Fig 1 - uploaded by Francesco Lambiase
Content may be subject to copyright.
Source publication
Laser hardening is a surface treatment process characterized by a high level of performance. The resulting physical, chemical, and mechanical properties of the surface layers can be accurately designed by modifying the process parameters i.e., scanning speed, frequency and laser power. Thus, the development of the laser hardening technology require...
Context in source publication
Context 1
... constituted by an 1-D analytical model for prediction of the temperature history at a given distance from the irradiated surface and a neural network that takes as input the thermal history and returns the estimated increase of hardness. The flow chart representing the interactions among the different modules of the expert system is reported in Fig. 1 whereas the optimization module (which has not yet developed) is depicted in ...
Similar publications
In this paper we present a fuzzy expert system for diagnosing osteoporosis based on mandibular cortical width and shape measurement on dental panoramic radiographs. We proposed a fuzzy thresholding method to find out optimal cut off threshold for input variables to provide optimal fuzzy membership functions. This system allows the dentists to deter...
The application of a software functional measurement method is an intellectual process carried out on a complex abstract artifact: this process includes both a mapping phase between the measurement model and the software model, and a measurement phase for the instantiation of the measurement rules to the derived mapping model. In industrial context...
This paper presents the elaboration of a cartographic expert system, for generation of thematic maps pursuing the implantation of the Organic Law of Social Assistance of the Paraná State. The cartographic expert system was created to assist users not specialists in cartography, to classify their information of economic and social indicators in the...
Citations
... J/mm 2 , and that of No. 10 group of experiment is This study only fabricated hardened layers of small depth. However, LSQ technology is widely applied to achieve hardening depths of below 1 mm in related references (Chen et al. 2018a, b;Colombini et al. 2014;Lambiase et al. 2013;Li et al. 2006;Yu et al. 2019;Zheng et al. 2017), where the application objects include parts subjected to tribological processes, such as railway (Zheng et al. 2017), wheel steel (Chen et al. 2018a), stress-carring part, and transmission parts (Chen et al. 2018b). The SDC workpiece is also applied in wear and friction processes, so its hardening depth by LSQ in this study is justified and acceptable. ...
Laser surface quenching (LSQ) is gaining popularity in engineering applications, but it generates non-negligible carbon emissions. However, existing research mostly focuses on quenching performance. Little attention has been paid to carbon emissions of LSQ process. In this study, we build an experimental platform including fiber laser system (IPG YLR-4 kW) and carbon emission measurement system for a synergistic study of environmental impacts and processing quality in LSQ. Based on the L16 (4³) Taguchi matrix, LSQ experiments are conducted on the shield disc cutter. The influences of laser power, scanning speed, and defocusing distance on carbon emissions and hardening effects are studied. The carbon emission efficiency of LSQ is analyzed and compared with the competitive technology. The geometry and the maximum average hardness (MAH) of LSQ high-hardness zone (HHZ) are studied. A comprehensive evaluation considering carbon emissions and hardening effects is conducted. The results show that the maximum value of carbon emission is 1.4 times the minimum value. The maximum depth and width of HHZ are respectively 0.507 and 3.254 mm. The maximum MAH is 3.5 times the hardness of base metal. Compared to the average experimental responses, the experiment with the highest comprehensive score respectively increases by 26.4%, 17.1%, and 30.3% in depth, width, and MAH of HHZ, and reduces by 5.8% in carbon emissions.
... The classical machine learning pipeline (sequence of actions) for modeling is used to analyze the data, treat the variables, split them into train and test sets, fit and construct the model, predict the results with testing data, and compare the model predictions with the ground truth to quantify the result error. ANN are regularly involved in metallurgy analysis under induction heating [36], surface hardness in carburizing quenching [37] and in laser hardening [38], and various mechanical properties in metal rolling [39]. Also, machine learning algorithms from the XGBoost library [40] are recognized of being efficient in some challenges while being convenient in the use and optimization [41]. ...
Induction hardening is a heat surface treatment technique widely employed for steel components in order to improve their fatigue life without affecting the metallurgy of the bulk material. The control of the treated components goes through the prediction and the optimization of the induction hardening process parameters. The aim of this work is to propose an approach based on artificial intelligence technique to predict the in-depth hardness profile. For this purpose, experimental tests were first carried out on 300M steel bar and C45 steel spur-gear under single and double frequencies, respectively. Intermediate variables were then generated to be used as input data. Data-driven model based on XGBoost library was finally developed. It was found that the proposed approach predicts with good agreement the hardness profiles and can be used in induction treatment process optimization.
... The mechanical properties of metal alloys have been predicted using machine learning models, which range from general models for elastic properties trained on data derived from first principles to models of macroscopic properties like hardness, toughness, and strength as well as phenomena like wear, fatigue, creep, hydrogen embrittlement, and crack initiation and propagation in particular alloy systems [8]. Similarly, predicting the effect of process parameters, quantitative structure-property relationships, using functional mappings of inputs to predict end-product quality, interpretability and the physical meaning of the computational intelligence methods were analyzed [9][10][11]. ...
... To control the process temperature, numerical simulations were used to minimize the experimental work required to develop a closed-loop temperature control system. Lambiase et al. [20] developed an artificial neural network to predict the hardness of laser hardened steels. The temperature history calculated using the 1-D analytical model was used for their model. ...
In the paper the methods of laser hardening of external tool corners on the example of bending tools for press brakes were presented. The disadvantages and limitations of the most commonly used techniques for guiding a hardening laser light beam are presented, i.e.: (i) in one pass parallel to the tool corner plane symmetry, (ii) in two passes perpendicular to the surfaces adjacent to the corner, and (iii) in one pass perpendicular to the surface adjacent to the corner by using two diode lasers. The microstructure of the tool material after laser and induction hardening was compared. A significant influence of the heating method on the microstructure of the tool material after hardening was demonstrated. The original method of hardening the outer corners of bending tools using a hardening laser beam splitter was subject to a more detailed analysis. The analysis of material heating in simultaneously hardened corner area and adjacent surfaces was carried out using the Marc/Mentat software based on the finite element method. By analyzing the temperature distributions it was shown that if a beam splitter was used, obtaining a continuous and uniform hardened layer (i.e. with comparable hardness, depth, without tempered or non-tempered areas) in the area of the outer corner and adjacent surfaces was possible. In practice, achieving such a layer is conditioned by the correct selection of the size of the k parameter which determines the distance between the separated beams of laser light. Depending on the geometry of the hardened tool corner and the parameters of the hardening laser beam, this distance can be determined experimentally or on the basis of numerical simulation.
... To address this, various modeling approaches are used for prediction and optimization in LST, among which metamodeling is effective in revealing the relationship between process parameters and processing qualities [5,9,[15][16][17][18] . Zhang et al. used non-linear equations of the Taylor series to establish the relationships between the laser process parameters and surface hardening effects (wear resistance, hardness, hardening depth, and surface roughness), and then applied particle swarm optimization (PSO) to achieve the hardening requirement and the high efficiency [18] . ...
... To address this, various modeling approaches are used for prediction and optimization in LST, among which metamodeling is effective in revealing the relationship between process parameters and processing qualities [5,9,[15][16][17][18] . Zhang et al. used non-linear equations of the Taylor series to establish the relationships between the laser process parameters and surface hardening effects (wear resistance, hardness, hardening depth, and surface roughness), and then applied particle swarm optimization (PSO) to achieve the hardening requirement and the high efficiency [18] . Lambiase et al. predicted the hardness of the laser hardened surface using an artificial neural network (ANN), where the analytical model of temperature history was used [19] . ...
... The residual stresses result from differences in the expansion and contraction ratios of the molten metal, heat-affected zone, and metal substrate, as well as volume variations of the phase transformation reactions (transformational stresses) [38] . Thus, LST can significantly affect the surface roughness of the processed workpiece [18,[39][40][41] . The higher surface roughness of the laser treated region on steel workpieces often leads to worse wear performance [42,43] . ...
Laser surface treatment (LST) is essential for advanced manufacturing but is extremely energy intensive. Being energy-aware is imperative as the industry pays increasing attention to energy management and environmental protection. However, existing literature mainly focuses on the laser-material interaction in LST, while few studies have considered energy consumption when investigating the processing quality. In this article, three metamodels (Kriging, RBF, and SVR) are integrated into an ensemble of metamodels (EM) by suitable weight coefficients, and the EM incorporates the predictive advantages of different metamodels. The EM establishes the relationship between laser process parameters (laser power, scan speed, and defocusing amount) and three outputs (total energy consumption, surface roughness, and depth-width ratio of LST track). The effectiveness of the presented prediction approach is validated by the leave-one-out method and additional experiments. Furthermore, the main influences of process parameters on the three outputs are studied. According to the technique for order preference by similarity to an ideal solution (TOPSIS), the optimal process parameter is Group No. 2, with the relative closeness of 78.04%, while the worst one is Group No. 13, with the relative closeness of 2.21%. The presented prediction approach can serve as a reliable foundation in the energy-aware application of laser processing.
... 7 In 2013, Lambiase et al. combined analysis models with a neural network to investigate the temperature distributions and transient temperature changes associated with the laser surface hardening processes and to predict the hardness of laser-hardened surfaces. 8 In the same year, El-Batahgy et al. studied the laser quenching process of AISI M2 high speed steel by combining experimental and numerical methods. This proves that numerical simulation can be used to predict surface temperature, surface hardness, and hardening depth for a wide range of laser processing parameters, but the influence of thermal convection and radiation during the quenching process is not considered, and the effect of the temperature variation of physical parameters is neglected. ...
It is extremely difficult to reveal the thermo-mechanical coupling evolution mechanism of the laser quenching process by traditional experimental methods. The numerical simulation provides an effective way to obtain the dynamic evolution information of multifield coupling in the quenching process. Based on comsol multiphysics, a thermo-mechanical coupling model of the 35CrMnSi laser quenching process by a disk laser was established. In the model, the thermophysical parameters of the matrix during the quenching process were calculated by the CALPHAD method. The transient changes of temperature, phase change, and thermal stress during quenching were obtained by solving the model, revealing the transient change law of temperature field and microstructure transformation of a 35CrMnSi laser under different process parameters. The formation and transformation degree of martensite were characterized by the depth and width of the quenched transformation hardening layer. Laser quenching experiments of 35CrMnSi were carried out with a TruDisk 4002 laser. The quenching structure and phase transformation hardening rule were observed by Axioskop 2 SEM, Zeiss-ΣIGMA HD FE-SEM, and HXS-1000A micro hardness tester. Experiments show that the influence zone of laser hardening of a disk laser shows Gauss distribution. The quenching layer consists of complete quenching phase transformation zone, incomplete quenching zone, and core matrix in turn from the surface to inside. In the complete quenched zone, dense and fine acicular martensite and a small amount of retained austenite are formed, and the hardened layer is Gaussian distribution. The phase transformation layer width and the phase transformation layer depth of workpiece 1-1# are 10 352.9891 and 1091.0945 μm, respectively. The phase transformation layer width and the phase transformation layer depth of workpiece 1-2# are 6592.3963 and 754.6135 μm, respectively. The phase transformation layer width and the phase transformation layer depth of workpiece 1-3# are 4361.7892 and 416.2139 μm, respectively. The experimental results are in good agreement with the simulation results, which verifies the validity of the thermo-mechanical coupling model and provides a theoretical basis for obtaining the optimized process parameters.
... One such example, laser hardening, which involves the heating and cooling of the target metal to introduce metallurgical modification, is inherently complex, and thus the attraction for an ANN prediction tool. Lambiase et al. [151] used an ANN with three hidden layers to predict the optimal laser parameters for the laser hardening of steel. Maji et al. [152] used an ANN (shape 3-11-1) to predict the optimal parameters for manufacturing dome profiles through surface melting of AISI 304 stainless steel sheets when using a Yb fibre laser, with inputs of laser power, scan speed and spot diameter, and associated output of dome height. ...
Abstract Laser machining is a highly flexible non‐contact fabrication method used extensively across academia and industry. Whilst simulations based on fundamental understanding offer some insight into the processes, both the highly non‐linear interactions between laser light and matter and the variety of materials involved mean that theoretical modelling is not particularly applicable to practical experimentation. However, recent breakthroughs in machine learning have resulted in neural networks that are capable of accurate and rapid modelling of laser machining at a scale, speed, and precision well beyond those of existing theoretical approaches with applications including 3‐D surface visualisation and real‐time error correction. A perspective at the intersection of laser machining and machine learning is presented, followed by a discussion of future milestones and challenges for this field.
... Owing to its flexibility, ANNs have been extensively used for process design [42] and or to determine optimal processing conditions e.g. friction stir welding of polymers [43], laser hardening [44] as well as laser forming [45]. In recent years, many studies involved machine Learning to predict the mechanical behavior of FSW welds [46][47][48][49][50][51]. ...
Several studies demonstrated a close relationship between the strength of metal-polymer joints made by thermo-mechanical processes and the temperature reached during the process. Machine Learning techniques have been adopted to forecast the temperature trends produced during Friction Assisted Joining varying the main process parameters. This was performed in four steps. First, the design of a campaign of experimental tests and the setup of an instrumented joining machine equipped with load sensors (plunging load and torque) was implemented. The machine was also equipped with an IR camera for temperature measurements during the process. Then, the experimental data were processed and filtered to produce a robust dataset, which was subsequently used for the training, calibration, and validation of an Artificial Neural Network (ANN). The developed approach was based on a data encoding-decoding approach that initially subdivided power-temperature data for training the network. During training, the ANN had no information on the origin curve. Then, once validated, the ANN reconstructed the temperature curve sequentially starting from power curve measurements. The results indicated that starting from the absorbed (measured) power, the developed model was capable to predict the temperature evolution with great accuracy. The resulting Artificial Neural Network represents a reliable tool for process design and identification of correct process parameters e.g. Dwell time; besides, it can be used during the joining process to achieve a prescribed temperature.
... This approach allows demonstrating an optimal combination of process parameters to obtain a high-quality microstructure with laser coating applied to Ti6Al4V. Lambiase et al. [15] proposed a prediction method that can determine the temperature distribution profile based on laser hardening process parameters using an artificial neural network technique. The artificial neural network model allows for a better understanding of laser heating process behavior and the validation of simulated data. ...
This study displays the effect of laser surface hardening parameters on the hardness profile (case depth) of a splined shaft made of AISI 4340 steel. The approach is mainly based on experimental tests wherein the hardness profile of laser hardened splines is acquired using micro-hardness measurements. These results are then evaluated with statistical analysis (ANOVA) to determine the principal effect and the contributions of each parameter in the laser hardening process. Using empirical correlations, the case depth of splined shaft at tip and root of spline's teeth is also estimated and verified with measured data. The obtained results were then used to study the sensitivity of the measured case depths according to the evolution of laser process parameters and geometrical factors. The feasibility and efficiency of the proposed approach lead to a reliable statistical model in which the hardness profile of the spline is estimated with respect to its specific geometry.
... Among the different laser systems available today, high-power diode lasers (HPDL) are particularly suited for the hardening treatments due to the rectangular or elliptical shape of the laser beam profile, which is able to ensure a uniform heating on large areas of the treated surface [14,15]. This is an essential requirement for the laser treatment to be effective [16]. In fact, typical industrial CO 2 lasers are not able to produce an energy flux into the stainless steel, and metals in general, high enough to promote the hardening process [17]. ...
... Values Unit Laser power (P) 100 150 200 250 300 W Scan speed (Ss) 12 14 16 18 20 mm/s ...
This study proposes a genetic algorithm-optimized model for the control of the fatigue life of AISI 1040 steel components after a high-power diode laser hardening process. First, the effect of the process parameters, i.e., laser power and scan speed, on the fatigue life of the components after the laser treatment was evaluated by using a rotating bending machine. Then, in light of the experimental findings, the optimization model was developed and tested in order to find the best regression model able to fit the experimental data in terms of the number of cycles until failure. The laser treatment was found to significantly increase the fatigue life of the irradiated samples, thus revealing its suitability for industrial applications. Finally, the application of the proposed genetic algorithm-based method led to the definition of an optimal regression model which was able to replicate the experimental trend very accurately, with a mean error of about 6%, which is comparable to the standard deviation associated with the process variability.
