Search Results (33)

This study evaluates the surface roughness of micromilled 316L stainless steel parts fabricated via fused filament fabrication (FFF) and sintering, establishing statistical links between additive manufacturing and post-machining parameters. The surface roughness of the final part is affected by both 3D printing and micromachining parameters. The presented work has direct practical relevance because micromilled 316L stainless steel components are frequently used in applications such as lab-on-a-chip (LOC) devices and micro-electro-mechanical systems (MEMS), where fatigue behavior and the rheological behavior of fluid flow play critical roles. Both fluid flow and fatigue performance of micromilled components are highly dependent on surface integrity, including surface roughness, residual stresses, and microstructure. Specimens were produced using a 3D printer, under controlled layer thicknesses, raster angles, and fabrication directions, followed by a sintering process for the 3D-printed parts. The sintered parts are then micromilled at varying cutting directions (Angle Cut). Surface roughness (Ra) was measured with a profilometer, generating 34 experimental datasets analyzed through correlation and regression modeling. Cutting direction (Angle Cut) exhibited the strongest positive correlation with Ra (r = 0.486, p = 0.004), followed by layer thickness (r = 0.326, p = 0.060), whereas raster angle and fabrication direction had minimal influence. The multiple linear regression model accounted for 33.5% of Ra variance (R² = 0.335, p = 0.0158), highlighting that fine-layer deposition and alignment of tool paths with filament orientation significantly improve post-machined surface quality. Results confirm that additive-induced anisotropy persists after sintering, affecting chip formation and surface morphology during micromilling. The novelty of this work lies in its integrated hybrid framework, linking metal FFF process parameters, fabrication direction, and machining outcomes through a unified statistical approach. This foundation supports machine-learning-based prediction and hybrid process optimization in metal FFF systems, providing guidance for high-quality additive–subtractive manufacturing. Full article

Iron ore sintering is a critical process in steelmaking, where the produced sinter is the main raw material for blast furnace ironmaking. The quality and yield of sinter ore directly affect the cost and efficiency of iron and steel production. Accurately predicting the burn-through point (BTP) temperature is of paramount importance for controlling quality and yield. Traditional BTP temperature prediction only utilizes data from bellows, neglecting the information contained in sinter images. This study combines color temperature information extracted from the cross-sectional frame at the discharge end with bellows data. Due to the non-stationarity of the BTP temperature, a hybrid prediction model of the BTP temperature integrating bidirectional long short-term memory and extreme gradient boosting is presented. By combining the advantages of deep learning and tree ensemble learning, a hybrid prediction model of the BTP temperature is established using the color temperature information in the cross-sectional frame at the discharge end and time-series data. Experiments were conducted with the actual running data in an iron and steel enterprise and show that the proposed method has higher accuracy than existing methods, achieving an approximately 4.3% improvement in prediction accuracy. The proposed method can provide an effective reference for decision-making and for the optimization of operating parameters in the sintering process. Full article

As a key parameter in the sintering process, the ferrous oxide content of sinter can reflect the working condition, energy consumption level, and quality level of the final sintered products in the sintering process. It has become a key problem to realize the prediction of ferrous oxide content in sinter and feedback control of sinter quality accordingly. The two commonly used methods for detecting ferrous oxide content in industrial production currently do not meet real-time requirements and cannot provide timely feedback for production regulation. Therefore, research on real-time prediction technology of ferrous oxide content in sinter was carried out, and an optimized back propagation neural network model was established to realize the mapping between characteristic parameters and the FeO content in sinter. The characteristic parameters include image parameters and process parameters. Through the research on the brightness change trend of the machine tail cross-section image, the best cross-section image acquisition method based on brightness difference is realized, and image parameters are obtained by image processing technology. The process parameters were selected using correlation analysis. Through data processing techniques such as data cleaning, normalization, and feature fusion, feature parameters were obtained as input vectors for the neural network. To improve prediction accuracy and system stability, an adaptive learning rate and genetic algorithm were used to optimize the traditional BP neural network. The average test error of the optimized prediction model was 0.32%. Taking actual data production as an example, test data on the FeO content of sinter were extracted from the laboratory. Compared with the FeO content predicted by the system, the prediction time of the system was about 2 h earlier than the test time. In terms of prediction accuracy, the average absolute error was 0.25%, and the absolute prediction error was not more than ±1%. Full article

Additive manufacturing processes such as the material extrusion of metals (MEX/M) enable the production of complex and functional parts that are not feasible to create through traditional manufacturing methods. However, achieving high-quality MEX/M parts requires significant experimental and financial investments for suitable parameter development. In response, this study explores the application of machine learning (ML) to predict the surface roughness and density in MEX/M components. The various models are trained with experimental data using input parameters such as layer thickness, print velocity, infill, overhang angle, and sinter profile enabling precise predictions of surface roughness and density. The various ML models demonstrate an accuracy of up to 97% after training. In conclusion, this research showcases the potential of ML in enhancing the efficiency in control over component quality during the design phase, addressing challenges in metallic additive manufacturing, and facilitating exact control and optimization of the MEX/M process, especially for complex geometrical structures. Full article

Aluminum metal matrix composites (AlMMCs) are widely employed in the aerospace and automotive industries due to their greater qualities in comparison to the base alloy. Adding nanocomposites like multi-walled carbon nanocomposites (MWCNTs) to aluminum enhances its mechanical properties. In the current research, aluminum 7075 with MWCNT particles was prepared and characterized to study its tribological behaviors, such as its hardness and specific wear rate. The experiment was designed with varying weight percentages of MWCNTs of 0.5, 1.0, and 1.5, and these were fabricated using powder metallurgy, employing compacting pressures of 300, 400, and 500 MPa and sintering temperatures of 400, 450, and 500 °C. Further, the experimental setup was designed using Design-Expert V13 to examine the impact of influencing parameters. A second-order mathematical model was developed via central composite design (CCD) using a response surface methodology (RSM), and the performance characteristics were analyzed using an analysis of variance (ANOVA). The hardness (HV) and specific wear rate (SWR) were measured using a hardness tester and pin-on-disk apparatus. From the results thus obtained, it was observed that an increase in compacting pressure and sintering temperature tends to increase the hardness and specific wear rate. An increasing weight percentage of MWCNTs increased their hardness, while the SWR was less between the weight percentages 0.9 and 1.3. A multi-objective genetic algorithm (MOGA) was trained and evaluated to provide the best feasible solutions. The MOGA suggested sixteen sets of non-dominated Pareto optimal solutions that had the best and lowest predicted values. The confirmatory analytical results and predicted characteristics were found to be excellent and consistent with the experiential values. Full article

Ceramic detachments in cladding systems are indicative of adhesion loss between the ceramic tiles and the substrate or its adhesive mortar due to inadequate quality workmanship, the quality of the adhesive mortar or that of the ceramic material, whether acting simultaneously or not. The shear stresses resulting from the ceramic tiles’ expansion due to humidity accelerate this process. There is a shortage of studies on the quality of ceramic tiles and adhesive mortars. This study conducted elemental, physical and microstructural characterization tests on ceramic tiles and adhesive mortars that showed detachment up to two years after being laid. At first glance, the adhesive mortar samples had adequate traits and degree of hydration. The ceramic tiles, on the other hand, showed high porosity and high levels of amorphous and poorly sintered materials, with no crystalline phase. In a second analysis, scanning electron microscopy (SEM) tests associated with boiling plus autoclave moisture expansion tests executed on unused ceramic pieces of the same conformation proved to be more suitable for predicting expansion potential than standard tests. Due to the costs and difficulties in accessing and analyzing the SEM tests, chemical analysis of the ceramic tiles was executed using X-ray fluorescence (XRF) to assess the presence of the amorphous silica (free quartz) and alkaline oxides. Together with pressure and temperature determination tests (autoclave), they may represent another alternative that is easier to access and more cost-effective for predicting future expansion. Full article

The sintering ignition process parameters fluctuate frequently and significantly, resulting in large variations in ignition temperature, which in severe cases can exceed 200 °C. This not only increases gas consumption but also affects the quality of the sinter. Because the intelligent control model based on feedback mechanisms struggles to deal with high-frequency fluctuation conditions over time, the prediction of sintering ignition temperature using feedforward regulation is attracting increasing attention. Given the multi-variable, time-sequential and strongly coupled characteristics of the sintering ignition process, a convolutional neural network (CNN) and a long short-term memory (LSTM) network are deeply integrated, with an attention mechanism incorporated to develop the sintering ignition temperature prediction model, enabling the accurate prediction of the ignition temperature. The research demonstrates that the combination of a CNN and the attention mechanism effectively addresses the challenges posed by the multi-variable and strongly coupled nature of sintering ignition data to predictive modeling. The LSTM network resolves the sequential data issues through its gating mechanism. As a result, the coefficient of determination ($R^2$ ) of the CNN_LSTM-Attention model in predicting the sintering ignition temperature can reach 0.97, with a mean absolute error ($MAE$) as low as 10.23 °C. The predicted values closely match the actual values, achieving a hit rate of 93% within the acceptable error range. These performance metrics are significantly superior to those of the CNN-Attention and LSTM-Attention models, greatly enhancing the control accuracy of the ignition temperature. Full article

The quality of sintered ore, which serves as the primary raw material for blast furnace ironmaking, is directly influenced by the moisture in the sintering mixture. In order to improve the precision of water addition in the sintering process, this paper proposes an intelligent model for predicting water-filling volume based on Temporal Fusion Transformer (TFT), whose symmetry enables it to effectively capture long-term dependencies in time series data. Utilizing historical sintering data to develop a prediction model for the amount of mixing and water addition, the results indicate that the TFT model can achieve the R squared of 0.9881, and the root mean square error (RMSE) of 3.5951. When compared to the transformer, long short-term memory (LSTM), and particle swarm optimization–long short-term memory (PSO-LSTM), it is evident that the TFT model outperforms the other models, improving the RMSE by 8.5403, 6.9852, and 0.453, respectively. As an application, the TFT model provides an effective interval reference for moisture control in normal sintering processes, which ensures that the error is within 1 t. Full article

This research addresses the challenge of determining the optimal parameters for the selective laser sintering (SLS) process using thermoplastic polyurethane elastomer (TPU) flexa black powder to achieve high-quality SLS parts. This study focuses on two key printing process parameters, namely layer thickness and the laser power ratio, and evaluates their impact on four output responses: density, hardness, modulus of elasticity, and time required to produce the parts. The primary impacts and correlations of the input factors on the output responses are evaluated using response surface methodology (RSM). A particular response optimizer is used to find the optimal settings of input variables. Additionally, the rationality of the model is verified through an analysis of variance (ANOVA). The research identifies the optimal combination of process parameters as follows: a 0.11 mm layer thickness and a 1.00 laser power ratio. The corresponding predicted values of the four responses are 152.63 min, 96.96 Shore-A, 2.09 MPa, and 1.12 g/cm³ for printing time, hardness, modulus of elasticity, and density, respectively. These responses demonstrate a compatibility of 66.70% with the objective function. An experimental validation of the predicted values was conducted and the actual values obtained for printing time, hardness, modulus of elasticity, and density at the predicted input process parameters are 159.837 min, 100 Shore-A, 2.17 MPa, and 1.153 g/cm³, respectively. The errors between the predicted and experimental values for each response (time, hardness, modulus of elasticity, and density) were found to be 4.51%, 3.04%, 3.69%, and 2.69%, respectively. These errors are all below 5%, indicating the adequacy of the model. This study also comprehensively describes the influence of process parameters on the responses, which can be helpful for researchers and industry practitioners in setting process parameters of similar SLS operations. Full article

Accurate computational models of sintering behavior would assist to enhance sinter quality and are anticipated to play a role in yield prediction. Sintering is a vital process in the manufacturing of iron and steel. As a consequence, the primary objective of these models will be a thorough simulation of mass and heat transport during the sintering process. In this paper, based on the examination and integration of previous studies, the fundamental physical formula and chemical reactions of the numerical simulation of the sintering process are introduced in depth with mechanism analysis. Furthermore, in view of the current numerical simulation methods and sintering process technology innovation development, the studies on sintering numerical simulation are reviewed from different angles, of which the main methods and assumptions are discussed. Finally, the current state of sintering simulation including the numerical simulation of innovative algorithm and optimized sintering technology is discussed in detail, along with potential implications for model development. Full article

In complex industrial processes such as sintering, key quality variables are difficult to measure online and it takes a long time to obtain quality variables through offline testing. Moreover, due to the limitations of testing frequency, quality variable data are too scarce. To solve this problem, this paper proposes a sintering quality prediction model based on multi-source data fusion and introduces video data collected by industrial cameras. Firstly, video information of the end of the sintering machine is obtained via the keyframe extraction method based on the feature height. Secondly, using the shallow layer feature construction method based on sinter stratification and the deep layer feature extraction method based on ResNet, the feature information of the image is extracted at multi-scale of the deep layer and the shallow layer. Then, combining industrial time series data, a sintering quality soft sensor model based on multi-source data fusion is proposed, which makes full use of multi-source data from various sources. The experimental results show that the method effectively improves the accuracy of the sinter quality prediction model. Full article

Sinter ore quality directly affects the stability of blast furnace production. In terms of both physical and chemical properties, the main indicators of sinter quality are the TFe content, alkalinity, and drum index. By analyzing the massive historical data on the sinter production of a steel company, this study proposes a sinter quality prediction system based on Granger causality analysis and a stacking integration algorithm. First, based on real historical data of sintering production in steel enterprises (including coal gas pressure, ignition temperature, combustion air pressure, etc.), data preprocessing of raw data was carried out using a combination of feature engineering and the sintering process. Second, Pearson correlation analysis, Spearman correlation analysis, and Granger causality analysis were used to screen out the characteristic parameters with a strong influence on the target variable of sinter quality (drum Index, TFe, alkalinity). Third, a prediction model for sinter quality parameters was developed using a stacking integration algorithm pair for training. Finally, a program development tool was used to realize the establishment and online operation of a sinter ore quality prediction system. The test results showed that the predicted goodness of fit of the model for the TFe content, alkalinity (R), and drum index were 0.942, 0.958, and 0.987, respectively, and the model calculation time met the actual production requirements. By establishing a suitable model and running the program online, the real-time prediction of the main indicators of sinter quality was realized to guide production promptly. Full article

To obtain high-quality and durable parts by 3D printing, specific characteristics (porosity and proportion of various sizes of particles) in the mixture used for printing or sintering must be assured. To predict these characteristics, a mathematical model of optimized packing polyhedral objects (particles of titanium alloys) in a cuboidal container is presented, and a solution algorithm is developed. Numerical experiments demonstrate that the results obtained by the algorithm are very close to experimental findings. This justifies using numerical simulation instead of expensive experimentation. Full article

The sulfur content of hot metal in a blast furnace is an important index that reflects the production effects and quality of the hot metal. Establishing an accurate prediction model for hot metal sulfur content can guide the production process. In the present study, the blast furnace production data were collected and then preprocessed using box plotting. Cross-validation was used in the training process of the model to improve the generalization performance and robustness of the model. Two models for predicting the sulfur content in hot metal were established based on extreme gradient boosting (XGBoost) and multilayer perceptron (MLP) algorithms. The results show that coal consumption (CC), coal ratio (CLR), and sinter consumption (SC) are all positively correlated with hot metal sulfur content. The oxygen enrichment rate (OER) was negatively related to hot metal sulfur content. Both the extreme gradient boosting (XGBoost) and multilayer perceptron (MLP) models predicted hot metal sulfur content effectively; however, the extreme gradient boosting (XGBoost) model had a higher hit rate, accuracy, and stability, with the hit rate achieving 95.07%. Full article

Porcelain tile manufacturing is an energy-intensive industry that is in dire need of increasing productivity, minimizing costs, and reducing CO₂ emissions, while keeping the product quality intact to remain competitive in today’s environment. In this contribution, alternative processing parameters for the porcelain tile production sequence were proposed based on simulation-based process optimization. Flowsheet simulations in the Dyssol framework were used to study the impact of the milling and firing process parameters on the electrical and thermal energy consumption, final product quality, and productivity of the entire processing sequence. For this purpose, a new model of gas flow consumption in the sintering stage was proposed and implemented. During optimization, the primary condition was to maintain the product quality by keeping the final open porosity of the tile within the specified industrial range. The proposed simulation methodology proved to be effective in predicting the influence of the processing parameters on the intermediate and final products of the manufacturing sequence, as well as in estimating the production costs for the Brazilian and Spanish economic conditions. This approach has shown great potential to promote digitalization and establish digital twins in ceramic tile manufacturing for further in-line process control. Full article