Concrete mixing temperature early warning method and system based on multi-source data fusion

Abstract

The application provides a concrete mixing temperature early warning method and system based on multi-source data fusion, which comprises the following steps: obtaining multi-source historical data of a target concrete mixing device during the execution of each concrete mixing task; taking each preprocessed multi-source historical data as a basic feature, extracting coupled features from the preprocessed multi-source historical data, and screening target features associated with the concrete temperature from all the basic features and coupled features; constructing a feature matrix according to the target features, and constructing a temperature prediction model according to the feature matrix; collecting real-time multi-source data of the target concrete mixing device, inputting the real-time multi-source data into the temperature prediction model, and obtaining the temperature distribution of the concrete; detecting the temperature distribution according to a first preset rule, and determining whether to execute a preset early warning strategy according to the detection result. The application can comprehensively improve the accuracy, comprehensiveness and timeliness of concrete mixing temperature monitoring and early warning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of concrete mixing temperature early warning, and particularly relates to a concrete mixing temperature early warning method and system based on multi-source data fusion. BACKGROUND

[0002] In the field of construction engineering, concrete is one of the most basic and widely used building materials, and its quality is directly related to the safety, durability and stability of the building structure. The concrete mixing process is a key link to ensure the quality of concrete, and temperature is an important parameter affecting the performance of concrete. Suitable mixing temperature helps to ensure the workability, strength development and durability of concrete. For example, too high temperature may cause rapid evaporation of concrete moisture, resulting in cracks and reduced strength; too low temperature may prolong the setting time of concrete, affecting the construction progress. With the continuous improvement of the quality requirements of the construction industry on engineering quality and the increase of large and complex construction projects, accurate control and early warning of concrete mixing temperature become increasingly important.

[0003] Traditional temperature measurement methods often rely on only a single type of sensor to monitor concrete temperature, which cannot comprehensively and accurately reflect the spatial temperature distribution of concrete in the mixing equipment, and is prone to miss local temperature abnormal points. At the same time, the comprehensive influence of multi-source data (such as environmental temperature, raw material temperature, equipment operating parameters, etc.) on concrete temperature is not fully considered, resulting in insufficient accuracy and timeliness of early warning. SUMMARY

[0004] The purpose of the present application is to provide a concrete mixing temperature early warning method and system based on multi-source data fusion, aiming to solve the problems of low monitoring accuracy and early warning lag in traditional concrete mixing temperature detection technology.

[0005] In a first aspect, the present application provides a concrete mixing temperature early warning method based on multi-source data fusion, the method comprising:

[0006] Obtaining multi-source historical data of a target concrete mixing equipment during the execution of each mixing concrete task, and preprocessing the multi-source historical data, the multi-source historical data including environmental temperature, raw material temperature data, equipment operating parameters and concrete temperature data;

[0007] Taking each preprocessed multi-source historical data as a basic feature, and extracting coupling features from the preprocessed multi-source historical data, and screening target features associated with concrete temperature from all basic features and coupling features;

[0008] Constructing a feature matrix according to the target features, and constructing a temperature prediction model representing the temperature distribution of concrete in the target concrete mixing equipment according to the feature matrix;

[0009] collecting real-time multi-source data of the target concrete mixing equipment, and inputting the real-time multi-source data into the temperature prediction model to obtain a temperature distribution of the concrete;

[0010] detecting the temperature distribution according to a first preset rule, and determining whether to execute a preset early warning strategy according to a detection result.

[0011] In some embodiments, the step of obtaining multi-source historical data of the target concrete mixing equipment when mixing concrete and pre-processing the multi-source historical data includes:

[0012] Under the same mixing batch, the raw material temperature data includes cement temperature and fineness, aggregate temperature and water content, additive temperature and addition amount, water temperature and addition amount, the equipment operation parameter is rotation speed, and the concrete temperature data includes multi-point temperature in the target concrete mixing equipment and discharge port temperature.

[0013] All data are sequentially cleaned and standardized to obtain pre-processed multi-source historical data.

[0014] In some embodiments, the step of taking each pre-processed multi-source historical data as a basic feature and extracting a coupling feature from the pre-processed multi-source historical data includes:

[0015] The first coupling feature is extracted according to the following formula:

[0016] ;

[0017] wherein, the first coupling feature is, the ambient temperature is, the time when the ith material is put into the equipment is, the heat exchange rate coefficient is, the total number of material types is, the specific heat capacity of the ith material is, the initial temperature of the ith material put into the mixer is, the input amount of the ith material is, the reference time when the mixer starts to work is;

[0018] The second coupling feature is extracted according to the following formula:

[0019] ;

[0020] wherein, the second coupling feature is, the interface thermal resistance coefficient is, the aggregate temperature is, is the temperature of the cement, is the input amount of the aggregate, is the input amount of the cement;

[0021] The third coupling feature is extracted according to the following formula:

[0022] ;

[0023] wherein, is the third coupling feature, is the instantaneous stirring power at the tth time step, is the rotating speed, is the total mass of the concrete in the device, is the specific heat capacity of the concrete, is the discharge port temperature when the stirring is completed, is the feeding port temperature when all the materials are inputted;

[0024] The fourth coupling feature is extracted according to the following formula:

[0025] ;

[0026] wherein, is the moisture evaporation-temperature suppression feature, is the evaporation coefficient of the concrete, is the average temperature of the concrete at the next point under the current stirring task, is the dew point temperature;

[0027] The fifth coupling feature is extracted according to the following formula:

[0028] ;

[0029] wherein, is the fifth coupling feature, is the total stirring time, is the fineness of the cement, is the water content of the aggregate, is the input amount of the additive.

[0030] In some embodiments, the step of screening the target features associated with the concrete temperature from all the basic features and coupling features comprises:

[0031] Let the concrete temperature at the jth point of the ith concrete stirring task point in the device at the tth time step be to calculate the first average concrete temperature of the jth point of the ith concrete stirring task point in the device ;

[0032] All the basic features and coupling features are summarized to obtain a feature set pairing the first average concrete temperature under the same concrete mixing task with each feature in the feature set, obtaining a plurality of feature pairs corresponding to each concrete mixing task, wherein, is the kth target feature, is the total number of base features and coupling features;

[0033] calculating the Pearson coefficients between all feature pairs in different seasons to screen target features associated with concrete temperature from the feature set according to the Pearson coefficients.

[0034] In some embodiments, the step of constructing a feature matrix according to the target features, and constructing an initial temperature prediction model representing the temperature distribution of concrete in the target concrete mixing equipment according to the feature matrix comprises:

[0035] taking the concrete mixing task number as the column name, taking the target feature number as the row name, and sequentially filling the numerical values of the corresponding target features according to the row name and the column name to obtain a feature matrix:

[0036] ;

[0037] wherein F is the feature matrix, 、 、 、 are the numerical values of the 1st target feature of the 1st mixing task, the 1st target feature of the Lth mixing task, the Kth target feature of the 1st mixing task, and the Kth target feature of the Lth mixing task, respectively, L is the total number of mixing tasks, and K is the total number of target features.

[0038] In some embodiments, the step of constructing a feature matrix according to the target features, and constructing a temperature prediction model representing the temperature distribution of concrete in the target concrete mixing equipment according to the feature matrix comprises:

[0039] constructing a temperature prediction model according to the following formula:

[0040] ;

[0041] wherein, is the concrete temperature at the jth measurement point at the tth time step of the ith mixing task, is the spatiotemporal weight coefficient of the kth target feature at the jth measurement point at the tth time step, is the base weight coefficient of the kth target feature, 、 、 are the numerical values of the kth row and the lth column, the uth row and the lth column, and the vth row and the lth column in the feature matrix, respectively, is a spatio-temporal interaction weight coefficient of the jth measurement point at the tth time step, is a feature interaction weight coefficient of the uth target feature and the vth target feature at the jth measurement point at the tth time step, is a set of neighborhood measurement points of the jth measurement point, is a set of neighborhood time steps of the tth time step.

[0042] In some embodiments, the step of detecting the temperature distribution according to the first preset rule, and determining whether to execute a preset warning strategy according to the detection result comprises:

[0043] The temperature distribution comprises predicted temperatures of each measurement point at multiple future time steps;

[0044] A first temperature change rate of a neighboring measurement point and a second temperature change rate of the same measurement point at adjacent time steps are calculated according to the temperature distribution;

[0045] It is determined whether the predicted temperature is within a first preset range, the first temperature change rate is within a second preset range, and the second temperature change rate is within a third preset range;

[0046] If the predicted temperature is within the first preset range, the first temperature change rate is within the second preset range, and the second temperature change rate is within the third preset range, the detection result is normal.

[0047] In some embodiments, the step of determining whether the predicted temperature is within the first preset range, the first temperature change rate is within the second preset range, and the second temperature change rate is within the third preset range further comprises:

[0048] If the predicted temperature is not within the first preset range and / or the first temperature change rate is not within the second preset range and / or the second temperature change rate is not within the third preset range, a warning information is issued.

[0049] In a second aspect, the present application provides a concrete mixing temperature warning system based on multi-source data fusion, which comprises:

[0050] A historical data acquisition module is configured to acquire multi-source historical data of a target concrete mixing device during each mixing task, and to pre-process the multi-source historical data, wherein the multi-source historical data comprises environmental temperature, raw material temperature data, device operating parameters, and concrete temperature data.

[0051] The target feature screening module is configured to take each preprocessed multi-source historical data as a basic feature, extract coupled features from the preprocessed multi-source historical data, and screen target features associated with the concrete temperature from all the basic features and coupled features.

[0052] The feature matrix construction module is configured to construct a feature matrix according to the target features, and construct a temperature prediction model representing the temperature distribution of the concrete in the target concrete mixing device according to the feature matrix.

[0053] The temperature prediction module is configured to collect real-time multi-source data of the target concrete mixing device, and input the real-time multi-source data into the temperature prediction model to obtain the temperature distribution of the concrete.

[0054] The detection module is configured to detect the temperature distribution according to a first preset rule, and determine whether to execute a preset warning strategy according to a detection result.

[0055] In a third aspect, the present application provides a storage medium, which stores one or more programs, and the programs are executed by a processor to implement the concrete mixing temperature warning method based on multi-source data fusion.

[0056] In a fourth aspect, the present application provides an electronic device, which includes a memory and a processor, wherein:

[0057] The memory is configured to store a computer program.

[0058] The processor is configured to execute the computer program stored in the memory to implement the concrete mixing temperature warning method based on multi-source data fusion.

[0059] Compared with the prior art, the present application has the following advantages:

[0060] 1. The present application proposes a new concrete mixing temperature warning method, which can comprehensively improve the accuracy, comprehensiveness and timeliness of concrete mixing temperature monitoring and warning. Specifically, first, collect and preprocess multi-source historical data to lay a solid foundation for analysis; deeply extract basic features and a variety of coupled features that reveal the complex temperature change mechanism, and accurately screen target features to construct a matrix, so that the model can focus on key factors; the temperature prediction model constructed accordingly can accurately represent the temperature distribution of the concrete, combined with real-time data acquisition and preset rule detection, timely execution of warning strategies, and comprehensive improvement of concrete mixing temperature monitoring and warning level, providing protection for ensuring the quality of concrete mixing.

[0061] 2、The application extracts various coupling features by designing specific formulas, and deeply extracts key features that may affect the temperature change of concrete during mixing. For example, the first coupling feature takes into account that the essence of concrete temperature change is the redistribution of heat enthalpy, overcoming the problem of ignoring nonlinear heat exchange during material mixing in traditional weighted average; the second coupling feature focuses on the local temperature mutation caused by the difference in hydration reaction rate when the aggregate contacts with cement; the third coupling feature reflects the temperature change in the mixing process in combination with parameters such as mixing power and speed; the fourth coupling feature takes into account the inhibitory effect of water evaporation on temperature; and the fifth coupling feature focuses on the combined influence of cement fineness, aggregate moisture content and additive dosage on temperature conduction. The extraction of these coupling features can make the model capture the details of the temperature change in the concrete mixing process more carefully, and improve the accuracy of temperature prediction.

[0062] 3、The application can further eliminate those features that are not closely related to temperature or are highly redundant with other features by screening out target features related to concrete temperature from basic features and coupling features, avoiding the interference of irrelevant features on the model. By calculating the Pearson coefficient of feature pairs in different seasons for screening, the model can focus on factors that have a substantial impact on concrete temperature, reducing the complexity and computational load of the model, improving the running efficiency of the model, and enhancing the sensitivity and prediction accuracy of the model to the temperature change of concrete.

[0063] 4、The application constructs a feature matrix according to the screened target features, and constructs a temperature prediction model based on the feature matrix. The model can comprehensively consider the spatial and temporal relationship and interaction between various factors, and accurately represent the temperature distribution of concrete in the target concrete mixing equipment. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 The flowchart of the concrete mixing temperature early warning method based on multi-source data fusion proposed by an embodiment of the application;

[0065] Figure 2 The structural schematic diagram of the concrete mixing temperature early warning system based on multi-source data fusion proposed by an embodiment of the application.

[0066] The following specific embodiments will further illustrate the application in conjunction with the above drawings. DETAILED DESCRIPTION

[0067] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Unless otherwise defined, the technical or scientific terms used herein should have the ordinary meaning understood by those skilled in the art. The terms "comprising" and similar expressions used herein mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but does not exclude other elements or objects.

[0068] like Figure 1 As shown, an embodiment of the present invention proposes a method for early warning of concrete mixing temperature based on multi-source data fusion. The method includes steps S101 to S105, wherein:

[0069] Step S101: Obtain multi-source historical data of the target concrete mixing equipment when performing each concrete mixing task, and preprocess the multi-source historical data, which includes ambient temperature, raw material temperature data, equipment operating parameters and concrete temperature data.

[0070] It should be noted that this step primarily involves collecting data from each concrete mixing task using various sensors and related recording systems of the target concrete mixing equipment. Specifically, ambient temperature data can be obtained through temperature sensors installed around the mixing plant. This reflects the external air temperature conditions during mixing operations. Ambient temperatures vary significantly across different seasons and times of day, significantly impacting heat exchange during concrete mixing. Raw material temperature data, such as the temperatures of cement, aggregates, admixtures, and water, can be obtained through temperature sensors installed in the raw material storage area or on the conveying pipelines. Raw material temperatures directly affect the initial concrete mixing temperature. Equipment operating parameters include mixer speed, mixing time, and motor power. These parameters reflect the equipment's operating status, and different combinations of operating parameters affect the concrete mixing effect and heat generation. Concrete temperature data is obtained through temperature sensors installed inside the mixer or at the discharge port at different stages of the mixing process and after mixing is completed. This directly reflects the temperature changes of the concrete during the mixing process.

[0071] Specifically, in some embodiments, the multi-source historical data includes relevant data under multiple mixing batches, for the same mixing batch, the raw material temperature data includes cement temperature and fineness, aggregate temperature and its water content, additive temperature and its addition amount, water temperature and its addition amount, the equipment operation parameter is rotating speed, and the concrete temperature data includes multi-point temperature in the target concrete mixing equipment and discharge port temperature.

[0072] In addition, all data need to be sequentially cleaned and standardized to obtain pre-processed multi-source historical data. The data is cleaned to process missing values, abnormal values, repeated data, format errors, etc., to ensure data quality. The data is standardized to eliminate the influence of dimension and make different features at the same scale.

[0073] Step S102: taking each pre-processed multi-source historical data as a basic feature, and extracting coupling features from the pre-processed multi-source historical data, and screening target features related to concrete temperature from all basic features and coupling features;

[0074] It should be pointed out that each type of data such as pre-processed ambient temperature, raw material temperature data, equipment operation parameter and concrete temperature data is taken as a basic feature. These basic features are directly obtained from the original data, have clear physical meaning, and are the basis for subsequent analysis.

[0075] In addition, considering the possible mutual relationship between different data, the purpose of extracting coupling features is to mine deeper relationship between data and more comprehensively reflect the factors affecting concrete temperature. Specifically, the first coupling feature is extracted according to the following formula:

[0076] ;

[0077] Wherein, is the first coupling feature, is the ambient temperature, is the time when the ith material is put into the equipment, is the heat exchange rate coefficient, is the total number of material types, is the specific heat capacity of the ith material, is the initial temperature of the ith material put into the mixer, is the input amount of the ith material, is the reference time when the mixer starts to work, and the material corresponds to the raw material;

[0078] During the mixing process of concrete, there are complex nonlinear heat exchange phenomena when various materials are mixed. The traditional weighted average ignores this nonlinear effect, which can lead to inaccurate prediction of temperature changes. By extracting the first coupling feature, the actual situation of heat transfer during the mixing process of materials can be more truly reflected. For example, under the condition of different input time and initial temperature of materials with different specific heat capacity, the influence of their heat exchange process on the overall temperature can be accurately considered, which helps to accurately grasp the temperature change trend of concrete at the initial stage of mixing.

[0079] The second coupling feature is extracted according to the following formula:

[0080] ;

[0081] Wherein, is the second coupling feature, is the interface thermal resistance coefficient, is the aggregate temperature, is the cement temperature, is the input amount of aggregate, is the input amount of cement;

[0082] It should be noted that when the aggregate (with inertia) and the cement (with activity) are in contact, a hydration reaction will occur. Due to the difference in reaction rates of the two, a local temperature jump will occur. This local temperature change has an important influence on the early performance development of concrete. For example, too high local temperature may cause the hydration speed of cement to be too fast, resulting in uneven distribution of hydration products, affecting the strength and durability of concrete. The extraction of the second coupling feature can capture this local temperature change.

[0083] The third coupling feature is extracted according to the following formula:

[0084] ;

[0085] Wherein, is the third coupling feature, is the instantaneous mixing power at the tth time step, is the rotational speed, is the total mass of concrete in the device, i.e. the total mass of the raw materials input, is the specific heat capacity of concrete, is the outlet temperature when mixing is completed, is the inlet temperature when all materials are input;

[0086] It should be noted that the instantaneous stirring power of the mixer affects the stirring effect and heat generation of the concrete. Different stirring powers result in different degrees of friction and mixing between materials, which in turn affect the temperature distribution. For example, high stirring power may result in more thorough mixing of materials, but it may also generate more frictional heat, causing the temperature of the concrete to rise. Extracting the third coupling feature can establish the relationship between stirring power and concrete temperature.

[0087] The fourth coupling feature is extracted according to the following formula:

[0088] ;

[0089] wherein, is the water evaporation-temperature suppression feature, is the evaporation coefficient of the concrete, is the average temperature of the concrete at the next point under the current mixing task, i.e., the average of all the concrete temperatures recorded at the point at different time steps under the current mixing task, is the dew point temperature;

[0090] It should be noted that during the mixing of concrete, water evaporation will take away heat, thereby suppressing the temperature of the concrete. The rate of water evaporation is related to factors such as the temperature of the concrete and environmental conditions. For example, when the temperature of the concrete is high, water evaporation accelerates, taking away more heat, and the upward trend of the temperature of the concrete is suppressed to some extent. Extracting the fourth coupling feature helps to accurately predict the temperature change of the concrete during the mixing process.

[0091] The fifth coupling feature is extracted according to the following formula:

[0092] ;

[0093] wherein, is the fifth coupling feature, is the total stirring time, is the fineness of cement, is the water content of the aggregate, is the input amount of the additive.

[0094] It should be noted that in the concrete mixing process, the cement fineness, the water content of aggregate and the amount of admixture will affect the temperature, and there is a complex interaction between them. For example, the change of cement fineness will affect the speed and degree of cement hydration, and the hydration reaction is an important exothermic process in the mixing process, thereby affecting the temperature change; the water content of aggregate is different, the evaporation and heat exchange of water in the mixing process will also be different, thereby producing inhibitory or promoting effect on temperature; the amount of admixture will change the rheological properties and hydration process of concrete, which will also indirectly affect the temperature. The fifth coupling feature integrates the cumulative synergistic effect of these factors in the mixing time by integrating the product of the partial derivatives of these factors on the temperature-related quantities through specific mathematical operations, which can more comprehensively reflect the comprehensive influence of these factors on temperature.

[0095] It should be noted that the above basic features and coupling features may be highly correlated, that is, there is a lot of overlap in the information they provide. In order to reduce the computational complexity of the subsequent model and improve the accuracy of the model prediction, target features need to be selected from all basic features and coupling features.

[0096] Specifically, in some embodiments, the concrete temperature at the jth point of the ith concrete mixing task point in the device at the tth time step is denoted as The average concrete temperature of all time steps under the same mixing task is calculated to obtain the first average concrete temperature of the jth point of the ith concrete mixing task point in the device ;

[0097] All basic features and coupling features are summarized to obtain a feature set The first average concrete temperature under the same concrete mixing task is paired with each feature in the feature set to obtain a plurality of feature pairs corresponding to each concrete mixing task, wherein is the kth target feature, is the total number of basic features and coupling features;

[0098] The Pearson coefficients between all feature pairs in different seasons are calculated to select target features related to concrete temperature from the feature set according to the Pearson coefficients.

[0099] Due to the huge difference in ambient temperature every quarter, the ambient temperature will directly affect the heat exchange in the concrete mixing process, and then affect the concrete temperature. Like in summer, high temperature environment will make the concrete in the mixing and curing process to dissipate heat slowly, the temperature is more likely to rise; winter is the opposite. The Pearson coefficient between each feature and the concrete temperature may change due to the change of the ambient temperature in different seasons, based on this, all features in different seasons such as spring, summer, autumn and winter need to be screened respectively to build a prediction model in different seasons.

[0100] In addition, the underlying formula for obtaining the Pearson coefficient between the first average concrete temperature and each feature is a conventional technique, which is not described in detail in this embodiment. The core of this step is to use Pearson analysis to select the target feature with strong correlation from the aggregated multiple features. Specifically, by judging whether the Pearson coefficient between the first average concrete temperature and each feature is greater than a preset threshold, if it is greater than the preset threshold, the feature is selected as the target feature.

[0101] Step S103: constructing a feature matrix according to the target features, and constructing a temperature prediction model representing the temperature distribution of the concrete in the target concrete mixing equipment according to the feature matrix;

[0102] It should be noted that by fusing these scattered target features into the feature matrix, the originally isolated information can be integrated together to form a complete data set.

[0103] Specifically, the concrete mixing task number is taken as the column name, the target feature number is taken as the row name, and the numerical value of the corresponding target feature is filled in sequence according to the row name and the column name to obtain the feature matrix:

[0104] ;

[0105] Where F is the feature matrix, 、 、 、 are the numerical values of the 1st target feature of the 1st mixing task, the 1st target feature of the Lth mixing task, the Kth target feature of the 1st mixing task, and the Kth target feature of the Lth mixing task, respectively, L is the total number of mixing tasks, and K is the total number of target features.

[0106] In addition, in some embodiments, the temperature prediction model is constructed according to the following formula:

[0107] ;

[0108] Where, is the concrete temperature of the i th mixing task, the j th measurement point, and the t th time step. is a spatio-temporal weight coefficient of the kth target feature at the jth measurement point at the tth time step, is a basic weight coefficient of the kth target feature, , , are respectively the values of the kth row and the lth column, the u th row and the lth column, and the vth row and the lth column in the feature matrix, is a spatio-temporal interaction weight coefficient of the jth measurement point at the tth time step, is a feature interaction weight coefficient of the u th target feature and the vth target feature at the jth measurement point at the tth time step, is a set of neighborhood measurement points of the jth measurement point, is a set of neighborhood time steps of the tth time step.

[0109] The basic weight coefficient reflects the basic importance of the kth target feature to the temperature, and gives the model basic weights of different features; the spatio-temporal weight coefficient further considers the dynamic changes of the kth target feature to the temperature weight at different times and spaces (measurement points); the spatio-temporal interaction weight coefficient reflects the special weight of the jth measurement point to the temperature at the tth time step, and can capture the influence of the difference between time and space; the feature interaction weight coefficient is used to quantify the influence of the interaction between the u th and the vth target features on the temperature, and helps the model to understand the synergistic or antagonistic effect between features.

[0110] In addition, in the actual training process, each column of the feature matrix is data under the same mixing task, and all the values of the target features in the same column need to be associated with the concrete temperatures of each point at each time step under the task, and then the associated data is input into the model for training, and then the model coefficients are determined.

[0111] Step S104: Collecting real-time multi-source data of the target concrete mixing equipment, and inputting the real-time multi-source data into the temperature prediction model to obtain the temperature distribution of the concrete;

[0112] It should be pointed out that the real-time multi-source data and the historical multi-source data are basically the same in kind, and the difference is that the concrete temperatures of each point at each time step are missing, because the data needs to be output after the model is predicted.

[0113] Step S105: detecting the temperature distribution according to the first preset rule, and judging whether to execute the preset warning strategy according to the detection result.

[0114] It should be noted that the temperature distribution includes the predicted temperature of each measurement point at multiple future time steps, and in some embodiments, the first preset rule is that a first temperature change rate of adjacent measurement points and a second temperature change rate of the same measurement point at adjacent time steps are calculated according to the temperature distribution.

[0115] It is judged whether the predicted temperature is within a first preset range, whether the first temperature change rate is within a second preset range, and whether the second temperature change rate is within a third preset range.

[0116] In addition, the number of measurement points set is related to the specific use requirement, but the measurement points set are generally uniformly distributed in the device, and in this embodiment, the measurement points set are not limited in detail. Assuming that the measurement point data set is 10, the measurement points are classified before prediction, so that it is set in advance which are adjacent measurement points.

[0117] In some embodiments, the first temperature change rate and the second temperature change rate are calculated according to the following formula:

[0118] ;

[0119] Wherein, is the first temperature change rate, is the second temperature change rate, is the temperature difference of measurement point a at the i-th time step and the i-1-th time step, is the temperature difference of measurement point b at the i-th time step and the i-1-th time step, is the temperature difference of measurement point a at the i+1-th time step and the i-th time step, is the interval of the vector time step, and measurement point a and measurement point b are vector measurement points.

[0120] Further, if the predicted temperature is within the first preset range, the first temperature change rate is within the second preset range, and the second temperature change rate is within the third preset range, the detection result is normal. If the predicted temperature is not within the first preset range and / or the first temperature change rate is not within the second preset range and / or the second temperature change rate is not within the third preset range, a warning information is issued, that is, a preset warning strategy is executed.

[0121] In this embodiment, the preset threshold, the first preset range, the second preset range, and the third preset range are related to the actual requirement, and are not limited in detail in this embodiment.

[0122] By comprehensively detecting the predicted temperature of each point at each time step, it can be judged in time and accurately whether there is a temperature in the mixing process of the concrete, so as to provide reliable guarantee for the mixing quality of the concrete.

[0123] In summary, according to the concrete mixing temperature early warning method based on multi-source data fusion described above, the following advantages are obtained:

[0124] 1. The concrete mixing temperature early warning method can comprehensively improve the accuracy, comprehensiveness and timeliness of concrete mixing temperature monitoring and early warning. Specifically, first, multi-source historical data is collected and preprocessed to lay a solid foundation for analysis; second, basic features and various coupled features that reveal the complex temperature change mechanism are extracted, and target features are accurately selected to construct a matrix, so that the model can focus on key factors; third, the temperature prediction model constructed based on the target features can accurately represent the temperature distribution of concrete, and combined with real-time data acquisition and preset rule detection, the early warning strategy can be executed in a timely manner, which comprehensively improves the concrete mixing temperature monitoring and early warning level and provides protection for ensuring the quality of concrete mixing.

[0125] 2. The specific formula is designed to extract various coupled features, which deeply extracts the key features that may affect the temperature change during the concrete mixing process. For example, the first coupled feature takes into account that the essence of concrete temperature change is the redistribution of heat content, which overcomes the problem of ignoring nonlinear heat exchange during material mixing in traditional weighted average; the second coupled feature focuses on the local temperature mutation caused by the difference in hydration reaction rate when aggregate and cement are in contact; the third coupled feature reflects the temperature change in the mixing process by combining parameters such as mixing power and speed; the fourth coupled feature considers the inhibitory effect of water evaporation on temperature; the fifth coupled feature focuses on the joint influence of cement fineness, aggregate moisture content and additive dosage on temperature conduction. The extraction of these coupled features can enable the model to capture the details of temperature change during the concrete mixing process in more detail, improving the accuracy of temperature prediction.

[0126] 3. The model can further eliminate features that are not closely related to temperature or are highly redundant with other features by selecting target features from basic features and coupled features that are associated with concrete temperature, avoiding the interference of irrelevant features on the model. By calculating the Pearson coefficient of feature pairs in different seasons, the model can focus on factors that have a substantial impact on concrete temperature, reducing the complexity and computational load of the model, improving the running efficiency of the model, and enhancing the sensitivity and prediction accuracy of the model to temperature changes of concrete.

[0127] 4. The feature matrix is constructed based on the selected target features, and the temperature prediction model is constructed based on the feature matrix. The model can comprehensively consider the spatio-temporal relationship and interaction between various factors, and accurately represent the temperature distribution of concrete in the target concrete mixing equipment.

[0128] For example, Figure 2As shown, an embodiment of the present application also proposes a concrete mixing temperature early warning system based on multi-source data fusion, which comprises:

[0129] A historical data acquisition module 10 is configured to acquire multi-source historical data of a target concrete mixing device during each mixing task and pre-process the multi-source historical data, wherein the multi-source historical data comprises environmental temperature, raw material temperature data, device operation parameters and concrete temperature data.

[0130] A target feature screening module 20 is configured to take each pre-processed multi-source historical data as a basic feature, extract coupled features from the pre-processed multi-source historical data, and screen target features associated with concrete temperature from all basic features and coupled features.

[0131] A feature matrix construction module 30 is configured to construct a feature matrix according to the target features and construct a temperature prediction model representing temperature distribution of concrete in the target concrete mixing device according to the feature matrix.

[0132] A temperature prediction module 40 is configured to acquire real-time multi-source data of the target concrete mixing device and input the real-time multi-source data into the temperature prediction model to obtain the temperature distribution of the concrete.

[0133] A detection module 50 is configured to detect the temperature distribution according to a first preset rule and determine whether to execute a preset early warning strategy according to a detection result.

[0134] In another aspect, the present application also proposes a storage medium having one or more programs stored thereon, wherein the program is executed by a processor to implement the above-mentioned concrete mixing temperature early warning method based on multi-source data fusion.

[0135] In another aspect, the present application also proposes an electronic device comprising a memory and a processor, wherein the memory is configured to store a computer program, and the processor is configured to execute the computer program stored in the memory to implement the above-mentioned concrete mixing temperature early warning method based on multi-source data fusion.

[0136] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain stored, communicated, propagated, or transmitted programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0137] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0138] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0139] While embodiments of the present invention have been described in detail above, it will be apparent to those skilled in the art that various modifications and variations can be made to these embodiments. However, it should be understood that such modifications and variations fall within the scope and spirit of the invention as set forth in the claims. Furthermore, the invention described herein may have other embodiments and can be implemented or carried out in various ways.

Claims

1. A method for early warning of concrete mixing temperature based on multi-source data fusion, characterized in that, The method includes: Acquire multi-source historical data of the target concrete mixing equipment when it performs each concrete mixing task, and preprocess the multi-source historical data, which includes ambient temperature, raw material temperature data, equipment operating parameters and concrete temperature data. Within the same batch of mixing, the raw material temperature data includes cement temperature and fineness, aggregate temperature and moisture content, admixture temperature and dosage, and water temperature and dosage. The equipment operating parameter is rotation speed. The concrete temperature data includes multiple temperatures within the target concrete mixing equipment and the discharge port temperature. All data were cleaned and standardized sequentially to obtain preprocessed multi-source historical data. Each type of preprocessed multi-source historical data is used as a basic feature, and coupled features are extracted from the preprocessed multi-source historical data. Target features that are related to concrete temperature are then selected from all the basic features and coupled features. The first coupling feature is extracted using the following formula: ； in, This is the first coupling feature. For ambient temperature, Let be the time when the i-th material is fed into the equipment. The heat exchange rate coefficient, This represents the total number of material types. Let be the specific heat capacity of the i-th material. Let be the initial temperature at which the i-th material is added to the mixer. Let i be the amount of material input. This serves as the reference time for the mixer to start operating. The second coupling feature is extracted using the following formula: ； in, This is the second coupling feature. The interfacial thermal resistance coefficient, For aggregate temperature, For cement temperature, The amount of aggregate input, This refers to the amount of cement used. The third coupling feature is extracted using the following formula: ； in, This is the third coupling feature. Let be the instantaneous stirring power at time step t. For rotational speed, This represents the total mass of the concrete inside the equipment. This refers to the specific heat capacity of concrete. The discharge temperature at the point where mixing is complete. The feed inlet temperature when all materials are fed in; The fourth coupling feature is extracted using the following formula: ； in, This is the fourth coupling feature. The evaporation coefficient of concrete. This represents the average temperature of the concrete at a point in the current mixing process. This refers to the dew point temperature. The fifth coupling feature is extracted using the following formula: ； in, This is the fifth coupling feature. This is the total mixing time. For cement fineness, The moisture content of the aggregate. This refers to the amount of admixture added; A feature matrix is ​​constructed based on the target features, and a temperature prediction model characterizing the temperature distribution of concrete in the target concrete mixing equipment is constructed based on the feature matrix. Real-time multi-source data of the target concrete mixing equipment is collected, and the real-time multi-source data is input into the temperature prediction model to obtain the temperature distribution of the concrete; The temperature distribution is detected according to the first preset rule, and a preset early warning strategy is executed based on the detection result.

2. The method for early warning of concrete mixing temperature based on multi-source data fusion according to claim 1, characterized in that, The step of filtering out target features that are correlated with concrete temperature from all basic and coupled features includes: Let the concrete temperature at point j, the i-th concrete mixing task point within the equipment, be t. The first average concrete temperature at point j, i-th concrete mixing task point within the equipment, is calculated. ; By summarizing all the basic features and coupled features, we obtain the feature set. The first average concrete temperature under the same concrete mixing task is paired with each feature in the feature set to obtain multiple feature pairs corresponding to each concrete mixing task. For the k-th target feature, The total number of basic features and coupling features; Calculate the Pearson coefficient between all feature pairs in different quarters to screen target features that are associated with concrete temperature from the feature set based on the Pearson coefficient.

3. The method for early warning of concrete mixing temperature based on multi-source data fusion according to claim 2, characterized in that, The steps of constructing a feature matrix based on target features and constructing an initial temperature prediction model characterizing the temperature distribution of concrete in the target concrete mixing equipment based on the feature matrix include: Using the concrete mixing task number as the column name and the target feature number as the row name, the values ​​of the corresponding target features are sequentially filled according to the row and column names to obtain the feature matrix: ； Where F is the characteristic matrix, 、 、 、 These are the values ​​of the first target feature of the first mixing task, the first target feature of the Lth mixing task, the Kth target feature of the first mixing task, and the Kth target feature of the Lth mixing task, respectively. L is the total number of mixing tasks, and K is the total number of target features.

4. The method for early warning of concrete mixing temperature based on multi-source data fusion according to claim 3, characterized in that, The step of constructing a feature matrix based on target features and constructing a temperature prediction model characterizing the temperature distribution of concrete in the target concrete mixing equipment based on the feature matrix includes: A temperature prediction model is constructed based on the following formula: ； in, The concrete temperature at the j-th measurement point and the t-th time step for the i-th mixing task. The spatiotemporal weight coefficient of the k-th target feature at the j-th measurement point and the t-th time step is given. The basic weight coefficients for the k-th target feature. , , These are the values ​​in the k-th row and l-th column, u-th row and l-th column, and v-th row and l-th column of the feature matrix, respectively. For the spatiotemporal interaction weight coefficient of the j-th measurement point at the t-th time step, The feature interaction weight coefficients for the u-th target feature and the v-th target feature at the j-th measurement point and the t-th time step are given. Let j be the set of neighboring measurement points of the j-th measurement point. Let be the set of neighborhood time steps at time step t.

5. The method for early warning of concrete mixing temperature based on multi-source data fusion according to claim 4, characterized in that, The step of detecting the temperature distribution according to a first preset rule and determining whether to execute a preset early warning strategy based on the detection result includes: The temperature distribution includes the predicted temperature of each measurement point at multiple future time steps; The first rate of temperature change at adjacent measurement points and the second rate of temperature change at the same measurement point at adjacent time steps are calculated based on the temperature distribution. Determine whether the predicted temperature is within a first preset range, whether the first temperature change rate is within a second preset range, and whether the second temperature change rate is within a third preset range; If the predicted temperature is within a first preset range, the first temperature change rate is within a second preset range, and the second temperature change rate is within a third preset range, then the detection result is normal.

6. The method for early warning of concrete mixing temperature based on multi-source data fusion according to claim 5, characterized in that, The step of determining whether the predicted temperature is within a first preset range, whether the first temperature change rate is within a second preset range, and whether the second temperature change rate is within a third preset range further includes: If the predicted temperature is not within the first preset range and / or the first temperature change rate is not within the second preset range and / or the second temperature change rate is not within the third preset range, an early warning message will be issued.

7. A system for implementing the concrete mixing temperature early warning method based on multi-source data fusion as described in any one of claims 1-6, characterized in that, The system includes: The historical data acquisition module is used to acquire multi-source historical data of the target concrete mixing equipment when performing each concrete mixing task, and to preprocess the multi-source historical data, which includes ambient temperature, raw material temperature data, equipment operating parameters and concrete temperature data. The target feature filtering module is used to take each type of preprocessed multi-source historical data as the basic feature, extract coupling features from the preprocessed multi-source historical data, and filter out target features that are related to concrete temperature from all basic features and coupling features. The feature matrix construction module is used to construct a feature matrix based on the target features, and to construct a temperature prediction model characterizing the temperature distribution of concrete in the target concrete mixing equipment based on the feature matrix. The temperature prediction module is used to collect real-time multi-source data of the target concrete mixing equipment and input the real-time multi-source data into the temperature prediction model to obtain the temperature distribution of the concrete. The detection module is used to detect the temperature distribution according to a first preset rule, and to determine whether to execute a preset early warning strategy based on the detection result.

8. A storage medium, characterized in that, The storage medium stores one or more programs that, when executed by a processor, implement the concrete mixing temperature early warning method based on multi-source data fusion as described in any one of claims 1-6.

Images