Commercial Engine Research Articles

Online neuro-fuzzy model learning of dynamic systems with measurement noise

Model identification of nonlinear time varying dynamic systems is challenging because the system behaviours may vary significantly in different operational conditions. If the changes are insufficiently captured by training data, the trained model is unable to capture the system response well when the operational condition changes. The model performance may also be deteriorated in real-time implementation due to the noise in sensors or the environment. This paper presents a self-adaptive Neuro-Fuzzy (NF) modelling framework to address these challenges. The NF model, trained offline based on experimental data, combines the Auto-Regressive with eXogenous (ARX) models and Gaussian activation functions to capture the nonlinear system behaviours. During online implementation, the ARX model parameters are updated using new data through a recursive generalised least squares method, which embeds a noise model to eliminate effects of the noise. The online updating algorithm has a provable convergence guarantee and enables the proposed NF model to adapt to changes in system behaviours automatically. Efficacy of the algorithm is verified through two numerical examples and an experiment on a commercial automotive engine.

Effects of intake manifold geometry in H2 & CNG fueled engine combustion

This study attempted to identify the effect of optimized intake manifold geometry on the behaviors and emission level of hydrogen compressed natural gas (H2CNG) fueled engine. For this purpose, a commercial Hyundai Sonata spark ignition engine (SIE) is modified to operate with CNG and hydrogen blend. The optimal intake pipe length was predicted using an analytical acoustic method. A new intake manifold is designed and implemented utilizing natural supercharging managed by over-pressure waves acoustic propagation. Several tests are conducted on the engine using the new manifold with a speed range from 1000 to 5000 rpm. Based on various engine speeds, the variation of brake torque (BT), in-cylinder pressure, NOx and CO emissions investigated by using gasoline, CNG and hydrogen CNG blend (HCNG) fueled engines via external mixtures. The first finding of the study is that the novel geometry improves the in-cylinder pressure by 10% at 3500 rpm. However, high engine speeds show a reduction of 14% in NOx and 40% in HC while speeds below 2000 rpm reduce CO by 40%. The second finding is that the new optimized geometry serves to get rid of both the auto-igni-tion and the backfire for high ratio of hydrogen in the blend.

Corelease of Genotoxic Polycyclic Aromatic Hydrocarbons and Nanoparticles from a Commercial Aircraft Jet Engine - Dependence on Fuel and Thrust.

Jet engines are important contributors to global CO2 emissions and release enormous numbers of ultrafine particles into different layers of the atmosphere. As a result, aviation emissions are affecting atmospheric chemistry and promote contrail and cloud formation with impacts on earth's radiative balance and climate. Furthermore, the corelease of nanoparticles together with carcinogenic polycyclic aromatic hydrocarbons (PAHs) affects air quality at airports. We studied exhausts of a widely used turbofan engine (CFM56-7B26) operated at five static thrust levels (idle, 7, 30, 65, and 85%) with conventional Jet A-1 fuel and a biofuel blend composed of hydro-processed esters and fatty acids (HEFA). The particles released, the chemical composition of condensable material, and the genotoxic potential of these exhausts were studied. At ground operation, particle number emissions of 3.5 and 0.5 × 1014 particles/kg fuel were observed with highest genotoxic potentials of 41300 and 8800 ng toxicity equivalents (TEQ)/kg fuel at idle and 7% thrust, respectively. Blending jet fuel with HEFA lowered PAH and particle emissions by 7-34% and 65-67% at idle and 7% thrust, respectively, indicating that the use of paraffin-rich biofuels is an effective measure to reduce the exposure of airport personnel to nanoparticles coated with genotoxic PAHs (Trojan horse effect).

Ready-to-use graphene-related material-added multi-grade oils: characterization and performance in car engine working conditions.

The need for energy efficiency is leading to the growing use of additives to enhance the performance of oil in automotive engines. Great interest is focused on nano-additives even if to date there is still no practical use in commercial liquid lubricants. Herein, the potential of industrially scalable and low-cost graphene-related materials (GRMs) as additives to enhance the performance of oil in automotive engines is explored. The use of polyalkylmethacrylate dispersants, the most common key additives to formulate "green technology" lubricant oils liquid-processed GRM, is explored, investigating the role of the lateral size and the chemical analysis in the stability of the lubricant GRM dispersions. Showing the maximum duration of stability and a production method that avoids the use of strong oxidants, rheological tests were then focused on multilayered graphene flakes with sub-micrometre lateral size mixed in two commercial oil grades (5W-30 and 5W-40) under conditions similar to those of engine operation. The addition of such a filler increases the viscosity without affecting the Newtonian fluid behavior, while four-ball tests show a reduction in wear, indicating improved lubrication performance. Finally, preliminary bench-test on a commercial car engine showed increased power output corresponding to enhanced engine efficiency. The results clearly indicate the effective improvement in lubricating commercial oils due to GRM additives.

Design and Analysis of the Exhaust Manifold in a 6-Cylinder Commercial Diesel Engine

The exhaust manifold is one of the engine parts in internal combustion engines that operates under the influence of high temperatures. To prevent issues arising from the expansion movement due to high temperature effects, the exhaust manifold of a 6-cylinder commercial diesel engine has been designed in three parts. Sealing rings that can withstand high temperatures are used in the three-part exhaust manifold to prevent gas leaks. For the exhaust manifold, 1-dimensional, thermal, flow, and structural analyses have been performed. Initially, based on the structural analysis of the exhaust manifold conducted without sealing rings, sealing ring selection was made according to the deformation values of the exhaust manifold. In the structural analysis, the PEEQ (equivalent plastic strain) method, which is utilized to determine the thermomechanical fatigue crack initiation area, is employed. In this study, an approach using this method was undertaken, and the crack initiation area was examined.

Analisa Jarak Center Lubang Connecting Rod diluar Standar pada PT. XYZ

PT. XYZ as a manufacturer of commercial vehicles and diesel engines has an important role in the automotive industry. This company consists of several departments, one of which is machining and assembly. Dynamic industrial developments encourage companies to continue to innovate in order to remain relevant, competitive and develop. Increasing competition in the business world will mean that consumers have more choices in choosing products. Therefore, to have competitiveness and survive competition with other products. This research seems to focus on identifying types of defects, their causes, and providing alternative recommendations for improvement to increase product competitiveness at the PT. Based on identifying factors that cause product defects through a fishbone diagram, namely human, machine and method factors. The proposal given in this research is to make parts or make tools such as Shim Plates which are used to help an object to be stable (connecting rod).

(Invited) Pt-Modified Aluminide Coatings for Ni-Base Single Crystal Superalloy

Single phase (Ni,Pt)Al coating has been widely employed as state-of-the-art bondcoat for protecting hot-sectional components in commercial aero engines, especially for the parts made of Ni-base single crystal (SX) superalloys. For high temperature protective coating serving on SX superalloy, two interfaces are vitally essential for acquiring reliably long service life: the interface growing thermally-grown oxide (TGO) and the interface connecting coating and substrate alloy. Normally, the excellent performance of PtAl coating derives from high Al content and the incorporation of Pt, which ensures formation of exclusively adherent oxide scale, α-Al2O3. To further improve the performance of Pt-modified aluminide coating, in present study reactive elements are introduced using co-electroplating method. Compared with singular doping, co-doping of Hf-Y demonstrated superior oxidation resistance. The oxide scale growth rate and spallation tendency of Hf-Y co-doped (Ni,Pt)Al coating were much smaller, as well as the surface rumpling extent. Besides, the grain size of Hf-Y co-doped (Ni,Pt)Al coating was finer than that of Hf- or Y- doped coatings in as-received state, indicating the capability of grain refinement. With the benefits of RE co-doping, the desirably thin/smooth TGO is thus accessible for Pt-modified aluminide coatings. The other issue is the element interdiffusion at high temperature, which would affect the mechanical property of SX superalloy. According to Fick′s law of diffusion, J Al = - D Al · δμ Al / δ x ,to reduce diffusion coefficient ( D Al ) or chemical potential ( δμ Al / δ x ) would both decrease the diffusion extent ( J Al ). Therefore, two strategies are employed: adding a diffusion barrier between coating and substrate, or designing a γʹ-PtAl coating. The performance of these modified aluminide coatings are evaluated in high temperature oxidation test. At last, doping behavior of some elements were explained by First-Principle Calculations.

Feasibility Study of Exhaust Energy Recovery System for Mobile Carbon Capture Operations in Commercial Engines through 1D Simulation

The global proportion of eco-friendly vehicles continues to increase; however, regarding hybrid vehicles, the vehicle powertrains in most countries include internal combustion engines. Therefore, research on reducing the carbon emissions from internal combustion engines must be conducted. Carbon capture technology must be developed for e-fuel, which has recently attracted attention, to achieve carbon neutrality. In this study, a turbo compound system capable of recovering waste exhaust gas energy was selected as the most appropriate energy supply system to operate a mobile carbon capture system. The feasibility was reviewed by analyzing the turbo compound speed, pressure drop, power generation, etc., using a one-dimensional simulation method. The maximum power generation of the configured turbo compound system was approximately 9 kW, and approximately 1–3 kW of energy could be recovered under medium speed and load conditions, which are the optimal operating conditions for a test engine with the displacement of a 4 L.

DR-Occluder: Generating Occluders Using Differentiable Rendering

The target of the occluder is to use very few faces to maintain similar occlusion properties of the original 3D model. In this paper, we present DR-Occluder, a novel coarse-to-fine framework for occluder generation that leverages differentiable rendering to optimize a triangle set to an occluder. Unlike prior work, which has not utilized differentiable rendering for this task, our approach provides the ability to optimize a 3D shape to defined targets. Given a 3D model as input, our method first projects it to silhouette images, which are then processed by a convolution network to output a group of vertex offsets. These offsets are used to transform a group of distributed triangles into a preliminary occluder, which is further optimized by differentiable rendering. Finally, triangles whose area is smaller than a threshold are removed to obtain the final occluder. Our extensive experiments demonstrate that DR-Occluder significantly outperforms state-of-the-art methods in terms of occlusion quality. Furthermore, we compare the performance of our method with other approaches in a commercial engine, providing compelling evidence of its effectiveness.

Topology Guaranteed B-Spline Surface/Surface Intersection

The surface/surface intersection technique serves as one of the most fundamental functions in modern Computer Aided Design (CAD) systems. Despite the long research history and successful applications of surface intersection algorithms in various CAD industrial software, challenges still exist in balancing computational efficiency, accuracy, as well as topology correctness. Specifically, most practical intersection algorithms fail to guarantee the correct topology of the intersection curve(s) when two surfaces are in near-critical positions, which brings instability to CAD systems. Even in one of the most successfully used commercial geometry engines ACIS, such complicated intersection topology can still be a tough nut to crack. In this paper, we present a practical topology guaranteed algorithm for computing the intersection loci of two B-spline surfaces. Our algorithm well treats all types of common and complicated intersection topology with practical efficiency, including those intersections with multiple branches or cross singularities, contacts in several isolated singular points or highorder contacts along a curve, as well as intersections along boundary curves. We present representative examples of these hard topology situations that challenge not only the open-source geometry engine OCCT but also the commercial engine ACIS. We compare our algorithm in both efficiency and topology correctness on plenty of common and complicated models with the open-source intersection package in SISL, OCCT, and the commercial engine ACIS.

Mistuning identification and model updating of a blisk with piezoelectric excitation components

Integrally bladed disks (blisks) are extensively used in military and commercial aircraft engines. There are inevitable deviations between blades called mistuning, leading to the vibration localization of blisks, which potentially results in high cycle fatigue (HCF). Furthermore, the dynamic performance is sensitive to mistuning patterns. Hence, to predict the vibration response of mistuned blisks accurately, the mistuning pattern needs to be identified experimentally and verified under traveling wave excitation (TWE). Piezoelectric TWE is a promising testing technique for blisk dynamics in a non-rotating state, offering advantages such as high excitation force, wide bandwidth, and a simple setup. However, piezoelectric materials are generally arranged on blades forming an electromechanically coupled structure, which challenges the existing mistuning identification methods. In this paper, an integral mistuning identification and model updating method with traveling wave excitation verification is developed. The detuning strategy is used to split natural frequencies of blades, whereupon the response is measured blade by blade. Measured response functions of isolated blades can be retrieved by data reconstruction. Then, the mistuning patterns of elastic modulus and damping ratio are identified by Kirchhoff-plate theory and half-power bandwidth method, respectively. Experimental studies are carried out to validate the method. A dummy blisk with piezoelectric patches is designed and the dynamic properties are calculated. Blade-by-blade measurement and TWE test are conducted. Results show that natural frequencies of the updated model are in excellent agreement with the measured ones. Under TWE, the deviations of natural frequencies for all blades are less than 0.25%. The response deviation of the updated model is decreased by 89.4% on average compared with the original model and the average response deviation of the updated model is 7.4%.

Novel top-down kg-scale processing of 2D multi-layered graphene powder and its application as excellent lubricating additives in commercial engine oils

Multi-layered graphene (MLG) powder is prepared on a kg-scale using a novel fluid-assisted processing of exfoliated graphite. Each MLG particle is a few μm laterally and is constituted by a few graphene layers. When MLG-dispersed commercial engine oil was used as a lubricant, the tribological properties (i.e., friction and resistance to wear) of the contacting metal surfaces were significantly enhanced. The average coefficient of friction (CoF) at room temperature and 75 °C was reduced by ~25.5 % and ~ 16 %, respectively, while the wear resistance at room temperature and 75 °C was improved by ~13 % and ~ 16 %, respectively. MLG-dispersed engine oil forms a protective tribo-film adhering to the contacting metal surfaces, resulting in ultra-low interface friction. The MLG-dispersed engine oil (acting as a tribo-film) diminishes the effective direct metal-to-metal contact area, minimizing the wear.

A novel approach to the deposition of Co-Mo-Cr-Si coating on Haynes 282 by laser fusion and laser remelting

This paper presents a novel hybrid method of the crack-free fusion of CoMoCrSi, which is a cobalt-based alloy with molybdenum additions with the composition analogous to Tribaloy® T400, on Haynes 282 for parts where extreme wear is problematic with high temperatures and corrosive media, such as industrial turbine applications, commercial jet engines, and rocket engines. To alleviate cracking of the coating during laser surface deposition/coating, previous attempts relied on preheating of the substrate to reduce cracks to alleviate a thermal mismatch between the substrate and molten powder. The primary aim of this work is accomplished by fusing crack free CoMoCrSi layers using a novel hybrid process of combining laser cladding and laser remelting processes. The optimal process conditions of coating crack-free CoMoCrSi on Haynes 282 were determined for both the laser powderbed fusion and remelting processes. Microhardness and chemical compositions of the coating layers produced using optimal process parameters with and without remelting the substrate were compared. The chemical compositions of different phases present in the coating layer were analyzed by Energy Dispersive X-ray Spectroscopy (EDS). The remelting process yielded no dilution at the surface, resulting in the preservation of the original CoMoCrSi coating properties.

Hybrid data-driven and mechanism-modeling approaches for online injection rate sensing of dual-fuel co-direct injector under carbon neutral background

This study proposes an innovative concept for online sensing of the injection process. By using the injector inlet as the pressure signal detection point, contactless testing of the injector is achieved, theoretically requiring no structural changes to commercial engines or standard injectors. For the pilot diesel injection, the pressure signal is abstracted as the evolution and transmission of Riemann waves, and the relationship between pressure and mass flow rate is established. Additionally, correction and decoupling methods for system interference and superimposed waves are proposed to extract Riemann single-wave components caused by injection. For the main fuel gas injection process, a data-driven injection mass neural network prediction model is constructed based on the pressure drop characteristic, which achieves quantitative sensing of the injection characteristics. Moreover, concerning gas pressure fluctuation, the interference phenomenon in the first-order differential pressure signal is identified. It is found that gas pressure waves propagate as second-order micro-pressure in the HPDI system, and the columns of pressure waves do not interfere with each other. A qualitative reconstruction method for the injection rate curve is developed based on 1D mechanistic models. In conclusion, this study uses hybrid data-driven and mechanism-modeling approaches to achieve online sensing. By comparing with offline testing methods, it exhibits high accuracy, with errors in the majority of injection parameters remaining within 5.5%.

Creation of Three-dimensional Anatomic Models in Pediatric Surgical Patients Using Cross-sectional Imaging: A Demonstration of Low-cost Methods and Applications

BackgroundPediatric surgery patients often present with complex congenital anomalies or other conditions requiring deep understanding of their intricate anatomy. Commercial applications and services exist for the conversion of cross-sectional imaging data into three-dimensional (3D) models for education and preoperative planning. However, the associated costs and lack of familiarity may discourage their use in centers with limited resources. The purpose of this report is to present a low-cost, reproducible method for generating 3D images to visualize patient anatomy. MethodsDe-identified DICOM files were obtained from the hospital PACS system in preparation for assorted pediatric surgical procedures. Using open-source visualization software, variations in anatomic structures were examined using volume rendering and segmentation techniques. Images were further refined using available editing tools or artificial intelligence-assisted software extensions. ResultsUsing the described techniques we were able to obtain excellent visualization of desired structures and associated anatomic variations. Once structures were selected and modeled in 3D (segmentation), they could be exported as one of several 3D object file formats. These could then be retained for 3D printing, visualization in virtual reality, or as an anatomic reference during the perioperative period. Models may also be imported into commercial gaming engines for rendering under optimal lighting conditions and with enhanced detail. ConclusionPediatric surgeons are frequently tasked with the treatment of patients with complex and rare anomalies. Visualization and preoperative planning can be assisted by advanced imaging software at minimal to no cost, thereby facilitating enhanced understanding of these conditions in resource-limited environments. Level of EvidenceV, Case Series, Description of Technique.

Solubility and stability enhancement of ethanol in diesel fuel by using tri-n-butyl phosphate as a new surfactant for CI engine

Nowadays, researchers are very interested in improving the stability and solubility of blending diesel fuel with a high percentage of ethanol. As a result, the goal of this paper was to find a way to use the surfactant of Tri-n-butyl phosphate (TBP) substance to blend ethanol with diesel fuel to a level of 40%. Diesel fuel is mixed with ethanol in volumetric proportions of 10%, 20%, 30%, and 40%, as well as a tiny amount of TBP from 1 to 4%. The prepared blends were the subject of an experiment evaluation by fueling a direct injection diesel engine. This engine is a water-cooled, commercial diesel engine, single cylinder, and four-stroke with 12 kW maximum power. The four blends were evaluated as clean fuel mixtures of 10% ethanol/90% diesel/1% TBP, 20% ethanol/80% diesel/2% TBP, 30% ethanol/70% diesel/3% TBP, and 40% ethanol/60% diesel/4% TBP. As the starting fuel, we used 100% diesel to compare the results. The engine’s output and emissions have been measured at various engine loads and constant speeds of 1500 rpm. According to the data gathered, even when the percentage of ethanol was increased to 40%, neither the base fuel nor the engine BTE changed significantly. The engine exhaust gas temperature was found to decrease slightly when the proportion of ethanol was increased. When bioethanol is increased to 40% of the base volume, it causes an increase in the combustion of unburned hydrocarbons and CO emissions. However, when the percentage of ethanol was increased from 100% diesel to the base fuel to 40%, CO2 emissions decreased, and O2 emissions slightly increased.

Level Building Sidekick: An AI-Assisted Level Editor Package for Unity

Developing an original video game requires high investment levels, market research, cost-effective solutions, and a quick development process. Game developers usually reach for commercial off-the-shelf components often available in the engine's marketplace to reduce costs. Mixed-initiative authoring tools allow us to combine the thoughtful work of human designers with the productivity gains of automated techniques. However, most commercial AI-assisted Procedural Content Generation tools focus on generating small independent components, and standalone research tools available for generating full game levels with state-of-the-art algorithms usually lack integration with commercial game engines. This article aims to fill this gap between industry and academia. The Level Building Sidekick (LBS) is a mixed-initiative procedural content generation tool built by our research lab in association with four small independent game studios. It has a modular software architecture that enables developers to extend it for their particular projects. The current version has two working modules for building game maps, an early version of a module for populating the level with NPCs or items, and the first stages of a quest editor module. An automated testing module is planned. LBS is distributed as an AI-Assisted videogame-level editor Unity package. Usability testing performed using the ``Think-Aloud'' methodology indicates LBS has the potential to improve game development processes convincingly. However, at this stage, the user interface and the AI recommendations could improve their intuitiveness. As a general comment, the tool is perceived as a substantial contribution to facilitating and shortening development times, compared to only using the base game engine. There is an untapped market for mixed-initiative tools that assist the game designer in creating complete game levels. We expect to fill that market for our partner development studios and provide the community with an open research and development platform in a standard game engine.

Experimental and Simulation Study on the Emissions of a Multi-Point Lean Direct Injection Combustor

Spurred by the world’s attention to pollution emissions from commercial aero-engines, the International Civil Aviation Organization (ICAO) has made more stringent emission regulations for civil aircraft engines, especially the NOx emission.This paper develops a Five-Point lean direct injection (LDI) combustor with three swirler schemes to reduce the emissions of commercial aircraft engines. The flowfield of the combustor is studied numerically. Moreover, the combustion efficiency and gaseous emissions in different inlet conditions and fuel ratios of the main stage (α) are studied experimentally. The corresponding results reveal that, under a fuel-air ratio (FAR) between 0.0130 and 0.0283 and an α value between 30% and 60%, the combustion efficiency is 99.18%, 98.83%, and 99.03% when the pilot stage works alone, and 99.69%, 99.23%, and 99.75% when the pilot and main stage work simultaneously. Furthermore, the experimental results suggest that the NOx emission decreases as α increases, demonstrating that the convergent swirler has a tremendous advantage in reducing NOx emissions over Venturi.

LNG 이종연료 운전이 상업용 디젤 엔진의 출력 및 배출가스 특성에 미치는 영향

In order to additionally supply LNG to a heavy-duty commercial diesel engine, a dual fuel system was installed; engine power and exhaust gas emissions while operating in the ‘ND-13 mode’, in accordance with the notice from the Ministry of Environment, were investigated. The feasibility of retrofitting the dual fuel system and plans based on mixture rate, power, and emission reduction to enable commercialization were evaluated. The engine power and torque values were within ±5% of the values for the existing engine; these were within the legal modification range. In case of exhaust gas emissions, the decrease in CO 2 emission due to the increase in load was apparent; it was reduced by 15.3%. NO X emission decreased by 58%; this could be attributed to the decrease in combustion temperature owing to water injection. THC and CO increased significantly, possibly due to the reduced combustibility of natural gas owing to bulk quenching, water injection, and the absence of catalysts. Additional research focused on modification of mapping values and installation of oxidation catalysts to improve the combustion performance of the system, is warranted.

Unearthing the Past for a Sustainable Future: Extracting and transforming data in the Biodiversity Heritage Library for climate action

As the urgency to address the climate crisis intensifies, the availability of accurate and comprehensive biodiversity data has become crucial for informing climate change studies, tracking key environmental indicators, and building global biodiversity monitoring platforms. The Biodiversity Heritage Library (BHL) plays a vital role in the core biodiversity infrastructure, housing over 60 million pages of digitized literature about life on Earth. Recognizing the value of over 500 years of data in BHL, a global network of BHL staff is working to establish a scalable data pipeline to provide actionable occurrence data from BHL’s vast and diverse collections. However, transforming textual content into FAIR (findable, accessible, interoperable, reusable) data poses challenges due to missing descriptive metadata and error-ridden unstructured outputs from commercial text engines. (Fig. 1) Despite the wealth of knowledge in BHL now available to global audiences, the underutilization of biodiversity and climate data contained in BHL's textual corpus hinders scientific research, hampers informed decision-making for conservation efforts, and limits our understanding of biodiversity patterns crucial for addressing the climate crisis. By leveraging recent advancements in text recognition engines, along with cutting-edge AI (Artificial Intelligence) models like OpenAI’s CLIP (Contrastive Language-Image Pre-Training) and nascent features in transcription platforms, BHL staff are beginning to process vast amounts of textual and image data and transform centuries worth of data from BHL collections into computationally usable formats. Recent technological breakthroughs now offer a transformative opportunity to empower the global biodiversity community with prescient insights from our shared past and facilitate the integration of historical knowledge into climate action initiatives. To bridge gaps in the historical record and unlock the potential of the Biodiversity Heritage Library (BHL), a multi-pronged effort utilizing innovative cross-disciplinary approaches is being piloted. These technical approaches were selected for their efficiency and ability to generate rapid results that could be applied across the diverse range of materials in BHL. (Fig. 2) Piloting a data pipeline that is scalable to 60 million pages requires considerable investigation, experimentation, and resources but will have an appreciable impact on global conservation efforts by informing and establishing historic baselines deeper into time. This presentation will focus on the identification, extraction, and transformation of OCR into structured data outputs in BHL. Approaches include: Upgrading legacy OCR text using Tesseract OCR engine to improve data quality by 20% and openly publish 40 GBs of textual data as FAIR data; Evaluating handwritten text recognition (HTR) engines (Microsoft Azure Computer Vision, Google Cloud Vision API (Application Programming Interface), and Amazon Textract) to improve scientific name-finding in BHL’s handwritten archival materials using algorithms developed by Global Names Architecture; Extracting data from collecting events using HTR coordinate outputs with Python library Pandas DataFrame to create structured data; Classifying BHL page-level images with OpenAI's CLIP, a neural network model to accurately identify the handwritten sub-corpus of primary source materials in BHL; Running an A/B test to evaluate the efficiency and accuracy of human-keyed transcription data extraction to provide high-quality, human-vetted datasets that can be deposited with data aggregators. Upgrading legacy OCR text using Tesseract OCR engine to improve data quality by 20% and openly publish 40 GBs of textual data as FAIR data; Evaluating handwritten text recognition (HTR) engines (Microsoft Azure Computer Vision, Google Cloud Vision API (Application Programming Interface), and Amazon Textract) to improve scientific name-finding in BHL’s handwritten archival materials using algorithms developed by Global Names Architecture; Extracting data from collecting events using HTR coordinate outputs with Python library Pandas DataFrame to create structured data; Classifying BHL page-level images with OpenAI's CLIP, a neural network model to accurately identify the handwritten sub-corpus of primary source materials in BHL; Running an A/B test to evaluate the efficiency and accuracy of human-keyed transcription data extraction to provide high-quality, human-vetted datasets that can be deposited with data aggregators. The ongoing development of a scalable data pipeline of BHL’s relevant biodiversity and climate-related datasets requires sustained support and partnership with the biodiversity community. Initial results demonstrate that liberating data from archival and handwritten field notes is arduous but feasible. Extending these methodologies to the broader scientific literature presents new research opportunities. Extracting and normalizing data from unstructured textual sources can significantly advance biodiversity research and inform environmental policy. The Biodiversity Heritage Library staff are committed to building multiple scalable data pipelines with the ultimate goal of erecting a global biodiversity knowledge graph, rich in interconnected data and semantic meaning, enabling informed decisions for the preservation and sustainable management of Earth's biodiversity.