Concrete intelligent production monitoring method and system

Abstract

The invention discloses a concrete intelligent production monitoring method and system, and the method comprises the steps: obtaining the distribution information of a pouring mold, generating a pouring parameter sequence containing the pouring height and volume, inputting the standard pouring density, the length of a conveying pipe and pouring parameters into a foam compensation prediction algorithm, and obtaining the first foam concrete density; foam concrete is modulated based on the density and conveyed to a pouring mold through a conveying pipe, when it is detected that the foam concrete reaches the output end of the conveying pipe, the second foam concrete density is obtained, and according to the first density and the second density, the PID control module is adopted to adjust the foam adding rate and analyze the remaining pouring volume; and if not, modulation and pouring are conducted based on the next pouring parameter till all the molds are poured. Foam loss is predicted through a foam compensation prediction algorithm, the initial density is adjusted, the foam adding rate is dynamically adjusted in combination with the PID control module, and the uniformity and stability of foam concrete are ensured.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to an intelligent concrete production monitoring method and system. Background Art

[0002] In modern building construction, foam concrete is widely used in many scenarios such as wall filling, ground leveling and roof insulation due to its advantages such as light weight, heat preservation, sound insulation and convenient construction. However, in the actual construction process, foam concrete often faces a series of problems when it is transported through the pipeline, which directly affects the final pouring quality and construction efficiency. When foam concrete is transported through the pipeline, it is easy to cause foam overflow due to factors such as the height difference of the construction site, the transmission pressure and the friction of the inner wall of the pipeline. Specifically, the height difference will cause the pressure in the pipeline to change, thereby affecting the fluidity and stability of the foam concrete; the fluctuation of the transmission pressure will cause the foam structure to change, causing the foam to rupture or merge; the friction of the inner wall of the pipeline will further aggravate the loss of foam. These factors work together to make the density of the foam concrete when it arrives at the pouring point significantly different from the pre-mixed density, and it cannot meet the expected design requirements.

[0003] Traditional construction methods often rely on manual experience to adjust the foam addition rate, which is not only inefficient, but also difficult to ensure the consistency and stability of density. Especially in large-scale construction projects, the construction environment is complex and changeable, and manual adjustments are difficult to respond to various emergencies in a timely manner, which can easily affect the construction quality and progress. Summary of the invention

[0004] In order to solve at least one of the above-mentioned technical problems, the present invention provides a method and system for intelligent concrete production monitoring.

[0005] In a first aspect, the present invention provides a method for intelligent concrete production monitoring, the method comprising:

[0006] Acquire distribution information of a casting mold, and generate a casting parameter sequence including a plurality of casting parameters according to the distribution information, wherein the casting parameters include a casting height and a casting volume;

[0007] Inputting a preset standard pouring density, a length of a delivery pipe, and pouring parameters into a preset foam compensation prediction algorithm to obtain a first foam concrete density;

[0008] Modulating the foamed concrete based on the first foamed concrete density and transporting it to the corresponding casting mold through the conveying pipe; when the foamed concrete arrives at the output end of the conveying pipe for the first time, obtaining the foamed concrete density at the output end of the conveying pipe to obtain the second foamed concrete density;

[0009] According to the first foam concrete density and the second foam concrete density, a PID control module is used to adjust the foam addition rate;

[0010] Analyze the remaining pouring volume of the current casting mold. If the remaining pouring volume is less than or equal to the volume of the conveying pipe, the foam concrete is modulated and poured based on the next pouring parameters until the casting molds are all poured.

[0011] Preferably, the foam compensation prediction algorithm is expressed as:

[0012]

[0013] In the formula, ρ in represents the first foam concrete density, ρ target represents the standard pouring density, k represents the proportional factor, P loss Indicates the total pressure loss, P ref represents the reference pressure, which is set to standard atmospheric pressure by default; g represents the acceleration of gravity; h represents the height difference between the input and output ends of the transport pipe; f represents the friction factor; L represents the length of the transport pipe; D represents the diameter of the transport pipe; and v represents the flow rate of the foam concrete in the transport pipe.

[0014] Preferably, the foam adding rate is adjusted by using a PID control module according to the first foam concrete density and the second foam concrete density, including:

[0015] Obtain the first PID parameter corresponding to the current environment from the database;

[0016] Based on the first PID parameter, the density of the foamed concrete is adjusted by self-tuning by adding or subtracting the foam adding rate, and the change rate of the density of the second foamed concrete during the entire self-tuning adjustment process is collected until the standard pouring density is reached;

[0017] Generate a self-tuning density adjustment curve based on the change rate, the real-time second foam concrete density and the basic PID parameters;

[0018] Identify the cut-off temperature, cut-off time and cut-off temperature change rate of the self-tuning density adjustment curve, and calculate and update the proportional parameters in combination with the standard pouring density;

[0019] Based on the updated proportional parameter, the first PID parameter of the PID control module is optimized to obtain the second PID parameter.

[0020] Preferably, the step of acquiring distribution information of the casting mold and obtaining a casting parameter sequence of the foamed concrete according to the distribution information includes:

[0021] Obtain the preset height difference threshold and horizontal distance difference threshold, and calculate the maximum straight-line distance according to the height difference threshold and the horizontal distance difference threshold;

[0022] Based on the maximum straight-line distance, clustering parameters are set, and based on the distribution information of the casting molds, the casting molds are clustered using the DBSCAN algorithm according to the clustering parameters to obtain multiple classification clusters;

[0023] Analyze whether the distribution information of the casting molds in the classification cluster meets the height difference threshold and horizontal distance difference threshold constraints, screen out the casting molds that do not meet the conditions, perform secondary clustering, and integrate the two clustering results to obtain a new classification cluster;

[0024] Based on the average height difference of the classification clusters, the classification clusters are sorted from small to large to obtain the pouring parameter sequence.

[0025] In a second aspect, the present invention further provides an intelligent concrete production monitoring system, the system comprising:

[0026] A casting data acquisition module, used to obtain distribution information of the casting mold, and generate a casting parameter sequence including a plurality of casting parameters according to the distribution information, wherein the casting parameters include a casting height and a casting volume;

[0027] A first foamed concrete density analysis module, used for inputting a preset standard pouring density, a length of a conveying pipe and pouring parameters into a preset foam compensation prediction algorithm to obtain a first foamed concrete density;

[0028] A second foam concrete density acquisition module is used to modulate the foam concrete based on the first foam concrete density and transport it to the corresponding casting mold through the conveying pipe; when the foam concrete arrives at the output end of the conveying pipe for the first time, the foam concrete density at the output end of the conveying pipe is acquired to obtain the second foam concrete density;

[0029] A foam adding rate adjustment module, used for adjusting the foam adding rate using a PID control module according to the first foam concrete density and the second foam concrete density;

[0030] The casting mold casting module is used to analyze the remaining casting volume of the current casting mold. If the remaining casting volume is less than or equal to the volume of the conveying pipe, the foam concrete is modulated and poured based on the next casting parameters until the casting molds are all cast.

[0031] Preferably, the foam addition rate adjustment module is further used for:

[0032] Obtain the first PID parameter corresponding to the current environment from the database;

[0033] Based on the first PID parameter, the density of the foamed concrete is adjusted by self-tuning by adding or subtracting the foam adding rate, and the change rate of the density of the second foamed concrete during the entire self-tuning adjustment process is collected until the standard pouring density is reached;

[0034] Generate a self-tuning density adjustment curve based on the change rate, the real-time second foam concrete density and the basic PID parameters;

[0035] Identify the cut-off temperature, cut-off time and cut-off temperature change rate of the self-tuning density adjustment curve, and calculate and update the proportional parameters in combination with the standard pouring density;

[0036] Based on the updated proportional parameter, the first PID parameter of the PID control module is optimized to obtain the second PID parameter.

[0037] Preferably, the pouring data acquisition module is also used for:

[0038] Obtain the preset height difference threshold and horizontal distance difference threshold, and calculate the maximum straight-line distance according to the height difference threshold and the horizontal distance difference threshold;

[0039] Based on the maximum straight-line distance, clustering parameters are set, and based on the distribution information of the casting molds, the casting molds are clustered using the DBSCAN algorithm according to the clustering parameters to obtain multiple classification clusters;

[0040] Analyze whether the distribution information of the casting molds in the classification cluster meets the height difference threshold and horizontal distance difference threshold constraints, screen out the casting molds that do not meet the conditions, perform secondary clustering, and integrate the two clustering results to obtain a new classification cluster;

[0041] Based on the average height difference of the classification clusters, the classification clusters are sorted from small to large to obtain the pouring parameter sequence.

[0042] In a third aspect, the present invention further provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer program code, and the computer program code comprises computer instructions. When the processor executes the computer instructions, the electronic device executes the method as described in the first aspect above and any possible implementation thereof.

[0043] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the method as described in the first aspect above and any possible implementation thereof.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] 1) The present invention accurately predicts foam loss and adjusts the initial density of foam concrete in advance through an accurate foam compensation prediction algorithm, thereby ensuring the uniformity and stability of the material and effectively solving the problem of concrete density deviation caused by foam loss in traditional construction. Furthermore, the application of the PID control module realizes the dynamic adjustment of the foam addition rate, which not only reduces the need for human intervention, but also further improves the consistency of the density of foam concrete.

[0046] 2) The present invention quantifies various factors affecting the density of foam concrete through a foam compensation prediction algorithm and provides a practical tool for calculating the corrected density. By accurately calculating the initial density of foam concrete, the density fluctuation caused by pressure loss during transportation can be overcome to a large extent, ensuring that the density of the final poured concrete meets the design requirements.

[0047] 3) The present invention classifies casting molds through secondary clustering, so that the casting molds in the classification clusters that meet the height difference threshold and the horizontal distance difference threshold use the same casting parameters, which significantly improves the uniformity and stability of foam concrete, optimizes the casting sequence, reduces the number of adjustments and rework during the construction process, improves construction efficiency and economic benefits, and enhances the adaptability to complex construction environments.

[0048] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0050] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0051] Figure 1 A schematic diagram of a flow chart of a method for intelligent concrete production monitoring provided by an embodiment of the present invention;

[0052] Figure 2 A structural schematic diagram of an intelligent concrete production monitoring system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0055] When existing foam concrete is transported through pipelines at construction sites, factors such as height difference, transmission pressure and friction cause foam overflow, resulting in a difference between the final solidification density and the pre-mixed density, affecting construction quality and efficiency.

[0056] See also Figure 1 , Figure 1 The following is a flow chart of a method for intelligent concrete production monitoring provided by an embodiment of the present invention. Figure 1 As shown, the method includes:

[0057] S100, obtaining distribution information of a casting mold, and generating a casting parameter sequence including a plurality of casting parameters according to the distribution information, wherein the casting parameters include a casting height and a casting volume;

[0058] Before construction, the distribution information of the casting mold is obtained. The distribution information of the casting mold includes but is not limited to the total volume of the mold and the specific coordinates of each pouring port. The acquisition of distribution information is not limited to manual measurement records, but can also be accurately measured and mapped with the help of modern technical means such as drones or 3D scanners to ensure the accuracy and reliability of the data. Based on the distribution information of the casting mold, a casting parameter sequence containing multiple casting parameters can be generated, where each casting mold corresponds to a set of casting parameters, and the casting parameters should at least cover the casting height, casting volume and pouring port coordinates. It should be noted that the generation of the casting parameter sequence is not randomly arranged, but is arranged in an orderly manner according to the order of the height of the pouring port coordinates to form an orderly casting plan to ensure that the foam concrete can be distributed to each pouring point according to the optimal path.

[0059] S200, inputting a preset standard pouring density, a length of a delivery pipe, and pouring parameters into a preset foam compensation prediction algorithm to obtain a first foam concrete density;

[0060] The preset standard pouring density, the actual length of the conveying pipe and the pouring parameter sequence generated in the above steps are taken as input and imported into a fully trained foam compensation prediction algorithm. The foam compensation prediction algorithm is based on a large amount of historical construction data and is trained by a support vector regression algorithm. It can accurately predict the possible loss of foam in the process of foam concrete from the mixing station to the pouring mold under specific conveying conditions. It should be noted that the foam compensation prediction algorithm outputs an adjusted first foam concrete density, which is usually lower than the standard pouring density, and is used to pre-compensate for the density drop caused by foam loss during the transmission process to ensure the final pouring quality.

[0061] Support vector regression (SVR) is a supervised learning model commonly used for classification and regression analysis. The following is the process of training a foam compensation prediction algorithm based on support vector machines, including data preparation, model selection, parameter tuning, and model verification steps:

[0062] Collect data: First, a large amount of foam concrete construction case data needs to be collected. This data should include but is not limited to the initial density of foam concrete, the height difference of the construction site, the length of the delivery pipeline, the temperature and humidity of the construction environment, and the final density after pouring and molding.

[0063] Data preprocessing: Clean the collected data, remove invalid or erroneous data points, convert non-numerical attributes (such as material type) into numerical data for SVR model processing, and standardize or normalize the data to ensure that all features are on the same scale to improve model training efficiency;

[0064] Feature selection: Select features related to the density variation of foamed concrete from the preprocessed data set, such as the length of the delivery pipeline, height difference, ambient temperature, humidity, etc.;

[0065] Divide the dataset: Divide the dataset into training set and test set, usually in a ratio of 70%:30% or 80%:20%;

[0066] The SVR model is trained using the training set. During the training process, the kernel function type (such as linear kernel, polynomial kernel, radial basis function kernel, etc.) needs to be specified. For problems with strong nonlinear relationships such as foam compensation prediction, the radial basis function kernel is used by default; the key parameters of SVR include the penalty coefficient C, the kernel function parameter γ (for the RBF kernel), etc., and different parameter combinations can be tried within a certain range through grid search or random search to find the optimal solution. Commonly used evaluation indicators include mean square error (MSE), determination coefficient (R2R2), etc. In order to prevent overfitting, the k-fold cross-validation method can be used to evaluate the model performance. The training set is divided into k subsets again, one of the subsets is used as the validation set in turn, and the remaining subsets are used as the training set. The training and validation process is repeated k times, and the average performance is finally taken as the model evaluation result.

[0067] S300, modulating the foamed concrete based on the first foamed concrete density, and transporting the foamed concrete to the corresponding casting mold through the conveying pipe; when the foamed concrete first arrives at the output end of the conveying pipe, obtaining the foamed concrete density at the output end of the conveying pipe to obtain a second foamed concrete density;

[0068] According to the first foamed concrete density calculated above, an automated batching system is used to accurately proportion the required raw materials such as cement, water, and foaming agent, and mixed with a high-efficiency mixer to form foamed concrete that meets the requirements. Then, the foamed concrete is transported to the position of the corresponding casting mold through a pre-arranged conveying pipeline. A gravity detection unit is set at the end of the conveying pipe. Combined with the volume of the corresponding conveying pipe part, the foamed concrete density at the output end is calculated, and the second foamed concrete density can be obtained immediately.

[0069] S400, adjusting the foam adding rate by using a PID control module according to the first foam concrete density and the second foam concrete density;

[0070] The core task of the PID control module is to dynamically adjust the foam addition rate to ensure that the density of the foamed concrete remains within the target range.

[0071] When the second foam concrete density (D2) is measured by the gravity detection unit at the end of the conveying pipe, this value is compared with the previously calculated first foam concrete density (D1). The density deviation (ΔD) can be calculated by the formula ΔD = D1-D2. This deviation value reflects the actual reduction in the density of the foam concrete during the conveying process and is an important basis for adjusting the foam addition rate. The PID controller adjusts the output through three main parameters: proportional coefficient Kp, integral time constant Ti and differential time constant Td. The selection of these parameters depends on the dynamic characteristics of the system and the requirements for control accuracy. In this embodiment, Kp is set to a moderate value to ensure that the system response is neither too slow nor too aggressive; Ti is used to eliminate static errors and ensure stability in long-term operation; and Td helps to reduce the system's sensitivity to external interference and improve anti-interference ability.

[0072] Based on the calculated density deviation ΔD, the PID control module calculates the new foam addition rate R by the following formula new :

[0073]

[0074] In the formula, R old represents the current foam addition rate, ∫ΔDdt is the accumulated value of density deviation over time, is the rate of change of density deviation. Through the above formula, the PID controller can calculate a more reasonable foam addition rate according to the current density deviation and its changing trend, so as to gradually reduce the density deviation until it is maintained within an acceptable small range.

[0075] Once the new foam addition rate R is calculated new , immediately sends updated control instructions to the foam adding equipment, and at the same time, continuously monitors the density changes of foam concrete during the transportation process so as to adjust the control strategy in time. This real-time feedback mechanism ensures that good control performance can be maintained even when external conditions change.

[0076] S500, analyzing the remaining pouring volume of the current pouring mold, if the remaining pouring volume is less than or equal to the volume of the conveying pipe, modulating and pouring the foam concrete based on the next pouring parameter until the pouring of the pouring mold is completed.

[0077] During each pouring process, the remaining pouring volume in the current pouring mold is automatically analyzed. This analysis process mainly relies on the difference between the weight of the standard mold in the full state and the current weight, and then this difference is converted into volume units to accurately calculate the remaining pouring volume (the remaining weight can be obtained by subtracting the current weight from the weight of the standard mold in the full state, and the remaining pouring volume can be obtained by multiplying the ratio of the remaining weight to the weight of the standard mold in the full state by the mold volume). If it is found that the remaining pouring volume is less than or equal to the volume of the conveying pipe, it means that the existing foam concrete in the conveying pipe is sufficient to meet the pouring needs of the current mold. At this time, the foam concrete required for the next pouring mold will be prepared in advance. This method effectively improves construction efficiency and reduces unnecessary waiting time.

[0078] In this embodiment, an accurate foam compensation prediction algorithm is used to accurately predict foam loss and adjust the initial density of foam concrete in advance, thereby ensuring the uniformity and stability of the material and effectively solving the problem of concrete density deviation caused by foam loss in traditional construction. Furthermore, the application of the PID control module realizes dynamic adjustment of the foam addition rate, which not only reduces the need for human intervention, but also further improves the consistency of the density of foam concrete.

[0079] Preferably, the foam compensation prediction algorithm is expressed as:

[0080]

[0081] In the formula, ρ in represents the first foam concrete density, ρ target represents the standard pouring density, k represents the proportional factor, P loss Indicates the total pressure loss, P ref represents the reference pressure, which is set to standard atmospheric pressure by default; g represents the acceleration of gravity; h represents the height difference between the input and output ends of the transport pipe; f represents the friction factor; L represents the length of the transport pipe; D represents the diameter of the transport pipe; and v represents the flow rate of the foam concrete in the transport pipe.

[0082] ρ in ·g·h is the static head loss, which indicates the static pressure loss caused by the height difference of the conveying pipe. The static head loss refers to the pressure loss caused by the height difference between the starting point and the end point of the conveying pipe during the transportation of liquid or slurry. This pressure loss is caused by gravity and is proportional to the density and height difference. ρ in is the density of foam concrete at the input end of the delivery pipe (kg / m 3 ) is also the first foam concrete density, which is the density of the foam concrete at the beginning of transportation. The static head loss is caused by the height difference. The greater the height difference, the greater the static head loss. It is the friction loss, which indicates the pressure loss caused by the friction of the inner wall of the delivery pipe. The friction loss refers to the pressure loss caused by the friction of the inner wall of the pipe when the fluid flows in the pipe. This loss is proportional to the square of the flow velocity, proportional to the length of the pipe, and inversely proportional to the diameter of the pipe. The friction factor f is a dimensionless coefficient used to describe the friction resistance of the fluid in the pipe. loss It represents the total pressure loss. The total pressure loss is the total pressure drop caused by the combined effect of height difference and pipeline inner wall friction during transportation. The total pressure loss is a key parameter to ensure that foam concrete does not suffer from excessive foam burst during transportation.

[0083] The foam burst will lead to the reduction of bubbles in the foam concrete, thus causing the density to increase. Assuming that the density change caused by the foam burst can be expressed by a proportional factor k, that is, The proportional factor reflects the sensitivity of pressure loss to the change of foam concrete density. It is obtained based on historical data statistics. In order to make the foam concrete density ρ at the output end of the delivery pipe out Meet the requirements target , you can adjust the density of the input In order to ensure that the density of the foam concrete at the output end of the conveying pipe meets the predetermined target density ρ target , according to the total pressure loss P loss and the scaling factor k to adjust the input density ρ in , this formula ensures that density changes during the transportation process are effectively compensated through reverse calculation.

[0084] In this embodiment, various factors affecting the density of foam concrete are quantified through a foam compensation prediction algorithm, and a practical tool for calculating the corrected density is provided. By accurately calculating the initial density of foam concrete, the density fluctuation caused by the pressure loss during transportation can be overcome to a large extent, ensuring that the density of the final poured concrete meets the design requirements.

[0085] Preferably, the foam adding rate is adjusted by using a PID control module according to the first foam concrete density and the second foam concrete density, including:

[0086] Obtain the first PID parameter corresponding to the current environment from the database;

[0087] Based on the first PID parameter, the density of the foamed concrete is adjusted by self-tuning by adding or subtracting the foam adding rate, and the change rate of the density of the second foamed concrete during the entire self-tuning adjustment process is collected until the standard pouring density is reached;

[0088] Generate a self-tuning density adjustment curve based on the change rate, the real-time second foam concrete density and the basic PID parameters;

[0089] Identify the cut-off temperature, cut-off time and cut-off temperature change rate of the self-tuning density adjustment curve, and calculate and update the proportional parameters in combination with the standard pouring density;

[0090] Based on the updated proportional parameter, the first PID parameter of the PID control module is optimized to obtain the second PID parameter.

[0091] Before pouring foam concrete, the system will obtain the initial PID parameters (including proportional coefficient Kp, integral time constant Ti and differential time constant Td) corresponding to the current construction environment from the pre-stored database. These parameters are pre-set based on historical data and laboratory test results, and can reflect the characteristics of the density change of foam concrete under specific construction conditions. The information stored in the database includes not only environmental factors such as different seasons, temperature, humidity, etc., but also physical properties such as material, length and diameter of different types of conveying pipes, to ensure that the selected PID parameters can adapt to the current construction environment to the greatest extent. In the actual construction process, according to the first PID parameter obtained, the foam addition rate is dynamically adjusted through the PID control module. Specifically, the PID control module will calculate the foam addition rate increment that needs to be adjusted based on the deviation between the currently measured second foam concrete density and the standard pouring density, and then gradually increase or decrease the foam addition rate, while continuously collecting and recording the rate of change of the second foam concrete density during the entire adjustment process. This process will continue until the density of the second foam concrete is stabilized near the standard pouring density to ensure that the density of the foam concrete remains consistent throughout the pouring process. During the adjustment process, the change rate of the density of the second foam concrete and the corresponding foam addition rate adjustment value are recorded in real time. These data will be used to generate a detailed self-tuning density adjustment curve. This curve not only shows the trend of density change over time, but also reveals the relationship between the foam addition rate adjustment and density change. By analyzing this curve, we can more intuitively understand the density adjustment law under the current construction conditions and provide a reference for subsequent optimization. In order to further optimize the performance of the PID control module, the generated self-tuning density adjustment curve is deeply analyzed, especially the key points on the curve are identified, such as the tangent point temperature (i.e. the temperature when the density change rate changes significantly), the tangent point time (the time point when the density reaches a stable value) and the tangent point temperature change rate (the maximum value of the density change rate). The data of these key points will be combined with the standard pouring density to calculate the new proportional parameters. The calculation of the new proportional parameters is intended to make the PID control module more sensitive and accurate in the future adjustment process and reduce overshoot and oscillation. Finally, the calculated update proportional parameters will be used to optimize the first PID parameters of the PID control module, and the optimized second PID parameters will be applied to the next stage of foam concrete density adjustment. Through this process, the PID control module can better adapt to changes in the current construction environment and achieve more accurate and stable density control.

[0092] In this embodiment, by dynamically adjusting the foam addition rate and combining with the PID control module, the foam loss during transportation can be compensated in real time, the density of the foam concrete can be accurately controlled, and the construction quality and efficiency can be significantly improved.

[0093] Preferably, the step of acquiring distribution information of the casting mold and obtaining a casting parameter sequence of the foamed concrete according to the distribution information includes:

[0094] Obtain the preset height difference threshold and horizontal distance difference threshold, and calculate the maximum straight-line distance according to the height difference threshold and the horizontal distance difference threshold;

[0095] Based on the maximum straight-line distance, clustering parameters are set, and based on the distribution information of the casting molds, the casting molds are clustered using the DBSCAN algorithm according to the clustering parameters to obtain multiple classification clusters;

[0096] Analyze whether the distribution information of the casting molds in the classification cluster meets the height difference threshold and horizontal distance difference threshold constraints, screen out the casting molds that do not meet the conditions, perform secondary clustering, and integrate the two clustering results to obtain a new classification cluster;

[0097] Based on the average height difference of the classification clusters, the classification clusters are sorted from small to large to obtain the pouring parameter sequence.

[0098] Before pouring foam concrete, it is necessary to first obtain the preset height difference threshold H th and horizontal distance difference threshold D th These two thresholds are pre-set based on construction experience and material properties to ensure the uniformity and stability of foam concrete during pouring. th Defines the maximum height difference allowed between two casting molds, and the horizontal distance difference threshold D th The maximum horizontal distance allowed between two casting molds is defined. Based on these two thresholds, the geometric calculation formula Calculate the maximum straight line distance L max ,This distance is used in the subsequent clustering process to ensure that the distance between the casting molds in each classification cluster does not exceed the allowable range.

[0099] After obtaining the maximum straight-line distance L max After that, we need to set the clustering parameters of the DBSCAN algorithm. DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based clustering algorithm suitable for finding clusters of any shape. In this process, we mainly set two parameters: radius ∈ and minimum number of points MinPts. The radius ∈ is set to the maximum straight-line distance L max, and the minimum number of points MinPts is determined according to the actual construction requirements, usually 3-5 points. Then, based on the distribution information of the casting molds, the DBSCAN algorithm is used to cluster all the casting molds to obtain multiple classification clusters. The distance between the casting molds in each classification cluster does not exceed L max , thus ensuring that the same casting parameters can be used for these molds.

[0100] After the initial clustering is completed, the casting mold in each classification cluster needs to be further analyzed to check whether it meets the height difference threshold H th and horizontal distance difference threshold D th Specifically, for each classification cluster, the height difference and horizontal distance difference between any two casting molds are calculated. If there are casting molds that do not meet the conditions, they will be screened out from the current classification cluster and subjected to secondary clustering. The secondary clustering also uses the DBSCAN algorithm to perform secondary classification on the screened results. Finally, the results of the two clusterings are integrated to obtain a new classification cluster, ensuring that the casting molds in each classification cluster meet the constraints of height difference and horizontal distance difference.

[0101] After completing the clustering process, each classification cluster needs to be sorted in order to generate a reasonable sequence of casting parameters. Specifically, the average height difference of the casting mold in each classification cluster is calculated, and the classification clusters are sorted from small to large according to the average height difference. The purpose of this is to ensure that the area with a smaller height difference is processed first during the casting process, and then gradually transition to the area with a larger height difference, thereby avoiding casting quality problems caused by excessive height differences. Finally, a casting parameter sequence is generated based on the sorting results. Each classification cluster corresponds to a set of casting parameters to ensure the efficiency and consistency of the casting process.

[0102] In this embodiment, the casting molds are classified through secondary clustering, so that the casting molds in the classification clusters that meet the height difference threshold and the horizontal distance difference threshold use the same casting parameters, which significantly improves the uniformity and stability of the foam concrete, optimizes the casting sequence, reduces the number of adjustments and rework during the construction process, improves the construction efficiency and economic benefits, and enhances the adaptability to complex construction environments.

[0103] In summary, the method provided in this embodiment can at least achieve the following effects:

[0104] 1) The present invention accurately predicts foam loss and adjusts the initial density of foam concrete in advance through an accurate foam compensation prediction algorithm, thereby ensuring the uniformity and stability of the material and effectively solving the problem of concrete density deviation caused by foam loss in traditional construction. Furthermore, the application of the PID control module realizes the dynamic adjustment of the foam addition rate, which not only reduces the need for human intervention, but also further improves the consistency of the density of foam concrete.

[0105] 2) The present invention quantifies various factors affecting the density of foam concrete through a foam compensation prediction algorithm and provides a practical tool for calculating the corrected density. By accurately calculating the initial density of foam concrete, the density fluctuation caused by pressure loss during transportation can be overcome to a large extent, ensuring that the density of the final poured concrete meets the design requirements.

[0106] 3) The present invention classifies casting molds through secondary clustering, so that the casting molds in the classification clusters that meet the height difference threshold and the horizontal distance difference threshold use the same casting parameters, which significantly improves the uniformity and stability of foam concrete, optimizes the casting sequence, reduces the number of adjustments and rework during the construction process, improves construction efficiency and economic benefits, and enhances the adaptability to complex construction environments.

[0107] See also Figure 2 In one embodiment, a concrete intelligent production monitoring system is also provided, the system comprising:

[0108] A pouring data acquisition module 100 is used to obtain distribution information of a pouring mold and generate a pouring parameter sequence including a plurality of pouring parameters according to the distribution information, wherein the pouring parameters include a pouring height and a pouring volume;

[0109] The first foamed concrete density analysis module 200 is used to input the preset standard pouring density, the length of the delivery pipe and the pouring parameters into the preset foam compensation prediction algorithm to obtain the first foamed concrete density;

[0110] The second foam concrete density acquisition module 300 is used to modulate the foam concrete based on the first foam concrete density and transport it to the corresponding casting mold through the delivery pipe; when the foam concrete arrives at the output end of the delivery pipe for the first time, the foam concrete density at the output end of the delivery pipe is acquired to obtain the second foam concrete density;

[0111] A foam adding rate adjustment module 400 is used to adjust the foam adding rate using a PID control module according to the first foam concrete density and the second foam concrete density;

[0112] The casting mold casting module 500 is used to analyze the remaining casting volume of the current casting mold. If the remaining casting volume is less than or equal to the volume of the conveying pipe, the foam concrete is modulated and cast based on the next casting parameter until the casting mold is completed.

[0113] Preferably, the foam addition rate adjustment module 400 is further used for:

[0114] Obtain the first PID parameter corresponding to the current environment from the database;

[0115] Based on the first PID parameter, the density of the foamed concrete is adjusted by self-tuning by adding or subtracting the foam adding rate, and the change rate of the density of the second foamed concrete during the entire self-tuning adjustment process is collected until the standard pouring density is reached;

[0116] Generate a self-tuning density adjustment curve based on the change rate, the real-time second foam concrete density and the basic PID parameters;

[0117] Identify the cut-off temperature, cut-off time and cut-off temperature change rate of the self-tuning density adjustment curve, and calculate and update the proportional parameters in combination with the standard pouring density;

[0118] Based on the updated proportional parameter, the first PID parameter of the PID control module is optimized to obtain the second PID parameter.

[0119] Preferably, the pouring data acquisition module 100 is also used for:

[0120] Obtain the preset height difference threshold and horizontal distance difference threshold, and calculate the maximum straight-line distance according to the height difference threshold and the horizontal distance difference threshold;

[0121] Based on the maximum straight-line distance, clustering parameters are set, and based on the distribution information of the casting molds, the casting molds are clustered using the DBSCAN algorithm according to the clustering parameters to obtain multiple classification clusters;

[0122] Analyze whether the distribution information of the casting molds in the classification cluster meets the height difference threshold and horizontal distance difference threshold constraints, screen out the casting molds that do not meet the conditions, perform secondary clustering, and integrate the two clustering results to obtain a new classification cluster;

[0123] Based on the average height difference of the classification clusters, the classification clusters are sorted from small to large to obtain the pouring parameter sequence.

[0124] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0125] The present invention also provides an electronic device, including a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any possible implementation manner.

[0126] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0127] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0128] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those skilled in the art can also clearly understand that the descriptions of the various embodiments of the present invention have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

Claims

1. A method for intelligent concrete production monitoring, characterized in that: The method comprises: Acquire distribution information of a casting mold, and generate a casting parameter sequence including a plurality of casting parameters according to the distribution information, wherein the casting parameters include a casting height and a casting volume; Inputting a preset standard pouring density, a length of a delivery pipe, and pouring parameters into a preset foam compensation prediction algorithm to obtain a first foam concrete density; Modulating the foamed concrete based on the first foamed concrete density and transporting it to the corresponding casting mold through the conveying pipe; when the foamed concrete arrives at the output end of the conveying pipe for the first time, obtaining the foamed concrete density at the output end of the conveying pipe to obtain the second foamed concrete density; According to the first foam concrete density and the second foam concrete density, a PID control module is used to adjust the foam addition rate; Analyze the remaining pouring volume of the current casting mold. If the remaining pouring volume is less than or equal to the volume of the conveying pipe, the foam concrete is modulated and poured based on the next pouring parameters until the casting molds are all poured.

2. The intelligent concrete production monitoring method according to claim 1 is characterized in that: The foam compensation prediction algorithm is expressed as: In the formula, ρ in represents the first foam concrete density, ρ target represents the standard pouring density, k represents the proportional factor, P loss Indicates the total pressure loss, P ref represents the reference pressure, which is set to standard atmospheric pressure by default; g represents the acceleration of gravity; h represents the height difference between the input and output ends of the transport pipe; f represents the friction factor; L represents the length of the transport pipe; D represents the diameter of the transport pipe; and v represents the flow rate of the foam concrete in the transport pipe.

3. The intelligent concrete production monitoring method according to claim 1 is characterized in that: The method of adjusting the foam adding rate by using a PID control module according to the first foam concrete density and the second foam concrete density comprises: Obtain the first PID parameter corresponding to the current environment from the database; Based on the first PID parameter, the density of the foamed concrete is adjusted by self-tuning by adding or subtracting the foam adding rate, and the change rate of the density of the second foamed concrete during the entire self-tuning adjustment process is collected until the standard pouring density is reached; Generate a self-tuning density adjustment curve based on the change rate, the real-time second foam concrete density and the basic PID parameters; Identify the cut-off temperature, cut-off time and cut-off temperature change rate of the self-tuning density adjustment curve, and calculate and update the proportional parameters in combination with the standard pouring density; Based on the updated proportional parameter, the first PID parameter of the PID control module is optimized to obtain the second PID parameter.

4. The intelligent concrete production monitoring method according to claim 1 is characterized in that: The step of obtaining the distribution information of the casting mold and obtaining the casting parameter sequence of the foamed concrete according to the distribution information includes: Obtain the preset height difference threshold and horizontal distance difference threshold, and calculate the maximum straight-line distance according to the height difference threshold and the horizontal distance difference threshold; Based on the maximum straight-line distance, clustering parameters are set, and based on the distribution information of the casting molds, the casting molds are clustered using the DBSCAN algorithm according to the clustering parameters to obtain multiple classification clusters; Analyze whether the distribution information of the casting molds in the classification cluster meets the height difference threshold and horizontal distance difference threshold constraints, screen out the casting molds that do not meet the conditions, perform secondary clustering, and integrate the two clustering results to obtain a new classification cluster; Based on the average height difference of the classification clusters, the classification clusters are sorted from small to large to obtain the pouring parameter sequence.

5. An intelligent concrete production monitoring system, characterized in that: The system comprises: A pouring data acquisition module, used to obtain distribution information of a pouring mold, and generate a pouring parameter sequence including a plurality of pouring parameters according to the distribution information, wherein the pouring parameters include a pouring height and a pouring volume; A first foamed concrete density analysis module, used for inputting a preset standard pouring density, a length of a conveying pipe and pouring parameters into a preset foam compensation prediction algorithm to obtain a first foamed concrete density; A second foam concrete density acquisition module is used to modulate the foam concrete based on the first foam concrete density and transport it to the corresponding casting mold through the conveying pipe; when the foam concrete arrives at the output end of the conveying pipe for the first time, the foam concrete density at the output end of the conveying pipe is acquired to obtain the second foam concrete density; A foam adding rate adjustment module, used for adjusting the foam adding rate using a PID control module according to the first foam concrete density and the second foam concrete density; The casting mold casting module is used to analyze the remaining casting volume of the current casting mold. If the remaining casting volume is less than or equal to the volume of the conveying pipe, the foam concrete is modulated and poured based on the next casting parameters until the casting molds are all cast.

6. The intelligent concrete production monitoring system according to claim 5 is characterized in that: The foam addition rate adjustment module is also used for: Obtain the first PID parameter corresponding to the current environment from the database; Based on the first PID parameter, the density of the foamed concrete is adjusted by self-tuning by adding or subtracting the foam adding rate, and the change rate of the density of the second foamed concrete during the entire self-tuning adjustment process is collected until the standard pouring density is reached; Generate a self-tuning density adjustment curve based on the change rate, the real-time second foam concrete density and the basic PID parameters; Identify the cut-off temperature, cut-off time and cut-off temperature change rate of the self-tuning density adjustment curve, and calculate and update the proportional parameters in combination with the standard pouring density; Based on the updated proportional parameter, the first PID parameter of the PID control module is optimized to obtain the second PID parameter.

7. The intelligent concrete production monitoring system according to claim 5 is characterized in that: The pouring data acquisition module is also used for: Obtain the preset height difference threshold and horizontal distance difference threshold, and calculate the maximum straight-line distance according to the height difference threshold and the horizontal distance difference threshold; Based on the maximum straight-line distance, clustering parameters are set, and based on the distribution information of the casting molds, the casting molds are clustered using the DBSCAN algorithm according to the clustering parameters to obtain multiple classification clusters; Analyze whether the distribution information of the casting molds in the classification cluster meets the height difference threshold and horizontal distance difference threshold constraints, screen out the casting molds that do not meet the conditions, perform secondary clustering, and integrate the two clustering results to obtain a new classification cluster; Based on the average height difference of the classification clusters, the classification clusters are sorted from small to large to obtain the pouring parameter sequence.

8. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and when the processor executes the computer instructions, the electronic device executes the intelligent concrete production monitoring method according to any one of claims 1 to 4.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the intelligent concrete production monitoring method according to any one of claims 1 to 4.

Images