Knowledge Of Configuration Research Articles

Estimation of gas hold-up in bubble columns using wall pressure fluctuations and machine learning

We present a novel approach to estimate gas hold-up in bubble columns using wall pressure fluctuations – without requiring knowledge of operating flow regime, column configuration or physical properties. The approach uses machine learning and pressure fluctuations acquired from a wall mounted pressure sensor. The approach is validated by carrying out experiments with different physical properties of liquid (deionised water, deionised water – alcohol [ethanol, propanol and butanol] mixture up to 2 % alcohol, deionised water – glycerine (30 %), tap water). The majority of the data was obtained with 0.1 m diameter bubble column. Data with tap water in this column was obtained for four different spargers. Data with tap water was also obtained for 0.15 m and 0.33 m diameter bubble columns. Gas velocity was varied up to 0.1 m/s. The covered physical properties, sparger configurations, column diameter and gas velocities span different flow regimes. An artificial neural network (ANN) based model was developed to relate characteristics of wall pressure fluctuations and superficial gas velocity to the gas hold-up. The approach was validated by comparing predicted results with the experimental data unseen by the ANN model. The approach demonstrates the feasibility of using wall pressure fluctuations with machine learning to estimate key characteristics without prior knowledge of column configuration, flow regimes or physical properties.

Accuracy of Cone-beam Computed Tomography in diagnosing root canal configuration: a literature review

Objectives: This review article aims to describe the accuracy of cone-beam computed tomography (CBCT) in diagnosing root canal configuration. Review: This study is a literature review consisting of English articles about the accuracy of cone-beam computed tomography in diagnosing root canal configuration, published in 2013 – 2023. The article search databases used were Pubmed and Science Direct with the keyword “(cone-beam computed tomography[MeSH Terms]) AND (configuration, root canal[MeSH Terms]).” The selected articles were screened by checking the publication year, duplicating articles, reading the titles and abstracts, and the entire article's contents. The total search results for articles based on keywords obtained were 205 and only seven were included. In order to successfully perform root canal treatment, thorough knowledge of the root canal configuration is essential. Cone-beam computed tomography (CBCT) can improve our understanding of root canal configuration. The development of CBCT has brought to light the disadvantages of conventional radiography, which include the compression of three-dimensional anatomy, geometric distortion, and anatomical noise. Conclusion: Radiology is essential in treatment planning, disease monitoring, and assessmen t of treatment outcomes. The development of cone-beam computed tomography (CBCT) offers three-dimensional accuracy with a reasonable cost, no geometric distortion and anatomical noise, and the ability to create cross-sectional images, revolutionizing the imaging of dentomaxillofacial structures. This imaging system has been shown to overcome some of the limitations of conventional radiography.

Root anatomy and canal configuration of human permanent maxillary third molar - systematic review.

Knowledge of the root canals configuration is essential for the success of endodontic treatment. The main aim of the systematic review is to determine the number of roots and the number of root canals in maxillary third molars, in addition, where possible, to determine the Vertucci classification. This systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement guidelines. The study protocol was registered and approved on the International Prospective Register of Systematic Reviews PROSPERO (Reg. No: CRD42022366444) before the start of the study. Twelve studies were included in the analysis, differing in sample origin and methodology. The combined studies were analyzed based on the number of roots, number of canals, and root canal configurations, and the findings were compared with those of other international studies. Analyzing the available research results regarding the root anatomy and canal configuration of the third maxillary molar, the most commonly maxillary third molars had 3 roots (59.00%). Single-rooted teeth (24.20%) or double-rooted teeth (13.80%) were less common. In addition, it was observed that maxillary third molars typically possessed three root canals (47.28%) and the MB (mesiobuccal), DB (distobuccal), and P (palatal) canals most often showed Vertucci Type I (59.53%, 95.83% and 98.61%, respectively) in three-rooted form. Due to the small number of available studies, it is necessary to conduct further analyses taking into account demographic and ethnic differences that may affect the anatomical and morphological structure of the teeth.

High-throughput investigation of stability and Li diffusion of doped solid electrolytes via neural network potential without configurational knowledge

Solid electrolytes hold substantial promise as vital components of all-solid-state batteries. Enhancing their performance necessitates simultaneous improvements in their stability and lithium conductivity. These properties can be calculated using first-principles simulations, provided that the crystal structure of the material and the diffusion pathway through the material are known. However, solid electrolytes typically incorporate dopants to enhance their properties, necessitating the optimization of the dopant configuration for the simulations. Yet, performing such calculations via the first-principles approach is so costly that existing approaches usually rely on predetermined dopant configurations informed by existing knowledge or are limited to systems doped with only a few atoms. The proposed method enables the optimization of the dopant configuration with the support of neural network potential (NNP). Our approach entails the use of molecular dynamics to analyze the diffusion after the optimization of the dopant configuration. The application of our approach to Li10\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${_{10}}$$\\end{document}MP2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${_{2}}$$\\end{document}S12-x\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${_{12-x}}$$\\end{document}Ox\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${_{x}}$$\\end{document} (M = Ge, Si, or Sn) reproduce the experimental results well. Furthermore, analysis of the lithium diffusion pathways suggests that the activation energy of diffusion undergoes a percolation transition. This study demonstrates the effectiveness of NNPs in the systematic exploration of solid electrolytes.

Fully automatic online geometric calibration for non-circular cone-beam CT orbits using fiducials with unknown placement.

Cone-beam CT (CBCT) with non-circular scanning orbits can improve image quality for 3D intraoperative image guidance. However, geometric calibration of such scans can be challenging. Existing methods typically require a prior image, specialized phantoms, presumed repeatable orbits, or long computation time. We propose a novel fully automatic online geometric calibration algorithm that does not require prior knowledge of fiducial configuration. The algorithm is fast, accurate, and can accommodate arbitrary scanning orbits and fiducial configurations. The algorithm uses an automatic initialization process to eliminate human intervention in fiducial localization and an iterative refinement process to ensure robustness and accuracy. We provide a detailed explanation and implementation of the proposed algorithm. Physical experiments on a lab test bench and a clinical robotic C-arm scanner were conducted to evaluate spatial resolution performance and robustness under realisticconstraints. Qualitative and quantitative results from the physical experiments demonstrate high accuracy, efficiency, and robustness of the proposed method. The spatial resolution performance matched that of our existing benchmark method, which used a 3D-2D registration-based geometric calibrationalgorithm. We have demonstrated an automatic online geometric calibration method that delivers high spatial resolution and robustness performance. This methodology enables arbitrary scan trajectories and should facilitate translation of such acquisition methods in a clinical setting.

INFORMEDQX: Informed Conflict Detection for Over-Constrained Problems

Conflict detection is relevant in various application scenarios, ranging from interactive decision-making to the diagnosis of faulty knowledge bases. Conflicts can be regarded as sets of constraints that cause an inconsistency. In many scenarios (e.g., constraint-based configuration), conflicts are repeatedly determined for the same or similar sets of constraints. This misses out on the valuable opportunity for leveraging knowledge reuse and related potential performance improvements, which are extremely important, specifically interactive constraint-based applications. In this paper, we show how to integrate knowledge reuse concepts into non-instructive conflict detection. We introduce the InformedQX algorithm, which is a reuse-aware variant of QuickXPlain. The results of a related performance analysis with the Linux-2.6.3.33 configuration knowledge base show significant improvements in terms of runtime performance compared to QuickXPlain.

Formation of a-b twin induced by tension in Ni-Mn-Ga magnetic shape memory alloys

Deformation of twinned martensite can effectively reformulate the variant configuration as well as the inter-variant correlation. In this work, the deformed microstructure of 7M martensite induced by tension were examined in a polycrystalline Ni50Mn30Ga20 alloy prepared by means of directional solidification. The uniaxial tensile loading applied along the solidification direction triggers the collective variant reorientation in the horizontal variant colonies, transforming four initial variants of a-c twin with self-accommodation into four differently oriented variants in b-c twin relation. Moreover, another four new variants can be induced by the variant penetration from an inclined variant colony into the reoriented variant region. Notably, the newly formed variants develop the a-c twin and a-b twin relation with the adjacent reoriented variants, thereby constituting a complicated microstructure covering a-c twin, a-b twin and b-c twin. Through further detwinning to eliminate a-c twin and b-c twin, the mixed three types of twins finally evolve into the simplified variant configuration including only a-b twin in the local region. This work advances the knowledge of variant configuration induced by deformation and contributes to the insights into martensite deformation behavior as well as twinning system evolution in Ni-Mn-Ga based magnetic shape memory alloys.

A mathematical model describing an unsteady leak of compressed air from an open underwater storage tank

A new mathematical model is developed here to predict the discharge dynamics of compressed air from a massive leak occurring at the top of a submerged storage tank with an original bottom opening. The model represents a transient leak due to variations in the air volume and air pressure remaining inside the tank using a mass balance equation and the compressible Bernoulli equation. A first-order-non-linear ordinary differential equation is solved in terms of the air height inside the reservoir for different tank geometries: a right circular cylinder and a remaining combined with a hemisphere of the same radius to form a bell. The total discharge time is obtained by analytical integration. The model is then applied to a case study in which the amount of air is fixed, and the investigated parameters are the immersion depth (ranging from 75 to 200 m) and the radius of the storage tanks (5 or 7.5 m) on the discharge time. Finally, a representative steady rate is given based on the average discharge rate in order to rapidly estimate the discharge time without further knowledge of the storage tank configuration. The immersion depth has no influence in the discharge time of a cylindrical tank, and a wide tank causes a longer discharge than a narrow one. It has also been shown that, in the range of initial air height considered (close to ten meters), the variation of density can be neglected in the model for the cylindrical geometry, and for the bell geometry provided that the ratio radius-to-initial height remains low.

Impacts of landscape pattern on plants diversity and richness of 20 restored wetlands in Chaohu Lakeside of China

The recovery of wetland function and biodiversity conservation aroused considerable interest in the past decades. Although many advances have been achieved in revealing disturbing factors on plants diversity, the knowledge of biodiversity manipulation, landscape configuration and ecosystem process in restored wetlands remains incomplete. To address this issue, the landscape of 20 restored wetlands' vegetation was classified into five vegetation formations including: upland plants, wet grassland, emergent plants, floating plants and submerged plants. Meanwhile, the configuration of landscape, plants' function traits and the structure of plants communities of each wetland were analyzed. A total of 142 herbaceous plants were identified from 399 samples of 20 lakeside wetlands. The top five predominant species were Typha orientalis, Alternanthera philoxeroides, Phragmites australis, Echinochloa caudata, and Erigeron canadensis. The highest of diversity index was observed in upland plants with Shannon-Wiener index (H) of 0.92 while higher richness of plants was obtained in wet grassland with species of 88. In dry year, the immigration of upland xerophyte and obligated aquatic species to facultative area increased the biodiversity of the ecotone. Meanwhile, this change may also aggravate the diffusion risk of exotic invasive species Erigeron canadensis. Additionally, the results indicated that number and evenness of landscape outweighed Shannon diversity index (SHDI) of wetlands in shaping the richness and diversity of wetland plants. Whereas, the high value of maximum proportion of landscape (Pmax) have reduced the landscape evenness and species richness. A suggested Pmax of <0.5 was benefit for the stability and biodiversity of restored wetlands.

Assessing Spatial Knowledge and Mental Map Development Under Virtual Training Conditions

Mental maps are the core of wayfinding because they contain representations of point, route, and configuration related spatial knowledge. Currently, methods spatial knowledge do not clearly separate these theoretically disparate facets. The purpose of this research is to examine the relationships between point-related, route-related, and configuration-related spatial knowledge tests administered to participants in the context of training to comprehend a virtual environment. Results indicated that measures which are often interchanged under the assumption that they are reflective of spatial knowledge may in fact measure different and unrelated constructs. Futher, analyses showed that measures that are commonly used to tap point-related and route-related knowledge may have different influences on the development of configuration knowledge, and little to none on the ability for individuals to leverage their holistic mental map for wayfinding.

Advanced Diagnostic Approach for High-Voltage Insulators: Analyzing Partial Discharges through Zero-Crossing Rate and Fundamental Frequency Estimation of Acoustic Raw Data

Acoustic inspection is a valuable technique that can detect early stage defects in equipment, thereby facilitating predictive maintenance. In recent times, ultrasonic sensors have made detecting partial discharges through acoustic sensing increasingly feasible. However, interpreting the acoustic signals can pose challenges, as it requires extensive expertise and knowledge of equipment configuration. To address this issue, a technique based on zero-crossing rate and fundamental frequency estimation has been proposed to standardize insulator diagnosis. In an experiment involving a database of 72 raw acoustic signals with frequencies ranging from 0 to 128 kHz, various types of pollution and defects were introduced to a chain of insulators. By employing the proposed technique, the occurrence of partial discharges can be detected and classified according to type, such as corona or surface discharges. This advanced approach to diagnosis simplifies the process while providing valuable insights into the severity of observed phenomena in the field.

Augmented reality landmarks on windshield and their effects on the acquisition of spatial knowledge in autonomous vehicles

ABSTRACT Autonomous vehicles, which free drivers from driving, are gaining increasing interest for future travel needs. But the degradation of driver’s spatial knowledge will likely worsen when drivers no longer need to actively steer nor pay attention to the environment. This study extends the theory of visualising distant landmarks on mobile phone to windshield using Augmented Reality (AR), to support spatial learning. This study investigates the impact of AR distant landmarks (with vs. without AR landmarks) and road conditions (highway vs. local road) on acquiring spatial knowledge through an experiment using simulated videos of autonomous driving. Participants are randomly assigned to one of two scenarios to complete tasks which assessed their acquired spatial knowledge one the route-, directional, and configural levels. Results show that distant landmarks enhance the efficiency of acquiring route- and directional knowledge, although the effectiveness of acquiring route knowledge with AR landmarks is not significant on local road. Configurational knowledge is more likely impacted by the road type instead of the AR landmarks. The results indciate the necessity of carrying out follow-up studies on symbolising additional information in AR landmarks for supporting spatial learning and evaluate their impacts on the spatial knowledge at the configurational level.

Multi-Person Pose Estimation in the Wild: Using Adversarial Method to Train a Top-Down Pose Estimation Network

Recent studies estimate human anatomical key points through the single monocular image, in which multichannel heatmaps are the key factor in determining the quality of human pose estimation. Multichannel heatmaps can efficiently handle the image-to-coordinate mapping task and the processing of semantic features. Most methods ignore physical constraints and internal relationships of human body parts, which easily misclassify left and right symmetrical parts as similar features. Some studies use RNNs on the top to incorporate priors about the structure of pose components and body configuration. Therefore, a novel top-down convolutional network is proposed to consider these priors during training, which can improve the robustness under complex field conditions in the wild. In order to learn the prior knowledge of human pose configuration, the hierarchy of fully convolutional networks (discriminator) is used to distinguish real poses from fake ones. Consequently, the pose network is inclined to make a pose estimation that the discriminator misjudges as true, which is reasonable in complex situations. The performance of the method is experimentally validated by pose estimation on the MS COCO human key point detection task. The proposed approach outperforms the original method and generates robust pose predictions, demonstrating efficiency by using adversarial learning.

FASTDIAGP: An Algorithm for Parallelized Direct Diagnosis

Constraint-based applications attempt to identify a solution that meets all defined user requirements. If the requirements are inconsistent with the underlying constraint set, algorithms that compute diagnoses for inconsistent constraints should be implemented to help users resolve the “no solution could be found” dilemma. FastDiag is a typical direct diagnosis algorithm that supports diagnosis calculation without pre-determining conflicts. However, this approach faces runtime performance issues, especially when analyzing complex and large-scale knowledge bases. In this paper, we propose a novel algorithm, so-called FastDiagP, which is based on the idea of speculative programming. This algorithm extends FastDiag by integrating a parallelization mechanism that anticipates and pre-calculates consistency checks requested by FastDiag. This mechanism helps to provide consistency checks with fast answers and boosts the algorithm’s runtime performance. The performance improvements of our proposed algorithm have been shown through empirical results using the Linux-2.6.3.33 configuration knowledge base.

Analysis of Extreme Precipitation Events in the Mountainous Region of Rio de Janeiro, Brazil

Extreme rainfall events cause diverse loss of life and economic losses. These disasters include flooding, landslides, and erosion. For these intense rainfall events, one can statistically estimate the time when a given rainfall volume will occur. Initially, this work estimated rainfall volumes for the mountainous region of Rio de Janeiro, and the frequency with which rainfall events occur. For this, we analyzed daily precipitation data using the ANOBES method and the Gumbel statistical distribution to estimate return times. Extreme prec’ipitation volumes of up to 240 mm per day were identified in some locations, with 100 years or more return periods. On 11 January 2011 precipitation volumes were high, but on 12 January they were extreme, similar to the 100-year return time data. The analysis method presented enables the determination of the return time of heavy rainfall, assisting in the prevention of its effects. Knowledge of the atmospheric configuration enables decision support. The atmospheric systems that combined to cause the event were local circulations (orographic and sea breeze) and large-scale systems (SACZ and frontal systems).

SAGE: Stealthy Attack Generation in cyber-physical systems

Cyber-physical systems (CPSs) have been increasingly attacked by hackers. CPSs are especially vulnerable to attackers that have full knowledge of the system's configuration. Therefore, novel anomaly detection algorithms in the presence of a knowledgeable adversary need to be developed. However, this research is still in its infancy, due to limited attack data availability and test beds. By proposing a holistic attack modeling framework, we aim to show the vulnerability of existing detection algorithms and provide a basis for novel sensor-based cyber-attack detection. Stealthy Attack GEneration (SAGE) for CPSs serves as a tool for cyber-risk assessment of existing systems and detection algorithms for practitioners and researchers alike. Stealthy attacks are characterized by malicious injections into the CPS through input, output, or both, which produce bounded changes in the detection residue. By using the SAGE framework, we generate stealthy attacks to achieve three objectives: (i) Maximize damage, (ii) Avoid detection, and (iii) Minimize the attack cost. Additionally, an attacker needs to adhere to the physical principles in a CPS (objective (iv)). The goal of SAGE is to model worst-case attacks, where we assume limited information asymmetries between attackers and defenders (e.g., insider knowledge of the attacker). Those worst-case attacks are the hardest to detect, but common in practice and allow understanding of the maximum conceivable damage. We propose an efficient solution procedure for the novel SAGE optimization problem. The SAGE framework is illustrated in three case studies. Those case studies serve as modeling guidelines for the development of novel attack detection algorithms and comprehensive cyber-physical risk assessment of CPSs. The results show that SAGE attacks can cause severe damage to a CPS, while only changing the input control signals minimally. This avoids detection and keeps the cost of an attack low. This highlights the need for more advanced detection algorithms and novel research in cyber-physical security.

Can an observational training improve the ability of children to navigate in familiar and unfamiliar environments?

The ability to orient and navigate successfully in large-scale space is crucial in daily life and develops gradually during childhood. The present study aimed to investigate whether an observational training - in which children observe an actor exploring an environment - fosters the acquisition of spatial orientation skills in children 4.6 - 7.4 years of age, specifically improving their ability to efficiently explore a previously observed environment (familiar) or even a never observed one (unfamiliar). With this aim, we administered - or not - the observational training and tested children on a modified version of the Open Field with multiple rewards (OFmr) task to evaluate the children's explorative behavior and their landmark, route, and configural knowledge. We found that observational training improved both route and configural knowledge fostering the use of both egocentric and allocentric coding requested to solve the OFmr. The beneficial effect was not only limited to when children navigated in a familiar environment but, more importantly, it was present also when they had to navigate in a new environment. As a result of observational training, children moved through the environment to collect the rewards adopting a more organized and structured explorative behavior. Moreover, observational training also exerted a beneficial effect on cognitive mapping abilities, improving the children's capacity of transforming the egocentric information acquired during the navigation into an allocentric world-centered representation. Overall, these findings indicate that observational training promotes an earlier acquisition of high-level spatial abilities and brings new insights on the role of observation in promoting spatial skills in children.

Acoustic emission-based structural health monitoring concept for corrosion of aluminum aircraft structures

In the aircraft industry, where highly optimized aluminum structures and most stringent safety requirements meet, corrosion of aluminum is an important issue to be controlled. To this end, several structural health monitoring (SHM) methods have already been demonstrated, including the acoustic emission (AE) method, which has shown potential for corrosion monitoring. Typically, immersion-like setups are used for demonstration. However, recent results at the authors’ research group also show the potential of the AE method to monitor atmospheric corrosion of aluminum aircraft structures. This contribution presents a SHM concept for the identification, i.e., detection, localization, quantification, and typification, of corrosion of thinwalled aluminum structures by AE. The proposed monitoring concept combines time and frequency domain features of corrosion triggered AE signals and AE source localization-based imaging with a-priori knowledge of structural configuration and loading by the utilization of machine learning methods to quantify and typify corrosion. Successful detection of atmospheric corrosion of aluminum by AE is briefly presented. Furthermore, the concept is theoretically discussed for quantification and typification of corrosion forms typical for atmospheric corrosion conditions.

Nurses’ knowledge and attitudes toward patient-controlled analgesia for postoperative pain control in a tertiary hospital in South Korea

BackgroundThis study investigated the knowledge and attitude of surgical ward nurses toward patient-controlled analgesia (PCA) to develop educational material for nurses on the use of PCA.MethodsThis study was a cross-sectional study comprising 120 nurses from eight surgical wards in a tertiary hospital in South Korea. A questionnaire addressing 6 domains of knowledge of and attitudes towards PCA was conducted over 1 week and analyzed using descriptive and inferential statistical methods. Knowledge was measured on a categorical scale of 0 and 1 (20 points), and attitude was measured on a Likert scale of 1 to 4 points (60 points).ResultsThe total score quantifying the knowledge of and attitudes toward PCA of surgical ward nurses was 59.5 ± 5.5 out of 80.0 points. The average age of the subjects was 28.58 ± 5.68 years old, and nurses above the age of 28 had significantly greater knowledge and better attitudes (61.7 ± 5.5) than those below the age of 28 (57.9 ± 4.9) (p < .001). Nurses working on the upper abdominal surgical ward had significantly greater knowledge (16.2 ± 1.9) than nurses working on other wards (thorax: 14.0 ± 2.3, lower abdominal: 15.4 ± 1.9, and musculoskeletal: 14.5 ± 2.2) (p = .001). Nurses who received education about PCA had significantly better attitudes (45.3 ± 4.6) than those who did not (41.3 ± 3.5) (p < .001). The average correct answer rate for knowledge of opioid analgesics was lower (68.2%) than that for knowledge of the basic configuration of PCA equipment (73.3%) and areas to be identified and managed when using PCA (84.6%), and there was a significant correlation with attitudes toward side effect management (p < .05, r = .19).ConclusionsThere was a significant correlation between the knowledge and attitude of nurses regarding opioid use in PCA. Older nurses with greater clinical experience on the surgical wards who had received PCA education had a better attitude toward PCA. Therefore, newly trained nurses on surgical wards with no experience of PCA education should undergo an intensive education program on opioid analgesics used in PCA.

A factorisation-based recommendation model for customised products configuration design

ABSTRACT Product configuration design combines the existing configurable components of enterprises to quickly form a new product that meets customised requirements. However, the representation, maintenance, and update of the configuration knowledge, and the mismatch problem restrict the rationality and efficiency of existing configuration design methods. In this paper, a recommendation model is developed for customised product configuration design, which takes personalised customer requirements and product component information as input and outputs a ranked list of component instances. It consists of two sub-models: a retrieval sub-model and a ranking sub-model. The retrieval sub-model selects a set of component instance candidates from all possible candidates, and then the ranking sub-model ranks them and selects the best possible candidate. To boost the ranking sub-model performance, we propose a novel interacting network, DualAdap, to extract meaningful low-order, high-order, and adaptive-order cross features. Based on learned cross features, the ranking sub-model computes the adoption scores of all candidates and then selects the best possible candidate according to adoption scores. The configuration design of the elevator traction machine is taken as a case study. Results verify that our recommendation model can identify similar component instances and then accurately pick out the best possible candidate that meets customer requirements.