Separate Operations Research Articles

Game-Based Backstepping Design for Strict-Feedback Nonlinear Multi-Agent Systems Based on Reinforcement Learning.

In this article, the game-based backstepping control method is proposed for the high-order nonlinear multi-agent system with unknown dynamic and input saturation. Reinforcement learning (RL) is employed to get the saddle point solution of the tracking game between each agent and the reference signal for achieving robust control. Specifically, the approximate optimal solution of the established Hamilton-Jacobi-Isaacs (HJI) equation is obtained by policy iteration for each subsystem, and the single network adaptive critic (SNAC) architecture is used to reduce the computational burden. In addition, based on the separation operation of the error term from the derivative of the value function, we achieve the different proportions of the two agents in the game to realize the regulation of the final equilibrium point. Different from the general use of the neural network for system identification, the unknown nonlinear dynamic term is approximated based on the state difference obtained by the command filter. Furthermore, a sufficient condition is established to guarantee that the whole system and each subsystem included are uniformly ultimately bounded. Finally, simulation results are given to show the effectiveness of the proposed method.

Выбор и проверка метода схематизации случайного процесса нагружения пружин буксового подвешивания

The product life cycle contract also contains its cost for the preparation of the product, delivery to the supplier, subsequent maintenance, operation and repair of the product up to disposal. The article considers the development of a methodology for calculating the life cycle of axle box suspension springs (and later frames) of the Lastochka electric train trolley. The method of analysis is based on the assessment of the spring strength and the results of strength tests obtained during sea trials. These tests have been carried out on separate operating sections of railways, based on the results of data from the removed blocks of oscillograms recording forces from models of electric train bogies of virtual sea trials. Virtual sea trials have been conducted on certain created sections of the track, taking into account the horizontal and vertical irregularities of the track for different track conditions. The paper analyzes the tutorials on the methods for schematization of test results in the form of oscillograms recording the forces of random processes; the method of falling rain is used. The implementation in the software product of the methodology for analyzing the stress-strain state of box suspension springs and the results of sea trials, which have been proceed by the falling rain method, allows us to determine the actual service life of box suspension springs.

ОРГАНІЗАЦІЯ ТЕХНОЛОГІЧНИХ ПРОЦЕСІВ ТА ПРОЕКТУВАННЯ ВИРОБНИЧИХ ПІДРОЗДІЛІВ ПІДПРИЄМСТВ АВТОМОБІЛЬНОГО ТРАНСПОРТУ В ІНТЕРАКТИВНОМУ НАВЧАЛЬНОМУ СЕРЕДОВИЩІ WORKLAB-AUTO

Abstract. The general structure, principles of operation and application of the author's interactive learning envi-ronment Worklab-Auto for the organization of technological processes of diagnosis, maintenance and repair of cars and the design of pro-duction units of automobile transport enterprises are described. The software complex includes a fairly extensive data-base, server and client parts with a WEB interface and access via the INTERNET network. System modules provide inter-active implementation and simulation of production situations, which significantly improves the quality and realism of design. The environment contains modules for the analysis of the enterprise's production activity, which analyze the state of the production and technical base and the organization of work in production units, providing tech-nological equipment and tools. Calculation modules provide for the determination of the annual volume of work, the number of workers and the number of posts, as well as the distribution of work by types and place of execution. The pro-duction units of the enterprise are formed in the organizational modules. Technological equipment is selected from the database for each production unit. The organization of workplaces involves in an interactive mode fixing for each work-place works that are similar in execution technology, as well as the necessary technological equipment and tools. The types of diagnostic maintenance or repair posts are selected from the database which are equipped with an inspection ditch, a lift or stationary post equipment, respectively. The graphic window of the room plan makes it possible to display and move the selected equipment, service posts, workplaces, gates, doors, windows on a large scale. The development and optimization of route technology involves the visual division of a given technological process into separate operations. Keywords: design, automobile transport enterprise, technological process, education, interactive and distance learning.

Inertial label-free sorting and chemotaxis of polymorphonuclear neutrophil in sepsis patients based on microfluidic technology

Reduced chemotactic migration of polymorphonuclear neutrophil (PMN) in sepsis patients leads to decreased bacterial clearance and accelerates the progression of sepsis disease. Quantification of PMN chemotaxis in sepsis patients can help characterize the immune health of sepsis patients. Microfluidic microarrays have been widely used for cell chemotaxis analysis because of the advantages of low reagent consumption, near-physiological environment, and visualization of the migration process. Currently, the study of PMN chemotaxis using microfluidic chips is mainly limited by the cumbersome cell separation operation and low throughput of microfluidic chips. In this paper, we first designed an inertial cell sorting chip to achieve label-free separation of the two major cell types by using the basic principle that leukocytes (mainly granulocytes, lymphocytes and monocytes) and erythrocytes move to different positions of the spiral microchannel when they move in the spiral microchannel under different strength of inertial force and Dean's resistance. Subsequently, in this paper, we designed a multi-channel cell migration chip and constructed a microfluidic PMN inertial label-free sorting and chemotaxis analysis platform. The inertial cell sorting chip separates leukocyte populations and then injects them into the multi-channel cell migration chip, which can complete the chemotaxis test of PMN to chemotactic peptide (fMLP) within 15 min. The remaining cells, such as monocytes with slow motility and lymphocytes that require pre-activation with proliferative culture, do not undergo significant chemotactic migration. The test results of sepsis patients ( n=6) and healthy volunteers ( n=3) recruited in this study showed that the chemotaxis index (CI) and migration velocity ( v) of PMN from sepsis patients were significantly weaker than those from healthy volunteers. In conclusion, the microfluidic PMN inertial label-free sorting and chemotaxis analysis platform constructed in this paper can be used as a new tool for cell label-free sorting and migration studies.

Microfluidic chip with integrated separation, mixing, and concentration operations for rapid and sensitive bacterial detection utilizing synthetic inorganic antibodies

In this paper, we presented a microfluidic chip that integrates bacterial separation, mixing, and concentration solely through fluid dynamics. Size-based bacterial separation was achieved through Dean flow and inertial focusing by harnessing the attributes of a spiral-shaped fluidic channel. Furthermore, Dean flow was capitalized upon to enable the mixing of bacteria with the detection substance, complemented by the integration of PDMS membrane filter for bacterial concentration, all unified within the chip architecture. The performance of individual components was validated using E. coli. In the separation experiment between 4.1 µm particles and E. coli, a separation efficiency of 87.07 ± 2.21% was measured for E. coli, and the mixer demonstrated a mixing efficiency of 92.8% at 30 μL/min flow rate. Concentrating E. coli through the filter for 30 min yielded an average loss rate of 7.47%. Moreover, the proposed microfluidic device was applied for bacterial detection using both our in-house-developed inorganic synthetic antibodies and commercially available fluorescent antibodies. Real-time optical measurements demonstrated the potential of the chip for cost-effective, rapid, and sensitive bacterial detection. The versatility of the chip was substantiated by its successful implementation for the E. coli detection at a concentration of 102 CFU/mL in spiked urine samples.

Възможности за приложение на теорията на ограниченията в предприятия от аграрния сектор

The theory of constraints (TOC) arose in the 1980s. Its creator is Eliahu Goldratt. It is mainly applied in industrial activities. Goldratt proposes a new concept of enterprise management, based on the systems approach and the management of cash flows - incoming and outgoing. However, if the enterprise carries out many functionally separated activities or it has several geographical segments with complex connections between them, then the scheme of a linear chain, without branches, proposed by Goldratt cannot be applied. Separate functional activities or geographic segments are organized and operated as separate operating segments for financial reporting purposes. The presented article explores the possibilities of applying TOC within agricultural enterprises, where there is diversification of activity and existing separate functional or geographical operational segments, something that is characteristic of Bulgarian agricultural enterprises. Two separate cases encountered in the business practice of enterprises from the agricultural sector are analyzed: 1. When the individual operating segments function independently of each other. 2. When the individual operating segments are interconnected.

Continuous microfluidic platform combining cell lysis and protein extraction for screening overall process conditions

AbstractBACKGROUNDMicrofluidic devices have been increasingly used as tools to accelerate the development of new biomanufacturing methods, given their ability to test a large set of variables in a short amount of time with minimal reagent consumption. However, while being able to expedite a bioprocess design, the modular aspect of these devices has not been systematically explored, with most applications focusing on single unitary operations. This paper explores the modular design of these devices through the development of an integrated microfluidic chip.RESULTSTwo separate unitary operations were included into a single device for continuous operation: product release by chemical cell lysis and product concentration by aqueous two‐phase system. In this way, it is possible to screen multiple conditions for each operation and evaluate their combined effect on the final product, making this a great tool in the development and optimization of a process. A recombinant Escherichia coli (E. coli) strain producing green fluorescent protein (GFP) was used as model system, which allows for lysis efficiency and partition coefficient to be evaluated by fluorescence microscopy. A chemical lysis solutions was used in the lysis step, presenting lysis efficiencies of about 100%, while a polyethylene glycol (PEG)/phosphate system was screened for the separation stage, presenting partition coefficients of about 4.CONCLUSIONSThe integrated device allowed for the continuous screening of multiple combinations of operation conditions, highlighting, for example, conditions where improvements on the lysis efficiency subsequently impaired the separation, decreasing the partition of the target product, thus demonstrating the need for the evaluation of a process in its entirety. In this way, the microfluidic device delivered a rapid process screening and optimization, with very low reagent consumption, and using a simple fluorescence microscope for data collection. © 2023 Society of Chemical Industry (SCI).

WEB DESIGN AND WEB PROGRAMMING IN THE MODERN INTERNET WORLD

Modern web content development capabilities are undergoing characteristic changes due to the improvement of web technologies in programming. The origin of web technologies began in the early 80s of the last century when the Hypertext Transfer Protocol (HTTP) and the Hypertext Markup Language (HTML) made a significant contribution to the development of Internet capabilities. The web evolution, characterised by scientific and technological progress in information technology, has opened up new opportunities for the development of web programming, which has led to the emergence of programming languages, frameworks, cascading style sheets, and hypertext markup languages. This research aims to study and analyse the key aspects of web programming and web design with a combination of modern features of the Internet environment. To analyse web design, the article considers the possibilities of using the Bootstrap framework, which combines and contains the HTML5 hypertext markup language, CSS3 cascading style sheets, and the JavaScript programming language. Having analysed two web development technologies—front-end and back-end—we can conclude that the presentation level (front-end development) corresponds to the client side, with which the client can interact and where dynamic elements can be added to an HTML page using JavaScript with the visual definition of a web page using CSS. In the case of back-end development, the application layer corresponds to the server side, with which the client cannot interact, as the shell is hidden. Using the modern capabilities of the programming language, its code, and a set of auxiliary tools in website development, the paper presents a development algorithm where each stage contains separate processes and operations during website development, which makes it impossible for them to exist independently. Thus, tools for designing and laying out websites using modern technologies can greatly simplify the development process, which can create higher-quality web content. Keywords: Web, web environment, web technologies, front-end, framework, Bootstrap, CSS3, HTML5, CCS3, JavaScript.

RATIONAL CONTROL BY TEMPERATURE IN VORTEX ENERGY SEPARATOR UNDER DESTABILIZING EFFECTS

The focus of this study is the arrangement of a rational control technique used to maintain the airflow temperature in a vortex energy separator (VES) under destabilizing effects. The objectives include the development of tools for the rational control of temperature in the cold and hot air flows of a VES. Methods used: Discrete state space, production rule statement, resolution of two-valued predicate equations, dichotomous trees, diagnosis, and recovery of dynamic objects. Problems settled: the studied features of the vortex energy separation process, architecture, and operation links of the rational control system were considered, mathematical models were deduced, and tools for diagnosing and recovering the efficiency of the vortex energy separator as a rational control object were developed. The scientific novelty of the study lies in the formation of instrumental tools to provide rational control of the airflow condition in the VES, where the control object is subjected to the substantial influence of various destabilizing effects.

Convolutional transformer network for fine-grained action recognition

Fine-grained action recognition is one of the critical problems in video processing, which aims to recognize similar actions of subtle interactions between humans and objects. Inspired by the remarkable performance of the Transformer in natural language processing, Transformer has been applied to the fine-grained action recognition task. However, Transformer needs abundant training data and extra supervision to achieve comparable results with convolutional neural networks (CNNs). To address these issues, we propose a Convolutional Transformer Network (CTN), which integrates the merits of CNN (e.g., sharing weights, capturing low-level features in videos and locality) and the benefits of Transformer (e.g., dynamic attention and learning long-range dependencies). In this paper, we propose two modifications to the original Transformer: (i) We propose a video-to-tokens module that can extract tokens from extracted spatial-temporal features in videos by 3D convolutions instead of the direct token embedding from raw input video clips; (ii) We completely replace the linear mapping in multi-head self-attention layer with depth-wise convolutional mapping, which applies a depth-wise separable convolution operation on embedded token maps. With these two modifications, our approach can extract effective spatial-temporal features from videos and process the long sequences of tokens encountered in videos. Experimental results demonstrate that our proposed CTN can achieve state-of-the-art accuracy on two fine-grained action recognition datasets (i.e., Epic-Kitchens and Diving 48) with a small computational increase.

Control of microfluidic separation processes governed by the Zweifach-Fung effect

This paper addresses several control problems for a prototypical microfluidic process designed for the separation operations of a fluid containing particles. The device is composed of one or several cascaded bifurcations that are traveled by the fluid. The volume fraction of particles in the flow is modified at each bifurcation. Fractionation is caused by the Zweifach–Fung effect, which governs the fluid dynamics in this device. It is a nonlinear effect that solely depends on the ratio of the flow rates in the branches. Propagation through the dead- volumes of the device and its capillary tubings generate input-varying delays of hydraulic type. These hydraulic delays strongly contribute to the complexity of the input–output dynamics to be controlled. The paper presents a model of the device and formulates some concise control problem statements for future research, along with illustrative simulation results. The case of single and dual bifurcation are presented.

Optimized resource usage with hybrid auto-scaling system for knative serverless edge computing

In the most popular serverless platform - Knative, dynamic resource allocation is implemented using horizontal auto-scaling algorithms to create or delete service instances based on different monitored metrics. However, the assigned resources for each instance are fixed. Vertical scaling up or down assigned resources per instance is required to avoid over-provisioning resources which are limited at the edge. Hybrid (horizontal and vertical) auto-scaling solutions proposed by existing works have several limitations. These solutions are optimized for separated services and get degraded performance when applied in a normal environment with multiple concurrent services. Further, most methods make significant changes to the original Knative platform, and have not been considered to be adopted since then. In this article, instead of Knative modification, we developed separated Kubernetes operators and custom resources (CRs) that can assist the Knative auto-scaler with optimal hybrid auto-scaling configurations based on traffic prediction. First, we characterize each service with a profile of different assigned resource levels pairing with their optimal target Knative’s horizontal scaling request concurrency. Then, based on these profiles, we calculate the best-assigned resources level, target concurrency level, and the number of required instances corresponding to each future time step’s predicted traffic. Finally, these configurations are applied to Knative’s default auto-scaler and services’ CR. Experiments done on our testbed compared our solution with a Knative hybrid auto-scaler solution that does not consider the service’s target request concurrency, and the default Knative horizontal auto-scaler. The results show our solution improvements up to 14% and 20% in terms of resource usage, respectively.

Ensuring the environmental safety of inland waterways by using off-board environmental technical means

The water transport operation, its safety and the organization of the fleet on inland waterways are presented in the paper. The problem of protecting water bodies from pollution by oil products, which are contained in the ship's bottom water (NW) formed during the operation of inland navigation vessels is considered. The results of studying this problem by the authors of the paper, based on the experience of solving this problem in the field of ships operation on the inland waterways, have shown that the most expedient, and often the only possible, way to solve it is an off-vessel treatment strategy, which involves organizing the treatment of bottom-bed water using technical means, which include in general specialized floating facilities providing reception of bilge water from operating vessels, transportation and treatment. The main principles for the offshore cleaning strategy implementation are formulated. In accordance with this strategy it is proposed to consider offshore cleaning as a certain technology, the content of individual operations of which, as well as the composition of the complex of technical means that ensure the implementation of its various options, is determined by the conditions for organizing off-board cleaning on the considered sections of the waterways, which include the need to ensure safety, requirements for the disposal of treated bilge water, as well as economic efficiency. It is shown that under certain conditions it is expedient to carry out separate operations for water purification using different technical means. The main options for the composition of the complex of technical means, including autonomous floating treatment facilities, are proposed. It has been shown that the possibility of choosing the composition of technical means makes it possible to take into account the operating conditions of ships, as well as the organization of off-board cleaning, which provides an effective solution to the problem of ensuring the safety of navigation.

An Efficient and Stable Lithium‐Oxygen Battery Based on Metal‐Organic Framework Separator Operating at 160 °C

AbstractA lithium oxygen battery (LOB) with molten salt electrolyte operating at elevated temperature has aroused great interest because it enables fast reaction kinetics. However, there is still a lack of open literature on the separator (membrane) of this kind of LOB. Metal‐organic framework (MOF) materials are widely used as components of separators in many kinds of energy storage devices, due to their regular crystalline and well‐defined pore structures. In this work, a MOF material, zirconium (II) 1,4‐benzenedicarboxylate after lithiation (UiO‐66‐SO3Li) with a narrow pore size (6 Å), is used as a key component of the separator for LOB operating at elevated temperature. A “rolling dough” method is adopted to prepare the separator, which achieves 100% material utilization. The LOB with this membrane operates at 160 °C and delivers a specific capacity of 5.1 mAh cm−2 with an overpotential as low as 40 mV at 0.1 mA cm−2 and a prolonged cycle life, 180 cycles with a high coulombic efficiency of 99.9% at 0.5 mA cm−2. This MOF‐based membrane provides efficient Li+ transfer and restricts discharge product migration during battery operation, which is promising for the development of LOB in large‐scale practical applications.

Electric Separation of Ash and Slag Waste Kashirskaya GRES

The advantage of electrical separation in the processing of classified ash and slag as the main separation operation was substantiated. It was recommended to switch to electrical separation as the first technological operation and carry out the entire cycle of ash and slag processing using dry methods due to their economic benefits compared to wet ones. It was emphasized that dry methods do not require the reagents and do not lead to subsequent secondary pollution of the environment. The possibility of obtaining iron-containing and aluminosilicate products for construction and other industries was confirmed.

Benefit compensation of hydropower-wind-photovoltaic complementary operation in the large clean energy base

Under the goal of global carbon reduction, hydropower-wind-photovoltaic complementary operation (HWPCO) in the clean energy base (CEB) has become the key to achieving a high-quality clean energy supply. However, stochastic wind power and photovoltaic need the help of adjustable hydropower to get onto the grid in the HWPCO process, which makes the conflict between different power generation entities more and more complex. This paper takes Yalong River CEB as the research object and sets up the separate operation scenario and complementary operation scenario of hydropower stations and wind-photovoltaic plants. Meanwhile, the corresponding day-ahead schedule model considering the stability of the power system is established. On this basis, this paper analyzes changes in profit and loss indexes of each power generation entity and clarifies the profit and loss relationship of different power generation entities in the CEB. Further, based on the model group for quantifying contributions and the compensation electricity contribution value, this paper proposes the benefit compensation mechanism between the cascade hydropower station and wind-photovoltaic plants and the benefit compensation mechanism between each hydropower station within the cascade hydropower station. The main results of the research are as follows: (1) after HWPCO, the total revenue of wind-photovoltaic plants increases by 61.48 million RMB (8.61 million dollars), and the total revenue of the cascade hydropower station decreases by 10.77 million RMB (1.51 million dollars), which means wind-photovoltaic plants are the beneficiary and the cascade hydropower station is the loss. (2) after the benefit compensation, the total revenue of wind-photovoltaic plants increases by 20.97 million RMB (2.94 million dollars), and the total revenue of the cascade hydropower station increases by 29.74 million RMB (4.16 million dollars) compared with the hydropower-wind-photovoltaic separate operation (HWPSO). By the benefit compensation mechanism proposed in this paper, the benefit of each power generation entity can reach a relative balance in the Yalong River clean energy base.

Superoleophobic TiO2@SSM membranes with antifouling and photocatalytic ability for efficient microbubbles flotation emulsion separation and organic pollutants degradation

In this paper, a stainless steel mesh coated with titanium dioxide (TiO2@SSM) membrane was developed for the separation of stable oil-water emulsions and the degradation of soluble pollutants. The TiO2@SSM membrane showed excellent underwater anti-oil adhesion performance and efficient emulsion separation under gravity (flux of 207.7 L m−2 h−1 and efficiency of 99.58 % for toluene-water emulsion). The emulsion could also be pre-broken by microbubble flotation to enhance the separation performance of the TiO2@SSM membrane (microbubble flotation followed by separation has a flux of 369.3 L m−2 h−1, and efficiency of 99.71 %). And the synergistic operation of separation and microbubble flotation can increase the flux to 451.6 L m−2 h−1. The membrane showed outstanding stability and could be recycled for more than 20 times without significant deterioration, and demonstrated chemical stability for corrosion resistance test (pH 0–14). In addition, the membrane, which is easily modified with silver nanoparticles, achieves improved photocatalytic degradation properties (efficiency from 58.8 % to 88.7 %) and microbubble flotation effect (flux of 613.4 L m−2 h−1). This work provides a rational strategy for the preparation and optimization of inorganic functional membranes for effective emulsion separation and dye degradation, and demonstrates promising applications of the separation and purification in oil-containing sewage and wastewater remediation.

Numerical Investigation on the Performance of Cyclone Separators

Cyclone separators are commonly employed in the solid particle separation process due to their simplicity and low-cost manufacture. Collection efficiency and pressure drop are two of the most important factors. Small-size cyclone separator has outperformed collection efficiency. However, due to its small size, it’s hard to detailed flow investigation experimentally. So, the target of this work is to perform a numerical investigation of the flow characteristics as well as the collection efficiency and pressure drop of small cyclone separators, using Ansys Fluent software. Discrete Phase Model is included to simulate the particle-flow interaction. Different values of velocity inlet and particle size are considered. Typical flow characteristics of cyclone separators with a strong vortex are revealed. Results also show that the larger particle size or the stronger inlet velocity provides higher collection efficiency. Particularly, for a typical particle diameter of 2.96 micrometers, the collection efficiency of the cyclone separator is always higher than 91% when the inlet velocity surpasses 15 m/s. All these results provide a valuable framework for the operation of cyclone separators.

Modeling of a low-temperature gas treatment system

Objective. The main purpose of the work is: investigation of the effect of changes in technological parameters on the efficiency of the separation process and determination of optimal technological modes of operation of gas field X CNTS in the separation process.Method. The problem was solved in the KBC Petro-SIM computer program and the LTS model was built. To conduct the study, a model of the LTS was built in the KBC Petro-SIM computer program.Result. The results obtained with the help of it showed: with the current composition of the gas with a decrease in temperature for every 2oC, with other technological indicators being equal, the specific condensate yield increases in the range from 15 to 30%, and the lower the temperature, the higher this percentage. When the pressure on the throttle decreases by every 0.4 MPa, the condensate output increases, if the pressure drops below 1.8 MPa, the specific condensate output will begin to decrease, which is explained by the pressure drop below the maximum condensation line of the phase diagram. The change in gas flow within the design values did not affect the operation of low-temperature separation. At any available low temperature and high pressure at the inlet to the ILTS, the most optimal mode will be when the pressure after the throttle is maintained within 1.8 - 1.9 MPa. The maximum specific yield of gas condensate (48.21%) was obtained at a pressure at the inlet to the ILTS of 5.1 MPa, a temperature after the heat exchanger of minus 2oC and a pressure drop at the throttle of 3.05 MPa. As part of the numerical research, the following results were obtained: with an increase in the pressure at the inlet to the ILTC, the change in the specific output of the gas condensate is insignificant, but with this parameter it is possible to create a larger pressure drop on the throttle; with a decrease in the gas temperature at the outlet of the heat exchanger, the specific yield of the gas condensate will increase; with an increase in the pressure drop at the throttle, the specific output of the gas condensate increases until the pressure after the throttle reaches the range of values of 1.8 – 1.9 MPa. In this interval, the maximum specific condensate yield is achieved. With a further increase in the pressure drop on the throttle, the specific output of the gas condensate decreases. This is explained by the phenomenon of retrograde condensation, since the maximum condensation line is in the range of these pressures.Conclusion. Based on the results of the work, it was found that the developed software module can be used to solve the emerging series of problems. The results of the work show the suitability of the proposed method for practical purposes.

Computer vision application for industrial Li-ion battery module disassembly

Automated robot-assisted disassembly is essential for the flexible disassembly of Li-ion battery modules for economic and safety reasons. In such a case, a CAD model for the planning process is of immense benefit. The geometric uncertainties due to the breathing of the Li-ion cells as well as the presence of component tolerances underline the importance of a sensor-based detection approach to determine the actual state of the battery module, which is crucial to ensure an automated and reliable disassembly process. In this paper, we present a method for 3D camera-based localization of points on deformed battery modules, aiding in identifying support points for milling operations in robot-assisted disassembly cells. This separation operation planning employs a CAD model, and our introduced computer vision “data processing pipeline”—a systematic series of processing steps—bridges the gap between the CAD model and the actual battery module. This involves capturing the module using a 3D camera and subsequently registering its points with the CAD model’s points. Central to this process are two algorithms: The Bayesian Coherent Point Drift (BCPD) algorithm ensures accurate non-rigid registration, while TEASER++ aids in reducing computational time. We demonstrate the effectiveness of these combined algorithms in our pipeline through rigorous testing and metrics, evidencing that a balance between accuracy and computational speed can be attained by adjusting point density.