Antiskid liquid formulation tuning method and system in combination with environmental perception

Abstract

The application discloses a method and system for optimizing antiskid liquid formula combined with environmental perception, and relates to the technical field of antiskid liquid, which comprises the following steps: obtaining a periodic environmental sequence, performing big data screening to determine a target formula; developing a compatibility decision module in an antiskid liquid information platform, defining a compatibility data pool by mining a performance matrix under environmental guidance, executing hierarchical cascade optimization based on a greedy decision tree with a cross-linking reaction relationship as a constraint, and determining a compatibility scheme; performing multi-node environmental field evaluation and fine-tuning optimization on the compatibility scheme, and visualizing on the display interface of the antiskid liquid information platform. The technical problems that the antiskid liquid formula cannot be optimized in real time according to dynamic environmental changes and lacks chemical feasibility constraints in the prior art, resulting in poor adaptability and performance stability of the antiskid liquid under different environmental conditions, are solved, and the technical effects of realizing adaptive and accurate optimization of the antiskid liquid formula and improving the adaptability and performance stability under different environmental conditions are achieved.

Description

Technical Field

[0001] This application relates to the technical field of anti-slip fluids, specifically to a method and system for optimizing anti-slip fluid formulations by incorporating environmental perception. Background Technology

[0002] Anti-skid fluids are important functional materials widely used in road anti-skid applications and industrial safety protection. Their performance directly affects the effectiveness and safety of use, especially under complex and variable environmental conditions, requiring anti-skid fluid formulations to possess high adaptability and dynamic optimization capabilities. However, traditional anti-skid fluid formulation design relies on static experimental data, making it difficult to cope with dynamic changes in environmental factors. This leads to unstable performance of the formulation in practical applications and may even cause safety hazards. Currently, anti-skid fluid formulation optimization is mostly based on fixed environmental assumptions or limited experimental data, lacking a holistic consideration of the periodic changes in environmental sequences such as temperature, humidity, and pollutants. Furthermore, the complex polymer compatibility relationships in the formulation and the difficulty in accurately predicting the impact of crosslinking reactions on the final performance result in low optimization efficiency and difficulty in achieving synergistic improvement of multiple performance objectives.

[0003] Therefore, in the current related technologies, there are technical problems such as the inability to optimize the anti-slip fluid formula in real time according to dynamic environmental changes and the lack of chemical feasibility constraints, resulting in poor adaptability and performance stability of the anti-slip fluid under different environmental conditions. Summary of the Invention

[0004] This application provides a method and system for optimizing anti-slip fluid formulations by incorporating environmental perception. This solves the technical problems in the prior art where anti-slip fluid formulations cannot be optimized in real time according to dynamic environmental changes and lack chemical feasibility constraints, resulting in poor adaptability and performance stability of anti-slip fluids under different environmental conditions. The application achieves the technical effect of realizing adaptive and precise optimization of anti-slip fluid formulations and improving adaptability and performance stability under different environmental conditions.

[0005] This application provides a method for optimizing anti-skid fluid formulations based on environmental perception. The method includes: acquiring a periodic environmental sequence and performing big data screening to determine the target formulation; developing a compatibility decision module in an anti-skid fluid information platform, defining a compatibility data pool by mining the performance matrix under environmental guidance, performing hierarchical cascade optimization based on a greedy decision tree with cross-linking reaction relationships as constraints, and determining the compatibility scheme; using the periodic environmental sequence, performing multi-node environmental field evaluation and fine-tuning optimization on the compatibility scheme, and visualizing the results on the display interface of the anti-skid fluid information platform.

[0006] In a possible implementation, the anti-slip fluid formulation optimization method combined with environmental awareness also performs the following processing: mining an environment-oriented performance matrix based on the periodic environmental sequence, wherein the performance matrix includes dynamic performance classes and static performance classes, and each performance index is identified by a weight; constructing a compatibility data pool based on the performance matrix, wherein the compatibility data pool consists of candidate polymers with performance correlations, and each candidate polymer is identified by a crosslinking reaction relationship.

[0007] In a possible implementation, the method for optimizing anti-slip fluid formulation based on environmental perception also performs the following processing: constructing a multi-layered cascaded greedy decision layer; constructing a greedy decision tree based on the greedy decision layer by introducing inter-layer avoidance rules, wherein the lower-level avoidance of the upper-level under performance index optimization collision is used as the inter-layer avoidance rule; supervising the training of the greedy decision tree until convergence, and determining the matching decision module.

[0008] In a possible implementation, the anti-slip fluid formulation optimization method combined with environmental perception further performs the following processing: according to the performance matrix, performing weight-based sequential integration to determine a performance index sequence; initializing the greedy decision tree with the performance index sequence, wherein the first greedy decision layer is initialized with a first performance index, the first performance index being the performance index with the highest weight in the performance index sequence; writing the compatibility data pool into the module data area, and using the crosslinking reaction relationship as a constraint, performing cascade optimization decision based on the initialized greedy decision tree to determine the compatibility scheme.

[0009] In a possible implementation, the anti-slip fluid formulation optimization method combined with environmental awareness further performs the following processing: taking the first performance index as the optimization guide, the first greedy decision layer performs candidate polymer screening based on the compatibility data pool to determine the first optimization sub-pool; taking the first ratio and the second addition as optimization methods and the first crosslinking reaction relationship as constraints, the target formulation is subjected to compatibility method adjustment and iterative evaluation to determine the first optimized compatibility scheme, wherein the conformational state of the polymer chain based on the optimization guide is used as the evaluation basis, and the first crosslinking reaction relationship corresponds to the candidate polymer in the first optimization sub-pool.

[0010] In a possible implementation, the anti-slip fluid formulation optimization method combined with environmental perception also performs the following processing: using the second performance index as the optimization guide, the second greedy decision layer screens and determines the second optimization sub-pool; using the first ratio and the second addition as optimization methods, and the second cross-linking reaction relationship as constraints, the first optimized compatibility scheme is iteratively optimized to determine the second compatibility scheme; based on the second compatibility scheme, a hierarchical polling decision based on the greedy decision tree is executed to determine the compatibility scheme.

[0011] In a possible implementation, the anti-slip fluid formulation optimization method combined with environmental perception also performs the following processing: iteratively optimizing the first optimized formulation scheme, and if there is a hierarchical optimization-guided collision, performing relaxation avoidance processing of the second greedy decision layer.

[0012] In a possible implementation, the anti-slip fluid formulation optimization method combined with environmental awareness also performs the following processing: for the periodic environmental sequence, key environmental nodes are screened; the key environmental nodes are traversed, and the anti-slip fluid performance of the node environmental state is inferred for the formulation scheme to determine the node performance coefficient; if the node performance coefficient meets the performance threshold, the formulation scheme is displayed on the platform interface.

[0013] In a possible implementation, the anti-slip fluid formulation optimization method combined with environmental perception also performs the following processing: if any node performance coefficient is not satisfied, locate the environmental factors and compatibility factors, perform greedy decision-making layer matching and re-optimization decision, update the compatibility scheme and display it on the platform interface.

[0014] This application also provides an anti-skid fluid formulation optimization system that incorporates environmental perception. The system includes: a target formulation determination module, used to acquire periodic environmental sequences and perform big data screening to determine the target formulation; a compatibility scheme determination module, used to develop a compatibility decision module in an anti-skid fluid information platform, define a compatibility data pool by mining the performance matrix under environmental guidance, and perform hierarchical cascade optimization based on a greedy decision tree with cross-linking reaction relationships as constraints to determine the compatibility scheme; and an evaluation and fine-tuning optimization module, used to perform multi-node environmental field evaluation and fine-tuning optimization of the compatibility scheme based on the periodic environmental sequences, and visualize the results on the display interface of the anti-skid fluid information platform.

[0015] This application proposes a method and system for optimizing anti-skid fluid formulations based on environmental perception. This involves acquiring periodic environmental sequences and using big data screening to determine target formulations. A compatibility decision module is developed within an anti-skid fluid information platform. By mining performance matrices guided by environmental factors, a compatibility data pool is defined. Using cross-linking reaction relationships as constraints, a hierarchical cascade optimization based on a greedy decision tree is performed to determine the compatibility scheme. The compatibility scheme undergoes multi-node environmental field evaluation and fine-tuning optimization, which is then visualized on the anti-skid fluid information platform's display interface. This addresses the technical problems in existing technologies where anti-skid fluid formulations cannot be optimized in real-time according to dynamic environmental changes and lack chemical feasibility constraints, leading to poor adaptability and performance stability of anti-skid fluids under different environmental conditions. The proposed method achieves the technical effect of adaptive and precise optimization of anti-skid fluid formulations, improving adaptability and performance stability under different environmental conditions. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 This is a schematic diagram of the process for optimizing the anti-slip fluid formulation based on environmental perception, provided in an embodiment of this application.

[0018] Figure 2 A schematic diagram of the anti-slip fluid formulation optimization system combined with environmental perception provided in this application embodiment.

[0019] Explanation of reference numerals in the attached diagram: Target formulation determination module 10, compatibility scheme determination module 20, evaluation, fine-tuning and optimization module 30. Detailed Implementation

[0020] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0023] This application provides a method for optimizing anti-slip fluid formulations based on environmental awareness, such as... Figure 1 As shown, the method includes:

[0024] Step S100: Obtain the periodic environmental sequence and perform big data screening to determine the target formula.

[0025] Preferably, dynamic environmental parameters, including climate parameters such as temperature, humidity, and rainfall, and pollutants such as road surface oil, dust concentration, and salt content, are collected in real time through a sensor network to form time series data. Time series analysis is then used to identify significant cycles of environmental elements, such as diurnal cycles and seasonal cycles, thereby determining the periodic environmental sequence. The sensor network includes road temperature and humidity sensors, snow and ice monitoring radar, and salt spray concentration meters. For example, in winter, temperature, humidity, and road surface friction coefficient are collected every 30 minutes on urban roads. Then, historical environment-performance correlation data is used to train a model to match the optimal initial formulation for the current environmental sequence. That is, using the periodic environmental sequence as input, clustering algorithms such as DBSCAN are used to select cases with similar environments from a historical formulation library and sort them according to performance weights, such as prioritizing anti-slip properties over curing speed, to output the target formulation.

[0026] Step S200: Develop a compatibility decision module in the anti-slip fluid information platform. By mining the performance matrix under environmental guidance, define a compatibility data pool, and perform hierarchical cascade optimization based on a greedy decision tree, constrained by cross-linking reaction relationships, to determine the compatibility scheme.

[0027] Preferably, the anti-slip fluid information platform is an anti-slip fluid formulation workbench that integrates environmental data, a chemical knowledge base, a computing engine, and a visual interface. A compatibility decision module is developed within this platform. This module is a software decision-making unit embedded within the platform, essentially an intelligent formulation optimizer that couples environment, chemistry, and performance. Specifically, it is a dynamic formulation generation unit that takes environmental data as input, chemical cross-linking reactions as constraints, and a greedy decision tree as its engine. Specifically, the input layer receives environmental data and performance requirements; the decision engine configures a greedy decision tree, filtering raw materials layer by layer in descending order of weight, prioritizing high-priority performance, and then resolving conflicts through inter-layer avoidance; the chemical constraint layer verifies the feasibility of cross-linking reactions, calculates the cross-linking density of raw material combinations in real time, and eliminates incompatible formulations.

[0028] Preferably, the environmental sequence is input into the compatibility decision module, which outputs a weighted performance requirement matrix. For example, ice surface friction coefficient ≥ 0.45, weight 0.40; salt spray resistance level ≥ 1000h, weight 0.30; curing time ≤ 2h, weight 0.20; elasticity retention rate ≥ 80%, weight 0.10. Then, candidate polymers / auxiliaries that contribute to the four properties and can crosslink with each other are identified from the raw material database, forming a candidate material list. At the same time, the feasibility of crosslinking reaction is marked for each pair of raw materials, such as hydroxyl value / isocyanate ratio and gel time, thereby determining the compatibility data pool. The crosslinking reaction relationship is used as a constraint, i.e., chemical feasibility verification is performed. If the crosslinking of A+B is... If the density is less than 90% or phase separation occurs, the component is directly eliminated. Then, a hierarchical cascade optimization based on a greedy decision tree is performed. Specifically, the performance index with the highest weight is placed at the root of the tree, with the ice surface friction coefficient as the root node. The combination with the highest friction coefficient and the cross-linking constraint is selected from the compatibility data pool to obtain sub-pool 1. Then, salt spray resistance is used as the secondary node. The combination with the best salt spray resistance and the cross-linking constraint is selected from sub-pool 1 to obtain sub-pool 2. The cascade is performed downward according to weight until the optimization of the higher level causes the lower level objective to be unsatisfied. At this point, relaxation avoidance is triggered, that is, sacrificing 5% of the performance of the higher level to allow the lower level index to meet the target. After the last layer is completed, the remaining combination is the final compatibility scheme, that is, the anti-slip fluid formula.

[0029] Furthermore, step S200 also includes step S201, mining an environment-oriented performance matrix based on the periodic environment sequence, wherein the performance matrix includes dynamic performance classes and static performance classes, and each performance index is identified by a weight value; step S202, constructing a compatibility data pool based on the performance matrix, wherein the compatibility data pool is composed of candidate polymers with performance associations, and each candidate polymer is identified by a crosslinking reaction relationship.

[0030] Preferably, by quantifying the environmental requirements for anti-skid fluid performance, suitable candidate components are screened, and the chemical compatibility rules between components are clarified. Specifically, based on the periodic environmental sequence, the environmental factors affecting the anti-skid effect are identified, a performance matrix is ​​extracted, and the corresponding performance is focused on. For example, if the periodic environmental sequence shows that high temperature and high humidity will dominate in the future, then the anti-skid fluid needs to focus on ensuring the anti-skid coefficient in high humidity environments and the viscosity stability at high temperatures. The performance matrix is ​​used to quantify the correspondence between environmental requirements and anti-skid fluid performance indicators, including dynamic performance categories and static performance categories. Dynamic performance categories refer to performances that are sensitive to environmental changes, such as the anti-skid coefficient in high humidity environments, fluidity at low temperatures, and the anti-skid attenuation rate after contaminant adhesion. These directly determine the adaptability of the anti-skid fluid in dynamic environments and usually have higher weights. Static performance categories refer to relatively stable basic performances that are less affected by the environment, such as basic adhesion to the road surface and aging resistance after long-term use. These have relatively lower weights. Each performance indicator is labeled with a weight, that is, the weight of each performance indicator represents its importance in the current environment. The higher the weight, the higher the priority.

[0031] Preferably, a compatibility data pool is constructed based on the performance matrix to screen polymers that can meet the key performance requirements in the performance matrix and determine whether they can be safely mixed, i.e., to determine the crosslinking reaction relationship. The compatibility data pool is a database that stores candidate polymers associated with the indicators in the performance matrix. Specifically, performance association means that the candidate polymers in the compatibility data pool are directly related to the performance indicators in the performance matrix, i.e., a certain polymer can specifically improve a certain type of performance. For example, if the high-humidity anti-skid coefficient is the core indicator in the performance matrix, then the compatibility data pool includes polyacrylates containing hydrophilic groups to enhance the affinity with water and improve the friction of wet and slippery surfaces. Each candidate polymer must be labeled with its crosslinking reaction relationship with other polymers to ensure the chemical feasibility of the formulation. Compatible means that the two polymers can undergo benign crosslinking after mixing, such as forming a stable three-dimensional network structure to enhance anti-skid performance. Incompatible means that adverse reactions occur after mixing, such as gelation, delamination, or performance failure. For example, a polymer containing carboxyl groups and a polymer containing amine groups may undergo excessive crosslinking in a high-humidity environment, leading to hardening and failure of the anti-skid liquid.

[0032] Furthermore, step S200 also includes step S210, constructing a multi-layered cascaded greedy decision layer; step S220, based on the greedy decision layer, constructing a greedy decision tree by introducing inter-layer avoidance rules, wherein the lower-level avoidance of the upper-level under the performance index collision optimization is used as the inter-layer avoidance rule; step S230, supervising the training of the greedy decision tree until convergence, and determining the matching decision module.

[0033] Preferably, multi-layered optimization units are constructed according to the importance of performance. Each layer is used to optimize one performance index, and there is a transitive relationship between the layers. Specifically, the layers correspond to performance indices with different weights in the performance matrix. The performance index with the highest weight corresponds to the first greedy decision layer, the one with the next highest weight corresponds to the second greedy decision layer, and so on, forming multiple layers. The optimization of the next layer must be based on the result of the previous layer. For example, the first decision layer first optimizes the high-wet anti-slip coefficient to obtain the basic formula, and then the second decision layer optimizes the high-temperature viscosity stability on the basic formula. When optimizing each layer, only the optimal performance index of the current layer is pursued, without considering the impact on subsequent layers, to ensure efficiency. For example, in order to maximize the high-wet anti-slip coefficient, the first greedy decision layer prioritizes polymers that can significantly improve this performance, without considering cost or other secondary performances for the time being.

[0034] Preferably, based on the greedy decision-making layer, a greedy decision tree is constructed by introducing inter-layer avoidance rules. The greedy decision tree is a tree-like decision model that integrates multiple cascaded decision layers according to logical relationships. The inter-layer avoidance rules are the core mechanism for resolving conflicts between optimization objectives at different levels. Specifically, the root node of the greedy decision tree is the first greedy decision layer, and the child nodes are the second and third greedy decision layers. The decision result of each layer is passed to the next layer along the branches of the tree, ultimately forming a complete optimization path. The inter-layer avoidance rule means that when optimization objectives at different levels collide, i.e., when the optimization of the next layer affects the optimal performance already achieved by the previous layer, the lower layer must yield. For example, if the first greedy decision layer has optimized the high-humidity anti-slip coefficient to the target value, and the second greedy decision layer finds that the adjustment scheme will decrease the high-humidity anti-slip coefficient when optimizing the high-temperature viscosity stability, the avoidance rule is triggered. The second decision layer must abandon the scheme and choose the alternative scheme with the least impact on the high-humidity anti-slip coefficient.

[0035] Preferably, the greedy decision tree is trained under supervised supervision using historical data. This historical data includes past environmental sequences, corresponding optimal formulations, and performance index results. Specifically, a certain period's environmental sequence and corresponding performance matrix are used as input, with the desired output being the formulation that performs best under that environment. The optimization parameters at each level of the greedy decision tree are adjusted, such as the weighting method for performance indicators and the trigger threshold for avoidance rules, until the formulation output by the greedy decision tree matches the desired output or the error is within an acceptable range. When the output of the greedy decision tree stabilizes (e.g., multiple inputs of the same data show minimal differences in the output formulations), and the optimization effect on new data meets the standards, the greedy decision tree is considered to have converged. Finally, the compatibility decision module is determined. This module can be embedded in the anti-slip fluid information platform to automatically receive environmental sequences and performance matrices and output the optimized formulation scheme.

[0036] Furthermore, step S200 also includes step S240, performing weight-based sequential integration according to the performance matrix to determine a performance index sequence; step S250, initializing the greedy decision tree with the performance index sequence, wherein the first greedy decision layer is initialized with a first performance index, the first performance index being the performance index with the highest weight in the performance index sequence; step S260, writing the matching data pool into the module data area, and performing cascade optimization decision based on the initialized greedy decision tree with the cross-linking reaction relationship as a constraint to determine the matching scheme.

[0037] Preferably, the optimal compatibility scheme is intelligently generated under chemical constraints by ranking performance weights and hierarchical progressive screening. Specifically, firstly, the indicators such as frost resistance and friction coefficient in the performance matrix are sorted and integrated according to environmental weights from high to low to generate a priority sequence, i.e., a performance indicator sequence. Then, the greedy decision tree is initialized with the performance indicator sequence. The performance indicator with the highest weight is used as the first performance indicator, and it is used as the root node to initialize the first greedy decision layer. For example, if the frost resistance weight is the highest, the optimization objective of the first layer is to maximize the frost resistance and screen all materials in the compatibility data pool that can improve the frost resistance, such as ethylene glycol-based polymers.

[0038] Preferably, all materials in the compatibility data pool are written into the module data area, and the cross-linking reaction relationship is used as a constraint. That is, the cross-linking reaction relationship is strictly verified at each level of decision. For example, if polymer A is selected in the first greedy decision layer, substances that react harmfully with A are automatically excluded in the second layer of screening. Then, cascade optimization decision based on the initialized greedy decision tree is executed. Specifically, the first layer of greedy decision selects candidate materials that meet the antifreeze target from the data pool. The second layer of greedy decision selects from compatible materials again based on the results of the first layer, with the second highest weight index as the target. If the optimization of the lower layer affects the performance of the upper layer, the avoidance rule is triggered, and the suboptimal solution is selected or the ratio is adjusted. Finally, the material combination and ratio that meet the target of all levels are output, that is, the compatibility scheme, such as polymer X (60%) + nano silica (30%) + corrosion inhibitor (10%), thereby achieving fast and accurate formulation decision.

[0039] Furthermore, step S260 also includes step S261, whereby, guided by the first performance index, the first greedy decision layer performs candidate polymer screening based on the compatibility data pool to determine the first optimized sub-pool; step S262, whereby, guided by the first ratio and the second addition, and constrained by the first crosslinking reaction relationship, the target formulation is subjected to compatibility adjustment and iterative evaluation to determine the first optimized compatibility scheme, wherein the conformational state of the polymer chain based on the optimization guidance is used as the evaluation basis, and the first crosslinking reaction relationship corresponds to the candidate polymer in the first optimized sub-pool.

[0040] Preferably, with the highest weighted performance index as the target, the first greedy decision layer screens all candidate polymers that can significantly improve the performance from the compatibility data pool, forming the first optimization sub-pool. Then, the first ratio optimization is performed, that is, the proportion of existing polymers in the first optimization sub-pool is optimized, such as adjusting the ethylene glycol concentration from 50% to 60% to enhance freeze resistance. Then, the second addition optimization is performed, that is, introducing new materials that are not used in the first optimization sub-pool but can synergistically improve the target performance, such as adding nano-clay to further improve low-temperature stability. Then, the compatibility method is adjusted and iteratively evaluated for the target formulation. Specifically, after each adjustment, chemical compatibility and conformational state evaluation are tested, that is, to ensure that the crosslinking reaction between the added or adjusted materials and the existing components is harmless. At the same time, the conformational changes of polymer chains are analyzed through molecular dynamics simulation or experimental data, such as whether ethylene glycol can still maintain a flexible chain structure at low temperatures, so as to judge the actual performance improvement effect. Through multiple rounds of iteration, the optimal temporary solution at the current level is finally obtained, that is, the first optimized compatibility solution. For example, taking the increase in friction under humid conditions as the optimization guide, after adjusting the ratio or introducing a certain polymer as the optimization method, for the polymer chain under the optimization method, the fitness is determined by the tendency of the micro-nano pit structure to conformational state and the fit between the structure and the requirements, and random iteration is carried out, such as random perturbation adjustment to obtain the optimal matching scheme.

[0041] Furthermore, step S260 also includes step S263, using the second performance index as the optimization guide, the second greedy decision layer screens and determines the second optimization sub-pool, using the first ratio and the second addition as the optimization method, and using the second cross-linking reaction relationship as the constraint, to iteratively optimize the first optimized matching scheme and determine the second matching scheme; step S264, based on the second matching scheme, to perform hierarchical polling decision based on the greedy decision tree to determine the matching scheme.

[0042] Preferably, based on the optimization of the first greedy decision layer, the global optimization of the anti-slip liquid formulation is ultimately achieved through fine-tuning driven by secondary performance indicators. Specifically, guided by the second-highest weighted performance indicator, materials that can improve this performance and are compatible with the first optimized formulation are screened from the compatibility data pool to form a second optimization sub-pool. For example, the ethylene glycol-based polymer of the first layer is retained, and nano-silica is added, but materials that will gel with ethylene glycol must be excluded. Optimization is performed using the first ratio, that is, adjusting the existing component ratio, and then optimization is performed using the second addition, that is, introducing materials from the second optimization sub-pool, such as... Adding 5% nano-silica simultaneously satisfies the constraints of the second crosslinking reaction and the performance protection of the first greedy decision layer. The first optimized formulation is iteratively optimized to determine the second formulation. Then, a hierarchical polling decision based on a greedy decision tree is executed on the second formulation. That is, through the hierarchical backtracking mechanism of the greedy decision tree, the performance of each layer is checked cyclically. If the optimization of the second layer leads to the degradation of the performance of the first layer, relaxation avoidance is triggered, such as downgrading the amount of material in the second layer or replacing it with a suboptimal friction-increasing material. Finally, a formulation that satisfies both antifreeze and friction coefficient is output, maximizing the overall performance of the anti-slip fluid.

[0043] Furthermore, step S260 also includes iteratively optimizing the first optimized matching scheme, and if there is a hierarchical optimization-oriented collision, performing relaxation avoidance processing of the second greedy decision layer.

[0044] Preferably, the first optimal compatibility scheme is iteratively optimized. When the adjustment of the second greedy decision layer causes a significant decrease in the core performance of the first layer, a hierarchical optimization-oriented collision occurs. For example, adding 5% nano-silica increases the coefficient of friction to 0.75, but reduces the antifreeze performance from 0.9 to 0.82. In this case, the relaxation avoidance process of the second greedy decision layer is executed, including conflict detection, strategy selection, and re-verification after avoidance. Specifically, the degree of decay of the performance indicators of the first layer is monitored in real time. When the preset tolerance is exceeded, the avoidance rule is triggered, and different strategies are selected for optimization, such as reducing the amount of conflicting materials added, selecting alternative materials with less impact on the upper layer, or fine-tuning the proportion of other components for compensation. Then, the adjusted compatibility scheme is re-evaluated to ensure that the performance of the second layer is still effectively improved, the performance of the first layer is restored to the safe threshold, and all cross-linking reaction relationships remain stable.

[0045] Step S300: Using the periodic environmental sequence, perform multi-node environmental field evaluation and fine-tuning optimization of the compatibility scheme, and visualize the results on the display interface of the anti-slip fluid information platform.

[0046] Preferably, the universality of the formulation in complex scenarios is ensured through multi-dimensional environmental simulation testing and dynamic visualization feedback. Specifically, representative extreme / typical working condition nodes are extracted from the periodic environmental sequence to construct a virtual environmental field test set. Then, the compatibility scheme is evaluated in a multi-node environmental field, that is, the compatibility scheme is simulated in different scenarios. For example, the curing temperature and ice surface adhesion are tested at low temperature nodes, the evaporation rate and ultraviolet stability are evaluated at high temperature nodes, and the friction coefficient attenuation rate in oily environments is detected at pollution nodes, thereby outputting quantitative indicators. Then, targeted fine-tuning and optimization are carried out for nodes that do not meet the standards, including locating the cause of failure, replacing materials and optimizing the ratio, to obtain the compatibility scheme with the best overall performance. The system is visualized on the display interface of the anti-slip fluid information platform, which displays the performance balance under different environments and the correlation between materials, environment and performance in real time. It also supports manual dragging of the slider to fine-tune the component ratio, and the system predicts performance changes in real time.

[0047] Furthermore, step S300 also includes step S310, for the periodic environmental sequence, screening key environmental nodes; step S320, traversing the key environmental nodes, performing anti-slip fluid performance inference on the node environmental state of the matching scheme, and determining the node performance coefficient; step S330, if the node performance coefficient meets the performance threshold, displaying the matching scheme on the platform interface.

[0048] Preferably, the reliability of the formulation is ensured across all scenarios through extreme environmental value testing and intelligent performance prediction. Specifically, a peak-valley detection algorithm is used to screen key environmental nodes from the periodic environmental sequence, including stress nodes, high-frequency nodes, and corrosion nodes. Then, the key environmental nodes are traversed, and the anti-slip fluid performance of the formulation is inferred based on the node environmental state. That is, multi-scale simulation is performed for each key environmental node. The conformational stability of the material molecular chain under extreme temperatures is evaluated based on molecular dynamics simulation, and the surface friction loss under different loads is calculated based on finite element analysis. Then, the node performance coefficient is predicted and determined using a performance degradation prediction model. If the node performance coefficient meets the performance threshold, the formulation is displayed on the platform interface, such as marking the test results of each node with a 3D topographic map and flashing red to indicate the material interaction chain of the failed node.

[0049] Furthermore, step S300 also includes, if any node performance coefficient is not satisfied, locating environmental factors and compatibility factors, performing greedy decision-making matching and re-optimization decision-making, updating the compatibility scheme and displaying it on the platform interface.

[0050] Preferably, when the performance evaluation of any key environmental node fails to meet the performance threshold, the environmental and compatibility factors are located. This involves identifying the dominant environmental parameters causing the failure through feature decomposition, identifying sensitive components using material influence factor analysis, and then performing greedy decision-making matching and re-optimization decisions. Specifically, the optimization level is automatically associated based on the failure type. If it is a core performance failure, the system reverts to the first greedy decision-making level; if it is a minor performance problem, the system calls the second greedy decision-making level and performs constraint reconstruction, i.e., dynamically updating the crosslinking reaction constraint library and eliminating fault combinations. Then, the compatibility scheme is updated, retaining 90% of the effective components of the original scheme and only targeting and modifying the relevant elements of the problem node, including material replacement, fine-tuning of the ratio, and addition of interface agents. Finally, the system is displayed on the platform interface to achieve adaptive and precise optimization of the anti-slip fluid formula and improve its adaptability and performance stability under different environmental conditions.

[0051] In the above text, refer to Figure 1 A method for optimizing anti-slip fluid formulation based on environmental awareness according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 2 A system for optimizing anti-slip fluid formulations incorporating environmental awareness, according to an embodiment of the present invention, is described.

[0052] The anti-slip fluid formulation optimization system based on environmental perception, as described in this invention, addresses the technical problems in existing technologies where anti-slip fluid formulations cannot be optimized in real time according to dynamic environmental changes and lack chemical feasibility constraints, resulting in poor adaptability and performance stability of anti-slip fluids under different environmental conditions. This system achieves the technical effect of enabling adaptive and precise optimization of anti-slip fluid formulations and improving adaptability and performance stability under different environmental conditions. Figure 2 As shown, the anti-slip fluid formulation optimization system combined with environmental perception includes: a target formulation determination module 10, a compatibility scheme determination module 20, and an evaluation and fine-tuning optimization module 30.

[0053] The target formulation determination module 10 is used to acquire the periodic environmental sequence and perform big data screening to determine the target formulation; the compatibility scheme determination module 20 is used to develop a compatibility decision module in the anti-skid fluid information platform, define a compatibility data pool by mining the performance matrix under the guidance of the environment, and perform hierarchical cascade optimization based on greedy decision tree with cross-linking reaction relationship as constraint to determine the compatibility scheme; the evaluation and fine-tuning optimization module 30 is used to evaluate and fine-tune the compatibility scheme in a multi-node environmental field using the periodic environmental sequence, and visualize it on the display interface of the anti-skid fluid information platform.

[0054] The specific configuration of the compatibility scheme determination module 20 will be described in detail below. The compatibility scheme determination module 20 further includes: mining an environment-oriented performance matrix based on the periodic environmental sequence, wherein the performance matrix includes dynamic performance classes and static performance classes, and each performance index is identified by a weight; and constructing a compatibility data pool based on the performance matrix, wherein the compatibility data pool consists of candidate polymers with performance correlations, and each candidate polymer is identified by a crosslinking reaction relationship.

[0055] The specific configuration of the matching scheme determination module 20 will be described in detail below. The matching scheme determination module 20 further includes: constructing a multi-layered cascaded greedy decision layer; constructing a greedy decision tree based on the greedy decision layer by introducing inter-layer avoidance rules, wherein the lower-level avoidance of the upper-level under the performance index collision optimization is used as the inter-layer avoidance rule; and performing supervised training on the greedy decision tree until convergence to determine the matching decision module.

[0056] The specific configuration of the matching scheme determination module 20 will be described in detail below. The matching scheme determination module 20 further includes: performing weight-based sequential integration based on the performance matrix to determine a performance index sequence; initializing the greedy decision tree with the performance index sequence, wherein a first greedy decision layer is initialized with a first performance index, which is the performance index with the highest weight in the performance index sequence; writing the matching data pool into the module data area; and performing cascade optimization decision based on the initialized greedy decision tree, using the cross-linking reaction relationship as a constraint, to determine the matching scheme.

[0057] The specific configuration of the compatibility scheme determination module 20 will be described in detail below. The compatibility scheme determination module 20 further includes: using the first performance index as an optimization guide, the first greedy decision layer performs candidate polymer screening based on the compatibility data pool to determine a first optimized sub-pool; using the first ratio and the second addition as optimization methods, and the first crosslinking reaction relationship as a constraint, the target formulation undergoes compatibility method adjustment and iterative evaluation to determine the first optimized compatibility scheme, wherein the conformational state of the polymer chain based on the optimization guide is used as the evaluation basis, and the first crosslinking reaction relationship corresponds to the candidate polymers in the first optimized sub-pool.

[0058] The specific configuration of the matching scheme determination module 20 will be described in detail below. The matching scheme determination module 20 further includes: using the second performance index as the optimization guide, a second greedy decision layer to screen and determine a second optimized sub-pool; using the first ratio and the second addition as optimization methods, and the second cross-linking reaction relationship as a constraint, iteratively optimizing the first optimized matching scheme to determine the second matching scheme; and based on the second matching scheme, performing hierarchical polling decision based on the greedy decision tree to determine the matching scheme.

[0059] The specific configuration of the matching scheme determination module 20 will be described in detail below. The matching scheme determination module 20 further includes: iteratively optimizing the first optimized matching scheme; if there is a hierarchical optimization-oriented collision, performing relaxation avoidance processing of the second greedy decision layer.

[0060] The specific configuration of the evaluation and fine-tuning optimization module 30 will be described in detail below. The evaluation and fine-tuning optimization module 30 further includes: screening key environmental nodes for the periodic environmental sequence; traversing the key environmental nodes, performing anti-slip fluid performance inference on the node environmental state of the compatibility scheme, and determining the node performance coefficient; if the node performance coefficient meets the performance threshold, displaying the compatibility scheme on the platform interface.

[0061] The specific configuration of the evaluation and fine-tuning optimization module 30 will be described in detail below. The evaluation and fine-tuning optimization module 30 further includes: if any node performance coefficient is not satisfied, locating environmental factors and compatibility factors, performing greedy decision-making matching and re-optimization decision-making, updating the compatibility scheme and displaying it on the platform interface.

[0062] The anti-slip fluid formulation optimization system with environmental perception provided in this embodiment of the invention can execute the anti-slip fluid formulation optimization method with environmental perception provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0063] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0064] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for optimizing anti-slip fluid formulation based on environmental perception, characterized in that, The method includes: Obtain the periodic environmental sequence and use big data screening to determine the target formula; In the anti-slip fluid information platform, a compatibility decision module was developed. By mining the performance matrix under the guidance of the environment, a compatibility data pool was defined. With the cross-linking reaction relationship as a constraint, a hierarchical cascade optimization based on a greedy decision tree was performed to determine the compatibility scheme. The compatibility scheme is evaluated and fine-tuned using the periodic environmental sequence, and visualized on the display interface of the anti-skid fluid information platform. Develop a compatibility decision module, including: Construct a multi-layered, cascading greedy decision-making layer; Based on the greedy decision layer, a greedy decision tree is constructed by introducing inter-layer avoidance rules, wherein the lower-level avoidance of the upper-level under the performance index collision optimization is used as the inter-layer avoidance rule. The greedy decision tree is trained under supervision until convergence, and the matching decision module is determined. Perform hierarchical cascade optimization based on a greedy decision-maker tree to determine the matching scheme, including: Based on the performance matrix, a weighted sequential integration is performed to determine the performance index sequence; The greedy decision tree is initialized with the performance index sequence, wherein the first greedy decision layer is initialized with the first performance index, which is the performance index with the highest weight in the performance index sequence. The compatibility data pool is written into the module data area, and the cross-linking reaction relationship is used as a constraint to perform cascade optimization decision based on the initialized greedy decision tree to determine the compatibility scheme.

2. The method for optimizing anti-slip fluid formulation based on environmental perception as described in claim 1, characterized in that, The acquisition of the performance matrix and matching data pool includes: Based on the periodic environment sequence, an environment-oriented performance matrix is ​​mined, wherein the performance matrix includes dynamic performance classes and static performance classes, and each performance index is identified by a weight value; Based on the performance matrix, a compatibility data pool is constructed, wherein the compatibility data pool consists of candidate polymers with performance correlations, and each candidate polymer is identified with a crosslinking reaction relationship.

3. The method for optimizing anti-slip fluid formulation based on environmental perception as described in claim 1, characterized in that, Performing cascaded optimization decisions based on the initialized greedy decision tree includes: Guided by the first performance index, the first greedy decision layer performs candidate polymer screening based on the compatibility data pool to determine the first optimization sub-pool; Using the first ratio and the second addition as optimization methods, and the first crosslinking reaction relationship as a constraint, the target formulation is subjected to compatibility adjustment and iterative evaluation to determine the first optimized compatibility scheme. The conformational state of the polymer chain based on optimization guidance is used as the evaluation basis, and the first crosslinking reaction relationship corresponds to the candidate polymer in the first optimized sub-pool.

4. The method for optimizing anti-slip fluid formulation based on environmental perception as described in claim 3, characterized in that, With the second performance index as the optimization guide, the second greedy decision layer screens and determines the second optimization sub-pool. With the first ratio and the second addition as the optimization method and the second cross-linking reaction relationship as the constraint, the first optimization combination scheme is iteratively optimized to determine the second combination scheme. Based on the second matching scheme, a hierarchical round-robin decision based on the greedy decision tree is executed to determine the matching scheme.

5. The method for optimizing anti-slip fluid formulation based on environmental perception as described in claim 4, characterized in that, The first optimal matching scheme is iteratively optimized. If there is a hierarchical optimization-oriented collision, the relaxation avoidance processing of the second greedy decision layer is executed.

6. The method for optimizing anti-slip fluid formulation based on environmental perception as described in claim 1, characterized in that, The compatibility scheme is evaluated and fine-tuned using a multi-node environmental field, including: For the aforementioned periodic environment sequence, key environment nodes are selected; Traverse the key environmental nodes and perform anti-slip fluid performance inference based on the node environmental state of the compatibility scheme to determine the node performance coefficients; If the node performance coefficient meets the performance threshold, the matching scheme is displayed on the platform interface.

7. The method for optimizing anti-slip fluid formulation based on environmental perception as described in claim 6, characterized in that, If any node performance coefficient is not met, the environmental factors and compatibility factors are located, and a greedy decision-making layer matching and re-optimization decision is performed to update the compatibility scheme and display it on the platform interface.

8. A system for optimizing anti-slip fluid formulations based on environmental perception, characterized in that: The system is used to implement the anti-slip fluid formulation optimization method combining environmental perception as described in any one of claims 1 to 7, the system comprising: The target formulation determination module is used to obtain the periodic environmental sequence and perform big data screening to determine the target formulation. The compatibility scheme determination module is used to develop a compatibility decision module in the anti-skid fluid information platform. By mining the performance matrix under the guidance of the environment, a compatibility data pool is defined. With the cross-linking reaction relationship as a constraint, a hierarchical cascade optimization based on a greedy decision tree is performed to determine the compatibility scheme. The evaluation and fine-tuning optimization module is used to evaluate and fine-tune the compatibility scheme using the periodic environmental sequence, and visualize the results on the display interface of the anti-slip fluid information platform.

Images