AI-based method for predicting concrete flowability

Abstract

To provide a concrete fluidity estimation method capable of estimating slumps and slump flows at high precision in all seasons.SOLUTION: Concrete fluidity is estimated by a neural network (14) with a multilayer structure. In advance, regarding plural pieces of concrete, their fundamental data, concrete fluidity data, e.g., slumps are obtained, and the fundamental data as input data and the fluidity data as teaching data are given to the neural network (14) so as to be learned. Then, concrete fundamental data in which fluidity data are unknown are inputted to the learned neural network (14), and fluidity data are estimated. In this invention, the fundamental data denote time sequence acoustic data sampled at a prescribed cycle from a sound in which plural pieces of concrete are kneaded by a mixer (4) or a sound in which they are charged to a hopper (5).SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a method for estimating the slump or flumph of concrete, i.e., the fluidity of concrete. [Background technology]

[0002] Concrete is produced by mixing ordinary Portland cement, mixing water, fine aggregate, coarse aggregate, and optional admixtures in a batcher plant mixer. The produced concrete is transported by agitator truck and unloaded at the concrete pouring site. The required strength and properties of concrete vary depending on the concrete pouring site and are specified at the time of ordering. Slump is one indicator of concrete's properties. Slump is an indicator of its fluidity and is officially measured as follows: concrete is filled into a 30-cm-tall conical container (a slump cone), which is then inverted and gently removed. The concrete loses its shape and its top drops. The height of this drop is the slump; a higher value indicates greater fluidity, while a lower value indicates less fluidity. In practice, when mixing concrete in a batcher plant mixer, the slump is estimated by a slump monitor, based on the current driving the mixer. Alternatively, the slump is estimated visually by an operator before shipping. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6680936 [Patent Document 2] Japanese Patent Application Laid-Open No. 2003-177115

[0004] Patent Document 1 describes a method for estimating slump using machine learning. In this estimation method, concrete is first photographed in a mixer while being mixed, and the obtained image data is input to a neural network, which learns the slump at that time as training data. An image of the concrete whose slump is to be estimated is input to the trained neural network, which then outputs an estimated slump value.

[0005] Patent Document 2 describes a method for estimating slump flow, an index of the fluidity of highly fluid concrete (so-called high-fluidity concrete). The slump flow test method is similar to that for slump, but involves measuring the diameter of the circular area of ​​the concrete that remains after the slump cone is removed. Unlike slump, however, this method is suitable for measuring the fluidity of highly fluid concrete. In the method described in Patent Document 2, the sound generated during mixing of multiple high-fluidity concretes is acquired and spectrally analyzed. This method obtains the distribution of sound energy, i.e., sound pressure, which varies with frequency. The slump flows of these multiple high-fluidity concretes are then compared with the spectrally analyzed sound pressure distribution, and frequencies highly correlated with slump flow are identified using regression analysis or other methods. This allows the estimation of slump flow, or a model. Once the model is determined, the slump flow of any high-fluidity concrete can be estimated. Specifically, the sound is acquired during mixing of the high-fluidity concrete. The acquired sound is then spectrally analyzed to obtain the sound pressure at that specific frequency. This is then input into the model, which outputs the slump flow. In other words, the slump flow is estimated. Summary of the Invention [Problem to be solved by the invention]

[0006] The conventional method of estimating slump using a slump monitor is also excellent in that it can estimate slump with practical accuracy. However, although the slump can be estimated with a certain degree of accuracy at the time of shipment, the properties of concrete can change during transportation in an agitator truck. It is not possible to know the slump at the time of unloading the concrete. Therefore, when unloading, for example, after 150m 3 Slump must be inspected by conducting a slump test every time. On the other hand, the method described in Patent Document 1 estimates slump from concrete images, so by photographing the concrete when unloading it from an agitator truck or immediately before pouring, slump can be estimated at that point. Around 2018, the inventors tested and verified a method similar to the method described in Patent Document 1, i.e., a method for estimating slump from concrete images. Specifically, multiple concretes with different slumps were mixed, and the concrete images photographed at the time were used as input data. The slump was used as a training signal to train a neural network, and the trained neural network was used to estimate slump. More specifically, the images were 8-bit grayscale, 360 pixels wide x 240 pixels high. Concrete was produced at two batcher plants, A and B. Images were taken inside the mixer and inside the loading hopper when loading the concrete into the agitator truck. A total of 40,489 training images were prepared, and training was performed using these images. The target for estimation was a different concrete produced in similar batcher plants A and B, and 78,376 images were prepared using images taken inside the mixer and inside the loading hopper when loading onto the agitator truck. When the slump was estimated from these images, the deviation from the correct slump value was as shown in the table below.

[0007] [Table 1]

[0008] This experiment confirmed that slump can be estimated with a certain degree of accuracy. Therefore, slump can be estimated by photographing concrete during unloading. However, there is room for improvement. Specifically, there is a demand for further improvement in the accuracy of the estimated slump, i.e., the accuracy of the estimation. When examining the deviation of slump estimated from concrete images from the correct slump, the percentage within ±1.5 cm was relatively high (87–92%), while the percentage within ±0.5 cm was slightly lower (43–47%). Further improvement in estimation accuracy should make it possible to omit slump inspections during unloading. Furthermore, there are problems during the harsh winter. While widely practiced in cold regions such as Hokkaido, the aggregate is heated with steam and warm water is used for mixing to prevent the concrete from freezing, this practice results in steam escaping from the concrete, clouding the camera lens and making it difficult to obtain clear images. Or, even if an image is taken from a distance to prevent fogging of the lens, a clear image cannot be obtained due to steam rising from the concrete. In experiments conducted by the inventors in midwinter, the accuracy of estimating slump from images decreased from normal levels, and there were cases where slump could not be estimated even within a range of ±2.5 cm. In other words, there are problems with methods of estimating slump using only concrete images.

[0009] It is possible to estimate the slump of concrete by referring to the method described in Patent Document 2. However, the method described in Patent Document 2 is a method for estimating slump flow, which is different from slump, and the concrete in question is high-fluidity concrete, which has significantly different properties from ordinary concrete. Therefore, there is no guarantee that it can be applied to estimating the fluidity of ordinary concrete. Furthermore, even if it is used as a reference, the method described in Patent Document 2 requires processing by spectral analysis when estimating slump flow from the sound obtained when mixing concrete. In other words, preprocessing is essential. This requires a certain amount of time for estimation and makes the work complicated.

[0010] Therefore, an object of the present invention is to provide a method for estimating the fluidity of concrete which does not require any complicated work, yet can estimate slump and slump flow, i.e., the fluidity of concrete, with high accuracy regardless of the season, and which can estimate the fluidity of concrete not only in a batcher plant but also when unloading concrete. [Means for solving the problem]

[0011] To achieve the above-mentioned object, the present invention is configured to estimate slump or slump flow, i.e., concrete fluidity, using a multilayered neural network. Basic data and fluidity data consisting of slump or slump flow are obtained in advance for multiple concrete samples, and the basic data are provided as input data and the fluidity data as training data to the neural network for learning. Then, when the basic data for a concrete whose fluidity data is unknown is input to the trained neural network, the slump or slump flow can be obtained. In this invention, the basic data is time-series acoustic data sampled at a predetermined interval from the sound of concrete being mixed in a mixer or the sound of concrete being poured into a hopper.

[0012] That is, the invention described in claim 1 relates to the basic data and the 、 Liquidity data consisting of slumps and a method for estimating the fluidity of concrete, the method comprising: obtaining a concrete flowability data; providing the basic data as input data and the fluidity data as teacher data to a multi-layered neural network for learning; inputting the basic data into the neural network that has already learned about concrete whose fluidity data is unknown, and outputting fluidity data; wherein the basic data is time-series acoustic data on sound pressure obtained by sampling, at a predetermined period, sounds made when mixing concrete in a mixer. The invention described in claim 2 is configured as a method for estimating the fluidity of concrete, which is the estimation method described in claim 1, characterized in that the basic data includes image data of concrete in addition to the time-series acoustic data. [Effects of the Invention]

[0013] As described above, the present invention provides basic data and 、 Liquidity data consisting of slump flows andThe method is configured as a concrete fluidity estimation method in which a multilayer neural network is trained by providing basic data as input data and fluidity data as training data, and the basic data is then input to a neural network that has already been trained on concrete with unknown fluidity data, and the trained neural network outputs fluidity data. In other words, this method estimates slump using AI that learns with so-called training data. In such AI learning, if there is a correlation between the input data and the output data, a nonlinear model of this relationship is automatically constructed within the neural network, making estimation with a certain degree of accuracy possible. However, whether or not highly accurate estimation can be achieved depends on the selection of input data, i.e., whether input data that is highly correlated with the output data can be selected, and how the selected input data is processed and provided to the AI. According to the present invention, the basic data is configured as time-series acoustic data of sound pressures sampled at a predetermined interval during mixing of concrete in a mixer. As will be described in detail later with respect to an experiment conducted, estimating slump fluidity data using time-series acoustic data during concrete mixing, etc., enables stable and highly accurate estimation. Acquiring the time-series acoustic data requires only a microphone, and is inexpensive. This allows for accurate estimation of concrete fluidity data not only when concrete is produced in a batcher plant, but also at the concrete pouring site, i.e., when the concrete is unloaded. This eliminates the need for inspections during unloading, thereby reducing costs. Furthermore, because the microphone is not affected by steam, it is guaranteed that concrete fluidity data can be estimated reliably even in the coldest of winter, just as it can be estimated in other seasons. According to another invention, the basic data includes image data of the concrete in addition to time-series acoustic data. While time-series acoustic data has a high correlation with concrete fluidity data, concrete images also have a relatively high correlation with slump. Therefore, using concrete images in addition to time-series acoustic data as basic data enables even more accurate estimation of concrete fluidity data. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a schematic diagram of a concrete fluidity data estimation system that implements a concrete fluidity data estimation method according to an embodiment of the present invention. [Figure 2] FIG. 1 is a schematic diagram showing a neural network that realizes a method for estimating fluidity data of concrete according to an embodiment of the present invention. [Figure 3] FIG. 10 is a schematic diagram of a concrete fluidity data estimation system that implements a concrete fluidity data estimation method according to a second embodiment of the present invention. [Figure 4] FIG. 10 is a schematic diagram showing a neural network that realizes a method for estimating fluidity data of concrete according to a second embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0015] An embodiment of the present invention will now be described. The concrete fluidity data estimation method according to this embodiment is a method for estimating concrete slump or slump flow. It can be implemented in a conventional batcher plant 1 as shown in FIG. 1 and at any concrete pouring site 2. Although only a portion of the batcher plant 1 is shown in the figure, it is composed of a cement bin for storing and charging ordinary Portland cement, an aggregate bin for storing and charging aggregate, multiple measuring tanks for measuring the materials charged from these bins, a measuring tank for charging mixing water and admixtures, and a mixer 4 for mixing the materials charged from these bins to produce concrete. The mixer 4 is equipped with a slump monitor 7 that measures the torque required to drive the mixer, i.e., the current consumed, to estimate the slump during concrete production. This allows the slump to be obtained with sufficient accuracy for practical use. The concrete mixed in the mixer 4 is loaded onto an agitator truck 6 via a loading hopper 5. The loaded concrete is transported by an agitator truck 6 and unloaded at any concrete pouring site 2. For example, a concrete pump truck 8 is prepared at the concrete pouring site 2, and the concrete is unloaded into the hopper of this concrete pump truck 8. The concrete is poured by the concrete pump truck 8.

[0016] The concrete fluidity estimation method according to this embodiment estimates slump, an index of concrete fluidity, when concrete is produced in a batcher plant 1 or when concrete is unloaded at a concrete pouring site 2. The concrete fluidity estimation system 3 according to this embodiment comprises a computer 10, multiple microphones 11, 12, and 13, and a slump monitor 7. The first and second microphones 11 and 12 are provided in the batcher plant 1 and are connected to the computer 10 via a network, along with the slump monitor 7. The first and second microphones 11 and 12 are provided near the mixer 4 and the loading hopper 5, respectively. They pick up the sounds of concrete being mixed and concrete being poured into the loading hopper 5, respectively. The third microphone 13 is portable and can be connected to the computer 10 via a wireless network or other suitable means. The third microphone 13 is used to pick up the sounds of concrete being unloaded from the agitator truck 6. In the concrete fluidity estimation system 3 according to this embodiment, the computer 10 is trained using a neural network, which will be described below, and the fluidity of the concrete is estimated using the trained neural network. The estimated value of slump obtained from the slump monitor 7 is only necessary during the training stage, and the connection between the slump monitor 7 and the computer 10 may be disconnected once training is complete.

[0017] The computer 10 includes a multilayer neural network 14, as shown in FIG. 2. The neural network 14 includes an input layer 15 consisting of a plurality of neurons, an output layer 16 consisting of a predetermined number of neurons, and a plurality of intermediate layers 17 consisting of a plurality of neurons. However, in this embodiment, there is only one output layer 16. The neurons in each layer have an activation function, such as a sigmoid function, and a predetermined bias. They add the bias to input data, process it using the activation function, and output the data. Neurons in a given layer are connected to neurons in the adjacent layer by synapses, and the synapses consist of output weights, i.e., coefficients by which the output is multiplied. Therefore, the outputs of multiple neurons in a given layer are multiplied by synapses, i.e., coefficients, and then added together before being input to neurons in the next layer. In other words, when input data is given, it is processed by neurons in the input layer 15 and transmitted to the intermediate layer 17. The input data is then processed by neurons in the intermediate layer 17 and transmitted to the output layer 16, where it is finally processed by neurons in the output layer 16 to obtain output data. Meanwhile, in the output layer 16, training data, which is the output data to be output, is provided, and learning is performed by so-called backpropagation. In other words, the synaptic weights, i.e., coefficients, and the bias of each neuron are corrected. When predetermined input data is provided to a neural network 14 that has undergone sufficient learning, output data appropriate for that input data is output. So-called deep learning is a neural network that employs multiple techniques to dramatically improve the efficiency of learning by backpropagation, and the neural network 14 in this embodiment is also designed to learn with high efficiency.

[0018] In this embodiment, the input data given to the neural network 14 is basic data related to concrete, and the output data is an estimated value of concrete fluidity. Specifically, the basic data is time-series acoustic data obtained by predetermined processing from the sounds of mixing, pouring, and unloading concrete, and the slump is estimated as concrete fluidity. The time-series acoustic data is generated by the computer 10, and is generated as follows: sounds collected by any of the first to third microphones 11, 12, and 13 are sampled at a predetermined fixed cycle over a predetermined period. For example, sampling is performed every 100 ms for 30 seconds. Then, at the sampling timing, sound pressure are arranged in time series and used as time-series acoustic data. When 30 seconds of sound is sampled every 100 ms, the time-series acoustic data consists of a data string of 300 frequencies. In this case, the input layer 15 of the neural network 14 should have 300 neurons.

[0019] The neural network 14 according to this embodiment is configured as a machine learning model that learns using so-called training data, and must first be trained. The input data and output data required for training, i.e., the training data, are prepared as follows: Concrete is produced in the batcher plant 1. Time-series acoustic data is obtained from sounds collected by the first and second microphones 11 and 12, and an estimated slump value, i.e., an estimated value of concrete fluidity data, is obtained by the slump monitor 7. Multiple concretes with different slumps are produced, and time-series acoustic data and estimated slump values ​​are obtained in the same way. Once many pairs of time-series acoustic data and estimated slump values ​​are obtained in this way, the former are provided as input data and the latter as training data to the neural network 14, and iterative training is performed. Once sufficient training has occurred, the preparation stage is completed.

[0020] The trained neural network 14 can be used to estimate the slump of concrete whose slump is unknown. Sounds related to the concrete are collected by any of the first to third microphones 11, 12, and 13 and sent to the computer 10. Time-series acoustic data is obtained in the computer 10 and provided as input data to the neural network 14. The neural network 14 outputs an estimated value of slump as output data. The trained neural network 14 can estimate the slump with high accuracy from any of the sounds of concrete mixing, pouring into a hopper, and unloading. Therefore, highly reliable slump values ​​can be obtained not only at the batcher plant 1 but also at any concrete pouring site 2. [Example]

[0021] An experiment was conducted to confirm that the concrete fluidity estimation system 3 according to this embodiment can estimate slump with sufficiently high accuracy. Experimental method: In a batcher plant 1, multiple lots of concrete with different slumps were produced, as shown in Table 2. Estimated slumps were obtained using a slump monitor 7, and the results were compiled for each slump. For example, 38 lots of concrete with a slump of 18.5 were produced. For each lot, the sounds of concrete being mixed were recorded using a first microphone 11 and saved. 10% of the recorded sounds were extracted to generate time-series acoustic data, which were then fed to a neural network 14 for training along with the estimated slump values. Next, the trained neural network 14 was used to estimate the slump. The time-series acoustic data used as input data was generated from the recordings not used in training, i.e., from 90% of the recordings. [Table 2] Experimental results: When the trained neural network 14 was used to estimate the slump, the results shown in Table 3 were obtained. [Table 3] Observations: When estimation was made using the concrete fluidity estimation system 3 according to this embodiment, it was confirmed that the percentage of estimations that could be made with an error of ±0.5 cm exceeded 80%. Furthermore, it was confirmed that 45.8% of the time, estimations could be made with no estimation error, that is, with an error of ±0.0 cm. It was confirmed that slump can be estimated with sufficient accuracy for practical purposes.

[0022] FIG. 3 shows a concrete fluidity estimation system 3' according to a second embodiment of the present invention. The concrete fluidity estimation system 3' according to the second embodiment includes a computer 10, first, second, and third microphones 11, 12, and 13, a slump monitor 7, and first, second, and third cameras 21, 22, and 23. The first and second cameras 21 and 22 are connected to the computer 10, and the third camera 23 is connected as needed via a wireless network or the like. In the concrete fluidity estimation system 3' according to the second embodiment, the first, second, and third cameras 21, 22, and 23 capture images of the concrete during production, pouring, and unloading, respectively. The concrete fluidity estimation system 3' according to the second embodiment is configured to estimate the slump based on time-series acoustic data and concrete images, which are provided as basic data related to the concrete. Therefore, as shown in Fig. 4, the neural network 14' used for slump estimation has neurons for concrete images in addition to neurons for time-series acoustic data in the input layer 15. The concrete fluidity estimation system 3' according to the second embodiment is configured to estimate slump by inputting concrete images in addition to time-series acoustic data, and therefore can estimate slump with even higher accuracy.

[0023] The concrete fluidity estimation system 3 according to this embodiment can be modified in various ways. For example, slump flow may be used as the fluidity of the concrete to be estimated. Slump flow may be obtained by actual measurement or the like, and this may be provided to the neural network 14 as training data in place of slump, along with time-series acoustic data, for learning. The trained neural network 14 can estimate the slump flow by providing time-series acoustic data, such as the mixing sound of concrete with an unknown slump flow, to the trained neural network 14. The slump provided as training data can also be modified. In this embodiment, the slump estimated by the slump monitor 7 is used. However, the slump may also be obtained by actual experimentation using a slump cone and provided as training data. Slump may also be obtained by other means. The time-series acoustic data is obtained from sounds collected by the first to third microphones 11, 12, and 13. However, for example, a microphone may be provided on the agitator truck 6 to capture the sound of the drum rotating to agitate the concrete during transport. Any sound generated during concrete processing can be used. Furthermore, the method of processing the time-series acoustic data can also be modified. In the description of this embodiment, the time-series acoustic data is generated as frequency data at a sampling period of 100 ms for 30 seconds. Other periods and sampling periods may be used. Furthermore, if only short-term audio data is available, this may be copied multiple times to generate a longer period, from which time-series acoustic data may be generated. The slump estimation system 3 uses one computer 10, but multiple computers may be used. For example, once the neural network 14 has been fully trained, a small computer with low processing power, such as a laptop computer, can be equipped with a replica of the neural network 14 to estimate slump. A combination of a laptop computer equipped with the trained neural network 14 and a third microphone 13 can be carried to any concrete pouring site 2 and can estimate slump without connecting to a wireless network.

[0024] The concrete fluidity estimation system 3' according to the second embodiment can also be modified. In the second embodiment, time-series acoustic data and image data are provided as input data to a single neural network 14'. However, for example, two neural networks can be provided, one of which is provided with time-series acoustic data and the other with image data, and concrete fluidity data can be estimated using each. These can then be combined using another AI to adopt one of the concrete fluidity data or average the data to obtain an estimated concrete fluidity data. Furthermore, when using two neural networks, one neural network can be provided with time-series acoustic data to estimate concrete fluidity data. The obtained concrete fluidity data can be input to the other neural network along with image data to further estimate concrete fluidity data. In the concrete fluidity estimation system 3' according to the second embodiment, additional basic data can be added. That is, data correlated with concrete fluidity can be added as input data. Examples of additional basic data include concrete mix information, mixing time, and mixing temperature, which can further improve the accuracy of fluidity estimation.

[0025] The concrete fluidity estimation system 3 according to this embodiment can be modified in other ways. In this embodiment, the data output by the neural network 14 is fluidity data, i.e., slump or slump flow, only. However, by adding neurons to the output layer, it is possible to predict other indicators of concrete performance, such as the air content of concrete, compressive strength at 28 days, and mix proportions, as well as the proper operation of concrete manufacturing equipment. Naturally, these data are also required as training data, but this system is highly valuable because it can estimate many indicators of concrete performance. [Explanation of symbols]

[0026] 1. Batcher Plant 2. Concrete pouring site 3. Concrete fluidity estimation system 4 Mixer 5 Loading hopper 6 Agitator Truck 7 Slump Monitor 8 Concrete pump truck 10 Calculator 11 First microphone 12 Second Microphone 13 Third Microphone 14 Neural Networks 15 Input layer 16 Output layer 17 Middle Class 21 First Camera 22 Second Camera 23 The Third Camera

Claims

1. A method for estimating the fluidity of concrete, comprising the steps of: obtaining basic data for a plurality of concretes and fluidity data consisting of slump; providing the basic data as input data and the fluidity data as training data to a multi-layered neural network for learning; and inputting the basic data for concrete with unknown fluidity data into the trained neural network to output the fluidity data, A method for estimating the fluidity of concrete, characterized in that the basic data is time-series acoustic data on sound pressure sampled at a predetermined period from the sound produced when mixing concrete in a mixer.

2. 2. The method for estimating concrete fluidity according to claim 1, wherein the basic data includes image data of the concrete in addition to the time-series acoustic data.

Images