Efficient Bayesian Function Optimization of Evolving Material Manufacturing Processes.
Ontology highlight
ABSTRACT:
SUBMITTER: Rubin de Celis Leal D
PROVIDER: S-EPMC6906790 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:To explore how different reaction parameters affect the major features of short-chain ammonium polyphosphate (APP) fertilizers, a batch of manufacturing experiments were conducted under two different manufacturing processes [phosphoric acid (PA)-urea and monoammonium phosphate (MAP)-urea]. The APP features including polymerization degree, polymerization rate, solubility, and N and P recovery rates were significantly varied and influenced by the molar ratio of raw materials (P:N), reaction temperature, time, and pressure under different manufacturing conditions. In the MAP-urea process, the optimized APP products were gained under the combination condition of molar ratio = 1.6:1, T = 130 °C, and t = 45 min, while this happened in molar ratio = 1:1.7, T = 180 °C, and t = 60 min in the PA-urea process. Comprehensively, the features of APP fertilizers produced by the MAP-urea process were better than those produced by the PA-urea process. Our results provide valuable references for manufacturing high-quality short-chain APP fertilizers.
| S-EPMC8320069 | biostudies-literature
Project description:Functional data are defined as realizations of random functions (mostly smooth functions) varying over a continuum, which are usually collected on discretized grids with measurement errors. In order to accurately smooth noisy functional observations and deal with the issue of high-dimensional observation grids, we propose a novel Bayesian method based on the Bayesian hierarchical model with a Gaussian-Wishart process prior and basis function representations. We first derive an induced model for the basis-function coefficients of the functional data, and then use this model to conduct posterior inference through Markov chain Monte Carlo methods. Compared to the standard Bayesian inference that suffers serious computational burden and instability in analyzing high-dimensional functional data, our method greatly improves the computational scalability and stability, while inheriting the advantage of simultaneously smoothing raw observations and estimating the mean-covariance functions in a nonparametric way. In addition, our method can naturally handle functional data observed on random or uncommon grids. Simulation and real studies demonstrate that our method produces similar results to those obtainable by the standard Bayesian inference with low-dimensional common grids, while efficiently smoothing and estimating functional data with random and high-dimensional observation grids when the standard Bayesian inference fails. In conclusion, our method can efficiently smooth and estimate high-dimensional functional data, providing one way to resolve the curse of dimensionality for Bayesian functional data analysis with Gaussian-Wishart processes.
| S-EPMC5634932 | biostudies-literature
Project description:Bayesian optimization (BO) can accelerate material design requiring time-consuming experiments. However, although most material designs require tuning of multiple properties, the efficiency of multi-objective (MO) BO in time-consuming experimental material design remains unclear, due to the complexity of handling multiple objectives. This study introduces MO BO method that efficiently achieves predefined goals and shows that by focusing on achieving the goals, BO can efficiently accelerate realistic MO design problems with small efforts. Benchmarks showed that the proposed BO method dramatically reduced the number of experiments needed to achieve goals relative to a baseline method. Virtual MO inverse design experiments with realistic material design problems were also performed, during which the proposed method could achieve goals within only around ten experiments in average and showed over 1000-fold acceleration relative to the random sampling for the most difficult case. The introduction of goal-oriented BO will precede real-world application of BO.
| S-EPMC8273421 | biostudies-literature
Project description:We consider alternate formulations of recently proposed hierarchical Nearest Neighbor Gaussian Process (NNGP) models (Datta et al., 2016a) for improved convergence, faster computing time, and more robust and reproducible Bayesian inference. Algorithms are defined that improve CPU memory management and exploit existing high-performance numerical linear algebra libraries. Computational and inferential benefits are assessed for alternate NNGP specifications using simulated datasets and remotely sensed light detection and ranging (LiDAR) data collected over the US Forest Service Tanana Inventory Unit (TIU) in a remote portion of Interior Alaska. The resulting data product is the first statistically robust map of forest canopy for the TIU.
| S-EPMC6753955 | biostudies-literature
Project description:Finding low-energy molecular conformers is challenging due to the high dimensionality of the search space and the computational cost of accurate quantum chemical methods for determining conformer structures and energies. Here, we combine active-learning Bayesian optimization (BO) algorithms with quantum chemistry methods to address this challenge. Using cysteine as an example, we show that our procedure is both efficient and accurate. After only 1000 single-point calculations and approximately 80 structure relaxations, which is less than 10% computational cost of the current fastest method, we have found the low-energy conformers in good agreement with experimental measurements and reference calculations. To test the transferability of our method, we also repeated the conformer search of serine, tryptophan, and aspartic acid. The results agree well with previous conformer search studies.
| S-EPMC8023666 | biostudies-literature
Project description:Background:Quality by design (QbD) is an advanced drug quality control concept that has been gradually implemented in the optimization of manufacturing processes of Chinese medicines. However, the variation of Chinese medicinal material quality has rarely been considered in published works. Because manufacturing processes may lower the variation introduced through different batches of materials, a material quality control strategy should be developed considering the influences of manufacturing processes. Methods:In this work, the processes of extraction, concentration, water precipitation, and chromatography for notoginseng total saponin (NTS) production were investigated while considering Panax notoginseng quality variation as a sample. Ten process parameters were studied simultaneously using a definitive screening design. After the process critical quality attributes (CQAs) were determined, critical process parameters (CPPs) and critical material attributes (CMAs) were identified simultaneously. Then, models utilizing the CMAs, CPPs, and process CQAs were developed. The design space was then calculated using a Monte Carlo simulation method with an acceptable probability of 0.90. A material quality control strategy considering the influences of manufacturing processes was proposed. Results:The ginsenoside Rd purity and total saponin purity in the eluate were identified as process CQAs. The ethanol solution concentration used for extraction, the ethanol solution concentration used for elution, and elution time were identified as CPPs. The extractable dry matter content of Panax notoginseng was one of the CMAs. The extractable contents of notoginsenoside R1, ginsenoside Rg1, ginsenoside Rb1, and ginsenoside Rd were the other CMAs. The inequalities implemented to discriminate the high quality and low quality of Panax notoginseng were developed according to the NTS standard of the Xuesaitong injection. Low quality Panax notoginseng should not be released for NTS production. High quality Panax notoginseng can be treated with feasible manufacturing processing parameters. Verification experiments were carried out successfully for 2 batches of high quality Panax notoginseng. Conclusions:In this work, a quality control strategy for herbal materials was developed considering the matching of process characteristics and material quality attributes. This strategy is promising for application to other Chinese medicines.
| S-EPMC6760055 | biostudies-literature
Project description:BACKGROUND:The ability of collections of molecules to spontaneously assemble into large functional complexes is central to all cellular processes. Using the viral capsid as a model system for complicated macro-molecular assembly, we develop methods for probing fine details of the process by learning kinetic rate parameters consistent with experimental measures of assembly. We have previously shown that local rule based stochastic simulation methods in conjunction with bulk indirect experimental data can meaningfully constrain the space of possible assembly trajectories and allow inference of experimentally unobservable features of the real system. RESULTS:In the present work, we introduce a new Bayesian optimization framework using multi-Gaussian process model regression. We also extend our prior work to encompass small-angle X-ray/neutron scattering (SAXS/SANS) as a possibly richer experimental data source than the previously used static light scattering (SLS). Method validation is based on synthetic experiments generated using protein data bank (PDB) structures of cowpea chlorotic mottle virus. We also apply the same approach to computationally cheaper differential equation based simulation models. CONCLUSIONS:We present a flexible approach for the global optimization of computationally costly objective functions associated with dynamic, multidimensional models. When applied to the stochastic viral capsid system, our method outperforms a current state of the art black box solver tailored for use with noisy objectives. Our approach also has wide applicability to general stochastic optimization problems.
| S-EPMC5994016 | biostudies-literature
Project description:In resource-constrained environments, such as low-power edge devices and smart sensors, deploying a fast, compact, and accurate intelligent system with minimum energy is indispensable. Embedding intelligence can be achieved using neural networks on neuromorphic hardware. Designing such networks would require determining several inherent hyperparameters. A key challenge is to find the optimum set of hyperparameters that might belong to the input/output encoding modules, the neural network itself, the application, or the underlying hardware. In this work, we present a hierarchical pseudo agent-based multi-objective Bayesian hyperparameter optimization framework (both software and hardware) that not only maximizes the performance of the network, but also minimizes the energy and area requirements of the corresponding neuromorphic hardware. We validate performance of our approach (in terms of accuracy and computation speed) on several control and classification applications on digital and mixed-signal (memristor-based) neural accelerators. We show that the optimum set of hyperparameters might drastically improve the performance of one application (i.e., 52-71% for Pole-Balance), while having minimum effect on another (i.e., 50-53% for RoboNav). In addition, we demonstrate resiliency of different input/output encoding, training neural network, or the underlying accelerator modules in a neuromorphic system to the changes of the hyperparameters.
| S-EPMC7396641 | biostudies-literature
Project description:Post-stroke cognitive and linguistic impairments are debilitating conditions, with limited therapeutic options. Domain-general brain networks play an important role in stroke recovery and characterizing their residual function with functional MRI has the potential to yield biomarkers capable of guiding patient-specific rehabilitation. However, this is challenging as such detailed characterization requires testing patients on multitudes of cognitive tasks in the scanner, rendering experimental sessions unfeasibly lengthy. Thus, the current status quo in clinical neuroimaging research involves testing patients on a very limited number of tasks, in the hope that it will reveal a useful neuroimaging biomarker for the whole cohort. Given the great heterogeneity among stroke patients and the volume of possible tasks this approach is unsustainable. Advancing task-based functional MRI biomarker discovery requires a paradigm shift in order to be able to swiftly characterize residual network activity in individual patients using a diverse range of cognitive tasks. Here, we overcome this problem by leveraging neuroadaptive Bayesian optimization, an approach combining real-time functional MRI with machine-learning, by intelligently searching across many tasks, this approach rapidly maps out patient-specific profiles of residual domain-general network function. We used this technique in a cross-sectional study with 11 left-hemispheric stroke patients with chronic aphasia (four female, age ± standard deviation: 59 ± 10.9 years) and 14 healthy, age-matched control subjects (eight female, age ± standard deviation: 55.6 ± 6.8 years). To assess intra-subject reliability of the functional profiles obtained, we conducted two independent runs per subject, for which the algorithm was entirely reinitialized. Our results demonstrate that this technique is both feasible and robust, yielding reliable patient-specific functional profiles. Moreover, we show that group-level results are not representative of patient-specific results. Whereas controls have highly similar profiles, patients show idiosyncratic profiles of network abnormalities that are associated with behavioural performance. In summary, our study highlights the importance of moving beyond traditional 'one-size-fits-all' approaches where patients are treated as one group and single tasks are used. Our approach can be extended to diverse brain networks and combined with brain stimulation or other therapeutics, thereby opening new avenues for precision medicine targeting a diverse range of neurological and psychiatric conditions.
| S-EPMC8370405 | biostudies-literature
Project description:Material extrusion (ME) is a layer-by-layer additive manufacturing process that is now used in personal and commercial production where prototyping and customization are required. However, parts produced from ME frequently exhibit poor mechanical performance relative to those from traditional means; moreover, fundamental knowledge of the factors leading to development of inter-layer strength in this highly non-isothermal process is limited. In this work, we seek to understand the development of inter-layer weld strength from the perspective of polymer interdiffusion under conditions of rapidly changing mobility. Our framework centers around three interrelated components: in situ thermal measurements (via infrared imaging), temperature dependent molecular processes (via rheology), and mechanical testing (via mode III fracture). We develop the concept of an equivalent isothermal weld time and test its relationship to fracture energy. For the printing conditions studied the equivalent isothermal weld time for Tref = 230 °C ranged from 0.1 ms to 100 ms. The results of these analysis provide a basis for optimizing inter-layer strength, the limitations of the ME process, and guide development of new materials.
| S-EPMC5684701 | biostudies-other