Sequential Operations Research Articles

Nonlinear periodic response analysis of mechatronic systems with friction

Nonlinearities are present in many coupling components of mechanical and mechatronic systems, with the most common nonlinear coupling property being that of friction force. Transient simulation of systems with nonlinear friction can be a challenge in terms of solver robustness and calculation time. Moreover, many manufacturing processes lead to periodic forces and motions such as in milling, or repetitive pick-and-place serial production operations. In this paper, a method and application for nonlinear periodic response analysis (NPRA) of reduced-order mechatronic systems is presented, which leverages the fact that the majority of components in common mechatronic systems (e.g. machine tools) are linear. The dynamic behaviour of these components can thus be represented using a linear reduced order model (ROM). The analysis is implemented using the Harmonic Balance Method (HBM), which is then applied to the ROM of a simple, structurally compliant mechatronic system with a motion controller and profiled rail guideways. A practical case encountered in industrial settings is analysed, that being the testing of a system’s frequency response. Periodic responses to a harmonic velocity setpoint input oscillation are analysed in both time and frequency domains and comparisons then made between measurement and simulation. This comparison shows that many significant effects of nonlinear friction in ROMs of mechatronic systems can be modelled using the NPRA method and a simple friction model with a presliding regime. The combination of HBM with model order reduction (MOR) opens up a field of applications for the efficient and robust simulative analysis of periodic processes with nonlinear couplings in complicated mechatronic systems.

Highly efficient combination of multiple single cells using a deterministic single-cell combinatorial reactor.

Compartmentalization of multiple single cells and/or single microbeads holds significant potential for advanced biological research including single-cell transcriptome analysis or cell-cell interactions. To ensure reliable analysis and prevent misinterpretation, it is essential to achieve highly efficient pairing or combining of single objects. In this paper, we introduce a novel microfluidic device coupled with a multilayer interconnect Si/SiO2 control circuit, named the deterministic single-cell combinatorial reactor (DSCR) device, for the highly efficient combination of multiple single cells. The deterministic combination of multiple single cells is realized by sequentially introducing and trapping each cell population into designated trap-wells within each DSCR. These cell-sized trap-wells, created by etching the SiO2 passivation layer, generate a highly localized electric field that facilitates deterministic single-cell trapping. The device's multilayer interconnection of electrodes enables the sequential operation of each trap-well, allowing precise trapping of each cell population into designated trap-wells within an array of combinatorial reactors. We demonstrated the feasibility of the DSCR by sequentially trapping three distinct groups of PC3 cells, each stained with a different fluorescent dye (blue, green, or red). This method achieved a 93 ± 2% pairing efficiency for two cell populations and an 82 ± 7% combination efficiency for three cell populations. Our innovative system offers promising applications for analyzing multiple cell-cell communications and combinatorial indexing of single cells.

Powder Bed Additive Manufacturing Using Machine Learning Algorithms for Multidisciplinary Applications: A Review and Outlook

Additive manufacturing overcomes the limitations associated with conventional processes, such as fabricating complex parts, material wastage, and a number of sequential operations. Powder-bed additives fall under the category of additive manufacturing process, which, in recent years, has captured the attention of researchers and scientists working in various fields of science and engineering. Production of powder bed additive manufacturing (PBAM) parts with consistent and predictable properties of powders used during the manufacturing process plays an important role in deciding printed parts' reliability in aeronautical, automobile, biomedical, and healthcare applications. In the PBAM process, the most commonly used powders are polymer, metal, and ceramic, which cannot be effectively used without understanding powder particles' physical, mechanical, and chemical properties. Several metallic powders like titanium, steel, copper, aluminum, and nickel, several polymer polyamides (nylon), polylactide, polycarbonate, glass-filled nylon, epoxy resins, etc., and the most commonly used ceramic powders like aluminum oxide (Al2O) and zirconium oxide (ZrO2) can be utilized depending upon the method being adopted during PBAM process. Adoption of some post-processing techniques for powder, such as grain refinement can also be employed to improve the physical or mechanical properties of powders used for the PBAM process. In this paper, the effect of powder parameters, such as particle size, shape, density, and reusing of powder, etc., on printed parts have been reviewed in detail using characterization techniques such as X-ray computed tomography, scanning electron microscopy, and X-ray photoelectron spectroscopy. This helps to understand the effect of particle size, shape, density, virgin and reused powders, etc., used during the PBAM process. This article has reviewed the selection of appropriate process parameters like laser power, scanning speed, hatch spacing, and layer thickness and their effects on various mechanical or physical properties, such as tensile strength, hardness, and the effect of porosity, along with the microstructure evolution. One of the drawbacks of additive manufacturing is the variability in the quality of printed parts, which can be eliminated by monitoring the process using machine learning techniques. Also, the prediction of the best combination of process parameters using some advanced machine learning algorithms (MLA), like random forest, k nearest neighbors, and support vector machine, can be effectively utilized to quantify the performance parameters in the PBAM process. Thus, implementing machine learning in the additive manufacturing process not only helps to learn the fundamentals but helps to identify, predict and help to make actionable recommendations that help optimize printed parts quality. The performance of various MLAs has been evaluated and compared for projecting future research directions and suggestions. In the last part of this article, multidisciplinary applications of the PBAM process have been reviewed in detail. Additive manufacturing processes carried out by using conventional machines, called hybrid additive manufacturing, have also been reviewed by discussing their methods and arrangements in detail.

Memristive Ion Dynamics to Enable Biorealistic Computing.

Conventional artificial intelligence (AI) systems are facing bottlenecks due to the fundamental mismatches between AI models, which rely on parallel, in-memory, and dynamic computation, and traditional transistors, which have been designed and optimized for sequential logic operations. This calls for the development of novel computing units beyond transistors. Inspired by the high efficiency and adaptability of biological neural networks, computing systems mimicking the capabilities of biological structures are gaining more attention. Ion-based memristive devices (IMDs), owing to the intrinsic functional similarities to their biological counterparts, hold significant promise for implementing emerging neuromorphic learning and computing algorithms. In this article, we review the fundamental mechanisms of IMDs based on ion drift and diffusion to elucidate the origins of their diverse dynamics. We then examine how these mechanisms operate within different materials to enable IMDs with various types of switching behaviors, leading to a wide range of applications, from emulating biological components to realizing specialized computing requirements. Furthermore, we explore the potential for IMDs to be modified and tuned to achieve customized dynamics, which positions them as one of the most promising hardware candidates for executing bioinspired algorithms with unique specifications. Finally, we identify the challenges currently facing IMDs that hinder their widespread usage and highlight emerging research directions that could significantly benefit from incorporating IMDs.

Epidemiology of Rounding Error.

This work represents a significant contribution to understanding the importance of appropriately rounding numbers with minimal error. That is, to reduce inexact rounding and data truncation error and simultaneously eliminate unintentional misleading findings in epidemiological studies. The rounding of numbers represents a compromise solution that attempts to find a balance between the loss of information from reporting too few significant digits versus retaining more digits than necessary. Substituting a rounded number for its original value may be acceptable and practical in many applied situations if an adequate degree of accuracy is retained. On the other hand, numeric error may result from improper rounding or data truncation which, in effect, compromises the credibility of study findings and may lead to a false sense of discovery. Performing complex computations on such values, especially when sequential or composite operations are involved, can lead to error propagation and inaccurate results. Having an overall awareness of the nature and impact of rounding error, including preventive actions, can contribute greatly to the integrity of research, yielding more reliable and accurate conclusions. Heuristic examples are provided to illustrate the consequences of rounding and data truncation error in epidemiology studies, specifically those pertaining to relative effect estimation.

Ternary Logic Transistors Using Multi-Stacked 2D Electron Gas Channels in Ultrathin Oxide Heterostructures.

2D electron gas field-effect transistors (2DEG-FETs), employing 2DEG formed at an interface of ultrathin (≈6nm) Al2O3/ZnO heterostructure as the active channel, exhibit outstanding drive current (≈215µA), subthreshold swing (≈132mV dec-1), and field effect mobility (≈49.6 cm2V-1 s-1) with a high on/off current ratio of ≈107. It is demonstrated that the Al2O3 upper layer in Al2O3/ZnO heterostructure acts as the source/drain resistance component during transistor operations, and the applied potential to the 2DEG channel is successfully modulated by Al2O3 thickness variations so that the threshold voltage (Vth) is effectively tuned. Remarkably, double-stacked 2DEG-FETs consisting of two Al2O3/ZnO heterostructured 2DEG channels with a single gate exhibit multiple Vth, enabling a ternary logic state in a single device. By inducing a voltage difference between the stacked channels, a sequential operation of the upper and lower FETs is achieved, successfully realizing a stable ternary logic operation.

РОЗРОБКА ТА ВИРОБНИЦТВО ЛЕГКИХ ЛІТАЛЬНИХ АПАРАТІВ СІЛЬСЬКОГОСПОДАРСЬКОГО ПРИЗНАЧЕННЯ

Issues of protecting plants from diseases and pests are becoming more and more urgent. Climate change causes an increase in the activity of weedy plants and insects harmful to agriculture. Because of this, the chemical treatment of fields by aviation in modern agriculture should serve the purpose of preserving the future harvest in both a qualitative and quantitative sense. An important role in this is played by the biological method of plant protection, which is quite effective and environmentally friendly. It is based on the use of living organisms, their waste products and biologically active substances that regulate the development and reproduction of harmful plant organisms. Scientists have developed technologies for the breeding of such zoophages to protect plants from plant pests: Trichogramma, predatory mite Phytoseiulus, encarzia, Aphidimyza gallica, etc., as well as the production of microbiological preparations to protect plants from diseases and pests, the high efficiency of their use has been proven. Aircraft (planes, helicopters, ultralight aircraft) that are registered in the State Register of Civil Aviation Aircraft of Ukraine and have a certificate for the right to perform aerochemical work are allowed to carry out aerial work on the application of pesticides during agrochemical activities on agricultural and forest crops. The requirements for the characteristics of the aircraft, directive requirements for the technology of production, operation and maintenance of airworthiness were formulated. The evaluation of the manufacturability of the considered products (agricultural LA) cannot be evaluated without taking into account the operational manufacturability, which largely determines the costs when performing work in the field. Along with the requirements for the manufacturability of the aircraft design, the so-called operational requirements are of great importance. These requirements determine the suitability of the structure and equipment for its maintenance and repair during the operation of the aircraft, taking into account the high quality of work, the least consumption of time, labor and materials. Satisfying operational requirements ensures reliability, durability of the aircraft, high labor productivity during maintenance, reduction of operational costs and efficiency of use of the aircraft fleet. The appearance of the trichogram required the development of special means for its introduction. An attempt to use existing means showed their unsuitability due to their low functional efficiency and high cost of work. The task was solved by increasing the manufacturability of agricultural aircraft during their production and operation. This made it possible to organize its serial production and operation in many farms of the country.

Optimizing Batch Scheduling of Multiproduct Pipelines Using a Smooth Modeling Approach

Summary The main method of delivering oil products is by the sequential operation of pipelines. Scheduling oil batches efficiently, considering intricate constraints, is typically a challenging problem that is not readily solvable. The present work developed a systematic approach for the optimization of batch scheduling. The model utilized a continuous-time representation with the objective of minimizing the total costs related to energy and oil mixing loss. The analysis included multiple constraints, including time frame, oil download, flow rate, and fluctuations in pressure caused by friction at various batch interface locations. By applying the penalty function approach, the original model was transformed into an unconstrained model. Smoothing was applied to the noncontinuous variables using the Dirac delta function and the maximum entropy function. A novel nonlinear programming (NLP) model was successfully devised to enhance the efficiency of oil product scheduling. A successive function approximation algorithm was used to solve the model, and the decision variables were modified to decrease the number of model decision variables and enhance the system’s capacity to surpass the local optimum. Subsequently, the model was calculated to address a practical multiproduct pipeline scheduling problem. The model presented in this study identified 74 decision variables, which account for around 1% of the typical mixed integer linear programming (MILP) model. The method presented in this work has the capability to accurately obtain an enhanced solution, making it useful for real applications.

Estimation and Control of WRRF Biogas Production

The development of resource-efficient digital technologies is a critical challenge in the wastewater sector. This industrial case study, conducted in collaboration with the Veas Water Resource Recovery Facility in Norway, focused on creating data pre-processing methods and resource-efficient control strategies. Using data from the Veas biogas plant, dynamic models were developed to compare control outcomes. The primary objective was to maximize biogas production and hot water usage while maintaining optimal temperature and hydraulic retention time by adjusting inlet sludge and hot water flow rates. Sequential operations were approximated as continuous operations using a 30-min moving minimum/maximum for bimodal data and a 2-h moving average for noisy data. The data-driven dynamic models achieved an accuracy of up to R2 of 0.85. The control strategy, which included one feedback controller, one ratio controller, and flow rate restrictions, was compared to real production data (baseline) and tested across six scenarios. The best improvement over the baseline scenario resulted in a 3% increase in total biogas production, a 6% increase in total organic loading, a 13% increase in hot water use, and a one-day reduction in hydraulic retention time. Future work should focus on control studies using extended datasets and nonlinear models.

Autonomous online optimization of a closed-circuit reverse osmosis system

As freshwater becomes increasingly scarce, many industrial and municipal water utilities look at premise-scale water treatment and reuse to meet water demand. Closed-circuit reverse osmosis (CCRO) has been proposed as a promising process design to do so. This sequencing batch process enables operation at higher brine salinity levels by means of a recycle flow. Optimal operation requires that the maximum salinity level at the membrane surface represents an optimal trade-off between brine disposal costs and energy efficiency. This maximum salinity level may change over time as the feed water composition changes and electricity markets fluctuate. In this article, we present the results of the experimental evaluation of an automatic technique for continuous online optimization, known as extremum seeking control. This technique has a long history in the process control community but has received little traction so far in the water industry. We modify this technique to enable its use for online optimization of CCRO, specifically to account for its sequential batch operation. We challenge the optimization schemes through several experimental tests and illustrate the advantages and drawbacks of extremum-seeking control.

Realization of quasi-steady-state piled smouldering using sequential operation chambers for industrial treatment of biomass wastes.

Piled smouldering has great potential for treatment and utilization of biomass wastes. However, its unsteady-state nature limits its industrial utilization, as well as treatment of smoke. This article addresses this issue by proposing the sequential operation of numerous smouldering chambers to realize steady- or quasi-steady-state piled smouldering. The superposition characteristics of sequential unsteady-state curves were analysed theoretically, and a code was developed to determine an appropriate number of piled chambers at an allowance oscillation percentage. Smouldering experiments were performed on a single mini chamber (length × width × height: 340 × 140 × 140 mm3) containing piled wood pellets mixed with wood powder. The superposition of sequential burning rate curves was demonstrated using the code based on the mass loss data of experiments. Analysis shows that the perfect-steady state is possible given the superposition value of the burning rate curve is a constant in this proposed system. Experiments show that the molar ratio of CO/CO2 in smoke is almost a constant around 0.5 during densely piled smouldering, showing the great potential for self-sustained burning out the smoke. Based on the experimental results, the calculation results show that the relative oscillation range of burning rate (OSC) decreases from 75% to 3% while increasing the number of chambers from 2 to 7. This work provides a novel technology to enable quasi-steady-state smouldering for industrial utilization.

Technology of production of aluminosilicate refractories for units processing fluorinated waste

The aluminium production process through the electrolysis of cryolite-alumina melts involves a series of interconnected, sequential, and parallel technological operations, each defined by a specific level of engineering and technological advancement. The development of the modern aluminum industry is closely tied to the adoption of resource-efficient and environmentally friendly technologies, which focus on recycling secondary materials and industrial waste. Fluorinated carbon-based materials release fluorine into the gas phase at relatively low temperatures when heated, and in thermal units processing fluorinated waste, this fluorine, along with alkali metals, will remain in the gas phase. To enhance the durability of furnace linings against the corrosive atmosphere, refractories with the highest possible density (low porosity) and a high concentration of mullite in the matrix (the finely ground component of the batch) are required. These properties can only be achieved in refractory products produced by the semi-dry pressing method, which ensures high grain packing density and leads to the formation of a ceramic mullite bond after firing.

Structure and Properties of the Electroexplosive Coating of the TiB2-Ag System after Electron Beam Treatment

A coating of the TiB2-Ag system was formed through the use of sequential operations of electroexplosive spraying and electron beam processing. The values of electrical conductivity (62.0 MS/m), Vickers microhardness (0.251-0.265 GPa at the point of measurement on a silver matrix and 25-32 GPa at the point of measurement at inclusions of boride phases), nanohardness (4.48 ± 0.76 GPa) were determined), Young’s modulus (116±29 GPa), wear parameter under dry friction-sliding conditions (1.2 mm3/N • m) and friction coefficient (0.5). Switching wear resistance during accelerated tests was 7000 on and off cycles with an electrical resistance of 10.01 - 11.76 LiOhm. The thickness of the coatings is 100 microns. The coatings are formed by a silver matrix with inclusions of titanium borides located in it with three types of sizes: nanocrystalline, submicrocrystalline and microcrystalline. Quantitatively, in the structural composition among titanium borides, titanium diboride and silver (56 wt. %) are formed predominantly (41 wt. %), while other titanium borides account for 3 wt. %. Structural transformations are described using complementary methods of X-ray phase analysis, scanning and transmission electron microscopy.

Закладка виноградника на основе принципов энерго-ресурсосбережения

Abstract. The article contains materials that form the basis of a feasibility study (FS) for laying a vineyard (from planting to fructification), developed according to the principle of energy and resource conservation provided for in the project assignment. The project documentation is being developed in order to optimize the complex of sequential technological operations and production processes aimed at creating a sustainably functioning viticultural economy. The general principles of energy and resource conservation include: the latest achievements of science and best practices in the field of viticulture, rational use of land funds, thanks to preliminary soil surveys, optimized varietal composition, design of plantings and compact placement of arrays with the prospect of irrigation, reduction of energy losses to the level of operationally unavoidable, the use of highly concentrated, complex agrochemicals and methods of their application, the availability of appropriate infrastructure, design estimates optimized with the prospect of improvement and modernization (energy and resource-saving object estimates), planned economic productivity of plantations, measures to maintain the economic fertility of soils corresponding to the biological requirements of grape culture, which determines the stability and productivity of perennial plantations. Methodological approaches and current methods, publications of a recommendatory nature used for the development of a feasibility study are indicated. The successive stages of the development of project documentation are considered, the techniques that contribute to reducing the costs of production processes are outlined. The recommended regionalized and promising assortment of grapes for the formation of highly productive stable ampelocenoses ensuring stable highly profitable functioning of enterprises of the grape-growing industry in the Krasnodar region is presented and justified. The recommended current varietal composition of plantings is compiled taking into account the edaphoclimatic conditions of the design object, the agrobiological characteristics of grape varieties, as well as taking into account current global trends in the organization of a sustainably functioning highly efficient industrial enterprise for the production of viticulture products. Keywords: ampelocenosis, project assignment, long-term planning, varietal policy, energy and resource conservation

Pilot microbial electrolysis cell closes the hydrogen loop for hydrothermal wet waste conversion to jet fuel

The global shift toward net-zero emissions necessitates resource recovery from wet waste. In this study, we demonstrate the first feasibility of combining pilot-scale microbial electrolytic cells (MECs) with hydrothermal liquefaction (HTL) for simultaneous post-hydrothermal liquefaction wastewater (PHW) treatment and efficient hydrogen (H₂) production to meet biocrude upgrading requirements. Long-term single reactor operation revealed that fixed anode potential enabled rapid startup, and low catholyte pH and high salinity were effective in suppression of cathodic methanogenesis and acetogenesis – resulting in high current density of 16.6 A m−2 and 9.3 A m−2 when feeding synthetic wastewater and PHW respectively. Additionally, the anode biofilm exhibited spatial variations in response to local environmental conditions. Onsite parallel or serial operations of multiple MECs showed good performance using actual PHW with a record-high H2 production rate of 0.5 L LR day−1 for MEC over 10 liters scale, and the optimal chemical oxygen demand (COD)-to-H2 yield reached 0.127 kg-H2 per kg-COD, supporting a self-sufficient, closed-loop upgrade to jet fuel.

ACU-TransNet: Attention and convolution-augmented UNet-transformer network for polyp segmentation.

UNet has achieved great success in medical image segmentation. However, due to the inherent locality of convolution operations, UNet is deficient in capturing global features and long-range dependencies of polyps, resulting in less accurate polyp recognition for complex morphologies and backgrounds. Transformers, with their sequential operations, are better at perceiving global features but lack low-level details, leading to limited localization ability. If the advantages of both architectures can be effectively combined, the accuracy of polyp segmentation can be further improved. In this paper, we propose an attention and convolution-augmented UNet-Transformer Network (ACU-TransNet) for polyp segmentation. This network is composed of the comprehensive attention UNet and the Transformer head, sequentially connected by the bridge layer. On the one hand, the comprehensive attention UNet enhances specific feature extraction through deformable convolution and channel attention in the first layer of the encoder and achieves more accurate shape extraction through spatial attention and channel attention in the decoder. On the other hand, the Transformer head supplements fine-grained information through convolutional attention and acquires hierarchical global characteristics from the feature maps. mcU-TransNet could comprehensively learn dataset features and enhance colonoscopy interpretability for polyp detection. Experimental results on the CVC-ClinicDB and Kvasir-SEG datasets demonstrate that mcU-TransNet outperforms existing state-of-the-art methods, showcasing its robustness.

Valved Microwell Array Platforms for Stepwise Liquid Dispensing.

The fabrication of microarray chips and the precise dispensing of nanoliter to microliter liquids are fundamental for high-throughput parallel biochemical testing. Conventional microwells, typically featuring a uniform cross section, fill completely in a single operation, complicating the introduction of multiple reagents for stepwise and combinatorial analyses. To overcome this limitation, we developed an innovative valved microwell array. Using ultraviolet (UV)-curing resin three-dimensional (3D) printing, these multilayer configurations can be rapidly fabricated through direct template printing and polydimethylsiloxane (PDMS) casting. Each microwell incorporates a microvalve structure, truncating fluids within the upper metering well and allowing transfer to the bottom reservoir well under centrifugal force. Sequential operations enable the introduction of multiple reagents, facilitating orthogonal combinations for complex assays. We explored four types of valving methods: DeepWell, Expansion, Bottleneck, and Membrane valve, each offering varying degrees of design complexity, operational efficiency, robustness, and precision. These methods constitute a versatile toolkit to accommodate a broad spectrum of analytical requirements. Our innovative approach redefines microwell architecture, direct manufacturing techniques, and stepwise fluid dispensation in microarrays.

Memristive Crossbar Array-Based Probabilistic Graph Modeling.

Modern graph datasets with structural complexity and uncertainties due to incomplete information or data variability require advanced modeling techniques beyond conventional graph models. This study introduces a memristive crossbar array (CBA)-based probabilistic graph model (C-PGM) utilizing Cu0.3Te0.7/HfO2/Pt memristors, which exhibit probabilistic switching, self-rectifying, and memory characteristics. C-PGM addresses the complexities and uncertainties inherent in structural graph data across various domains, leveraging the probabilistic nature of memristors. C-PGM relies on the device-to-device variation across multiple memristive CBAs, overcoming the limitations of previous approaches that rely on sequential operations, which are slower and have a reliability concern due to repeated switching. This new approach enables the fast processing and massive implementation of probabilistic units at the expense of chip area. In this study, the hardware-based C-PGM feasibly expresses small-scale probabilistic graphs and shows minimal error in aggregate probability calculations. The probability calculation capabilities of C-PGM are applied to steady-state estimation and the PageRank algorithm, which is implemented on a simulated large-scale C-PGM. The C-PGM-based steady-state estimation and PageRank algorithm demonstrate comparable accuracy to conventional methods while significantly reducing computational costs.

A Study on the Importance of Sequential Medical Property Development and Operation - focusing on location characteristics -

A Study on the Importance of Sequential Medical Property Development and Operation - focusing on location characteristics -

CTRNet: An Automatic Modulation Recognition Based on Transformer-CNN Neural Network

Deep learning (DL) has brought new perspectives and methods to automatic modulation recognition (AMR), enabling AMR systems to operate more efficiently and reliably in modern wireless communication environments through its powerful feature learning and complex pattern recognition capabilities. However, convolutional neural networks (CNNs) and recurrent neural networks (RNNs), which are used for sequence recognition tasks, face two main challenges, respectively: the ineffective utilization of global information and slow processing speeds due to sequential operations. To address these issues, this paper introduces CTRNet, a novel automatic modulation recognition network that combines a CNN with Transformer. This combination leverages Transformer’s ability to adequately capture the long-distance dependencies between global sequences and its advantages in sequence modeling, along with the CNN’s capability to extract features from local feature regions of signals. During the data preprocessing stage, the original IQ-modulated signals undergo sliding-window processing. By selecting the appropriate window sizes and strides, multiple subsequences are formed, enabling the network to effectively handle complex modulation patterns. In the embedding module, token vectors are designed to integrate information from multiple samples within each window, enhancing the model’s understanding and modeling ability of global information. In the feedforward neural network, a more effective Bilinear layer is employed for processing to capture the higher-order relationship between input features, thereby enhancing the ability of the model to capture complex patterns. Experiments conducted on the RML2016.10A public dataset demonstrate that compared with the existing algorithms, the proposed algorithm not only exhibits significant advantages in terms of parameter efficiency but also achieves higher recognition accuracy under various signal-to-noise ratio (SNR) conditions. In particular, it performs relatively well in terms of accuracy, precision, recall, and F1-score, with clearer classification of higher-order modulations and notable overall accuracy improvement.