Engineering g-C_(3)N_(4)based materials for advanced photocatalysis:Recent advances

Photocatalysis driven by abundant yet intermittent solar energy has considerable potential in renewable energy generation and environmental remediation.The outstanding electronic structure and physicochemical properties of graphitic carbon nitride(g-C_(3)N_(4)),together with unique metal-free characteristic,make them ideal candidates for advanced photocatalysts construction.This review summarizes the up-to-date advances on g-C_(3)N_(4)based photocatalysts from ingenious-design strategies and diversified photocatalytic applications.Notably,the advantages,fabrication methods and limitations of each design strategy are systemically analyzed.In order to deeply comprehend the inner connection of theory–structure–performance upon g-C_(3)N_(4)based photocatalysts,structure/composition designs,corresponding photocatalytic activities and reaction mechanisms are jointly discussed,associated with introducing their photocatalytic applications toward water splitting,carbon dioxide/nitrogen reduction and pollutants degradation,etc.Finally,the current challenges and future perspectives for g-C_(3)N_(4)based materials for photocatalysis are briefly proposed.These design strategies and limitations are also instructive for constructing g-C_(3)N_(4) based materials in other energy and environment-related applications.

Optimization Control of Multi-Mode Coupling All-Wheel Drive System for Hybrid Vehicle

The all-wheel drive(AWD)hybrid system is a research focus on high-performance new energy vehicles that can meet the demands of dynamic performance and passing ability.Simultaneous optimization of the power and economy of hybrid vehicles becomes an issue.A unique multi-mode coupling(MMC)AWD hybrid system is presented to realize the distributed and centralized driving of the front and rear axles to achieve vectored distribution and full utilization of the system power between the axles of vehicles.Based on the parameters of the benchmarking model of a hybrid vehicle,the best model-predictive control-based energy management strategy is proposed.First,the drive system model was built after the analysis of the MMC-AWD’s drive modes.Next,three fundamental strategies were established to address power distribution adjustment and battery SOC maintenance when the SOC changed,which was followed by the design of a road driving force observer.Then,the energy consumption rate in the average time domain was processed before designing the minimum fuel consumption controller based on the equivalent fuel consumption coefficient.Finally,the advantage of the MMC-AWD was confirmed by comparison with the dynamic performance and economy of the BYD Song PLUS DMI-AWD.The findings indicate that,in comparison to the comparative hybrid system at road adhesion coefficients of 0.8 and 0.6,the MMC-AWD’s capacity to accelerate increases by 5.26%and 7.92%,respectively.When the road adhesion coefficient is 0.8,0.6,and 0.4,the maximum climbing ability increases by 14.22%,12.88%,and 4.55%,respectively.As a result,the dynamic performance is greatly enhanced,and the fuel savings rate per 100 km of mileage reaches 12.06%,which is also very economical.The proposed control strategies for the new hybrid AWD vehicle can optimize the power and economy simultaneously.

Enhancing multifunctional photocatalysis with acetate-assisted cesium doping and unlocking the potential of Z-scheme solar water splitting

Graphitic carbon nitride(g-C_(3)N_(4))has been extensively doped with alkali metals to enlarge photocatalytic output,in which cesium(Cs)doping is predicted to be the most efficient.Nevertheless,the sluggish diffusion and doping kinetics of precursors with high melting points,along with imprecise regulation,have raised the debate on whether Cs doping could make sense.For this matter,we attempt to confirm the positive effects of Cs doping on multifunctional photocatalysis by first using cesium acetate with the character of easy manipulation.The optimized Csdoped g-C_(3)N_(4)(CCN)shows a 41.6-fold increase in visible-light-driven hydrogen evolution reaction(HER)compared to pure g-C_(3)N_(4) and impressive degradation capability,especially with 77%refractory tetracycline and almost 100%rhodamine B degradedwithin an hour.The penetration ofCs+is demonstrated to be a mode of interlayer doping,and Cs–N bonds(especially with sp^(2) pyridine N in C═N–C),along with robust chemical interaction and electron exchange,are fabricated.This atomic configuration triggers the broadened spectral response,the improved charge migration,and the activated photocatalytic capacity.Furthermore,we evaluate the CCN/cadmium sulfide hybrid as a Z-scheme configuration,promoting the visible HER yield to 9.02 mmol g^(−1) h^(−1),which is the highest ever reported among all CCN systems.This work adds to the rapidly expanding field of manipulation strategies and supports further development of mediating served for photocatalysis.

Core-Shell Semiconductor-Graphene Nanoarchitectures for Efficient Photocatalysis:State of the Art and Perspectives

Semiconductor photocatalysis holds great promise for renewable energy generation and environment remediation,but generally suffers from the serious drawbacks on light absorption,charge generation and transport,and structural stability that limit the performance.The core-shell semiconductorgraphene(CSSG)nanoarchitectures may address these issues due to their unique structures with exceptional physical and chemical properties.This review explores recent advances of the CSSG nanoarchitectures in the photocatalytic performance.It starts with the classification of the CSSG nanoarchitectures by the dimensionality.Then,the construction methods under internal and external driving forces were introduced and compared with each other.Afterward,the physicochemical properties and photocatalytic applications of these nanoarchitectures were discussed,with a focus on their role in photocatalysis.It ends with a summary and some perspectives on future development of the CSSG nanoarchitectures toward highly efficient photocatalysts with extensive application.By harnessing the synergistic capabilities of the CSSG architectures,we aim to address pressing environmental and energy challenges and drive scientific progress in these fields.

From the perspective of experimental practice: High-throughput computational screening in photocatalysis

Photocatalysis,a critical strategy for harvesting sunlight to address energy demand and environmental concerns,is underpinned by the discovery of high-performance photocatalysts,thereby how to design photocatalysts is now generating widespread interest in boosting the conversion effi-ciency of solar energy.In the past decade,computational technologies and theoretical simulations have led to a major leap in the development of high-throughput computational screening strategies for novel high-efficiency photocatalysts.In this viewpoint,we started with introducing the challenges of photocatalysis from the view of experimental practice,especially the inefficiency of the traditional“trial and error”method.Sub-sequently,a cross-sectional comparison between experimental and high-throughput computational screening for photocatalysis is presented and discussed in detail.On the basis of the current experimental progress in photocatalysis,we also exemplified the various challenges associated with high-throughput computational screening strategies.Finally,we offered a preferred high-throughput computational screening procedure for pho-tocatalysts from an experimental practice perspective(model construction and screening,standardized experiments,assessment and revision),with the aim of a better correlation of high-throughput simulations and experimental practices,motivating to search for better descriptors.

Synthesis of crystalline g-C_(3)N_(4) with rock/molten salts for efficient photocatalysis and piezocatalysis

Graphitic carbon nitride(g-C_(3)N_(4))is emerging as a promising visible-light photocatalyst while the low crystallinity with sluggish charge separation/migration dynamics significantly restricts its practical applications.Currently,synthesizing highly crystalline g-C_(3)N_(4) with sufficient surface activities still remains challenging.Herein,different from using alkali molten salts which is commonly reported,we propose an approach for synthesis of highly crystalline g-C_(3)N_(4) with FeCl3/KCl rock/molten mixed salts.The rock salt can serve as the structure-directing template while molten salt provides the required liquid medium for re-condensation.Intriguingly,the synthesized photocatalyst showed further enhanced crystallinity and improved surface area along with high p/p*excitation compared with crystalline C_(3)N_(4) prepared from conventional molten-salt methods.These catalytically advantageous features lead to its superior photocatalytic and piezocatalytic activities with a high reactivity for overall water splitting that is not commonly reported for C_(3)N_(4).This work provides an effective strategy for structural optimization of organic semiconductor based materials and may inspire new ideas for the design of advanced photocatalysts.

Fake News Detection Based on Text-Modal Dominance and Fusing Multiple Multi-Model Clues

In recent years,how to efficiently and accurately identify multi-model fake news has become more challenging.First,multi-model data provides more evidence but not all are equally important.Secondly,social structure information has proven to be effective in fake news detection and how to combine it while reducing the noise information is critical.Unfortunately,existing approaches fail to handle these problems.This paper proposes a multi-model fake news detection framework based on Tex-modal Dominance and fusing Multiple Multi-model Cues(TD-MMC),which utilizes three valuable multi-model clues:text-model importance,text-image complementary,and text-image inconsistency.TD-MMC is dominated by textural content and assisted by image information while using social network information to enhance text representation.To reduce the irrelevant social structure’s information interference,we use a unidirectional cross-modal attention mechanism to selectively learn the social structure’s features.A cross-modal attention mechanism is adopted to obtain text-image cross-modal features while retaining textual features to reduce the loss of important information.In addition,TD-MMC employs a new multi-model loss to improve the model’s generalization ability.Extensive experiments have been conducted on two public real-world English and Chinese datasets,and the results show that our proposed model outperforms the state-of-the-art methods on classification evaluation metrics.

Atomic Ni directional-substitution on ZnIn_(2)S_(4) nanosheet to achieve the equilibrium of elevated redox capacity and efficient carrier-kinetics performance in photocatalysis

It is a challenge to coordinate carrier-kinetics performance and the redox capacity of photogenerated charges synchronously at the atomic level for boosting photocatalytic activity.Herein,the atomic Ni was introduced into the lattice of hexagonal ZnIn_(2)S_(4) nanosheets(Ni/ZnIn_(2)S_(4))via directionalsubstituting Zn atom with the facile hydrothermal method.The electronic structure calculations indicate that the introduction of Ni atom effectively extracts more electrons and acts as active site for subsequent reduction reaction.Besides the optimized light absorption range,the elevation of Efand ECBendows Ni/ZnIn_(2)S_(4) photocatalyst with the increased electron concentration and the enhanced reduction ability for surface reaction.Moreover,ultrafast transient absorption spectroscopy,as well as a series of electrochemical tests,demonstrates that Ni/ZnIn_(2)S_(4) possesses 2.15 times longer lifetime of the excited charge carriers and an order of magnitude increase for carrier mobility and separation efficiency compared with pristine ZnIn_(2)S_(4).These efficient kinetics performances of charge carriers and enhanced redox capacity synergistically boost photocatalytic activity,in which a 3-times higher conversion efficiency of nitrobenzene reduction was achieved upon Ni/ZnIn_(2)S_(4).Our study not only provides in-depth insights into the effect of atomic directional-substitution on the kinetic behavior of photogenerated charges,but also opens an avenue to the synchronous optimization of redox capacity and carrier-kinetics performance for efficient solar energy conversion.

A Multi-mode Electronic Load Sensing Control Scheme with Power Limitation and Pressure Cut-off for Mobile Machinery

In mobile machinery,hydro-mechanical pumps are increasingly replaced by electronically controlled pumps to improve the automation level,but diversified control functions(e.g.,power limitation and pressure cut-off)are integrated into the electronic controller only from the pump level,leading to the potential instability of the overall system.To solve this problem,a multi-mode electrohydraulic load sensing(MELS)control scheme is proposed especially considering the switching stability from the system level,which includes four working modes of flow control,load sensing,power limitation,and pressure control.Depending on the actual working requirements,the switching rules for the different modes and the switching direction(i.e.,the modes can be switched bilaterally or unilaterally)are defined.The priority of different modes is also defined,from high to low:pressure control,power limitation,load sensing,and flow control.When multiple switching rules are satisfied at the same time,the system switches to the control mode with the highest priority.In addition,the switching stability between flow control and pressure control modes is analyzed,and the controller parameters that guarantee the switching stability are obtained.A comparative study is carried out based on a test rig with a 2-ton hydraulic excavator.The results show that the MELS controller can achieve the control functions of proper flow supplement,power limitation,and pressure cut-off,which has good stability performance when switching between different control modes.This research proposes the MELS control method that realizes the stability of multi-mode switching of the hydraulic system of mobile machinery under different working conditions.

Visible light triggered exfoliation of COF micro/nanomotors for efficient photocatalysis

We report a new facile light-induced strategy to disperse micron-sized aggregated bulk covalent organic frameworks(COFs)into isolated COFs nanoparticles.This was achieved by a series of metal-coordinated COFs,namely COF-909-Cu,-Co or-Fe,where for the first time the diffusio-phoretic propulsion was utilized to design COF-based micro/nanomotors.The mechanism studies revealed that the metal ions decorated in the COF-909 backbone could promote the separation of electron and holes and trigger the production of sufficient ionic and reactive oxygen species under visible light irradiation.In this way,strong light-induced self-diffusiophoretic effect is achieved,resulting in good dispersion of COFs.Among them,COF-909-Fe showed the highest dispersion performance,along with a drastic decrease in particle size from 5μm to500 nm,within only 30 min light irradiation,which is inaccessible by using traditional magnetic stirring or ultrasonication methods.More importantly,benefiting from the outstanding dispersion efficiency,COF-909-Fe micro/nanomotors were demonstrated to be efficient in photocatalytic degradation of tetracycline,about 8 times faster than using traditional magnetic stirring method.This work opens up a new avenue to prepare isolated nanosized COFs in a high-fast,simple,and green manner.

Self-adaptive bulk/surface engineering of Bi_(x)O_(y)Br_(z) towards enhanced photocatalysis:Current status and future challenges

The bulk/surface states of semiconductor photocatalysts are imperative parameters to maneuver their performance by significantly affecting the key processes of photocatalysis including light absorption,separation of charge carrier,and surface site reaction.Recent years have witnessed the encouraging progress of self-adaptive bulk/surface engineered Bi_(x)O_(y)Br_(z) for photocatalytic applications spanning various fields.However,despite the maturity of current research,the interaction between the bulk/surface state and the performance of Bi_(x)O_(y)Br_(z) has not yet been fully understood and highlighted.In this regard,a timely tutorial overview is quite urgent to summarize the most recent key progress and outline developing obstacles in this exciting area.Herein,the structural characteristics and fundamental principles of Bi_(x)O_(y)Br_(z)for driving photocatalytic reaction as well as related key issues are firstly reviewed.Then,we for the first time summarized different self-adaptive engineering processes over Bi_(x)O_(y)Br_(z)followed by a classification of the generation approaches towards diverse Bi_(x)O_(y)Br_(z)materials.The features of different strategies,the up-to-date characterization techniques to detect bulk/surface states,and the effect of bulk/surface states on improving the photoactivity of Bi_(x)O_(y)Br_(z)in expanded applications are further discussed.Finally,the present research status,challenges,and future research opportunities of self-adaptive bulk/surface engineered Bi_(x)O_(y)Br_(z)are prospected.It is anticipated that this critical review can trigger deeper investigations and attract upcoming innovative ideas on the rational design of Bi_(x)O_(y)Br_(z)-based photocatalysts.

Solar Photocatalysis of A Pesticide in A Tubular Reactor on Titaniferous Sand as A New Semi-Conductor

This present study comes in addition to overcome the problems of separation of fine particles of TiO2 in heterogeneous photocatalysis after treatment. It aims to show the potential for using titaniferous sand as a new semiconductor under solar irradiation. The photocatalytic efficiency of this titaniferous sand was tested on a pesticide (Azadirachtin). A tubular photocatalytic reactor with recirculation of the polluting solution was designed for the elimination of the pesticide in an aqueous solution. Before its use as a photocatalyst, the titaniferous sand has undergone a specific treatment that consists of calcination at 600℃ followed by extraction of the calcined natural organic materials, which can interfere with the measurement of analytical parameters such as COD. The titaniferous sand was also characterized by X-ray fluorescence spectroscopy (XRF). XRF analyses have shown that TiO2 is predominant in the titaniferous sand with a percentage that has been estimated at 46.34%. The influence of various experimental parameters such as the flow rate of the polluting solution, the concentration of titaniferous sand, the presence of oxygen and the intensity of the overall rate of sunshine, was studied to optimize the photocatalytic degradation of the pesticide. The results showed that the highest removal rate (70%) was observed under the following conditions: a pH of 6, a titaniferous sand concentration of 150 g/L, a flow rate of 0.3 mL/min, and a sunshine rate of 354 W/m2 and in the presence of atmospheric oxygen. Under these experimental conditions, the rate of photodegradation of the pesticide follows the pseudo first order kinetic model of Langmuir Hinshelwood with a coefficient of determination R2 of 0.9869 and an apparent rate constant of 0.0029 min-1. The results clearly demonstrated the potential of titaniferous sand as a photocatalyst sensitive to sunlight for the effective removal of pesticides in the aquatic environment.

Multi-mode Multi-frequency GNSS-IR Combination System for Sea Level Retrieval

With the development of Global Navigation Satellite Systems(GNSS),geodetic GNSS receivers have been utilized to monitor sea levels using GNSS-Interferometry Reflectometry(GNSS-IR)technology.The multi-mode,multi-frequency signals of GPS,GLONASS,Galileo,and Beidou can be used for GNSS-IR sea level retrieval,but combining these retrievals remains problematic.To address this issue,a GNSS-IR sea level retrieval combination system has been developed,which begins by analyzing error sources in GNSS-IR sea level retrieval and establishing and solving the GNSS-IR retrieval equation.This paper focuses on two key points:time window selection and equation stability.The stability of the retrieval combination equations is determined by the condition number of the coefficient matrix within the time window.The impact of ill-conditioned coefficient matrices on the retrieval results is demonstrated using an extreme case of SNR data with only ascending or descending trajectories.After determining the time window and removing ill-conditioned equations,the multi-mode,multi-frequency GNSS-IR retrieval is performed.Results from three International GNSS Service(IGS)stations show that the combination method produces high-precision,high-resolution,and high-reliability sea level retrieval combination sequences.

Introducing Spin Polarization into Mixed-Dimensional Van der Waals Heterostructures for High-Efficiency Visible-Light Photocatalysis

The low separation efficiency of the photogenerated carrier and the poor activity of the surface redox reaction are the main barrier to further improvement of photocatalytic materials.To address these issues,introducing spin-polarized electrons in single-component photocatalytic materials emerged as a promising approach.However,the decreased redox ability of photocarriers in these materials becomes a new challenge.Herein,we mitigate this challenge with a carbon nitride sheet(CNs)/graphene nanoribbon(GNR)composite material that has a van der Waals heterostructures(vdWHs)and spin-polarized electron properties.Experimental results and theoretical calculations show that the heterostructure has a strong redox ability,high carrier-separation efficiency,and enhanced surface catalytic reaction.Consequently,the mixed-dimensional CNs/GNR vdWHs exhibit remarkable performance for H_(2)and O_(2)generation as well as CO_(2)production under visible-light irradiation without any cocatalyst.The spin-polarized vdWHs discovered in this study revealed a new type of photocatalytic materials and advanced the development of spintronics and photocatalysis.

Efficient degradation of dye pollutants in wastewater via photocatalysis using a magnetic zinc oxide/graphene/iron oxide-based catalyst

In this paper, we present a proof-of-concept study of the enhancement of photocatalytic activity via a combined strategy of fabricating a visible-light responsive ternary heterostructure and improving overall photostability by incorporating magnetic zinc oxide/graphene/iron oxide (ZGF). A solvothermal approach was used to synthesize the catalyst. X-ray diffraction (XRD), scanning electron microscopic, energy dispersive X-ray, transmission electron microscopic, vibrating sample magnetometric, and ultraviolet–visible diffuse reflectance spectroscopic techniques were used to characterize the synthesized samples. The obtained optimal Zn(NO_(3))_(2) concentration, temperature, and heating duration were 0.10 mol/L, 600℃, and 1 h, respectively. The XRD pattern revealed the presence of peaks corresponding to zinc oxide, graphene, and iron oxide, indicating that the ZGF catalyst was effectively synthesized. Furthermore, when the developed ZGF was used for methylene blue dye degradation, the optimum irradiation time, dye concentration, catalyst dosage, irradiation intensity, and solution pH were 90 min, 10 mg/L, 0.03 g/L, 100 W, and 8.0, respectively. Therefore, the synthesized ZGF system could be used as a catalyst to degrade dyes in wastewater samples. This hybrid nanocomposite consisting of zinc oxide, graphene, and iron oxide could also be used as an effective photocatalytic degrader for various dye pollutants.

Method of Multi-Mode Sensor Data Fusion with an Adaptive Deep Coupling Convolutional Auto-Encoder

To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features extracted synchronously by the CCAE were stacked and fed to the multi-channel convolution layers for fusion. Then, the fused data was passed to all connection layers for compression and fed to the Softmax module for classification. Finally, the coupling loss function coefficients and the network parameters were optimized through an adaptive approach using the gray wolf optimization (GWO) algorithm. Experimental comparisons showed that the proposed ADCCAE fusion model was superior to existing models for multi-mode data fusion.

A Hand Features Based Fusion Recognition Network with Enhancing Multi-Modal Correlation

Fusing hand-based features in multi-modal biometric recognition enhances anti-spoofing capabilities.Additionally,it leverages inter-modal correlation to enhance recognition performance.Concurrently,the robustness and recognition performance of the system can be enhanced through judiciously leveraging the correlation among multimodal features.Nevertheless,two issues persist in multi-modal feature fusion recognition:Firstly,the enhancement of recognition performance in fusion recognition has not comprehensively considered the inter-modality correlations among distinct modalities.Secondly,during modal fusion,improper weight selection diminishes the salience of crucial modal features,thereby diminishing the overall recognition performance.To address these two issues,we introduce an enhanced DenseNet multimodal recognition network founded on feature-level fusion.The information from the three modalities is fused akin to RGB,and the input network augments the correlation between modes through channel correlation.Within the enhanced DenseNet network,the Efficient Channel Attention Network(ECA-Net)dynamically adjusts the weight of each channel to amplify the salience of crucial information in each modal feature.Depthwise separable convolution markedly reduces the training parameters and further enhances the feature correlation.Experimental evaluations were conducted on four multimodal databases,comprising six unimodal databases,including multispectral palmprint and palm vein databases from the Chinese Academy of Sciences.The Equal Error Rates(EER)values were 0.0149%,0.0150%,0.0099%,and 0.0050%,correspondingly.In comparison to other network methods for palmprint,palm vein,and finger vein fusion recognition,this approach substantially enhances recognition performance,rendering it suitable for high-security environments with practical applicability.The experiments in this article utilized amodest sample database comprising 200 individuals.The subsequent phase involves preparing for the extension of the method to larger databases.

A Comprehensive Survey on Deep Learning Multi-Modal Fusion:Methods,Technologies and Applications

Multi-modal fusion technology gradually become a fundamental task in many fields,such as autonomous driving,smart healthcare,sentiment analysis,and human-computer interaction.It is rapidly becoming the dominant research due to its powerful perception and judgment capabilities.Under complex scenes,multi-modal fusion technology utilizes the complementary characteristics of multiple data streams to fuse different data types and achieve more accurate predictions.However,achieving outstanding performance is challenging because of equipment performance limitations,missing information,and data noise.This paper comprehensively reviews existing methods based onmulti-modal fusion techniques and completes a detailed and in-depth analysis.According to the data fusion stage,multi-modal fusion has four primary methods:early fusion,deep fusion,late fusion,and hybrid fusion.The paper surveys the three majormulti-modal fusion technologies that can significantly enhance the effect of data fusion and further explore the applications of multi-modal fusion technology in various fields.Finally,it discusses the challenges and explores potential research opportunities.Multi-modal tasks still need intensive study because of data heterogeneity and quality.Preserving complementary information and eliminating redundant information between modalities is critical in multi-modal technology.Invalid data fusion methods may introduce extra noise and lead to worse results.This paper provides a comprehensive and detailed summary in response to these challenges.

Towards trustworthy multi-modal motion prediction:Holistic evaluation and interpretability of outputs

Predicting the motion of other road agents enables autonomous vehicles to perform safe and efficient path planning.This task is very complex,as the behaviour of road agents depends on many factors and the number of possible future trajectories can be consid-erable(multi-modal).Most prior approaches proposed to address multi-modal motion prediction are based on complex machine learning systems that have limited interpret-ability.Moreover,the metrics used in current benchmarks do not evaluate all aspects of the problem,such as the diversity and admissibility of the output.The authors aim to advance towards the design of trustworthy motion prediction systems,based on some of the re-quirements for the design of Trustworthy Artificial Intelligence.The focus is on evaluation criteria,robustness,and interpretability of outputs.First,the evaluation metrics are comprehensively analysed,the main gaps of current benchmarks are identified,and a new holistic evaluation framework is proposed.Then,a method for the assessment of spatial and temporal robustness is introduced by simulating noise in the perception system.To enhance the interpretability of the outputs and generate more balanced results in the proposed evaluation framework,an intent prediction layer that can be attached to multi-modal motion prediction models is proposed.The effectiveness of this approach is assessed through a survey that explores different elements in the visualisation of the multi-modal trajectories and intentions.The proposed approach and findings make a significant contribution to the development of trustworthy motion prediction systems for autono-mous vehicles,advancing the field towards greater safety and reliability.

Multi-dimension and multi-modal rolling mill vibration prediction model based on multi-level network fusion

Mill vibration is a common problem in rolling production,which directly affects the thickness accuracy of the strip and may even lead to strip fracture accidents in serious cases.The existing vibration prediction models do not consider the features contained in the data,resulting in limited improvement of model accuracy.To address these challenges,this paper proposes a multi-dimensional multi-modal cold rolling vibration time series prediction model(MDMMVPM)based on the deep fusion of multi-level networks.In the model,the long-term and short-term modal features of multi-dimensional data are considered,and the appropriate prediction algorithms are selected for different data features.Based on the established prediction model,the effects of tension and rolling force on mill vibration are analyzed.Taking the 5th stand of a cold mill in a steel mill as the research object,the innovative model is applied to predict the mill vibration for the first time.The experimental results show that the correlation coefficient(R^(2))of the model proposed in this paper is 92.5%,and the root-mean-square error(RMSE)is 0.0011,which significantly improves the modeling accuracy compared with the existing models.The proposed model is also suitable for the hot rolling process,which provides a new method for the prediction of strip rolling vibration.