SEARCH · Engineering Papers
Results for “embedding”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Embedding of Fiber Optic Sensors in Stainless Steel for Sensing in Harsh Environments
Structural health monitoring is critical for components working in harsh environments to assess their safety and integrity. This can be realized with advanced sensors, such as fiber optic sensors, embedded in these components. Recent studies have used ultrasonic consolidation (UC) and laser-based additive manufacturing (AM) techniques to embed fiber optic sensors in metals. However, sensor embedding using these techniques has been challenging, with gaps and voids around the embedded fiber. Successful embedding of fiber optic sensors requires good contact between the fiber and the matrix to eliminate potential gas/liquid leaks in critical systems such as in nuclear and aerospace services. Defect-free fiber/matrix bond is also essential for accurate measurement of parameters of interest, such as temperature and strain. This study developed a novel fiber embedding technique based on electric field-assisted sintering (EFAS). Sapphire optical fibers with diameters of 125 µm and 250 µm were embedded in stainless steel (SS) 316L using EFAS. The embedding was completed by sintering SS 316L powders at a pressure of 50MPa, hold time of 5 min, and temperatures of 1000°C, 1100°C, and 1200°C. Joule heating mechanism during EFAS enabled rapid sintering of the SS 316L powder with resulting sample densities over 99%. Microscopy analysis performed on the cross-sections revealed a defect-free bond between the embedded fiber and SS 316L. The good integrity of the embedded fiber was evidenced by optical transmittance measurement. Optical attenuation of the fiber before and after embedment was examined in the near-infrared region. Scanning electron microscopy was employed to investigate the grain morphology of SS 316L near the embedded fiber. Hardness distribution in the sintered part was also investigated to study the effect of the embedded fiber on the mechanical properties of the as-fabricated component. The results indicated that EFAS was able to embed fiber in SS with good fiber functionality and part quality.
Embedded metallized optical fibers for high temperature applications
Embedding fiber optics in metal components could enable new capabilities such as active monitoring of spatially distributed strain. Ultrasonic additive manufacturing is a suitable technique for embedding fiber optics because it allows fibers to be embedded in metals without melting and without the use of epoxy. However, for harsh environments that could have high temperatures or high radiation doses, traditional polymer-coated fibers cannot survive for extended periods of time. This work demonstrates successful embedding of commercially available copper-, nickel-, and aluminum-coated fibers into aluminum without any observable damage to the fiber. Copper-coated fibers embedded in copper show adequate light transmission, although residual strain could not be resolved. With further processing improvements, fibers embedded in copper or other high-temperature materials could enable even higher temperature operation. Optical transmission and spatially distributed strain were measured in the fibers embedded in aluminum. Measurements were taken after embedding and during heating to temperatures greater than 500 °C. Within the embedded region, both the copper- and aluminum-coated fibers showed strain that matched the expected strain in the surrounding aluminum matrix during heating. This suggests a strong interfacial bond strength that exceeds the maximum estimated fiber strain of 1.2% (871 MPa tensile stress). Furthermore this demonstration of embedded fibers that can survive high temperatures and remain bonded to the metal matrix is the first step toward embedded fiber optic sensors for harsh environment applications.
Embedded Sensor Development in Metallic Structures for the Transformational Challenge Reactor
The ability to make minimally intrusive measurements of process conditions has tremendous potential for improving system performance and control in applications such as nuclear power generation. Towards this end, emerging and evolving advanced manufacturing methods, such as additive manufacturing, present new opportunities for more seamlessly integrating sensing with structure. This technical report summarizes the progress of work performed to assess the feasibility of embedding commercial off-the-shelf (COTS) sensors in a metallic reactor core using advanced manufacturing methods. The progress of four research and development tasks are documented: 1) A survey of COTS sensors for nuclear applications that are candidates for embedded fabrication, 2) Development of a conceptual framework for investigating the feasibility of sensor embedment, 3) Definition of structural geometries and other characteristics that will represent compelling proof-of-concept, and 4) Preliminary prototyping of embedded sensors. For the purposes of this initial study, nuclear grade K-type thermocouples were selected for investigation of embedment methodologies. This sensor was selected as an initial candidate because it represents one of the simplest sensor configurations that can provide useful process information. A selective laser melting (SLM) additive manufacturing process was used to fabricate structures with complexity representative of the core design of the transformational challenge reactor (TCR) and methods were developed to embed a thermocouple with a complex two-dimensional routing path. There are many challenges associated with embedding sensors during the additive manufacturing process including securing the sensor in the structure, relocating the part in the additive machine if using a “pick and place” sensor placement method, mitigating the potential for powder contamination, optimizing energy deposition parameters to build as closely as possible around the sensor path and improve structural integrity of the part, and tuning energy deposition to mitigate thermally induced warpage of the sensor and part as well as potential for damaging the sensing device. Preliminary results indicate that it is feasible to integrate the sensor while minimally compromising the structural integrity of the part and preserving sensor performance. This first phase of this work focused on developing a workflow for embedding sensors and controlling energy deposition during the additive manufacturing process to better understand the build characteristics around the sensor. Future work will perform more in-depth characterization of prototype parts using X-ray computed tomography and scanning electron microscopy to better understand fabricated structures, performance testing of embedded sensors in high temperature environments, adding new embedded measurement modalities, embedding devices with dissimilar materials in contact with additive powders, and the development of methods for embedding sensors with three-dimensional routing paths.
In situ embedment of type K sheathed thermocouples with directed energy deposition
Advanced nuclear reactor systems require new technologies for heat transfer and system monitoring. Additive manufacturing (AM) offers the design flexibility to allow in-situ sensor embedment through smart manufacturing for real-time monitoring, and performance of these systems. Here, this study focuses on experiments investigating the feasibility of in-situ sensor embedment using directed energy deposition (DED). Type K thermocouples are embedded into 316L stainless steel (SS) samples using two different configurations (e.g., exposed and embedded tips) and two designs (e.g., flush to substrate) within an AM base. Embedded sensor samples are analyzed via in-situ measurements and high-temperature performance validation tests at 350ºC and 900ºC. Temperature performance results at both temperature tests show good agreement with manufacturer specifications proving that these sensors could still capture accurate temperature readings after in-situ embedment during DED processing. An additional optimization experiment was conducted on the exposed tip configuration using a surrogate thermocouple to improve tolerances and the embedment process. Results improved tolerances, lower porosity, smaller gaps between the sensor and base, and better junction contact for the sensor. Although further optimization of this embedment strategy is necessary to improve the structural stability and tolerances within the component, this research strategy provides a proof-of-feasibility for DED embedment with commercial sheathed thermocouples. This research provides early impact on embedment of sensor for multiple materials and complex geometric components..
Benchmarking an Embedded Adaptive Sampling Configuration Interaction Method for Surface Reactions: H 2 Desorption from and CH 4 Dissociation on Cu(111)
Embedded (emb-) correlated wavefunction (CW) theory enables accurate assessments of both ground- and excited-state reaction mechanisms involved in heterogeneous catalysis. Embedded multireference second-order perturbation theory (emb-MRPT2) based on reference wavefunctions generated via embedded complete active space self-consistent field (emb-CASSCF) theory is currently state-of-the-art. However, the factorial scaling of CASSCF limits the size of active space and the complexity of systems that can be studied. In this work, we assess the efficacy of an alternative CW method, adaptive sampling configuration interaction (ASCI)–which enables large active spaces to be used–for studying surface reactions. We couple ASCI with density functional embedding theory (DFET) and benchmark its performance for two reactions: H 2 desorption from and CH 4 dissociation on the Cu(111) surface. Unlike embedded complete active space second-order perturbation theory (emb-CASPT2) that accurately reproduces a measured H 2 desorption barrier, embedded ASCI, using a very large active space (though one that still comprises a small portion of the full set of orbitals) fails to do so. Adding an extra correlation term from embedded Møller–Plesset second-order perturbation theory (emb-MP2) improves the desorption barrier and endothermicity predictions. Thus, the inaccuracy of embedded ASCI comes from the missing dynamic correlation from the many other electrons and orbitals not included in the active space. For CH 4 dissociation, again embedded ASCI overestimates the dissociation barrier compared to emb-CASPT2 predictions. Adding dynamic correlation from emb-MP2 helps correct the barrier. However, this composite approach suffers from double counting of correlation within embedded ASCI followed by emb-MP2 calculations. We therefore conclude that the state-of-the-art emb-MRPT2 based on reference wavefunctions generated via emb-CASSCF remains the method of choice for studying surface reactions. emb-ASCI is useful when large active spaces beyond the limit of emb-CASSCF are essential, such as to study complex surface reactions with significant multiconfigurational character (static correlation) but weak dynamic correlation.
Replacing non-biomedical concepts improves embedding of biomedical concepts
Embeddings are semantically meaningful representations of words in a vector space, commonly used to enhance downstream machine learning applications. Traditional biomedical embedding techniques often replace all synonymous words representing biological or medical concepts with a unique token, ensuring consistent representation and improving embedding quality. However, the potential impact of replacing non-biomedical concept synonyms has received less attention. Embedding approaches often employ concept replacement to replace concepts that span multiple words, such as non-small-cell lung carcinoma, with a single concept identifier (e.g., D002289). Also, all synonyms of each concept are merged into the same identifier. Here, we additionally leveraged WordNet to identify and replace sets of non-biomedical synonyms with their most common representatives. This combined approach aimed to reduce embedding noise from non-biomedical terms while preserving the integrity of biomedical concept representations. We applied this method to 1,055 biomedical concept sets representing molecular signatures or medical categories and assessed the mean pairwise distance of embeddings with and without non-biomedical synonym replacement. A smaller mean pairwise distance was interpreted as greater intra-cluster coherence and higher embedding quality. Embeddings were generated using the Word2Vec algorithm applied to a corpus of 10 million PubMed abstracts. Our results demonstrate that the addition of non-biomedical synonym replacement reduced the mean intra-cluster distance by an average of 8%, suggesting that this complementary approach enhances embedding quality. Future work will assess its applicability to other embedding techniques and downstream tasks. Python code implementing this method is provided under an open-source license.
Embedding Sensors in 3D Printed Metal Structures
The Transformational Challenge Reactor (TCR) program is leveraging recent advances in modeling and simulation, materials, and additive manufacturing (AM) technologies to design a modern nuclear reactor. Some of the main TCR technologies include in situ monitoring and the integration of sensors during the manufacturing of quality-significant nuclear reactor components. This report describes the general procedure and process optimization for embedding sensors within generic stainless steel 316 (SS316) components using laser powder bed fusion (LPBF). A more detailed, quality-significant test plan and supporting procedures are available upon request (ORNL/TM-2021/2127). LPBF involves the use of a scanning laser to selectively melt regions of a powder bed, additively building a part layer by layer. This report describes the LPBF processing technique and discusses the effects of LPBF processing parameters on the success of the sensor embedding process. Experiments used machined cavities in the form of channels in an SS316 base for the sensors to lay in while material is additively built over the top, thereby embedding them in an SS316 matrix. A preliminary investigation involved using empty SS316 sheaths as surrogates to explore the effects of various LPBF processing parameters and the dimensional requirements of the machined channels. Microstructural investigations showed that a smaller channel width/depth combination closer to the sensor’s diameter was best for the embedding process. After the desired parameters were selected, Type-K thermocouples were embedded and evaluated post-embedding using nondestructive thermal testing, as well as destructive sectioning and microscopy. Post-build characterization showed that the thermocouples were well-bonded to the SS316 matrix and were fully functional after embedding. During thermal testing to temperatures up to 500 °C, the embedded thermocouples read consistently with one another and deviated only slightly from the readings of a nonembedded thermocouple located within the furnace. This slight discrepancy was most likely due to differences in the thermal time constants for a nonembedded thermocouple vs. a thermocouple embedded in a solid SS316 block. The results presented in this report will serve as the foundation for future work that will focus on embedding sensors in relevant TCR reactor components and eventually testing those components under neutron irradiation.
Effect of Embedded Piezoelectric Sensors on Fracture Toughness and Fatigue Resistance of Composite Laminates Under Mode I Loading
Double-cantilevered beam (DCB) specimens of a glass/epoxy composite material with embedded piezoelectric sensors were tested both statically and under fatigue loading to determine the effect of the embedded material on the Mode I fracture toughness and fatigue resistance compared to baseline data without the embedded elements. A material known as LaRC-Macrofiber Composite (LaRC-MFC (TradeMark)), or MFC, was embedded at the midplane of the specimen during the layup. Specimens were manufactured with the embedded MFC material either at the loaded end of the specimen to simulate an initial delamination; or with the MFC material located at the delaminating interface, with a Teflon film at the loaded end to simulate an initial delamination. There were three types of specimens with the embedded material at the delaminating interface: co-cured with no added adhesive; cured with a paste adhesive applied to the embedded element; or cured with a film adhesive added to the embedded material. Tests were conducted with the sensors in both the passive and active states. Results were compared to baseline data for the same material without embedded elements. Interlaminar fracture toughness values (G(sub Ic)) for the passive condition showed little change when the MFC was at the insert end. Passive results varied when the MFC was at the delaminating interface. For the co-cured case and with the paste adhesive, G(sub Ic) decreased compared to the baseline toughness, whereas, for the film adhesive case, G(sub Ic) was significantly greater than the baseline toughness, but the failure was always catastrophic. When the MFC was in the active state, G(sub Ic) was generally lower compared to the passive results. Fatigue tests showed little effect of the embedded material whether it was active or passive compared to baseline values.
Learning Canonical Embeddings for Unsupervised Shape Correspondence With Locally Linear Transformations
We present a new approach to unsupervised shape correspondence learning between pairs of point clouds. We make the first attempt to adapt the classical locally linear embedding algorithm (LLE)-originally designed for nonlinear dimensionality reduction-for shape correspondence. The key idea is to find dense correspondences between shapes by first obtaining high-dimensional neighborhood-preserving embeddings of low-dimensional point clouds and subsequently aligning the source and target embeddings using locally linear transformations. We demonstrate that learning the embedding using a new LLE-inspired point cloud reconstruction objective results in accurate shape correspondences. More specifically, the approach comprises an end-to-end learnable framework of extracting high-dimensional neighborhood-preserving embeddings, estimating locally linear transformations in the embedding space, and reconstructing shapes via divergence measure-based alignment of probability density functions built over reconstructed and target shapes. Our approach enforces embeddings of shapes in correspondence to lie in the same universal/canonical embedding space, which eventually helps regularize the learning process and leads to a simple nearest neighbors approach between shape embeddings for finding reliable correspondences. Comprehensive experiments show that the new method makes noticeable improvements over state-of-the-art approaches on standard shape correspondence benchmark datasets covering both human and nonhuman shapes.
Parallel Embeddings: a Visualization Technique for Contrasting Learned Representations
We introduce ``Parallel Embeddings'', a new technique that generalizes the classical Parallel Coordinates visualization technique from a sequence of features within a single matrix to a sequence of multiple feature matrices. This is accomplished by separately embedding each matrix in the sequence into a 2-D frame, juxtaposing these 2-D representations, then connecting points between frames. We outline how this visualization can be used for several ``model comparison'' tasks in machine learning. We compare user performance with Parallel Embeddings to a baseline using the TensorFlow Embedding Projector for estimating model accuracy and understanding conceptual model differences. We found that users were more accurate with Parallel Embeddings for model comparison and that users learned how to use Parallel Embeddings more quickly than TensorFlow Embedding Projector. Furthermore, users' analytical process using Embedding Projector was positively affected by using Parallel Embeddings beforehand.
Performance of Embedded Sensors in 3D Printed SiC
This report summarizes recent advances in embedding sensors in 3D printed silicon carbide (SiC) ceramic components under the Transformational Challenge Reactor (TCR) program. The additive manufacturing technologies developed under this program will enable fabrication of complex structures with embedded fuels and sensors. The sensors will be capable of characterizing fuel performance using spatially distributed measurements at the most strategic locations that would be otherwise inaccessible using conventional manufacturing techniques. While previous programmatic updates describe initial concepts for embedding sensors, materials selection, and initial characterization of the embedded sensors, the technology requires further demonstration, and quality-significant procedures must be established before the embedding technology is ready for adoption by industry. To this end, this report describes the most effective techniques that have been used to embed functional sensors in 3D printed components using a combination of binder-jet additive manufacturing and chemical vapor infiltration (CVI). A detailed procedure describes each step in the process and is available upon request. Molybdenum (Mo)-sheathed thermocouples have been successfully embedded in complex SiC components, and temperatures were monitored in situ during the embedding process. Post-embedding measurements showed no significant hysteresis, and characterization of the interface revealed qualitatively strong bonding around the entire perimeter of the sensor sheath. Distributed fiber-optic temperature sensors were able to briefly measure temperature profiles during CVI, but they ultimately failed prior to completion of the CVI run. The failure appears to be related to the fiber coating at temperatures close to 1,000°C. Future work will focus on irradiation testing of embedded thermocouples and other sheathed electrical sensors, as well as the identification of fiber-optic sensor coatings that can survive CVI.
Laser-assisted embedding of all-glass optical fiber sensors into bulk ceramics for high-temperature applications
We develop a laser-assisted sensor embedding process to embed all-glass optical fiber sensors into bulk ceramics for high-temperature applications. A specially designed two-step microchannel was fabricated on an Al 2 O 3 substrate for sensor embedment using a picosecond (ps) laser. An optical fiber Intrinsic Fabry-Perot Interferometer (IFPI) sensor was embedded at the bottom of the microchannel and covered by Al 2 O 3 slurry which was subsequently sintered by a CO 2 laser. The sensor spectrum was in-situ monitored during the laser sintering process to ensure the survival of the sensor and optimize the laser sintering parameters. By testing in furnace through high temperature, the embedded optical fiber shows improved stability after CO 2 laser sealing, resulting in the linear temperature response of the embedded optical fiber IFPI sensor. To improve the embedded IFPI sensor for thermal strain measurement, a dummy fiber was co-embedded with the sensing fiber to improve the mechanical bonding between the sensing fiber and the ceramic substrate so that the thermal strain of the ceramic substrate can apply on the sensing fiber. The response sensitivity, measurement repeatability and high-temperature long-term stability of the embedded optical fiber IFPI sensor were evaluated in this work.
4-Clique network minor embedding for quantum annealers
Quantum annealing is a quantum algorithm for computing solutions to combinatorial optimization problems. This study proposes a method for minor embedding optimization problems onto sparse quantum annealing hardware graphs called 4-clique network minor embedding. This method is in contrast to the standard minor embedding technique of using a path of linearly connected qubits in order to represent a logical variable state. The 4-clique minor embedding is possible on Pegasus graph connectivity, which is the native hardware graph for some of the current D-Wave quantum annealers. The Pegasus hardware graph contains many cliques of size 4, making it possible to form a graph composed entirely of paths of connected 4-cliques on which a problem can be minor-embedded. The 4-clique chains come at the cost of additional qubit usage on the hardware graph, but they allow for stronger coupling within each chain, thereby increasing chain integrity, reducing chain breaks, and allow for greater usage of the available energy scale for programming logical problem coefficients on current quantum annealers. The 4-clique minor embedding technique is compared with the standard linear path minor embedding with experiments on two D-Wave quantum annealing processors with Pegasus hardware graphs. We show proof-of-concept experiments where the 4-clique minor embeddings can use weak chain strengths while successfully carrying out the computation of minimizing random all-to-all spin glass problem instances. Published by the American Physical Society 2024
Demonstrate embedding of sensors in a relevant microreactor component
This report describes the first successful embedding of sensors in stainless steel pipe specimens and a miniature hex block to support structural health monitoring of microreactor components during electrically heated testing in non-nuclear testbed facilities. Sensors were embedded with an ultrasonic additive manufacturing process that uses a combination of downward pressure and an ultrasonic scrubbing motion to bond stainless steel foils to underlying materials. After placing sensors within cavities that have been machined to the size of the sensors, the ultrasonic bonding process fills the gaps around the sensors and embeds them within the part. Both Type K thermocouples and spatially distributed fiber-optic strain sensors were successfully embedded within two pipe specimens and a miniature hex block. After the fiber-optic sensors were embedded, they were interrogated and found to have minimal signal attenuation within the embedded region—a significant improvement compared to previous trials. This is likely because of the low-bend-loss fiber that was used, which greatly reduces microbending losses that occur after the embedding process. In addition to showing minimal signal attention, the fibers also showed adequate compressive strain, which is a strong indication that the sensors are physically embedded in the parts as opposed to simply being loosely contained inside the machined cavities. The embedded fibers were able to capture the strain induced in one of the pipe specimens while the pipe was actively heated with a moving heat source.
Characterization of Embedded Sensors in Stainless Steel Test Articles and Design/Planning for MAGNET Testing
The nuclear industry is pursuing microreactors that can be factory assembled and deployed to remote regions for reliable power generation. One class of microreactors uses a monolithic metal core block coupled to heat pipes for heat rejection, which results in significant thermal stresses in the monolithic structures. This work describes the initial characterization and test plan for evaluating stainless steel test articles fabricated with embedded sensors for measuring heat pipe performance limits, as well as spatially distributed temperatures and strains during electrically heated thermal testing. The electrically heated testing will be performed in the non-nuclear Microreactor Agile Non-Nuclear Testbed and Single Primary Heat Extraction and Removal Emulator facilities located at Idaho National Laboratory. The goals of these tests are to (1) accurately monitor temperature and strain distributions that result from differential thermal expansion in the test articles and (2) quantify heat rejection limits of heat pipes as a function of operating temperature and working fluid during steady-state and transient operations. More generally, the ability to monitor component and system health during microreactor operation is attractive for providing a high sensor density to inform a limited number of microreactor operators to ultimately reduce operation and maintenance costs and move toward semi-autonomous operation. This report discusses the characterization of embedded thermocouples and fiber optic sensors in relevant test articles, including cylindrical pipes and hexagonal monolithic test articles for heat pipe-based reactors. The sensors were embedded by placing them in machined channels and then building up additional material by using ultrasonic additive manufacturing (UAM). UAM is a solid-state welding process that uses downward pressure and a lateral scrubbing motion to bond thin metal foils to a base material layer by layer. The ultrasonic welding process relies on the plastic deformation of the metal—as opposed to typical melting and solidification—to break oxide scales and bond the metal layers. The characterization of these embedded sensors included evaluating fiber optic signal attenuation, observing residual strain in the fibers, investigating microstructural and mechanical aspects, and demonstrating the sensors under various thermal loads and acoustic vibrations. Post-embedding characterization showed a fine grain structure (<1 μm) near the interfaces of the bonded foils as a result of severe deformation from the welding process. A large increase in hardness was observed at the foil interfaces and the fiber/matrix interface compared with the bulk matrix. Even when compared with the SS304 interfaces, the higher hardness observed around the embedded fiber suggests a higher degree of deformation due to the soft metal coating around the silica fiber core. The distributed fiber-optic temperature sensors and embedded thermocouples reliably measured temperature distributions during steady-state and transient thermal testing. The embedded fiber-optic sensors reliably measured strain during both transient and steady-state testing and properly identified resonant frequencies during acoustic testing.
Efficiently embedding QUBO problems on adiabatic quantum computers
Adiabatic quantum computers like the D-Wave 2000Q can approximately solve the QUBO problem, which is an NP-hard problem, and have been shown to outperform classical computers on several instances. Solving the QUBO problem literally means solving virtually any NP-hard problem like the traveling salesman problem, airline scheduling problem, protein folding problem, genotype imputation problem, thereby enabling significant scientific progress, and potentially saving millions/billions of dollars in logistics, airlines, healthcare and many other industries. Yet, before QUBO problems are solved on quantum computers, they must be embedded (or compiled) onto the hardware of quantum computers, which in itself is a very hard problem. Here, we propose an efficient embedding algorithm, that lets us embed QUBO problems fast, uses less qubits and gets the objective function value close to the global minimum value. We then compare the performance of our embedding algorithm to that of D-Wave’s embedding algorithm, which is the current state of the art, and show that our embedding algorithm convincingly outperforms D-Wave’s embedding algorithm. Our embedding approach works with perfect Chimera graphs, i.e., Chimera graphs with no missing qubits.
Mixed Delay/Nondelay Embeddings Based Neuromorphic Computing with Patterned Nanomagnet Arrays
Patterned nanomagnet arrays (PNAs) have been shown to exhibit a strong geometrically frustrated dipole interaction. Some PNAs have also shown emergent domain wall dynamics. Previous works have demonstrated methods to physically probe these magnetization dynamics of PNAs to realize neuromorphic reservoir systems that exhibit chaotic dynamical behavior and high-dimensional nonlinearity. These PNA reservoir systems from prior works leverage echo state properties and linear/nonlinear short-term memory of component reservoir nodes to map and preserve the dynamical information of the input time-series data into nondelay spatial embeddings. Such mappings enable these PNA reservoir systems to imitate and predict/forecast the input time series data. However, these prior PNA reservoir systems are based solely on the nondelay spatial embeddings obtained at component reservoir nodes. As a result, they require a massive number of component reservoir nodes, or a very large spatial embedding (i.e., high-dimensional spatial embedding) per reservoir node, or both, to achieve acceptable imitation and prediction accuracy. These requirements reduce the practical feasibility of such PNA reservoir systems. To address this shortcoming, we present a mixed delay/nondelay embeddings-based PNA reservoir system. Our system uses a single PNA reservoir node with the ability to obtain a mixture of delay/nondelay embeddings of the dynamical information of the time-series data applied at the input of a single PNA reservoir node. Our analysis shows that when these mixed delay/nondelay embeddings are used to train a perceptron at the output layer, our reservoir system outperforms existing PNA-based reservoir systems for the imitation of NARMA 2, NARMA 5, NARMA 7, and NARMA 10 time series data, and for the short-term and long-term prediction of the Mackey Glass time series data.