This research explores the measurement of strain in a machining process on a milling machine. The goal is to develop a simple and easy method to determine the strain in a machine. Compared with other already existing approaches, the presented method separates the measurement locally from coolant and chips, which decreases the risk of a failure in the case of a continuously monitored machine. Furthermore, the measurement method does not influence the machining process itself. The separation of the machining process and the measurement enables the method to gather data without manipulating the process itself. By excluding any influence of the measurement process, the research presented in this article proves the general suitability of the method to increase the accuracy of the machining operation by modifying the toolpath of the machine.

The growing flexibility of modern production systems complicates the quality assurance and process safety of mechanical processing. As an import component of milling machines, the workpiece clamping systems plays a quality-determining role within every milling process. Thus, a sensory workpiece clamping system that utilizes sensory swing clamps was developed in former research work in order to provide monitoring capabilities. This contribution deals with the experimental analysis of the multiple integrated sensors of the sensory swing clamp and the characterization of their measuring capability toward different measurands. By means of the stepwise linear regression method, different models were developed that enable the determination of the clamping force, the hydraulic pressure, and the piston position. The results verify that the multi-sensor evaluation significantly increases the measuring accuracy of a sensory swing clamp. Thus, the measuring accuracy is measurable with a standard deviation of 0.05 MPa for the hydraulic pressure, 101 N for the clamping force, and 0.62 mm for the piston position. Furthermore, the practicability and flexible use at varying boundary conditions is proved.

X-ray computed tomography (XCT) is a promising nondestructive evaluation technique for additive manufacturing (AM) parts with complex shapes. Industrial XCT scanning is a relatively new development, and XCT has several acquisition parameters that a user can change for a scan whose effects are not fully understood. An artifact incorporating simulated defects of different sizes was produced using laser powder bed fusion (LPBF) AM. The influence of six XCT acquisition parameters was investigated experimentally based on a fractional factorial designed experiment. Twenty experimental runs were performed. The noise level of the XCT images was affected by the acquisition parameters, and the importance of the acquisition parameters was ranked. The measurement results were further analyzed to understand the probability of detection (POD) of the simulated defects. The POD determination process is detailed, including estimation of the POD confidence limit curve using a bootstrap method. The results are interpreted in the context of the AM process and XCT acquisition parameters.

Ultrasonic welding has been widely used in joining plastic parts since it is fast, economical, and suitable for automation. It also has great potential for joining thermoplastic composite structures in the aerospace and automotive industries. For a successful industrial application of ultrasonic composite welding, it is necessary to have effective weld quality prediction technology. This paper proposes a model for weld quality prediction by establishing a correlation between ultrasonic wave transmission and welding process signatures. The signatures, welding power, and force are directly related to the weld quality. This model is used to predict the weld quality with three contact conditions and validated by experiments. The results show that the quality model performs well when a centralized and consistent contact condition is achieved. The model provides a process physics-based solution for the online weld quality prediction in ultrasonic welding of carbon fiber composite.

Sensor signals acquired during the manufacturing process contain rich information that can be used to facilitate effective monitoring of operational quality, early detection of system anomalies, and quick diagnosis of fault root causes. This paper develops a method for effective monitoring and diagnosis of multisensor heterogeneous profile data based on multilinear discriminant analysis. The proposed method operates directly on the multistream profiles and then extracts uncorrelated discriminative features through tensor-to-vector projection, and thus, preserving the interrelationship of different sensors. The extracted features are then fed into classifiers to detect faulty operations and recognize fault types. The developed method is demonstrated with both simulated and real data from ultrasonic metal welding.

Dynamic milling forces have been widely used to monitor the condition of the milling process. However, it is very difficult to measure milling forces directly in operation, particularly in the industrial scene. In this paper, a dynamic force identification method in time domain, conjugate gradient least square (CGLS), is employed for reconstructing the time history of milling forces using acceleration signals in the peripheral milling process. CGLS is adopted for force identification because of its high accuracy and efficiency, which handles the ill-conditioned matrix well. In the milling process, the tool with high-speed rotation has different transfer functions between tool nose and accelerometers at different angular positions. Based on this fact, the averaged transfer functions are employed to reduce the error amplification of regularization processing for milling force identification. Moreover, in order to eliminate the effect of idling and high-frequency components on identification accuracy, the Butterworth band-pass filter is adopted for acceleration signals preprocessing. Finally, the proposed method is validated by milling tests under different cutting parameters. Experimental results demonstrate that the identified and measured milling forces are in good agreement on the whole time domain, which verifies the effectiveness and generalization of the indirect method for milling force measuring. In addition, the Tikhonov regularization method is also implemented for comparison, which shows that CGLS has higher accuracy and efficiency.

In mass customization, a manufacturing line is required to be kept in reliable operation to handle product demand volatility and potential machine degradations. Recent advances in data acquisition and processing allow for effective maintenance scheduling. This paper presents a systematic framework that integrates a sensor-driven prognostic method and an opportunistic maintenance policy. The prognostic method uses degradation signals of each individual machine to predict and update its time-to-failure (TTF) distributions in real time. Then, system-level opportunistic maintenance optimizations are dynamically made according to real-time TTF distributions and variable product orders. The online analytics framework is demonstrated through the case study based on the collected reliability information from a production line of engine crankshaft. The results can effectively prove that the real-time degradation updating and the opportunistic maintenance scheduling can efficiently reduce maintenance cost, avoid system breakdown, and ensure product quality. Furthermore, this framework can be applied not only in an automobile line but also for a broader range of manufacturing lines in mass customization.

Additive manufacturing (AM) is based on layer-by-layer addition of materials. It gives design flexibility and potential to decrease costs and manufacturing lead time. Because the AM process involves incremental deposition of materials, it provides unique opportunities to investigate the material quality as it is deposited. Development of in situ monitoring methodologies is a vital part of the assessment of process performance and understanding of defects formation. In situ process monitoring provides the capability for early detection of process faults and defects. Due to the sensitivity of AM processes to different factors such as laser and material properties, any changes in aspects of the process can potentially have an impact on the part quality. As a result, in-process monitoring of AM is crucial to assure the quality, integrity, and safety of AM parts. There are various sensors and techniques that have been used for in situ process monitoring. In this work, acoustic signatures were used for in situ monitoring of the metal direct energy deposition (DED) AM process operating under different process conditions. Correlations were demonstrated between metrics and various process conditions. Demonstrated correlation between the acoustic signatures and the manufacturing process conditions shows the capability of acoustic technique for in situ monitoring of the additive manufacturing process. To identify the different process conditions, a new approach of K-means statistical clustering algorithm is used for the classification of different process conditions, and quantitative evaluation of the classification performance in terms of cohesion and isolation of the clusters. The identified acoustic signatures, quantitative clustering approach, and the achieved classification efficiency demonstrate potential for use in in situ acoustic monitoring and quality control for the additive manufacturing process.

In metal cutting operations, energy efficiency can have significant consequences for the environment and for sustainable development (such as ever-increasing demand for cost saving and quality improvements), particularly when the processes are practiced on a very large scale. The energy efficiency state is a cutting process condition that coexists with other conditions such as cutter state, workpiece quality state, or machine tool state. It must be monitored by operators to avoid system failure of low energy efficiency state, on-line energy efficiency state monitoring is becoming more and more important in intelligent manufacturing and green manufacturing. The idea of energy efficiency state identification is proposed and the monitoring strategy of energy efficiency state is established for this subject. A combined application method of continuous wavelet transform (CWT) and fast independent component analysis (FICA) is proposed for feature extraction of low or high energy efficiency state. The feature of energy efficiency state is extracted by CWT on the premise of determining the state of high and low energy efficiency based on modeling of energy efficiency state and experiment data. The feature signal is reconstructed by FICA and the reconstruction signal is verified by short time Fourier transform (STFT). The feature tracing of cutting system is carried out. It is illustrated that the feature of energy efficiency state can be extracted and the different energy efficiency states also can be identified for milling processes. The proposed method will be helpful for energy efficiency state monitoring.

The regenerative milling chatter is usually regarded as some kind of bifurcation or chaos behaviors of the machining system. Although several chatter patterns such as the secondary Hopf, the period doubling, and the cyclic fold bifurcations were once reported, their relationships with cutting conditions remain undiscovered. This paper aims to uncover the dynamic mechanism of distinct chatter behaviors in general milling scenarios. First, two complementary methods, i.e., the generalized Runge–Kutta method and the time-domain simulation technique, are presented to jointly study the distribution rule of chatter patterns in stability lobe diagrams for milling processes with general flute-spacing tools considering runout. The theoretical predictions are validated by one published example and two cutting experiments under three different cutting conditions. Furthermore, the cutting signal characteristics and cutting surface topography of distinct chatter patterns are analyzed and compared in detail. On this basis, this paper studies the joint influences of cutting parameters, tool geometries, and runout on regenerative chatter behaviors with the proposed methods.

Milling exhibits forced vibrations at tooth passing frequency and its harmonics, as well as chatter vibrations close to one of the natural modes. In addition, there are sidebands, which are spread at the multiples of tooth passing frequency above and below the chatter frequency, and make the robust chatter detection difficult. This paper presents a novel on-line chatter detection method by monitoring the vibration energy. Forced vibrations are removed from the measurements in discrete time domain using a Kalman filter. After removing all periodic components, the amplitude and frequency of chatter are searched in between the two consecutive tooth passing frequency harmonics using a nonlinear energy operator (NEO). When the energy of any chatter component grows relative to the energy of forced vibrations, the presence of chatter is detected. The proposed method works in discrete real time intervals, and can detect the chatter earlier than frequency domain-based methods, which rely on fast Fourier Transforms. The method has been experimentally validated in several milling tests using both microphone and accelerometer measurements, as well as using spindle speed and current signals.

Cutting tool rotation errors have significant influence on the machined surface quality, especially in micromilling. Precision metrology instruments are usually needed to measure the rotation error accurately. However, it is difficult to directly measure the axial error of micromilling tools due to the small diameters and ultra-high rotational speed. To predict the axial error of high speed milling tools in the actual machining conditions and avoid the use of expensive metrology instruments, a novel method is proposed in this paper to quantify the cutting tool error in the axial direction based on the tool marks generated on the machined surface. A numerical model is established to simulate the surface topography generation, and the relationship between tool marks and the cutting tool axial error is then investigated. The tool axial errors at different rotational speeds can be detected by the proposed method. The accuracy and the reliability of the proposed method are verified by machining experiments.

Machining industry has been evolving toward implementation of automation into the processes for higher productivity and efficiency. Although many studies have been conducted in the past to develop intelligent monitoring systems in various application scenarios of machining processes, most of them just focused on cutting tools without considering the influence of the nonuniform hardness of workpiece material. This study develops a compact, reliable, and cost-effective tool condition monitoring (TCM) system to detect the cutting tool wear in machining of the workpiece material with hardness variation. The generated audible sound signals during the machining process are analyzed by state-of-the-art artificial intelligent techniques, support vector machine (SVM) and convolutional neural network (CNN), to predict the tool wear and the hardness variation of the workpiece. A four-level classification model is developed for the system to detect the tool wear condition based on the width of the flank wear land and the hardness variation of the workpiece. This study also involves the comparative analysis between two employed artificial intelligent techniques to evaluate the performance of the model in prediction. The proposed TCM system has shown a high prediction accuracy in detecting the tool wear from the audible sound into the proposed multiclassification wear level in end milling of the nonuniform hardened workpiece.

The goal of this work is to detect the onset of material cross-contamination in laser powder bed fusion (L-PBF) additive manufacturing (AM) process using data from in situ sensors. Material cross-contamination refers to trace foreign materials that may be introduced in the powder feedstock used in the process due to reasons such as poor cleaning of the machine after previous builds or inadequate quality control during production and storage of the powder. Material cross-contamination may lead to deleterious changes in the microstructure of the AM part and consequently affect its functional properties. Accordingly, the objective of this work is to develop and apply a spectral graph theoretic approach to detect the occurrence of material cross-contamination in real-time as the part is being built using in-process sensors. The central hypothesis is that transforming the process signals in the spectral graph domain leads to early and more accurate detection of material cross-contamination in L-PBF compared to the traditional delay-embedded Bon-Jenkins stochastic time series analysis techniques, such as autoregressive (AR) and autoregressive moving average (ARMA) modeling. To test this hypothesis, Inconel alloy 625 (UNS alloy 06625) test parts were made at Edison Welding Institute (EWI) on a custom-built L-PBF apparatus integrated with multiple sensors, including a silicon photodetector (with 300 nm to 1100 nm optical wavelength). During the process, two types of foreign contaminant materials, namely, tungsten and aluminum particulates, under varying degrees of severity were introduced. To detect cross-contamination in the part, the photodetector sensor signatures were monitored hatch-by-hatch in the form of spectral graph transform coefficients. These spectral graph coefficients are subsequently tracked on a Hotelling T 2 statistical control chart. Instances of Type II statistical error, i.e., probability of failing to detect the onset of material cross-contamination, were verified against X-ray computed tomography (XCT) scans of the part to be within 5% in the case of aluminum contaminant particles. In contrast, traditional stochastic time series modeling approaches, e.g., ARMA, had corresponding Type II error exceeding 15%. Furthermore, the computation time for the spectral graph approach was found to be less than one millisecond, compared to nearly 100 ms for the traditional time series models tested.

This paper describes a robust tool wear monitoring scheme for turning processes using low-cost sensors. A feature normalization scheme is proposed to eliminate the dependence of signal features on cutting conditions, cutting tools, and workpiece materials. In addition, a systematic feature selection procedure in conjunction with automated signal preprocessing parameter selection is presented to select the feature set that maximizes the performance of the predictive tool wear model. The tool wear model is built using a type-2 fuzzy basis function network (FBFN), which is capable of estimating the uncertainty bounds associated with tool wear measurement. Experimental results show that the tool wear model built with the selected features exhibits high accuracy, generalized applicability, and exemplary robustness: The model trained using 4140 steel turning test data could predict the tool wear for Inconel 718 turning with a root-mean-square error (RMSE) of 7.80 μ m and requests tool changes with a 6% margin on average. Furthermore, the developed method was successfully applied to tool wear monitoring of Ti–6Al–4V alloy despite different mechanisms of tool wear, i.e., crater wear instead of flank wear.

The goal of this work is to monitor the laser powder bed fusion (LPBF) process using an array of sensors so that a record may be made of those temporal and spatial build locations where there is a high probability of defect formation. In pursuit of this goal, a commercial LPBF machine at the National Institute of Standards and Technology (NIST) was integrated with three types of sensors, namely, a photodetector, high-speed visible camera, and short wave infrared (SWIR) thermal camera with the following objectives: (1) to develop and apply a spectral graph theoretic approach to monitor the LPBF build condition from the data acquired by the three sensors; (2) to compare results from the three different sensors in terms of their statistical fidelity in distinguishing between different build conditions. The first objective will lead to early identification of incipient defects from in-process sensor data. The second objective will ascertain the monitoring fidelity tradeoff involved in replacing an expensive sensor, such as a thermal camera, with a relatively inexpensive, low resolution sensor, e.g., a photodetector. As a first-step toward detection of defects and process irregularities that occur in practical LPBF scenarios, this work focuses on capturing and differentiating the distinctive thermal signatures that manifest in parts with overhang features. Overhang features can significantly decrease the ability of laser heat to diffuse from the heat source. This constrained heat flux may lead to issues such as poor surface finish, distortion, and microstructure inhomogeneity. In this work, experimental sensor data are acquired during LPBF of a simple test part having an overhang angle of 40.5 deg. Extracting and detecting the difference in sensor signatures for such a simple case is the first-step toward in situ defect detection in additive manufacturing (AM). The proposed approach uses the Eigen spectrum of the spectral graph Laplacian matrix as a derived signature from the three different sensors to discriminate the thermal history of overhang features from that of the bulk areas of the part. The statistical accuracy for isolating the thermal patterns belonging to bulk and overhang features in terms of the F-score is as follows: (a) F-score of 95% from the SWIR thermal camera signatures; (b) 83% with the high-speed visible camera; (c) 79% with the photodetector. In comparison, conventional signal analysis techniques—e.g., neural networks, support vector machines, linear discriminant analysis were evaluated with F-score in the range of 40–60%.

The evolution of the manufacturing industry has favored the use of new technologies that increase the level of autonomy in production systems. The work presented shows a methodology that allows for online estimation of cutting parameters based on the analysis of the cutting force signal pattern. The dynamic response of the tool is taken into account through a function that relates the response time to the input variables in the process. The force signal is obtained with a dynamometric platform based on piezoelectric sensors. The final section of the paper shows the experimental validation where machining tests with variable machining conditions were carried out. The results reveal high precision in the estimation of depths of cut in end milling.

Development of monitoring devices becomes crucially important in selective laser melting (SLM) due to the high process complexity and the high value of the products obtained. This work discusses the design of a coaxial monitoring system for SLM using multiple sensors. In particular, an optical model is developed for the propagation of the process emission from the workpiece to the monitoring module. The model is used to determine the field of view (FOV) around the monitored zone. The lens arrangements and the optical filters are chosen according to the model results. They were implemented to construct a monitoring module consisting of two cameras viewing visible and near-infrared wavelength bands, as well as a photodiode viewing the back-reflected laser emission, all integrated in a coaxial configuration. The system functionality is tested with a prototype SLM machine during the processing of 18Ni300 maraging steel, a material known to be prone to porosity. In particular, different remelting strategies were employed as possible correction strategies to reduce porosity. The signals were interpreted as being indicators of the change in absorptivity of the laser light by the powder bed, of the plasma and molten pool, as well as of the evolution of the temperature field.

Recent changes in legislation along with environmental initiatives to drive sustainability and reduce carbon emissions have sprouted the development of energy models to characterize manufacturing processes. In the case of injection molding, much work has been performed in coupling sensors with control statistical systems to promptly identify process' instabilities, such as pressure drops or fluctuations in the filling point. Latest energy models for injection molding make use of injection pressure and temperature parameters that are a function of the machine, mold geometry, and process characteristics. The latest state-of-the-art way to measure energy consumption is through the use of energy loggers, which provide power data at the end of the production cycles. Although seemingly correlated, little has been published on the extrapolation of cavity signals for their use in energy calculations. In this study, the advantages and disadvantages of using cavity sensors in injection molding are explored; a novel approach to the use of cavity sensors' pressure and temperature data is proposed by exploring their input in an energy model for the estimation of specific energy consumption (SEC). The model was validated against power data obtained via an energy logger; the averaged energy reported by the model indicated a range of 60–67% accuracy.

In high-speed cutting processes, late replacement of defective tools may lead to machine breakdowns and badly affect the product quality, which subsequently lead to scrap parts and high process costs. Accurate tool condition detection is essential to achieve high level of competitiveness via increasing process productivity and standardizing the quality of the produced parts. Therefore, tool condition monitoring (TCM) systems have been widely emphasized as an important principle to achieve these industrial demands. Several studies for TCM were carried out to capture tool failure using complex conventional and artificial intelligence (AI) techniques. However, these studies suffer from the absence of standardization and generalization. Hence, this paper presents a robust and reliable processing technique for the cutting process signals to extract generalized features in time and frequency domains. The proposed technique masks the effects of the cutting conditions on the extracted features and accentuates the tool condition effect. Characterization and statistical analysis of the processed features were performed to examine their sensitivity to the tool condition. The results revealed the processing technique capability to separate the features extracted from the spindle motor current signals into two mutually exclusive clusters according to their tool condition. The statistical analysis results were employed to optimize the tool condition detection approach using linear discrimination analysis (LDA) model. The results indicate the capability of the processing technique to minimize the system learning effort and to detect tool wear above the threshold level with accuracy above 90%.