Flow control method and system for flowable engineering material

Abstract

The invention provides a flow control method and system for a flowable engineering material. The flow control method comprises the steps that flow data of the flowable engineering material and current construction environment parameters are collected; the flow data and the current construction environment parameters are input into a preset flow prediction algorithm model for operation processing, and a flow trend prediction result is obtained; performing analysis according to the traffic trend prediction result and a preset traffic control strategy rule to obtain a traffic control adjustment parameter; and on the basis of the flow control adjustment parameters, operation parameters of the conveying equipment of the flowable engineering materials are adjusted, and the optimized flow output state is obtained. According to the flow control method and device, the flow trend prediction result is predicted in combination with the flow data of the engineering material and the current construction environment parameters, then the flow control adjustment parameters are generated, and the precision and stability of flow control are improved. And the problems of unstable flow, material waste or substandard construction quality are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering materials, and in particular to a flow control method and system for fluid engineering materials. Background Art

[0002] In the application fields of fluid engineering materials, such as bridge construction, road paving, and building construction, precise control of material flow plays a vital role in project quality and construction efficiency.

[0003] Traditional flow control methods mainly rely on experience and simple mechanical adjustment methods. For example, the flow rate can be roughly controlled by manually adjusting the valve opening. However, this method is difficult to adapt to the complex and changing construction environment and changes in material properties.

[0004] During the construction process, environmental factors such as temperature, humidity, and pressure will have a significant impact on the fluidity of fluid engineering materials, and traditional methods often cannot accurately incorporate these environmental parameters into the consideration of flow control. In addition, traditional flow control lacks an effective data collection and analysis mechanism and cannot accurately predict flow trends, resulting in unstable flow, material waste, or substandard construction quality during the construction process.

[0005] In other words, during the current construction process, there is a defect of unstable flow control of engineering materials. Summary of the invention

[0006] The main purpose of the present invention is to provide a flow control method and system for fluid engineering materials, aiming to overcome the defect of unstable flow control of engineering materials.

[0007] To achieve the above object, the present invention provides a flow control method for fluid engineering materials, comprising the following steps:

[0008] Collect flow data of mobile engineering materials and current construction environment parameters;

[0009] The flow data and the current construction environment parameters are input into a preset flow prediction algorithm model for calculation and processing to obtain a flow trend prediction result;

[0010] Analyze the flow trend prediction result and the preset flow control strategy rules to obtain flow control adjustment parameters;

[0011] Based on the flow control adjustment parameters, the operating parameters of the conveying equipment of the fluid engineering material are adjusted to obtain an optimized flow output state.

[0012] Furthermore, the flow data and the current construction environment parameters are input into a preset flow prediction algorithm model for calculation and processing to obtain a flow trend prediction result, including:

[0013] Input the flow data and current construction environment parameters into a preset flow prediction algorithm model; wherein the flow prediction algorithm model includes a first sub-model based on support vector regression, a second sub-model based on random forest, and a third sub-model based on long short-term memory network;

[0014] The output results of each sub-prediction model are weighted and fused according to the preset dynamic weight allocation strategy to obtain the traffic trend prediction result.

[0015] Furthermore, the flow data and current construction environment parameters are input into a preset flow prediction algorithm model, including:

[0016] Performing spectrum analysis on the flow data, extracting characteristic values ​​of different frequency components, and obtaining a spectrum characteristic set of the flow data; performing fuzzy clustering on the construction environment parameters, classifying environment parameters with similar characteristics into one category, and forming multiple environment parameter clustering groups;

[0017] The traffic data spectrum feature set and multiple environmental parameter clustering groups are input into a preset traffic prediction algorithm model.

[0018] Furthermore, after the output results of each sub-prediction model are weighted and fused according to a preset dynamic weight allocation strategy, the method further includes:

[0019] Obtain correction rules for different construction scenarios and data anomalies, perform rule matching and adjustment processing on the results of weighted fusion processing, and obtain the flow trend prediction results.

[0020] Furthermore, the flow control adjustment parameters are obtained by analyzing the flow trend prediction result and the preset flow control strategy rules, including:

[0021] Performing trend evaluation processing based on fuzzy logic on the flow trend prediction result to obtain fuzzy language variables;

[0022] Performing a structured representation based on a knowledge graph on the preset traffic control strategy rules to obtain a rule knowledge network, performing matching and associating processing on the fuzzy language variables and the nodes in the rule knowledge network to obtain a preliminary association result;

[0023] Based on the preliminary correlation results, an optimization search mechanism based on a genetic algorithm is used to search for an approximate solution of the optimal combination of flow control adjustment parameters and obtain an intermediate adjustment parameter solution;

[0024] The intermediate adjustment parameter scheme is optimized to obtain the flow control adjustment parameter.

[0025] Furthermore, the tuning process of the intermediate adjustment parameter scheme to obtain the flow control adjustment parameter includes:

[0026] Perform fine adjustment on the intermediate adjustment parameter scheme based on simulated annealing algorithm;

[0027] Among them, the simulated annealing algorithm uses the intermediate adjustment parameter scheme as the initial solution, performs random perturbations in the solution space, and gradually reduces the perturbation amplitude according to the preset cooling strategy. At the same time, it judges whether the perturbed solution is better according to the performance evaluation index function of the flow control system. If it is better, the solution is accepted as the final flow control adjustment parameter;

[0028] Otherwise, a worse solution is accepted with a preset probability to avoid falling into the local optimum, and the final flow control adjustment parameters are obtained after multiple iterations.

[0029] Furthermore, the collection of flow data of fluid engineering materials and current construction environment parameters includes:

[0030] The flow data is obtained by using a flow sensor device based on a microfluidic chip to monitor the flow data at multiple points in real time;

[0031] The construction environment parameters are collected through distributed wireless sensor networks.

[0032] The present invention also provides a flow control system for fluid engineering materials, comprising:

[0033] The collection module is used to collect the flow data of mobile engineering materials and the current construction environment parameters;

[0034] A processing module, used for inputting the flow data and current construction environment parameters into a preset flow prediction algorithm model for calculation and processing to obtain a flow trend prediction result;

[0035] An analysis module, used to analyze the flow trend prediction result and the preset flow control strategy rules to obtain flow control adjustment parameters;

[0036] The adjustment module is used to adjust the operating parameters of the conveying equipment of the fluid engineering material based on the flow control adjustment parameters to obtain an optimized flow output state.

[0037] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0038] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0039] The flow control method and system of fluid engineering materials provided by the present invention include: collecting flow data of fluid engineering materials and current construction environment parameters; inputting the flow data and current construction environment parameters into a preset flow prediction algorithm model for calculation and processing to obtain flow trend prediction results; analyzing according to the flow trend prediction results and preset flow control strategy rules to obtain flow control adjustment parameters; based on the flow control adjustment parameters, adjusting and processing the operating parameters of the conveying equipment of the fluid engineering materials to obtain an optimized flow output state. In the present invention, the flow data of engineering materials and the current construction environment parameters are combined to predict the flow trend prediction results, and then generate flow control adjustment parameters to improve the accuracy and stability of process control. Avoid problems such as unstable flow, waste of materials or substandard construction quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic flow chart of a flow control method of a fluid engineering material in one embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram of the steps of a flow control method of a fluid engineering material in one embodiment of the present invention;

[0042] Figure 3 is a structural block diagram of a flow control system for fluid engineering materials in one embodiment of the present invention;

[0043] Figure 4 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0044] The implementation, functional features and advantages of the present invention will be further described in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0046] Reference Figure 1 as well as Figure 2 In one embodiment of the present invention, a flow control method for a fluid engineering material is provided, comprising the following steps:

[0047] Step S1, collecting flow data of fluid engineering materials and current construction environment parameters;

[0048] Step S2, inputting the flow data and current construction environment parameters into a preset flow prediction algorithm model for calculation and processing to obtain a flow trend prediction result;

[0049] Step S3, analyzing the flow trend prediction result and the preset flow control strategy rules to obtain flow control adjustment parameters;

[0050] Step S4, based on the flow control adjustment parameters, the operating parameters of the conveying equipment of the fluid engineering material are adjusted to obtain an optimized flow output state.

[0051] In this embodiment, as described in step S1 above, a high-precision flow sensor is first used to monitor key data such as flow velocity and flow rate of the fluid engineering material in the conveying pipeline or equipment in real time. These sensors can quickly and accurately capture the dynamic changes of flow and provide basic data for subsequent analysis and control. For example, a sensor based on advanced microfluidic technology can be used, which has the characteristics of high sensitivity and fast response and can accurately measure flow at a micro scale.

[0052] Then, use a variety of environmental monitoring equipment to comprehensively collect data on various environmental factors at the construction site, which will have a direct or indirect impact on the fluidity of fluid engineering materials. Common construction environmental parameters include temperature, humidity, air pressure, etc. For example, changes in temperature cause changes in the viscosity of the material, thereby affecting its flow characteristics. By collecting these parameters, we can have a more comprehensive understanding of the external conditions that affect the flow.

[0053] As described in step S2 above, before inputting the data into the model, the collected raw data needs to be preprocessed to improve the data quality and the model's operational efficiency. This includes data cleaning, removing outliers and noise; data standardization, unifying data of different units and magnitudes into a standard range; data encoding, converting some non-numerical data into numerical forms suitable for model processing, etc.

[0054] The above-mentioned preset traffic prediction algorithm model is one of the cores of this technical solution. The model is built based on advanced data analysis and machine learning algorithms, and can fully explore the complex relationship between traffic data and construction environment parameters. For example, a deep learning neural network model can be used, which has a strong nonlinear fitting ability and can automatically learn the features and patterns in the data. Through training on a large amount of historical data, the model can learn the traffic change rules under different combinations of traffic data and environmental parameters, so as to achieve accurate prediction of future traffic trends. In the process of model operation, some special algorithms and techniques can also be applied, such as time series analysis and feature engineering. Time series analysis can help the model better understand the changing trend of traffic data over time; feature engineering can improve the prediction accuracy of the model by extracting and constructing effective features.

[0055] As described in step S3 above, the flow trend prediction results obtained in step S2 are analyzed and interpreted in depth. This includes determining the direction of flow change (such as increase, decrease or remain stable), change speed and fluctuation range. For example, if the prediction results show that the flow will continue to increase in the future, then it is necessary to consider taking corresponding control measures in advance to prevent the flow from exceeding the safe or ideal range.

[0056] The preset flow control strategy rules are a series of logical rules and algorithms developed based on engineering experience, material properties, flow control objectives, and other factors. The above rules match the flow trend prediction results with the actual control needs to determine the appropriate control strategy and adjustment direction. For example, when the flow trend prediction results show that the flow is about to exceed the upper limit, the rules will indicate that the output power of the conveying equipment needs to be reduced or the valve opening needs to be adjusted.

[0057] Furthermore, according to the trend analysis results and flow control strategy rules, through complex mathematical calculations and algorithm operations, specific flow control adjustment parameters are calculated. The above parameters include the speed adjustment value of the conveying equipment, the opening adjustment percentage of the valve, the pressure adjustment amount of the pump, etc. The calculation process needs to take into account the influence of various factors, such as the fluidity characteristics of the material, the performance parameters of the equipment, the changes in the construction environment, etc., to ensure the accuracy and effectiveness of the adjustment parameters.

[0058] As described in step S4 above, the flow control adjustment parameter calculated in step S3 is actually applied to the conveying device of the fluid engineering material. This involves setting and adjusting the corresponding parameters of the control system of the conveying device. For example, if the adjustment parameter is to increase the speed of the conveying device, then the speed needs to be increased to a specified value through the control system of the device.

[0059] After adjusting the operating parameters of the conveying equipment, it is necessary to continuously monitor the actual changes in flow to verify whether the adjustment effect is in line with expectations. If there is still a deviation between the actual flow and the target flow, it is necessary to further optimize and adjust the adjustment parameters based on the feedback information. This forms a closed-loop feedback control system, which continuously optimizes and improves flow control based on actual conditions to ensure that the flow always remains in the ideal output state.

[0060] In this embodiment, by combining flow data and construction environment parameters and applying a flow prediction algorithm model, it is possible to accurately predict flow trends, discover potential flow problems in advance, and provide strong support for timely control measures. The flow control strategy can be automatically adjusted according to different environmental conditions, which improves the adaptability and stability of the system. Through precise flow control, material waste and construction time can be reduced, and the overall construction efficiency and quality of the project can be improved. It integrates a variety of technologies and algorithms, such as microfluidics, deep learning neural networks, flow control strategy rules, etc., and is innovative and leading in the field of flow control.

[0061] In one embodiment, the flow data and the current construction environment parameters are input into a preset flow prediction algorithm model for calculation and processing to obtain a flow trend prediction result, including:

[0062] Input the flow data and current construction environment parameters into a preset flow prediction algorithm model; wherein the flow prediction algorithm model includes a first sub-model based on support vector regression, a second sub-model based on random forest, and a third sub-model based on long short-term memory network;

[0063] The output results of each sub-prediction model are weighted and fused according to the preset dynamic weight allocation strategy to obtain the traffic trend prediction result.

[0064] In this embodiment, a flow prediction algorithm model containing multiple sub-models is constructed, and a unique weighted fusion method is used to achieve accurate prediction of the flow trend of fluid engineering materials. The core idea is to make full use of the advantages of different types of sub-models and combine dynamic weight allocation strategies to adapt to various complex data characteristics and changes.

[0065] In this embodiment, the support vector regression is a machine learning method based on statistical learning theory. It seeks an optimal hyperplane so that the sum of the distances from all sample points to the hyperplane is minimized. In traffic prediction, it uses traffic data and construction environment parameters as input features, and attempts to establish a nonlinear mapping relationship between these features and traffic trends. It has good adaptability and generalization ability for small sample data. In actual engineering, the data samples in some construction scenarios are limited, and support vector regression can still give relatively accurate prediction results in this case.

[0066] The above random forest is an ensemble learning method that constructs multiple decision trees and combines their prediction results to obtain the final prediction result. When constructing each decision tree, random forest randomly selects a portion of samples and features for training, thereby increasing the diversity and stability of the model. It can handle high-dimensional data. For complex data types such as traffic data and construction environment parameters that contain multiple features, random forest can effectively perform feature selection and model construction. It has high prediction accuracy and stability. Because it is an integration of multiple trees, it is not prone to overfitting and can maintain good performance on different data subsets.

[0067] The above-mentioned LSTM network is a deep learning model specially designed for processing time series data. It can memorize long-term historical information and predict future trends based on current input and historical information. In traffic forecasting, it can make full use of the time series characteristics of traffic data and learn the law of traffic changes over time. It has strong modeling capabilities for time-dependent traffic data. It can capture the long-term trend, periodic changes and short-term fluctuation characteristics of traffic, and is very suitable for time series forecasting tasks such as traffic trend forecasting. It can automatically learn complex patterns and features in the data without the need for a lot of manual feature engineering. By learning a large amount of historical traffic data and construction environment parameters, the LSTM network can automatically extract important features related to traffic trends.

[0068] The above dynamic weight allocation strategy is to dynamically adjust the weight of each sub-model in the final prediction result according to the current construction status, data characteristics and the real-time performance of each sub-model. Its purpose is to ensure that the advantages of each sub-model can be fully utilized in different situations to improve the accuracy and stability of the prediction.

[0069] In one embodiment, the inputting of the flow data and the current construction environment parameters into a preset flow prediction algorithm model includes:

[0070] Performing spectrum analysis on the flow data, extracting characteristic values ​​of different frequency components, and obtaining a spectrum characteristic set of the flow data; performing fuzzy clustering on the construction environment parameters, classifying environment parameters with similar characteristics into one category, and forming multiple environment parameter clustering groups;

[0071] The traffic data spectrum feature set and multiple environmental parameter clustering groups are input into a preset traffic prediction algorithm model.

[0072] In this embodiment, the key is to perform specific preprocessing operations on the flow data and construction environment parameters before inputting them into the preset flow prediction algorithm model. The purpose is to provide the model with more targeted and effective data representation by extracting key features and performing reasonable classification, thereby improving the accuracy and reliability of flow trend prediction.

[0073] Spectral analysis is a method of converting signals from the time domain to the frequency domain for analysis. For flow data, it contains information such as flow velocity and flow rate that change over time. Through spectral analysis, flow data can be decomposed into a combination of different frequency components. For example, in fluid mechanics, fluctuations of different frequencies represent different flow phenomena, such as low-frequency parts are related to large-scale flow trends, while high-frequency parts reflect local turbulence or small fluctuations.

[0074] First, the continuous flow data is divided into a certain time window to form multiple data segments. Then, each data segment is subjected to a fast Fourier transform (FFT) or other spectrum analysis method to convert it from the time domain to the frequency domain. In the frequency domain, the characteristic values ​​of various frequency components are calculated. These characteristic values ​​can include the amplitude, phase, energy, etc. of the frequency. For example, the frequency component with a larger amplitude represents the main fluctuation mode in the flow data, and the energy distribution can reflect the contribution of different frequency components to the overall flow change. The characteristic values ​​of all data segments are summarized and sorted to form a flow data spectrum feature set. This feature set contains the key information of the flow data at different frequencies and can more comprehensively describe the dynamic characteristics of the flow data.

[0075] By extracting the spectral eigenvalues, the key fluctuation patterns and frequency components in the flow data can be highlighted, and the interference of irrelevant information and noise can be reduced. This helps the model to capture the essential change law of flow more accurately. At the same time, different frequency components correspond to changes on different time scales. For example, low-frequency components reflect long-term flow trends, while high-frequency components are related to short-term fluctuations. In this way, in the subsequent prediction model, the flow changes on different time scales can be analyzed and predicted according to the characteristics of different frequency components, thereby improving the adaptability of the model to various changes.

[0076] The above-mentioned fuzzy clustering is a clustering method based on fuzzy mathematical theory. Different from the traditional hard clustering method (which clearly divides data into different categories), fuzzy clustering allows a data point to belong to multiple clusters at the same time with a certain degree of membership. In the construction environment parameters, there are complex associations and similarities between different parameters. For example, temperature and humidity have similar changing trends to a certain extent, while pressure and flow rate affect each other in some cases. Fuzzy clustering can reasonably classify these parameters into different cluster groups based on the similarities between them.

[0077] First, the construction environment parameters that have an important impact on the flow rate are selected, such as temperature, humidity, pressure, etc. These parameters are then standardized and their values ​​are mapped to a uniform range for subsequent clustering calculations. Appropriate similarity metrics, such as Euclidean distance, cosine similarity, etc., are used to measure the similarity between different environmental parameters. Based on these similarity metrics, a similarity matrix is ​​constructed. The similarity matrix is ​​processed using a fuzzy clustering algorithm, such as the fuzzy C-means clustering (FCM) algorithm. In the FCM algorithm, each data point has a membership vector that indicates the degree to which it belongs to different clusters. The membership vector and cluster center are optimized through continuous iteration until certain convergence conditions are met. Finally, according to the membership vector after iterative optimization, environmental parameters with similar characteristics are classified into one category to form multiple environmental parameter clustering groups. Each clustering group represents a combination of construction environment parameters with similar characteristics.

[0078] After clustering numerous construction environment parameters, multiple representative cluster groups are formed, which greatly reduces the complexity of the data. In this way, in the subsequent model input, there is no need to process a large number of original environmental parameters, but input them in the form of cluster groups, which improves the operational efficiency and interpretability of the model. Through fuzzy clustering, the potential relationships and similarity patterns between construction environment parameters can be mined. This helps to better understand the impact mechanism of the construction environment on traffic flow and provide more valuable information for traffic flow prediction. For example, if it is found that the environmental parameters in a cluster group are closely related to the change of traffic flow, then in the subsequent traffic control, we can focus on the changes of these parameters and adjust the traffic control strategy in time according to their changes.

[0079] In one embodiment, after the output results of each sub-prediction model are weighted and fused according to a preset dynamic weight allocation strategy, the method further includes:

[0080] Obtain correction rules for different construction scenarios and data anomalies, perform rule matching and adjustment processing on the results of weighted fusion processing, and obtain the flow trend prediction results.

[0081] In this embodiment, after completing the weighted fusion processing of the output results of each sub-prediction model, this embodiment further introduces correction rules for different construction scenarios and data anomalies to fine-tune the preliminary fusion results and ultimately obtain more accurate and reliable traffic trend prediction results.

[0082] First, analyze the characteristics of various construction scenarios and their potential impact on flow trends. For example, in the foundation pouring stage of a construction project, the flow demand of mobile engineering materials is relatively large and a stable flow rate needs to be maintained to ensure the quality of pouring, while in the wall painting stage, the flow accuracy requirements are higher and need to be dynamically adjusted according to different parts of the wall. According to the characteristics of these scenarios, formulate corresponding correction rules. For example, in the foundation pouring scenario, if the weighted fusion results show that the flow trend shows signs of decreasing, but according to the needs of the scenario it should remain stable or increase, then a rule is needed to increase the value of the predicted result by adding a fixed adjustment value or increasing it by a certain proportion.

[0083] Then, identify manifestations of data anomalies, such as sudden and large fluctuations in flow data, values ​​of construction environment parameters that are outside the normal range, etc. For example, when a temperature sensor fails and causes abnormally high or low temperature data, this will mislead flow predictions.

[0084] Finally, establish corresponding response rules. For large fluctuations in flow data, a threshold can be set. When the fluctuation exceeds the threshold, the smoothing rule is activated, such as using the moving average method to recalculate recent data to eliminate the impact of abnormal fluctuations. For abnormal environmental parameters, formulate corresponding adjustment rules based on the importance and impact of different parameters. For example, when the humidity is abnormally low, resulting in increased material fluidity, the prediction results need to be corrected accordingly to take into account the actual impact of this special situation on the flow.

[0085] Furthermore, the results after weighted fusion processing are compared and matched with the preset correction rules one by one. This requires a matching algorithm or a logical judgment mechanism that can quickly and accurately determine which rules are applicable to the current prediction results. For example, the relevant correction rules can be screened out by judging the type of the current construction scene and whether there are abnormal flags in the detection data.

[0086] Once the applicable correction rules are determined, the results of the weighted fusion processing are adjusted according to the specific content of the rules. If it is a simple numerical adjustment rule, the addition and subtraction operations are performed directly according to the numerical values ​​specified by the rule. For example, according to a certain construction scenario rule, it is necessary to increase the prediction result by 10%, and the weighted fusion result is calculated accordingly. For complex adjustment rules, some algorithms or models need to be re-called for recalculation. For example, in the smoothing processing rules for processing data anomalies, it is necessary to re-analyze and calculate the relevant data to obtain the corrected traffic trend prediction value.

[0087] In this embodiment, by considering various complex situations in actual construction and making targeted corrections to the preliminary prediction results, the prediction errors caused by differences in construction scenarios and data anomalies can be effectively reduced, greatly improving the accuracy of flow trend prediction. The flow prediction model can better adapt to different construction environments and various emergencies, improve the flexibility and adaptability of the model, and provide a more reliable decision-making basis for the flow control of mobile engineering materials. Accurate flow trend prediction results help to achieve precise control of the flow of engineering materials, thereby ensuring the quality and progress of engineering construction and reducing material waste and engineering risks.

[0088] In one embodiment, the flow control adjustment parameters are obtained by analyzing the flow trend prediction results and the preset flow control strategy rules, including:

[0089] Performing trend evaluation processing based on fuzzy logic on the flow trend prediction result to obtain fuzzy language variables;

[0090] Performing a structured representation based on a knowledge graph on the preset traffic control strategy rules to obtain a rule knowledge network, performing matching and associating processing on the fuzzy language variables and the nodes in the rule knowledge network to obtain a preliminary association result;

[0091] Based on the preliminary correlation results, an optimization search mechanism based on a genetic algorithm is used to search for an approximate solution of the optimal combination of flow control adjustment parameters and obtain an intermediate adjustment parameter solution;

[0092] The intermediate adjustment parameter scheme is optimized to obtain the flow control adjustment parameter.

[0093] In this embodiment, fuzzy logic is a mathematical method for dealing with fuzziness and uncertainty. There are some uncertainties and fuzziness in the traffic trend prediction results. For example, the traffic trend is a fuzzy concept such as "slowly rising" and "rapidly falling" rather than an exact numerical value. Through fuzzy logic, these fuzzy trend descriptions can be converted into fuzzy language variables.

[0094] First, define a series of fuzzy linguistic variables, such as "low", "medium", "high", etc., to indicate the degree of traffic trend. Then, according to the numerical range of the traffic trend prediction results, map them to the corresponding fuzzy linguistic variables. For example, if the traffic trend prediction result is within a certain range, it will be classified as the fuzzy linguistic variable "medium-speed increase".

[0095] Then, the preset traffic control strategy rules are constructed in the form of a knowledge graph. Knowledge graph is a method of representing knowledge using a graph structure, where nodes represent concepts or entities and edges represent the relationship between them. In the traffic control strategy rules, nodes can be various traffic control parameters, construction environment conditions, traffic trend status, etc., and edges represent the logical relationship and influence between them.

[0096] Match and associate the fuzzy language variables obtained in the previous step with the nodes in the knowledge graph. For example, if the fuzzy language variable represents a "rapidly rising" flow rate trend, then find the nodes related to "rapidly rising" in the knowledge graph, such as "need to increase the speed of the conveying equipment", and establish associations. In this way, the connection between the flow rate trend and the flow control strategy rules can be preliminarily determined.

[0097] Genetic algorithm is an optimization algorithm that simulates the biological evolution process. It searches for the optimal solution in the search space by simulating processes such as natural selection, crossover and mutation. In the search of flow control adjustment parameters, various combinations of flow control adjustment parameters are regarded as individuals, and each individual has a corresponding fitness value, which indicates its performance in meeting the flow control target.

[0098] Specifically, a set of initial flow control adjustment parameter combinations is randomly generated as the initial population. Then, the fitness value of each individual is calculated according to the fitness function (usually defined by indicators such as the error between the flow control target and the actual flow). Then, through operations such as selection, crossover and mutation, the population is continuously evolved so that the fitness value gradually increases. In the evolution process of each generation, individuals with higher fitness values ​​are retained and individuals with lower fitness values ​​are eliminated. After multiple iterations, the approximate solution of the optimal flow control adjustment parameter combination scheme, that is, the intermediate adjustment parameter scheme, is searched out.

[0099] Further analysis and adjustment of the intermediate adjustment parameter scheme is performed, including consideration of some constraints in actual engineering, such as the maximum and minimum operating parameters of the equipment, the physical properties of the material, etc. For example, if a parameter in the intermediate adjustment parameter scheme exceeds the allowable range of the equipment, it needs to be adjusted.

[0100] In this embodiment, the uncertainty in the flow trend prediction results is processed by fuzzy logic, which can more accurately reflect the actual situation and improve the adaptability and flexibility of flow control. The flow control strategy rules are structured using knowledge graphs, making the relationship between the rules clearer, facilitating quick and accurate matching and association, and improving the efficiency and accuracy of decision-making. The application of genetic algorithms can effectively find the optimal combination of flow control adjustment parameters in a complex search space, avoiding the problem of traditional methods falling into local optimal solutions. The final tuning process can ensure that the obtained flow control adjustment parameters meet both the theoretical optimization requirements and the actual engineering constraints and performance requirements, thereby improving the reliability and stability of flow control.

[0101] In one embodiment, the step of optimizing the intermediate adjustment parameter scheme to obtain the flow control adjustment parameter includes:

[0102] Perform fine adjustment on the intermediate adjustment parameter scheme based on simulated annealing algorithm;

[0103] Among them, the simulated annealing algorithm uses the intermediate adjustment parameter scheme as the initial solution, performs random perturbations in the solution space, and gradually reduces the perturbation amplitude according to the preset cooling strategy. At the same time, it judges whether the perturbed solution is better according to the performance evaluation index function of the flow control system. If it is better, the solution is accepted as the final flow control adjustment parameter;

[0104] Otherwise, a worse solution is accepted with a preset probability to avoid falling into the local optimum, and the final flow control adjustment parameters are obtained after multiple iterations.

[0105] In this embodiment, the simulated annealing algorithm is derived from the principle of solid annealing in physics. In the algorithm, the intermediate adjustment parameter scheme is analogous to an initial state of the solid, the solution space is analogous to the set of all states of the solid, and finding the optimal flow control adjustment parameter is equivalent to finding the structure of the solid in the lowest energy state.

[0106] Specifically, the algorithm starts with an intermediate parameter adjustment scheme, which is a specific position in the solution space. This position has certain performance, corresponding to the operation effect of the flow control system under this parameter scheme.

[0107] Then, a small random change is made to the initial solution in the solution space, just like adding a small amount of energy to a solid to change its state. This disturbance can be a small increase or decrease in one or more parameters in the intermediate adjustment parameter scheme. For example, a small increase or decrease in the speed adjustment parameter of the conveying equipment, or a fine-tuning of the adjustment parameter of the valve opening.

[0108] The cooling process in the simulated annealing algorithm is a process of gradually lowering the "temperature" of the system. Here, "temperature" is a parameter that controls the algorithm's search behavior. As the number of iterations increases, the "temperature" is gradually lowered according to the preset cooling strategy. The cooling strategy is usually designed based on the number of iterations of the algorithm or other related indicators. For example, an exponential cooling strategy can be adopted, that is, as the number of iterations increases, the "temperature" gradually decreases in the form of a certain exponential function. The purpose of lowering the "temperature" is to gradually reduce the amplitude of random perturbations, so that the algorithm is more inclined to accept better solutions in the later stage, thereby achieving the transition from global search to local fine search.

[0109] For flow control systems, performance evaluation index functions can be designed based on the actual flow control objectives and the operating characteristics of the system. Common indicators include the deviation between flow and target flow, flow stability, system energy consumption, etc. For example, a performance evaluation index function can be the sum of the squares of the deviation between flow and target flow plus a penalty term related to system energy consumption.

[0110] After the intermediate adjustment parameter scheme is disturbed, the value of the new parameter scheme under the performance evaluation index function is calculated to determine whether the solution is better. If the performance evaluation index function value corresponding to the new parameter scheme is smaller, it means that it performs better in achieving the flow control goal, that is, it is a better solution.

[0111] When the perturbed solution is judged to be better, it is directly accepted as the new current solution, that is, the intermediate adjustment parameter scheme is updated to this better parameter combination. This is a natural choice that meets the optimization goal and helps the algorithm search in a better direction. During the search process, in order to prevent the algorithm from falling into the local optimal solution, even if the perturbed solution performs poorly, it is accepted with a preset probability.

[0112] The above probability is usually related to the current "temperature". The higher the "temperature", the greater the probability of accepting a worse solution. In this way, in the early stages of the algorithm, the solution space can be explored more extensively, increasing the probability of finding the global optimal solution. For example, when the "temperature" is high, a worse solution is accepted with a probability of 30%; as the "temperature" decreases, the probability of accepting a worse solution gradually decreases, such as dropping to less than 5% in the later stages.

[0113] In this embodiment, the simulated annealing algorithm can find a good balance between global search and local fine search during the search process. By accepting poor solutions in the early stage to maintain the diversity of the search, it avoids falling into the local optimum; in the later stage, it focuses more on the fine search of the local area to find a more accurate optimal solution. For different types of flow control systems and complex actual engineering environments, the simulated annealing algorithm can flexibly adapt to various optimization goals and constraints according to the performance evaluation index function. Whether in a simple flow control scenario or in a complex and changeable engineering practice, it can effectively find suitable flow control adjustment parameters. The algorithm has relatively little dependence on the initial solution. Even if the intermediate adjustment parameter scheme is not very ideal, a better solution can be gradually found through continuous iteration and optimization. This makes the entire technical solution have good robustness and stability in practical applications.

[0114] In one embodiment, the collecting of flow data of fluid engineering materials and current construction environment parameters includes:

[0115] The flow data is obtained by using a flow sensor device based on a microfluidic chip to monitor the flow data at multiple points in real time;

[0116] The construction environment parameters are collected through distributed wireless sensor networks.

[0117] In this embodiment, during the data collection stage, a flow sensor device based on a microfluidic chip is used, which can accurately monitor the flow data in real time at multiple key locations, and quickly and accurately obtain the dynamic change information of the flow. At the same time, with the help of a distributed wireless sensor network, which is widely distributed at the construction site, the construction environment parameters such as temperature and humidity are fully collected. Each sensor node works together to aggregate and process the collected data, providing accurate and comprehensive basic data for subsequent flow prediction and control, ensuring that the flow control method can make accurate decisions and adjustments based on actual conditions.

[0118] Reference Figure 3 In another embodiment of the present invention, a flow control system for fluid engineering materials is provided, comprising:

[0119] The collection module is used to collect the flow data of mobile engineering materials and the current construction environment parameters;

[0120] A processing module, used for inputting the flow data and current construction environment parameters into a preset flow prediction algorithm model for calculation and processing to obtain a flow trend prediction result;

[0121] An analysis module, used to analyze the flow trend prediction result and the preset flow control strategy rules to obtain flow control adjustment parameters;

[0122] The adjustment module is used to adjust the operating parameters of the conveying equipment of the fluid engineering material based on the flow control adjustment parameters to obtain an optimized flow output state.

[0123] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0124] Reference Figure 4 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0125] Those skilled in the art will understand that Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0126] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0127] In summary, the flow control method and system for fluid engineering materials provided in the embodiments of the present invention include: collecting flow data of fluid engineering materials and current construction environment parameters; inputting the flow data and current construction environment parameters into a preset flow prediction algorithm model for calculation and processing to obtain flow trend prediction results; analyzing according to the flow trend prediction results and preset flow control strategy rules to obtain flow control adjustment parameters; based on the flow control adjustment parameters, adjusting the operating parameters of the conveying equipment for fluid engineering materials to obtain an optimized flow output state. In the present invention, the flow data of engineering materials and the current construction environment parameters are combined to predict the flow trend prediction results, and then generate flow control adjustment parameters to improve the accuracy and stability of process control. Avoid problems such as unstable flow, waste of materials or substandard construction quality.

[0128] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0129] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0130] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A flow control method for fluid engineering materials, characterized in that: The following steps are involved: Collect flow data of mobile engineering materials and current construction environment parameters; The flow data and the current construction environment parameters are input into a preset flow prediction algorithm model for calculation and processing to obtain a flow trend prediction result; Analyze the flow trend prediction result and the preset flow control strategy rules to obtain flow control adjustment parameters; Based on the flow control adjustment parameters, the operating parameters of the conveying equipment of the fluid engineering material are adjusted to obtain an optimized flow output state.

2. The flow control method of fluid engineering material according to claim 1, characterized in that: The flow data and the current construction environment parameters are input into a preset flow prediction algorithm model for calculation and processing to obtain a flow trend prediction result, including: Input the flow data and current construction environment parameters into a preset flow prediction algorithm model; wherein the flow prediction algorithm model includes a first sub-model based on support vector regression, a second sub-model based on random forest, and a third sub-model based on long short-term memory network; The output results of each sub-prediction model are weighted and fused according to the preset dynamic weight allocation strategy to obtain the traffic trend prediction result.

3. The flow control method of fluid engineering material according to claim 2, characterized in that: The step of inputting the flow data and the current construction environment parameters into a preset flow prediction algorithm model includes: Performing spectrum analysis on the flow data, extracting characteristic values ​​of different frequency components, and obtaining a spectrum characteristic set of the flow data; performing fuzzy clustering on the construction environment parameters, classifying environment parameters with similar characteristics into one category, and forming multiple environment parameter clustering groups; The traffic data spectrum feature set and multiple environmental parameter clustering groups are input into a preset traffic prediction algorithm model.

4. The flow control method of fluid engineering material according to claim 2, characterized in that: After the output results of each sub-prediction model are weighted and fused according to a preset dynamic weight allocation strategy, the method further includes: Obtain correction rules for different construction scenarios and data anomalies, perform rule matching and adjustment processing on the results of weighted fusion processing, and obtain the flow trend prediction results.

5. The flow control method of fluid engineering material according to claim 1, characterized in that: The flow control adjustment parameters are obtained by analyzing the flow trend prediction result and the preset flow control strategy rules, including: Performing trend evaluation processing based on fuzzy logic on the flow trend prediction result to obtain fuzzy language variables; Performing a structured representation based on a knowledge graph on the preset traffic control strategy rules to obtain a rule knowledge network, performing matching and associating processing on the fuzzy language variables and the nodes in the rule knowledge network to obtain a preliminary association result; Based on the preliminary correlation results, an optimization search mechanism based on a genetic algorithm is used to search for an approximate solution of the optimal combination of flow control adjustment parameters and obtain an intermediate adjustment parameter solution; The intermediate adjustment parameter scheme is optimized to obtain the flow control adjustment parameter.

6. The flow control method of fluid engineering material according to claim 5, characterized in that: The step of optimizing the intermediate adjustment parameter scheme to obtain the flow control adjustment parameter includes: Perform fine adjustment on the intermediate adjustment parameter scheme based on simulated annealing algorithm; Among them, the simulated annealing algorithm uses the intermediate adjustment parameter scheme as the initial solution, performs random perturbations in the solution space, and gradually reduces the perturbation amplitude according to the preset cooling strategy. At the same time, it judges whether the perturbed solution is better according to the performance evaluation index function of the flow control system. If it is better, the solution is accepted as the final flow control adjustment parameter; Otherwise, the worse solution is accepted with a preset probability, and the final flow control adjustment parameters are obtained after multiple iterations.

7. The flow control method of fluid engineering material according to claim 1, characterized in that: The collected flow data of mobile engineering materials and current construction environment parameters include: The flow data is obtained by using a flow sensor device based on a microfluidic chip to monitor the flow data at multiple points in real time; The construction environment parameters are collected through distributed wireless sensor networks.

8. A flow control system for fluid engineering materials, characterized in that: include: The collection module is used to collect the flow data of mobile engineering materials and the current construction environment parameters; A processing module, used for inputting the flow data and current construction environment parameters into a preset flow prediction algorithm model for calculation and processing to obtain a flow trend prediction result; An analysis module, used to analyze the flow trend prediction result and the preset flow control strategy rules to obtain flow control adjustment parameters; The adjustment module is used to adjust the operating parameters of the conveying equipment of the fluid engineering material based on the flow control adjustment parameters to obtain an optimized flow output state.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images