority of future designs. In the present work the recommendations for optimal distance between a side feeder and a casting wall were formulated. The shrinkage problems with application of side feeders may arise from overheating of the moulding sand layer between casting wall and the feeder in case the neck is too short as well as formation of a hot spot at the junction of the neck and the casting. A large number of simulations using commercial software were carried out, in which the main independent variables were: the feeder’s neck length, type and geometry of the feeder, as well as geometry and material of the casting. It was found that the shrinkage defects do not appear for tubular castings, whereas for flat walled castings the neck length and the feeders’ geometry are important parameters to be set properly in order to avoid the shrinkage defects. The rules for optimal lengths were found using the Rough Sets Theory approach, separately for traditional and exothermic feeders.
EN
Statistical Process Control (SPC) based on the well known Shewhart control charts, is widely used in contemporary manufacturing industry, including many foundries. However, the classic SPC methods require that the measured quantities, e.g. process or product parameters, are not auto-correlated, i.e. their current values do not depend on the preceding ones. For the processes which do not obey this assumption the Special Cause Control (SCC) charts were proposed, utilizing the residual data obtained from the time-series analysis. In the present paper the results of application of SCC charts to a green sand processing system are presented. The tests, made on real industrial data collected in a big iron foundry, were aimed at the comparison of occurrences of out-of-control signals detected in the original data with those appeared in the residual data. It was found that application of the SCC charts reduces numbers of the signals in almost all cases It is concluded that it can be helpful in avoiding false signals, i.e. resulting from predictable factors.
PL
Artykuł dotyczy nowych rozwiązań z dziedzinie logistyki procesów produkcyjnych. Autorzy przedstawiają system wizyjny przeznaczony do automatycznej inspekcji defektów powierzchniowych. W zależności od konstrukcji wyrobu i techniki wykonania, proces odlewania może generować powierzchniowe defekty takiej jak: pęknięcia lub pory, które w sposób znaczący zmniejszają funkcjonalność wyrobu. Odkąd kontrola wzrokowa stała się powolna i kosztowana, systemy komputerowej inspekcji stały się alternatywa dla tego typu problemów w inspekcji dokonywanej w czasie rzeczywistym. Dlatego też została zaproponowana procedura składająca się z trzech etapów, w celu zwiększenia jakości końcowej wyrobów oraz zwiększenia wydajności procesu odlewania. W pierwszym etapie opracowano technikę obróbki obrazu opartej na metodzie detekcji krawędzi oraz metodę sieci neuronowych. W kolejnym kroku opracowano zaawansowaną technikę oświetlenia, kluczową dla wizualizacji defektów. Na koniec wprowadzono procedurę na automatyczną selekcję oraz kategoryzację rozpoznanych defektów.
EN
The paper presents some new solutions in logistics of production processes. The authors demonstrate a camera based machine vision system for the automatic inspection of surface defects in aluminum die casting. Depending on part design and processing techniques, castings may develop surface discontinuities such as cracks and pores that greatly influence the material’s ability. Since, the human visual inspection is slow and expensive a computer vision system is an alternative solution for on-line inspection. Therefore, a three steps procedure has been developed in order to improve quality and productivity of the manufacturing process. First, the developed vision system uses an advanced image processing algorithm based on edge detection method and advanced learning process, based on the methods of computational intelligence. Second, in addition to the developed image processing algorithm, advanced lighting system has been designed. Finally, the vision system allows the user automatic selection, and classification of the measured defects.
PL
Rosnąca popularność polimerów biodegradowalnych, możliwości ich wytwarzania, przetwarzania i wykorzystania, stwarzają szansę opracowania nowych materiałów wiążących, do zastosowania w przemyśle odlewniczym. Nowe spoiwa biopolimerowe, spełniające wymagania z zakresu ochrony środowiska, mogą stanowić alternatywę dla dotychczas stosowanych spoiw do mas formierskich i rdzeniowych, w przypadku uzyskania wymaganych właściwości wytrzymałościowych i technologicznych. Prezentowane rozwiązanie, alternatywne do dotychczas opisywanych w literaturze, obejmujące badania mas otrzymywanych z piasków otaczanych spoiwem biodegradowanlym PLA, dotyczy optymalizacji właściwości wytrzymałościowych, w odniesieniu do procentowej zawartości biopolimeru, temperatury i czasu wytwarzania form i rdzeni metodą HOT-BOX. Uzyskane wyniki pozwalają sądzić, że biopolimery mogą być skutecznym zamiennikiem dotychczas stosowanych spoiw mas formierskich i rdzeniowych, a metoda wytwarzania z użyciem piasków otaczanych, może być równie skuteczna jak metody alternatywne.
EN
Currently moulding sand with biopolymers as a binding agent appears to be probably the most interesting achievement in the mould production from ecology point of view. New biopolymer materials offer the parameters comparable to those which have been in use up to now. Moulding sands with a biopolymer binder were produced. The moulding process of 2% PLA sandmix involving different fusion temperatures and times was studied and the results presented. The results of observations and ultimate tensile strength tests were offered. The obtained results point to the fact that the new sandmix moulding method offered similar results that obtained in the literature. The issue is viewed as requiring further research.
EN
Simulation software dedicated for design of casting processes is usually tested and calibrated by comparisons of shrinkage defects distribution predicted by the modelling with that observed in real castings produced in a given foundry. However, a large amount of expertise obtained from different foundries, including especially made experiments, is available from literature, in the form of recommendations for design of the rigging systems. This kind of information can be also used for assessment of the simulation predictions. In the present work two parameters used in the design of feeding systems are considered: feeding ranges in horizontal and vertical plates as well as efficiency (yield) of feeders of various shapes. The simulation tests were conducted using especially designed steel and aluminium castings with risers and a commercial FDM based software. It was found that the simulations cannot predict appearance of shrinkage porosity in horizontal and vertical plates of even cross-sections which would mean, that the feeding ranges are practically unlimited. The yield of all types of feeders obtained from the simulations appeared to be much higher than that reported in the literature. It can be concluded that the feeding flow modelling included in the tested software does not reflect phenomena responsible for the feeding processes in real castings properly. Further tests, with different types of software and more fundamental studies on the feeding process modelling would be desirable.
EN
This chapter presents actual and potential applications of advanced data-driven models in control and fault diagnosis of manufacturing processes. Types of process control are discussed and the role of the computational intelligence as well as other data mining methods in them is shown. The main findings of the present authors, based on results of the previous works, are presented. They include the methodologies of determination of relative significances of process parameters and evaluation of prediction capabilities of time-series modeling. Results of a new research, aimed at assessment of capabilities of learning systems to detect out-of-control patterns of points observed in SPC charts, are presented.
PL
Niniejsze opracowanie przedstawia rzeczywiste i potencjalne zastosowania zaawansowanych modeli opartych na danych w sterowaniu i diagnostyce usterek procesów wytwarzania. Omówiono rodzaje sterowania procesem oraz pokazano rolę, jaką pełnią w nich metody inteligencji obliczeniowej i inne metody eksploracji danych. Zaprezentowano główne stwierdzenia, do jakich doszli autorzy na podstawie wyników wcześniejszych badań. Obejmują one metody określania istotności względnych parametrów procesu oraz ocenę zdolności predykcyjnych modelowania szeregów czasowych. Przedstawiono także wyniki nowych badań, mających na celu ocenę zdolności systemów uczących się do wykrywania układów punktów na kartach kontrolnych SSP, świadczących o rozregulowaniu procesu.
EN
Expert systems can be defined as computer programs, whose main task is to simulate a human expert, usually in a narrow field of expertise. Possible applications of modern information technology are very extensive, ranging from medicine, geology and technology to applications in the field of economic and financial decision support. The purpose of this paper is to present the practical application of an expert system that supports the process of managing the production of yachts and has a high suitability for use in this application. Using the expert system described in the paper reduces the time during the design and production preparation process.
PL
Systemy ekspertowe można określić jako programy komputerowe, których podstawowym zadaniem jest symulowanie działanie człowieka – eksperta, na ogół w wąskiej dziedzinie. Możliwości zastosowań tej nowoczesnej technologii informatycznej są bardzo duże, począwszy od medycyny, przez geologię, technikę aż do zastosowań w dziedzinie wspomagania podejmowania decyzji gospodarczych i finansowych. Celem niniejszego artykułu jest prezentacja praktycznego zastosowania systemu ekspertowego, który wspomaga proces przygotowania produkcji rekreacyjnych jednostek pływających i wykazuje dużą przydatność użytkową z jego stosowania. Korzystanie z opisanego systemu ekspertowego skraca czas w procesach projektowania i przygotowania produkcji jachtów.
16
Content available Advanced methods of foundry processes control
EN
The paper discusses two main approaches utilized in contemporary industry to control of discrete and continuous manufacturing processes: Statistical Process Control and Engineering Process Control as well as applications of learning systems and time-series analysis in the control systems. The use of time-series techniques for anticipated control of selected foundry processes is presented and positively evaluated using industry data obtained from the green molding sand processing.
PL
W artykule omówiono dwa podejścia stosowane we współczesnym przemyśle do sterowania dyskretnymi i ciągłymi procesami wytwarzania: Statystyczne Sterowanie Procesem oraz sterowanie techniczne (ang. Engineering Process Control), a także zastosowania systemów uczących się i analizy szeregów czasowych w systemach sterowania. Zaprezentowano i poddano pozytywnej ocenie wykorzystanie technik szeregów czasowych w antycypacyjnym sterowaniu wybranymi procesami odlewniczymi, z użyciem danych przemysłowych uzyskanych z procesu przerobu wilgotnych mas formierskich.
EN
The paper presents a vision based approach and neural network techniques in surface defects inspection and categorization. Depending on part design and processing techniques, castings may develop surface discontinuities such as cracks and pores that greatly influence the material’s properties Since the human visual inspection for the surface is slow and expensive, a computer vision system is an alternative solution for the online inspection. The authors present the developed vision system uses an advanced image processing algorithm based on modified Laplacian of Gaussian edge detection method and advanced lighting system. The defect inspection algorithm consists of several parameters that allow the user to specify the sensitivity level at which he can accept the defects in the casting. In addition to the developed image processing algorithm and vision system apparatus, an advanced learning process has been developed, based on neural network techniques. Finally, as an example three groups of defects were investigated demonstrates automatic selection and categorization of the measured defects, such as blowholes, shrinkage porosity and shrinkage cavity.
EN
The aim of the paper was an attempt at applying the time-series analysis to the control of the melting process of grey cast iron in production conditions. The production data were collected in one of Polish foundries in the form of spectrometer printouts. The quality of the alloy was controlled by its chemical composition in about 0.5 hour time intervals. The procedure of preparation of the industrial data is presented, including OCR-based method of transformation to the electronic numerical format as well as generation of records related to particular weekdays. The computations for time-series analysis were made using the author's own software having a wide range of capabilities, including detection of important periodicity in data as well as regression modeling of the residual data, i.e. the values obtained after subtraction of general trend, trend of variability amplitude and the periodical component. The most interesting results of the analysis include: significant 2-measurements periodicity of percentages of all components, significance 7-day periodicity of silicon content measured at the end of a day and the relatively good prediction accuracy obtained without modeling of residual data for various types of expected values. Some practical conclusions have been formulated, related to possible improvements in the melting process control procedures as well as more general tips concerning applications of time-series analysis in foundry production.
19
Content available remote Modeling of feeding of grey iron castings
EN
The aim of the paper was development and testing a new methodology for adjusting of simulation parameters of casting processes. Instead using production castings with limited shapes, the methodology utilizes especially designed virtual castings of arbitrary geometries, with rigging systems calculated according generally approved principles, based on industrial experience. The present work tests included risers for grey iron castings, designed according Karsay's recommendations; the simulations were made using the commercial software NovaFlow&Solid. The preliminary simulations have shown that the parameters, which are most important from the viewpoint of occurrence of the shrinkage defects, are the density change during solidification and the gravity influence. Further systematic simulations allowed to find that the feeding flow modeled in the computer program does fully correspond to those practical recommendations: the flow is too easy in vertical direction an to difficult in horizontal direction. Despite that, it was possible to formulate recommendations regarding settings of the above simulation parameters which would facilitate correct predictions of the shrinkage defects in grey iron castings: the influence of gravity should be 'high' and the density change between liquidus and solidus temperatures should be between 0 to 78 kg/m3, depending on the feeding distance.
EN
A new camera based machine vision system for the automatic inspection of surface defects in aluminum die casting was developed by the authors. The problem of surface defects in aluminum die casting is widespread throughout the foundry industry and their detection is o f paramount importance in maintaining product quality. The casting surfaces are the most highly loaded regions of materials and components. Mechanical and thermal loads as well as corrosion or irradiation attacks are directed primarily at the surface of the castings. Depending on part design and processing techniques, castings may develop surface discontinuities such as cracks or tears, inclusions due to chemical reactions or foreign material in the molten metal, and pores that greatly influence the material ability to withs tand these loads. Surface defects may act as a stress concentrator initiating a fracture point. If a pressure is applied in this area, the casting can fracture. The human visual system is well adapted to perform in areas of variety and change; the visual inspection processes, on the other hand, require observing the same type of image repeatedly to detect anomalies. Slow, expensive, erratic inspection usually is the result. Computer based visual inspection provides a viable alternative to human inspectors. Developed by authors machine vision system uses an image processing algorithm based on modified Laplacian of Gaussian edge detection method to detect defects with different sizes and shapes. The defect inspection algorithm consists of three parameters. One is a parameter of defects sensitivity, the second parameter is a thres hold level and the third parameter is to identify the detected defects size and shape. The machine vision system has been successfully tested for the different types of defects on the surface of castings.
first rewind previous Strona / 3 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.