A data analysis-driven intelligent optimization method for fair-faced concrete mix ratio

Abstract

The present application provides a data analysis-driven method for intelligent optimization of the proportion of plain concrete, which relates to the field of building materials technology, including: obtaining coating scene information, and performing logical grouping according to conditional relevance; using scene information to traverse the construction schedule to obtain multiple coating time domains; constructing K proportion optimization spaces; after selecting the first proportion optimization space according to the first coating structure type, using the first multi-level optimization condition to limit the proportion combination to obtain the first optimization performance database; performing proportion combination adjustment optimization, and after obtaining multiple plain concrete proportions, performing raw material pre-scheduling and concrete pre-production. This application can solve the technical problem in the prior art that the traditional concrete proportion is difficult to adjust according to the specific needs of the building structure, resulting in insufficient adaptability of the proportion to the scene. Through multi-dimensional optimization, accurate proportioning of plain concrete is achieved, and the adaptability of the plain concrete proportion to the coating scene is improved.

Description

Technical Field

[0001] The present application relates to the technical field of building materials, and in particular to a data analysis-driven intelligent optimization method for fair-faced concrete mix ratios. Background Art

[0002] Fair-faced concrete (also called "bare concrete" or "decorative concrete") is a type of concrete that does not require post-modification and is used to directly display its texture and natural beauty in buildings. The mix ratio and construction method of fair-faced concrete are relatively special, and it is necessary to ensure a balance between appearance and strength. It is not only affected by the basic materials and construction requirements, but also by the combined influence of the building facade conditions and external environmental factors. Traditional concrete mix ratios are often based on standard formulas or empirical methods, lacking customized designs for specific building structures. For complex construction projects, a single mix ratio cannot meet the requirements of different parts. For example, some areas require higher strength, while other areas require better aesthetics. Different building parts have different requirements for the strength, durability, crack resistance, etc. of concrete. If the mix ratio cannot be flexibly adjusted, various problems will arise during the construction process, affecting the safety and aesthetics of the structure.

[0003] In summary, there is a technical problem in the prior art that the traditional plain concrete mix ratio usually relies on standardized mix ratios or empirical data, which is difficult to flexibly adjust according to the needs of different building structures, resulting in insufficient adaptability of the mix ratio to actual scenarios. Summary of the invention

[0004] The purpose of this application is to provide a data analysis-driven intelligent optimization method for fair-faced concrete mix ratio, in order to solve the technical problem in the prior art that the traditional fair-faced concrete mix ratio usually relies on standardized mix ratios or empirical data, which is difficult to flexibly adjust according to the needs of different building structures, resulting in insufficient adaptability of the mix ratio to actual scenarios.

[0005] In view of the above problems, the present application provides a data analysis-driven intelligent optimization method for fair-faced concrete mix ratio, wherein the data analysis-driven intelligent optimization method for fair-faced concrete mix ratio comprises: interactively obtaining coating scene information of a target building, and logically grouping the coating scene information according to the coating condition correlation, to obtain multiple coating function requirements, multiple coating surface requirements, and multiple coating performance requirements for multiple coating objects, wherein the multiple coating objects are identified by multiple coating structure types; using the coating scene information to traverse the construction schedule of the target building, to obtain multiple coating time domains for the multiple coating objects; after aggregating the multiple coating structure types to obtain K types of sample coating structures, constructing K ratio optimization spaces mapped to the K types of sample coating structures; based on According to multiple coating time domains, the first coating object is sequentially called from the multiple coating objects, and the first coating time domain, the first coating function requirement, the first coating surface requirement and the first coating performance requirement of the first coating object are used as the first multi-level optimization condition; after selecting the first proportion optimization space in K proportion optimization spaces according to the first coating structure type of the first coating object, the proportion combination is narrowed in the first proportion optimization space using the first multi-level optimization condition to obtain a first optimization performance database; the proportion combination is adjusted and optimized according to the first optimization performance database to obtain a first plain concrete proportion; and so on, after analyzing and obtaining multiple plain concrete proportions of the multiple coating objects, the multiple coating time domains and the multiple plain concrete proportions are used for raw material pre-scheduling and concrete pre-production.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The coating scene information of the target building is obtained through interaction, and the coating scene information is logically grouped according to the relevance of coating conditions to obtain multiple coating function requirements, multiple coating surface requirements and multiple coating performance requirements of multiple coating objects, wherein the multiple coating objects are identified by multiple coating structure types; the construction schedule of the target building is traversed by the coating scene information to obtain multiple coating time domains of the multiple coating objects; after aggregating the multiple coating structure types to obtain K types of sample coating structures, K ratio optimization spaces mapped to the K types of sample coating structures are constructed; according to the multiple coating time domains, the first coating object is sequentially called from the multiple coating objects, and the first coating object is mapped to the first coating object. The first coating time domain, the first coating function requirement, the first coating surface requirement and the first coating performance requirement of the first coating object are used as the first multi-level optimization conditions; after selecting the first ratio optimization space in the K ratio optimization spaces according to the first coating structure type of the first coating object, the first multi-level optimization conditions are used to limit the ratio combination in the first ratio optimization space to obtain the first optimization performance database; the ratio combination is adjusted and optimized according to the first optimization performance database to obtain the first plain concrete ratio; and so on, after analyzing and obtaining multiple plain concrete ratios of the multiple coating objects, the multiple coating time domains and multiple plain concrete ratios are used for raw material pre-scheduling and concrete pre-production. In other words, through multi-dimensional optimization of the ratio, it is ensured that the plain concrete ratio can better adapt to different coating scenarios and conditions, and customized ratios are performed according to the specific needs of different coating objects, thereby improving the adaptability of the plain concrete ratio to the coating scenario.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 A flow chart of a data analysis-driven method for intelligent optimization of the mix ratio of plain concrete in this application;

[0011] Figure 2 A schematic diagram of the process of constructing a performance database in a data analysis-driven intelligent optimization method for fair faced concrete mix ratio in this application. DETAILED DESCRIPTION

[0012] This application provides a data analysis-driven intelligent optimization method for the ratio of plain concrete, which solves the technical problem in the prior art that the ratio of plain concrete is usually dependent on standardized ratios or empirical data, making it difficult to flexibly adjust the ratio according to the needs of different building structures, resulting in insufficient compatibility between the ratio and the actual scene. Through multi-dimensional optimization of the ratio, it is ensured that the ratio of plain concrete can better adapt to different coating scenes and conditions, and customized ratios are performed according to the specific needs of different coating objects, thereby improving the compatibility of the ratio of plain concrete with the coating scene.

[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0014] For examples, please see the attached Figure 1 The present application provides a data analysis driven method for intelligent optimization of the proportion of plain concrete, wherein the data analysis driven method for intelligent optimization of the proportion of plain concrete specifically comprises the following steps:

[0015] Step 1: interactively obtain coating scene information of the target building, and logically group the coating scene information according to the relevance of coating conditions to obtain multiple coating function requirements, multiple coating surface requirements and multiple coating performance requirements for multiple coating objects, wherein the multiple coating objects are identified by multiple coating structure types.

[0016] Specifically, all coating scene information of the target building, including the location, area, environmental conditions, etc. of the coating, is obtained through the building information model (BIM) system or direct communication with the architectural designer and construction team. The collected information is classified according to the relevance of the coating conditions to facilitate subsequent ratio optimization. The information is grouped according to the coating conditions (such as humidity, temperature, light, etc.) using a database management system or dedicated building data analysis software. Coating scene information refers to the environmental and construction condition information related to the coating object (such as building exterior finishes, interior finishes, different building parts, etc.). The coating scene information is grouped according to a certain logical relationship and classified according to the functional requirements, surface requirements and performance requirements of the coating object. The functional requirements of multiple scene objects (basic functions that need to be met by plain concrete coating, such as waterproofing, anti-fouling, load-bearing, etc.), surface requirements (appearance and quality standards of the coating surface, such as smoothness, color uniformity, crack-free, etc.), and performance requirements (performance indicators that the coating material needs to achieve, such as compressive strength, impermeability, fire resistance, wear resistance, etc.) are obtained. For example, the coating performance requirements for the exterior wall are compressive strength ≥ 30MPa, impermeability ≥ 48 hours, and the coating performance requirements for the floor are compressive strength ≥ 40MPa, wear resistance ≥ 200 abrasion values. Assign a coating structure type to each coating object (structure types of different coating parts in the building, such as exterior walls, floors, roofs, etc., each structure type may have different coating requirements) and mark them. By grouping multiple coating objects according to the relevance of coating conditions, the scheme can be more targeted and optimized according to different types of coating structures, rather than using a single ratio for all structures, thus avoiding the problem of inflexible concrete mix design and difficulty in adapting to complex building needs.

[0017] Step 2: Using the coating scene information, traverse the construction schedule of the target building to obtain multiple coating time domains of the multiple coating objects.

[0018] Specifically, the construction schedule of the target building is traversed according to the coating scene information to determine the specific construction time of each coating object. Through software tools or database management systems, the coating scene information is compared and synchronized with the construction schedule, and the specific location and time point of each coating object in the construction process are determined according to the functional requirements, surface requirements and performance requirements of each coating object. The construction schedule refers to the time arrangement and sequence of various construction activities during the entire construction process of the building project from the beginning to the end. For each coating object, its time window in the construction schedule is determined, that is, the coating time domain, which defines the time range in which the coating object can start and end construction. For example, the construction schedule includes: foundation construction from week 1 to week 8, main structure construction from week 9 to week 24, exterior wall coating from week 25 to week 30, interior decoration from week 31 to week 40, and floor coating from week 41 to week 44. Traversing the construction schedule, the following coating time domains are obtained: the exterior wall coating time domain is from week 25 to week 30, and the floor coating time domain is from week 41 to week 44. By combining coating scene information with the construction schedule, the construction of exposed concrete is ensured to be coordinated with the overall construction schedule of the building, reducing uncertainty and delays in the construction process.

[0019] Step 3: After aggregating the multiple coating structure types to obtain K types of sample coating structures, construct K ratio optimization spaces mapped to the K types of sample coating structures.

[0020] Specifically, the structural types of multiple coated objects collected are analyzed, and the coated structural types with similar characteristics or requirements are aggregated, which means that multiple coated objects are classified according to their structural characteristics and performance requirements, and similar types are merged into a sample coated structure. Through aggregation, K sample coated structures are finally determined, where K represents the number of samples after aggregation, depending on the different types and similarities of the coated objects. Using the location information of the building and the coating time domain as constraints, the climate and environmental information within the time period, such as temperature, humidity, wind speed, etc., is retrieved. According to the mapping relationship between the sample coated structure and multiple coated structure types, the retrieved environmental information is merged to obtain K fused environmental information. With the fused environmental information and sample coated structure as constraints, historical and current concrete performance data are collected to establish K performance databases, including indicators such as strength, durability, and surface finish. For each sample coated structure, K concrete performance databases are used to construct K mix optimization spaces, each of which is customized for a specific sample coated structure. Each mix optimization space is customized for a specific coating structure type, ensuring the applicability and performance of the mix.

[0021] Step 4: According to multiple coating time domains, sequentially call the first coating object from the multiple coating objects, and use the first coating time domain, first coating function requirement, first coating surface requirement and first coating performance requirement of the first coating object as the first multi-level optimization condition.

[0022] Specifically, according to multiple coating time domains (time windows in the construction schedule), the first coating object is sequentially called from multiple coating objects in chronological order. For example, if the construction schedule requires the coating of the exterior wall to be completed first, then the first coating object will be the exterior wall. The relevant information of the first coating object, including its coating time domain, functional requirements, surface requirements and performance requirements, is collected and integrated into the first multi-level optimization condition as the optimization constraint and target. The first coating time domain refers to the construction time window of the first coating object, for example, the specific time window for the exterior wall coating is from the 25th week to the 30th week; the first coating functional requirements include the functions that the exterior wall needs to meet, such as waterproofing, weather resistance, etc.; the first coating surface requirements are such as the quality standards of the exterior wall surface, such as flatness, color uniformity, etc.; the first coating performance requirements are such as the performance indicators that the exterior wall needs to achieve, such as compressive strength, impermeability, etc. For example, the optimization conditions may include that within a specific time window, the ratio must meet a compressive strength of at least 28MPa, a water-cement ratio of less than 0.5, and specific durability requirements. By setting multi-level optimization conditions, it is ensured that the ratio optimization process closely matches the specific requirements of each coating object.

[0023] Step 5: After selecting the first ratio optimization space from K ratio optimization spaces according to the first coating structure type of the first coating object, the first multi-level optimization condition is used to narrow the ratio combinations in the first ratio optimization space to obtain a first optimization performance database.

[0024] Specifically, according to the first coating structure type of the first coating object, the corresponding first ratio optimization space is selected from the K ratio optimization spaces, which contains the historical formula information and performance data related to the coating structure type. For example, if the first coating object is an exterior wall, the ratio optimization space corresponding to the exterior wall is selected. The first multi-level optimization condition may include but is not limited to the first coating time domain, the first coating function requirement, the first coating surface requirement and the first coating performance requirement (such as gloss, crack width, permeability and other constraints), which helps to narrow the scope of ratio selection and ensure that the selected ratio can meet specific construction requirements. In the first ratio optimization space, the ratio combination is limited according to the first multi-level optimization condition, and the ratio scheme that can complete the construction within the first coating time domain is screened out; according to the first coating function requirement, the ratio scheme is further screened to ensure that it can meet the specific use function; considering the first coating surface requirements, such as color, texture, etc., the ratio scheme that meets the surface requirements is screened out; according to the first coating performance requirements, such as gloss, crack width, etc., the ratio scheme is finally screened. Through the above-mentioned narrowing process, the final set of mix ratio schemes constitutes the first optimized performance database. Each mix ratio scheme is screened by multi-level optimization conditions, so it is more likely to meet the actual construction needs. By narrowing the mix ratio combination by multi-level optimization conditions, unnecessary tests and adjustments are reduced, the efficiency of mix ratio design is improved, and it is ensured that the mix ratio scheme can meet specific performance requirements, thereby ensuring the construction quality and the long-term performance of the building.

[0025] Step six: adjusting and optimizing the mix ratio combination according to the first optimization performance database to obtain a first plain concrete mix ratio.

[0026] Specifically, the mix ratio schemes in the first optimization performance database are analyzed in detail to understand the performance characteristics and potential improvement space of each mix ratio scheme. Communicate with the construction site manager or owner to obtain the construction cost constraint of the first coating object, that is, the budget cap. Evaluate the concrete demand of the first coating object, including volume, strength grade and other specific requirements. Calculate the unit cost of each formula, including material cost, transportation cost and possible waste disposal cost. Use the first concrete demand and the first set of formula unit costs to perform cost analysis on the formulas in the first optimization performance database, calculate the total cost of each formula through comprehensive cost solution, and establish the first formula cost information base, select multiple virtual concrete formulas that meet the first construction cost constraint, and evaluate the raw material supply stability, considering the market supply of raw materials, the reliability of suppliers, transportation distance and time, etc. According to the raw material supply stability evaluation results, select the formula with the best raw material supply stability as the first plain concrete mix. At the same time, in the process of adjusting the ratio to optimize, find the mix combination with the smallest fitness function value, that is, the mix with the best performance as the first plain concrete mix. The optimization of the mix ratio combination adjustment means that by further adjusting the optimized performance database, the solution can dynamically optimize the mix ratio of the plain concrete in different coating time domains. Through the optimization of the mix ratio combination adjustment, the first plain concrete mix ratio can be obtained, which can meet the first coating structure type, first coating time domain, first coating function requirements, first coating surface requirements and first coating performance requirements of the first coating object in terms of performance, and the plain concrete mix ratio is within the budget, reducing the supply risk during the construction process.

[0027] Step 7: Similarly, after analyzing and obtaining a plurality of plain concrete mix ratios of the plurality of coating objects, raw material pre-scheduling and concrete pre-production are performed based on the plurality of coating time domains and the plurality of plain concrete mix ratios.

[0028] Specifically, each coating object is analyzed separately to determine its specific fair-faced concrete mix ratio, ensuring that each mix ratio meets the corresponding performance requirements, such as strength, durability, cost constraints, etc. According to the construction schedule of each coating object (coating time domain), an overall construction timeline is integrated to guide the planning of raw material pre-scheduling and concrete pre-production. According to the integrated coating time domain and the demand for each mix ratio, the total amount and type of raw materials required are calculated, and factors such as the storage conditions, supply cycle and minimum order quantity of raw materials are considered. Coordinate with suppliers to pre-scheduling raw materials to ensure timely supply when needed. According to the pre-scheduling plan, arrange the pre-production of concrete, considering factors such as the transportation time of concrete, on-site storage conditions and solidification time, determine the production batch, time and quantity of each mix ratio, and match the construction schedule. During the pre-production and scheduling process, strict quality control measures are implemented to ensure that each batch of concrete meets the mix ratio requirements, and the quality of raw materials and concrete performance are regularly tested to ensure consistency. Through pre-scheduling and pre-production, the waiting time during the construction process is reduced, the overall construction efficiency is improved, and reasonable raw material procurement and concrete production plans help reduce storage costs and waste.

[0029] Further, step three of this application includes:

[0030] Environmental information retrieval is performed with the multiple coating time domains and the location information of the target building as two-dimensional constraints to obtain multiple climate environment information; the union of the multiple climate environment information is solved according to the mapping relationship between the K types of sample coating structures and the multiple coating structure types to obtain K fused environmental information; the K fused environmental information and the K types of sample coating structures are used as data collection constraints to collect K concrete performance databases; the K concrete performance databases are used to construct the K mix ratio optimization spaces.

[0031] Specifically, the location information of the building and the coating time domain (i.e., the construction time window) are used as two-dimensional constraints to limit the time range and geographical location of the retrieval. Using the constraints, the climate and environmental information in each time period, such as temperature, humidity, wind force, rainfall, and ultraviolet intensity, is retrieved to obtain multiple climate and environmental information. The sample coating structure is a coating structure obtained by merging coating structure types with similar characteristics and requirements. A mapping relationship between K types of sample coating structures and multiple coating structure types is established, and different coating structure types are mapped to the sample coating structure. For each sample coating structure, the data of the corresponding multiple coating structure types in each climate and environmental information are solved by union, which means that all relevant climate and environmental information are merged to obtain a comprehensive set of environmental conditions. Through the union solution, a fused environmental information is obtained for each sample coating structure, and K fused environmental information is obtained. According to the K fused environmental information and the K sample coating structures, the specific constraints for data collection are determined, and the performance data related to the proportion of plain concrete and matching the constraints are collected, including key indicators such as concrete strength, durability, and surface finish. The collected data are collated and K concrete performance databases are established, including concrete performance data under different coating structure types and corresponding environmental conditions. K mix optimization spaces are constructed based on the K concrete performance databases. Each optimization space corresponds to a sample coating structure and includes various possibilities and performance of concrete mix under this structure. By constructing a mix optimization space for each coating structure, the optimal mix can be found more accurately, improving the performance and construction quality of concrete.

[0032] Furthermore, the present application also includes the following steps:

[0033] According to the first coating structure type of the first coating object, in the K concrete performance databases, a first concrete performance database is called, wherein a plurality of historical formula information, a plurality of historical construction performances and a plurality of historical construction times are associated and stored in the first concrete performance database; a first group of formula indicators are obtained by aggregating formula components of the plurality of historical formula information; after constructing a multidimensional indicator space based on the first group of formula indicators, spatial particle points are positioned according to the plurality of historical formula information to obtain a plurality of formula particle points; data of the plurality of formula particle points are filled using the plurality of historical construction performances and the plurality of historical construction times to obtain the first mix ratio optimization space; and so on, the K mix ratio optimization spaces are constructed based on the K concrete performance databases.

[0034] Specifically, a first coating object is sequentially called from multiple coating objects, and according to the structural type of the first coating object, a corresponding first concrete performance database is selected from K concrete performance databases, including multiple historical formula information, multiple historical construction performances, and multiple historical construction time consumptions. Among them, the historical formula information refers to the concrete mix ratio records used in the past, including the types and proportions of various raw materials; the historical construction performance refers to the concrete performance when a specific mix ratio was used in the past, such as strength, durability, surface finish, etc.; the historical construction time consumption refers to the time required to complete concrete construction in the past, including the time of preparation, mixing, transportation, pouring and maintenance. The formula components of multiple historical formula information are analyzed, including cement, aggregate, water, admixture, etc. The same or similar formula components are aggregated, and the main components in the formula are aggregated to simplify the complexity of the formula data to obtain a first set of formula indicators. A multidimensional indicator space is constructed based on the first set of formula indicators, and each dimension represents a formula component or performance indicator. According to multiple historical formula information, each formula is located in the multidimensional indicator space to form multiple formula particle points. In the multidimensional indicator space, a position point is determined for each historical formula. Each particle point represents a historical formula, and its position is determined by the indicator values ​​of the formula.

[0035] Collect the historical construction performance and historical construction time data related to each formula particle point, and associate these data with the corresponding formula particle point. Each particle point not only represents a formula, but also contains the performance and time information of the formula in actual construction. Use historical construction performance and time data to fill each formula particle point, that is, add additional information dimensions to each particle point in the multidimensional indicator space, such as construction performance score, construction time, etc., to obtain the first mix ratio optimization space. For each sample coating structure, select the corresponding concrete performance database, each database is associated with a specific coating structure type and environmental conditions. Repeat the above steps to obtain K mix ratio optimization spaces constructed by K concrete performance databases.

[0036] In a specific example, assuming that the first coating object is an exterior wall, the first concrete performance database associated with it is called, and the historical formula information is: Formula 1: 300kg cement, 600kg sand, 900kg gravel, 150kg water; Formula 2: 320kg cement, 580kg sand, 920kg gravel, 160kg water. After polymerization, the cement content range is 300-320kg, the sand content range is 580-600kg, the gravel content range is 900-920kg, and the water content range is 150-160kg. A four-dimensional indicator space is constructed with cement content, sand content, gravel content and water content as four dimensions. The historical construction performance of formula 1: strength 35MPa, good durability, excellent surface finish; construction time: 5 hours; the historical construction performance of formula 2: strength 38MPa, good durability, good surface finish; construction time: 4.5 hours. In the multidimensional index space, the particle points of formula 1 and formula 2 are filled with the corresponding construction performance and time consumption data, forming the first ratio optimization space. Through the aggregation of formula components and the construction of multidimensional index space, the complexity of the formula is simplified, the analysis efficiency is improved, and combined with data filling, the ratio optimization is more based on the actual construction performance, which improves the practicality and accuracy of the ratio optimization.

[0037] Further, as attached Figure 2 As shown, step five of this application includes:

[0038] The first coating time domain is used to traverse the first ratio optimization space, and N formula particle points whose historical construction time satisfies the first coating time domain are screened and obtained; N historical construction performances of the N formula particle points are called, wherein each of the N historical construction performances includes historical structural function data, historical surface performance data and historical coating performance data; the first coating function requirement is used to traverse the N historical structural function data of the N historical construction performances to perform first-level ratio combination reduction, and the first coating function requirement is used to traverse the first-level ratio reduction result to perform second-level ratio combination reduction, and H historical construction performances and H historical structural function data that simultaneously meet the first coating function requirement and the first coating performance requirement are obtained, wherein H is a positive integer less than N; after calling H historical coating performance data based on the H historical structural function data, virtual particle points are selected in the first ratio optimization space according to the H historical coating performance data and the first coating performance requirement to construct the first optimization performance database.

[0039] Furthermore, the present application also includes the following steps:

[0040] The first coating performance requirement is composed of coating gloss constraint, crack width constraint, coating permeability constraint, surface hardness constraint, surface roughness constraint, coating wear resistance constraint and bonding strength constraint.

[0041] Specifically, according to the first coating time domain of the first coating object, traverse in the first ratio optimization space, check each formula particle point in the space, and determine whether its corresponding historical construction time meets the requirements of the time domain. From the traversal results, select N formula particle points whose historical construction time meets the first coating time domain, and the historical construction time corresponding to these particle points matches the first coating time domain. For the selected N formula particle points, call their corresponding historical construction performance, including structural function data, surface performance data, and coating performance data.

[0042] First, use the first coating function requirement to traverse the historical structural function data in N historical construction performances, compare the matching degree of each historical structural function data with the first coating function requirement, and thus screen out the historical construction performances that meet these function requirements. Then, use the first coating function requirement to traverse the results of the first-level ratio combination limitation again, and further screen out the historical construction performances and historical structural function data that meet both the first coating function requirement and the first coating performance requirement. H historical construction performances and historical structural function data are screened out from the results of the second-level ratio combination limitation, which meet both the first coating function requirement and the first coating performance requirement. Based on the H historical structural function data, the corresponding historical coating performance data is called.

[0043] The first coating performance requirement includes a series of specific performance indicators, coating gloss constraint, crack width constraint, coating permeability constraint, surface hardness constraint, surface roughness constraint, coating wear resistance constraint and bonding strength constraint. Among them, coating gloss constraint refers to the requirement for the surface gloss of plain concrete, which is usually related to the flatness and reflectivity of the surface. For example, the surface gloss after coating is not less than 70%; crack width constraint involves the restriction on the width of cracks on the surface of plain concrete. Too wide cracks may affect the structural strength and appearance. For example, the width of cracks in the coating layer shall not exceed 0.2 mm; coating permeability constraint refers to the requirement for the permeability performance of the coating on the surface of plain concrete, which is related to the coating's ability to block water. For example, the water permeability of the coating layer is required to be no more than 0.5 ml / hour; surface hardness constraint refers to the ability of the coating layer to resist being pressed into or scratched by hard objects. Surfaces with high hardness are more resistant to wear and scratches, ensuring that the coating layer has certain wear resistance and durability. For example, the hardness of the coating layer is required to be no less than 3 H; surface roughness constraint refers to the degree of microscopic unevenness of plain concrete. Roughness affects the visual effect of the surface and the adhesion of the coating. For example, the surface roughness Ra after coating is required to be no more than 0.5 microns; coating wear resistance constraint involves the requirements for the wear resistance of the surface coating of plain concrete. A coating with good wear resistance can better resist the damage of external factors and ensure that the coating layer can maintain its beauty and function for a long time under normal use conditions. For example, the wear loss of the coating layer is required to be no more than 50 mg; bonding strength constraint refers to the requirements for the bonding strength between the plain concrete coating and the substrate, which is related to the overall adhesion and durability of the coating, ensuring that the coating layer can be firmly attached to the substrate and will not fall off easily. For example, the bonding strength between the coating layer and the substrate is required to be no less than 1.5 MPa. In the first ratio optimization space, virtual particle points are selected according to H historical coating performance data and the first coating performance requirements, and the matching degree of each historical coating performance data with the first coating performance requirements is compared, so as to select virtual particle points that meet these performance requirements in the ratio optimization space. The selected virtual particle points are integrated to construct the first optimized performance database, which contains the formula information that meets the first coating performance requirements. Through multi-level ratio combination narrowing, it is ensured that the final selected ratio scheme can meet specific functional requirements and performance requirements. The optimized performance database constructed based on historical data and scientific principles can more accurately predict the actual performance of the new ratio, thereby improving the construction quality.

[0044] Furthermore, the present application also includes the following steps:

[0045] A coating performance fitness function is used to evaluate the H historical coating performance data and the first coating performance requirement to obtain H coating performance fitness coefficients; a fitness threshold is preset, and the fitness threshold is used to screen the H coating performance fitness coefficients to obtain V formula particle points; a spatial framework is constructed in the first ratio optimization space based on the V formula particle points to obtain a first optimization performance space; a particle point spacing constraint is predefined, and virtual particle points are selected in the first optimization performance space according to the particle point spacing constraint to form the first optimization performance database.

[0046] Specifically, the coating performance fitness function is used to evaluate the degree of match between H historical coating performance data and the first coating performance requirement, and H coating performance fitness coefficients are obtained. The performance indicators such as gloss, crack width, permeability, wear resistance and bonding strength in the historical coating performance data are input into the coating performance fitness function to obtain the coating performance fitness coefficient. According to the specific needs and goals of the fair-faced concrete mix design, a fitness threshold is preset, and the formula particle points that meet the requirements are screened out, and those formula particle points whose fitness coefficients are less than or equal to the threshold are selected. These particle points are considered to meet the first coating performance requirements. V formula particle points are screened out from the H historical data points, and V is a positive integer less than or equal to H. By setting the fitness threshold and screening the formula particle points, it is ensured that the final fair-faced concrete mix design not only meets the functional requirements, but also has good coating performance.

[0047] In the first ratio optimization space, a spatial framework is built based on the selected V formula particle points. This framework is a multi-dimensional data structure used to represent the relationship between different formula particle points and their distribution in the optimization space. Based on the expectations of the ratio performance and the actual construction conditions, the spacing constraints between the particle points are predefined. In the first optimization performance space, virtual particle points are selected according to the predefined particle point spacing constraints. These virtual particle points represent possible ratio schemes and are used to construct the first optimization performance database. The selected particle points should meet these constraints and also be able to represent different performance characteristics and ratio schemes. Through the selected virtual particle points, the first optimization performance database is constructed, which contains multiple ratio schemes with different performance characteristics for further ratio optimization and decision support. By constructing an optimized performance space based on historical data and performance indicators, and selecting the formula particle points that are most likely to meet the first coating performance requirements, it is helpful to find the best concrete ratio to meet specific building needs and improve construction efficiency.

[0048] Furthermore, the present application also includes the following steps:

[0049] The coating performance fitness function is as follows: ; ; ; ; ;in, G 1 To paint history with gloss, C 1 is the historical crack width, P 1 To coat history with permeability, H 1 is the historical surface hardness, R 1 is the historical surface roughness, W 1 Coating for history with wear resistance, B 1 is the historical bond strength; G 2 To apply glossiness constraints, C 2 is the crack width constraint, P 2 To coat the permeability constraint, H 2 is the surface hardness constraint, R 2 is the surface roughness constraint, W 2 To coat the wear resistance constraints, B 2 is the bond strength constraint; where S is the coating performance fitness coefficient, I gh is the interaction coefficient between gloss and surface hardness, I cr is the interaction coefficient between crack width and surface roughness, I pw The interaction coefficient between permeability and wear resistance, I b is the independent coefficient of bonding strength.

[0050] Specifically, the coating performance fitness function is , where S is the coating performance fitness coefficient, which is used to evaluate the overall performance of the coating material. The smaller the coefficient, the higher the similarity, indicating that the performance of the coating material is more in line with the requirements. When the value of S is close to 0, it indicates that the performance of the coating material is very close to the ideal performance requirements, that is, the difference between the actual performance of the coating material and the expected performance is very small.

[0051] in, I gh is the interaction coefficient between gloss and surface hardness, reflecting the effect of the interaction between the gloss and hardness of the material on the coating performance. ,G 1 To paint history with gloss, G 2 are coating gloss constraints, representing the past and expected gloss levels, H 1 is the historical surface hardness, H 2 are the surface hardness constraints, representing the past and expected surface hardness levels, respectively, and measuring the degree of match between the historical performance of gloss and surface hardness and their expected targets.

[0052] I cr is the interaction coefficient between crack width and surface roughness, reflecting the influence of the relationship between material crack width and surface roughness on coating performance. , C 1 is the historical crack width, C 2 is the crack width constraint, representing the past and expected crack width levels, R 1 is the historical surface roughness, R 2 is the surface roughness constraint, which represents the past and expected surface roughness levels, and the nonlinear relationship between crack width and surface roughness is considered by taking the logarithm.

[0053] The interaction coefficient of Ipw permeability and wear resistance reflects how the permeability and wear resistance of the material jointly affect the coating performance. , P 1 To coat history with permeability, P 2 For coating permeability constraints, representing past and expected permeability levels, W 1 Coating for history with wear resistance, W 2 For coating wear resistance constraints, historical and expected wear resistance levels are represented, focusing on the synergistic effects of permeability and wear resistance in actual operation. I b is the bonding strength independent coefficient, which represents the direct contribution of the bonding strength of the material itself to the coating performance. , B 1 is the historical bond strength, B 2For the bond strength constraint, it represents the past and expected bond strength levels, and directly averages the historical and expected bond strength values ​​to reflect their contribution to the coating performance. By quantifying the interrelationships between different performance indicators and their individual effects, a comprehensive framework is provided to evaluate the performance adaptability of coating materials. This multi-angle and multi-dimensional analysis method helps to more accurately understand the behavior of materials under different conditions, thereby guiding the selection and optimization in practical applications.

[0054] Further, step 4 of this application includes:

[0055] Interactively obtain a first construction cost constraint and a first concrete demand for the first coating object; perform network data call according to the first group of formula indicators to obtain a first group of formula unit costs; perform comprehensive cost solution on the first optimization performance database according to the first concrete demand and the first group of formula unit costs to obtain a first formula cost information library; after screening and obtaining multiple virtual concrete formulas that meet the first construction cost constraint in the first formula cost information library, perform raw material supply stability evaluation on the multiple virtual concrete formulas to locate the first fair-faced concrete mix ratio with the best raw material supply stability.

[0056] Specifically, through communication and exchanges with the construction party or project leader, the construction cost constraints and concrete requirements of the first coating object are obtained, including the budget constraints of the project, the amount of concrete required, etc. The construction cost constraints of the first coating object, that is, the budget upper limit, are obtained; the concrete requirements of the first coating object are evaluated, including volume, strength grade and other specific requirements. According to the first set of formula indicators, the unit cost information of different formula components is obtained by calling relevant data sources through the network, such as the material market price database, supplier quotations, etc. According to the called data, the unit cost of each formula is calculated, including material cost, transportation cost and possible waste disposal cost, and these cost information are integrated into the mix design process to obtain the first set of formula unit costs. Using the first concrete demand and the first set of formula unit costs, the formulas in the first optimization performance database are cost analyzed to calculate the total cost of each formula, including material cost, construction cost, etc. The calculated cost information is integrated into the database to build a first formula cost information database, which contains the cost information of each formula.

[0057] From the first formula cost information base, multiple virtual concrete formulas are screened out according to the first construction cost constraint. These formulas meet the budget constraints of the project in terms of cost and meet the performance requirements. The raw material supply stability of the multiple virtual concrete formulas screened out is evaluated, and the supply situation, price fluctuations, transportation time and other factors of each raw material are evaluated to determine the stability of the raw material supply. During the evaluation process, it is necessary to communicate with the supplier to obtain detailed information about the raw material supply. According to the evaluation results of the raw material supply stability, the first clear water concrete mix ratio with the best raw material supply stability is located. This ratio not only meets the requirements in terms of cost, but also has the highest reliability in raw material supply, reducing the supply risk during the construction process. The optimal mix ratio obtained can be used in actual concrete production to ensure that the performance of the concrete meets specific construction requirements and is stable in terms of cost and raw material supply. Through screening and evaluation, while ensuring that the concrete performance meets the requirements, the construction cost and the stability of raw material supply are considered, so as to find the clear water concrete mix ratio with the highest cost-effectiveness and stable supply, which helps to improve the quality of concrete and construction efficiency.

[0058] In summary, the data analysis-driven intelligent optimization method for fair-faced concrete mix ratio provided in this application has the following technical effects:

[0059] The coating scene information of the target building is obtained through interaction, and the coating scene information is logically grouped according to the relevance of coating conditions to obtain multiple coating function requirements, multiple coating surface requirements and multiple coating performance requirements of multiple coating objects, wherein the multiple coating objects are identified by multiple coating structure types; the construction schedule of the target building is traversed by the coating scene information to obtain multiple coating time domains of the multiple coating objects; after aggregating the multiple coating structure types to obtain K types of sample coating structures, K ratio optimization spaces mapped to the K types of sample coating structures are constructed; according to the multiple coating time domains, the first coating object is sequentially called from the multiple coating objects, and the first coating object is mapped to the first coating object. The first coating time domain, the first coating function requirement, the first coating surface requirement and the first coating performance requirement of the first coating object are used as the first multi-level optimization conditions; after selecting the first ratio optimization space in the K ratio optimization spaces according to the first coating structure type of the first coating object, the first multi-level optimization conditions are used to limit the ratio combination in the first ratio optimization space to obtain the first optimization performance database; the ratio combination is adjusted and optimized according to the first optimization performance database to obtain the first plain concrete ratio; and so on, after analyzing and obtaining multiple plain concrete ratios of the multiple coating objects, the multiple coating time domains and multiple plain concrete ratios are used for raw material pre-scheduling and concrete pre-production. In other words, through multi-dimensional optimization of the ratio, it is ensured that the plain concrete ratio can better adapt to different coating scenarios and conditions, and customized ratios are performed according to the specific needs of different coating objects, thereby improving the adaptability of the plain concrete ratio to the coating scenario.

[0060] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0061] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A data analysis-driven method for intelligent optimization of fair-faced concrete mix ratio, characterized in that: The data analysis-driven method for intelligent optimization of the proportion of plain concrete comprises: Interactively obtain coating scene information of a target building, and logically group the coating scene information according to coating condition relevance to obtain multiple coating function requirements, multiple coating surface requirements, and multiple coating performance requirements of multiple coating objects, wherein the multiple coating objects are identified by multiple coating structure types; Using the coating scene information to traverse the construction schedule of the target building, obtaining multiple coating time domains of the multiple coating objects; After aggregating the plurality of coating structure types to obtain K types of sample coating structures, constructing K ratio optimization spaces mapped to the K types of sample coating structures; According to the multiple coating time domains, sequentially calling a first coating object from the multiple coating objects, and taking the first coating time domain, the first coating function requirement, the first coating surface requirement and the first coating performance requirement of the first coating object as the first multi-level optimization condition; After selecting a first ratio optimization space from K ratio optimization spaces according to a first coating structure type of a first coating object, the first multi-level optimization condition is used to narrow the ratio combination in the first ratio optimization space to obtain a first optimization performance database; According to the first optimization performance database, the first mix ratio is adjusted and optimized to obtain a first plain concrete mix ratio; By analogy, after analyzing and obtaining a plurality of plain concrete mix ratios of the plurality of coating objects, raw material pre-scheduling and concrete pre-production are performed based on the plurality of coating time domains and the plurality of plain concrete mix ratios.

2. A data analysis driven intelligent optimization method for fair-faced concrete mix ratio according to claim 1, characterized in that: After aggregating the multiple coating structure types to obtain K sample coating structures, K ratio optimization spaces mapped to the K sample coating structures are constructed, including: Performing environmental information retrieval with the multiple coating time domains and the location information of the target building as two-dimensional constraints to obtain multiple climate environment information; Solve the union of the plurality of climate environment information according to the mapping relationship between the K types of sample coating structures and the plurality of coating structure types to obtain K fused environment information; Using the K fusion environment information and K sample coating structures as data collection constraints, K concrete performance databases are collected and obtained; The K concrete performance databases are used to construct the K mix ratio optimization spaces.

3. A data analysis driven intelligent optimization method for fair-faced concrete mix ratio according to claim 2, characterized in that: The K concrete performance databases are used to construct the K mix ratio optimization spaces, including: According to the first coating structure type of the first coating object, in the K concrete performance databases, calling a first concrete performance database, wherein the first concrete performance database stores a plurality of historical formula information, a plurality of historical construction performances, and a plurality of historical construction times in association with each other; Obtaining a first set of recipe indicators by aggregating recipe components of the plurality of historical recipe information; After constructing a multidimensional indicator space based on the first set of recipe indicators, spatial particle point positioning is performed according to the plurality of historical recipe information to obtain a plurality of recipe particle points; Using the plurality of historical construction performances and the plurality of historical construction times to fill the data of the plurality of formula particle points, to obtain the first ratio optimization space; By analogy, the K mix ratio optimization spaces are constructed based on the K concrete performance databases.

4. A data analysis driven intelligent optimization method for fair faced concrete mix ratio according to claim 3, characterized in that: The first multi-level optimization condition is used to narrow down the ratio combination in the first ratio optimization space to obtain a first optimization performance database, including: The first coating time domain is used to traverse the first ratio optimization space, and N formula particle points whose historical construction time satisfies the first coating time domain are screened and obtained; Calling N historical construction performances of the N recipe particle points, wherein each of the N historical construction performances includes historical structural function data, historical surface performance data, and historical coating performance data; The first coating function requirement is used to traverse the N historical structural function data of the N historical construction performances to perform primary ratio combination reduction, and the first coating function requirement is used to traverse the primary ratio reduction result to perform secondary ratio combination reduction, to obtain H historical construction performances and H historical structural function data that simultaneously meet the first coating function requirement and the first coating performance requirement, wherein H is a positive integer less than N; After calling H historical coating performance data based on the H historical structural function data, virtual particle points are selected in the first ratio optimization space according to the H historical coating performance data and the first coating performance requirement to construct the first optimization performance database.

5. A data analysis driven intelligent optimization method for fair-faced concrete mix ratio according to claim 4, characterized in that: Selecting virtual particle points in the first ratio optimization space according to the H historical coating performance data and the first coating performance requirement to construct the first optimization performance database includes: Using a coating performance fitness function to evaluate the H historical coating performance data and the first coating performance requirement to obtain H coating performance fitness coefficients; Preset a fitness threshold, and use the fitness threshold to screen the H coating performance fitness coefficients to obtain V formula particle points; In the first ratio optimization space, a space framework is constructed based on the V recipe particle points to obtain a first optimization performance space; A particle point spacing constraint is predefined, and virtual particle points are selected in the first optimization performance space according to the particle point spacing constraint to form the first optimization performance database.

6. A data analysis driven intelligent optimization method for fair-faced concrete mix ratio according to claim 5, characterized in that: The first coating performance requirement is composed of coating gloss constraint, crack width constraint, coating permeability constraint, surface hardness constraint, surface roughness constraint, coating wear resistance constraint and bonding strength constraint.

7. A data analysis driven intelligent optimization method for fair faced concrete mix ratio according to claim 6, characterized in that: The coating performance fitness function is as follows: ； ； ； ； ； in, G 1 To paint history with gloss, C 1 is the historical crack width, P 1 To coat history with permeability, H 1 is the historical surface hardness, R 1 is the historical surface roughness, W 1 Coating for history with wear resistance, B 1 is the historical bond strength; in, G 2 To apply glossiness constraints, C 2 is the crack width constraint, P 2 To coat the permeability constraint, H 2 is the surface hardness constraint, R 2 is the surface roughness constraint, W 2 To coat the wear resistance constraints, B 2 It is the bond strength constraint; in, S is the coating performance fitness coefficient, I gh is the interaction coefficient between gloss and surface hardness, I cr is the interaction coefficient between crack width and surface roughness, I pw The interaction coefficient between permeability and wear resistance, I b is the independent coefficient of bonding strength.

8. A data analysis driven intelligent optimization method for fair-faced concrete mix ratio according to claim 7, characterized in that: The first optimization performance database is used to adjust and optimize the mix ratio combination to obtain a first plain concrete mix ratio, including: interactively obtaining a first construction cost constraint and a first concrete requirement of the first coating object; Performing online data call according to the first set of formula indicators to obtain the unit cost of the first set of formulas; Performing comprehensive cost calculation on the first optimization performance database according to the first concrete demand and the first group of formula unit costs to obtain a first formula cost information database; After the first formula cost information database screens and obtains a plurality of virtual concrete formulas that meet the first construction cost constraint, a raw material supply stability evaluation is performed on the plurality of virtual concrete formulas to locate the first plain concrete mix ratio with the best raw material supply stability.

Images