A control system for mobile spray curing equipment for prefabricated box beams

Abstract

The present invention provides a control system for mobile spray curing equipment for prefabricated box girders, and relates to the technical field of prefabricated girder curing management. The method comprises: an environmental data module for acquiring environmental data; a startup equipment module for determining whether to start the spray curing equipment; a prefabricated box girder data module for acquiring prefabricated box girder data; a predicted moving speed data module for acquiring predicted moving speed data; a shooting module for acquiring high-definition prefabricated box girder images and infrared prefabricated box girder images; a predicted spray volume data module for acquiring predicted spray volume data for multiple prefabricated box girders; a round trip number data module for determining round trip number data; and an operation equipment module for operating the spray curing equipment according to the round trip number data and the predicted moving speed data. According to the present invention, the moving speed and round trip number of the spray curing equipment can be controlled according to the environmental conditions in the prefabricated box girder yard and the prefabricated box girder, thereby improving the efficiency and quality of the spray curing of the prefabricated box girder.

Description

Technical Field

[0001] The present invention relates to the technical field of prefabricated beam curing management, and in particular to a control system of mobile spray curing equipment for prefabricated box beams. Background Art

[0002] In related technology, CN111391096A discloses a control system for mobile spray curing equipment for precast box girders. The control system includes a remote service device and a beam yard control device. The remote service device includes a control and access terminal and a remote server, while the beam yard control device includes a beam yard water supply control unit and a precast box girder spray curing trolley control unit. The control and access terminal, beam yard water supply control unit, and precast box girder spray curing trolley control unit are all connected to the remote server. The beam yard water supply control unit is connected to the centrifugal pump and water supply pipeline. The precast box girder spray curing trolley control unit is connected to the travel motor, the water supply pipeline winch motor, and the clean water pump. This achieves fully automatic control of spray curing and eliminates geographical restrictions on curing operators. Curing operators can perform spraying operations on-site using the precast box girder spray curing trolley control unit or remotely through the control and access terminal.

[0003] CN116787590A discloses an automatic spray circulation curing system for prefabricated box girder concrete in a bridge project, comprising a main water tank, a water storage tank, a purification water tank, a main pipeline, and branch pipelines. The main water tank outlet is connected to the water storage tank inlet, the water storage tank outlet is connected to the main pipeline, the rear end of the main pipeline is connected to multiple branch pipelines, and multiple nozzles are arranged on the branch pipelines; a recovery ditch is provided below the branch pipeline, the recovery ditch is connected to the purification water tank inlet, and the purification water tank outlet is connected to the main water tank; a water level detection device is provided in the main water tank, and a return liquid solenoid valve is provided on the connecting pipe between the main water tank and the purification water tank, and the water level detection device controls the opening and closing of the return liquid solenoid valve; a pressure water pump is provided on the connecting pipe between the main water tank and the water storage tank, and the water storage tank is provided with a pressure gauge, which detects the water pressure in the water storage tank and controls the opening and closing of the pressure water pump; a spray time relay and a spray solenoid valve are also provided at the connection between the water storage tank and the main pipeline, and the spray time relay controls the opening and closing of the spray solenoid valve.

[0004] Therefore, although automatic control of spray curing can be achieved in the relevant technology, the relevant technology does not take into account the different environmental conditions in the prefabricated box girder yard and different prefabricated box girders, and the different requirements for the moving speed and number of round trips of the spray curing equipment. That is, it is impossible to accurately control the moving speed and number of round trips of the spray curing equipment according to the environmental conditions in the prefabricated box girder yard and the actual situation of the prefabricated box girder.

[0005] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the Invention

[0006] The present invention provides a control system for mobile spray curing equipment for prefabricated box girders, which can solve the technical problem that related technologies cannot accurately control the moving speed and number of round trips of the spray curing equipment according to the environmental conditions in the prefabricated box girder site and the actual conditions of the prefabricated box girder.

[0007] According to the present invention, a control system for mobile spray curing equipment of prefabricated box girders is provided, comprising: an environmental data module for acquiring environmental data at the current moment of curing through sensors arranged in the prefabricated box girder field, wherein the environmental data include environmental temperature data, environmental humidity data and environmental light data; a starting equipment module for determining whether to start the spray curing equipment based on the environmental data and preset environmental data; a prefabricated box girder data module for acquiring prefabricated box girder data at the current moment of curing through sensors arranged at multiple sampling points of the prefabricated box girder if it is determined to start the spray curing equipment, wherein the prefabricated box girder data include prefabricated box girder temperature data and prefabricated box girder humidity data; a predicted moving speed data module for inputting the environmental data and the prefabricated box girder data into a trained moving speed prediction model to obtain the predicted moving speeds of the spray curing equipment configured for the multiple prefabricated box girders at the current moment of curing data; a shooting module, used to shoot the prefabricated box girder through a binocular camera at the current moment of curing to obtain a high-definition prefabricated box girder image and an infrared prefabricated box girder image, wherein the binocular camera includes a high-definition camera and an infrared camera, the high-definition prefabricated box girder image is obtained by shooting the high-definition camera, and the infrared prefabricated box girder image is obtained by shooting the infrared camera; a predicted spray amount data module, used to input the high-definition prefabricated box girder image and the infrared prefabricated box girder image into a trained spray amount prediction model to obtain predicted spray amount data of multiple prefabricated box girders; a round trip number data module, used to determine the round trip number data of the spray curing equipment configured for multiple prefabricated box girders at the current moment of curing according to the predicted moving speed data and the predicted spray amount data; an equipment operation module, used to operate the spray curing equipment according to the round trip number data and the predicted moving speed data at the current moment of curing.

[0008] Further, according to the environmental data and the preset environmental data, determining whether to start the spray health care equipment includes: according to the formula The first condition C1 and the second condition C2 are obtained, wherein, To maintain the current ambient temperature data, To preset the ambient temperature data, To maintain the current environmental humidity data, To preset the ambient humidity data, To maintain the current ambient light data, is the preset ambient light data; when any one of the first condition C1 and the second condition C2 is met, it is determined to start the spray health equipment.

[0009] Furthermore, the training step of the moving speed prediction model includes: screening out the first historical moment of starting the spray curing equipment from the curing historical moments; obtaining historical environmental data, historical prefabricated box girder data and historical moving speed data corresponding to multiple first historical moments of curing, wherein the historical environmental data includes historical environmental temperature data, historical environmental humidity data and historical environmental lighting data, and the historical prefabricated box girder data includes historical prefabricated box girder temperature data and historical prefabricated box girder humidity data; processing the historical environmental data and the historical prefabricated box girder data through the moving speed prediction model to obtain the historical predicted moving speed data of the spray curing equipment configured for multiple prefabricated box girders at multiple first historical moments of curing; determining the loss function of the moving speed prediction model based on the historical environmental data, the historical prefabricated box girder data, the historical moving speed data and the historical predicted moving speed data; training the moving speed prediction model based on the training loss function to obtain the trained moving speed prediction model.

[0010] Further, according to the historical environmental data, the historical prefabricated box beam data, the historical moving speed data and the historical predicted moving speed data, the loss function of the moving speed prediction model is determined, including: according to the formula Determine the loss function of the moving speed prediction model ,in, To maintain the current ambient temperature data, is the historical ambient temperature data of the first historical moment of health preservation, To maintain the current environmental humidity data, The historical environmental humidity data for the hth historical moment of health preservation, To maintain the current ambient light data, The historical ambient light data for the hth historical moment of health preservation, is the historical precast box girder temperature data of the jth precast box girder at the first historical moment of curing, is the historical prefabricated box girder humidity data of the jth prefabricated box girder at the hth first historical moment, is the standard value of the temperature difference between the prefabricated box girder and the environment, is the standard moisture data of precast box beams, The historical moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the first historical moment of curing is: The historical predicted moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the h-th first historical moment of curing, H is the number of the first historical moments of curing, M is the number of prefabricated box girders, h≤H, j≤M, and h, j, H and M are all positive integers.

[0011] Furthermore, the training steps of the spray volume prediction model include: selecting the first historical moment of starting the spray curing equipment from the curing historical moments; obtaining historical spray volume data and historical infrared prefabricated box girder images of multiple prefabricated box girders at multiple first historical moments of curing; determining the historical average temperature of multiple prefabricated box girders at multiple first historical moments of curing according to the pixel values ​​of the pixel points of the historical infrared prefabricated box girder images; performing feature extraction processing on the prefabricated box girder area in the high-definition prefabricated box girder image through the size feature encoding layer of the trained image recognition neural network model, and obtaining multiple a size feature vector of a prefabricated box girder; the high-definition prefabricated box girder image and the historical infrared prefabricated box girder image are processed by a spray quantity prediction model to obtain historical predicted spray quantity data of multiple prefabricated box girders at multiple first historical moments; the loss function of the spray quantity prediction model is determined according to the historical ambient temperature data, the historical average temperature of the prefabricated box girder, the size feature vector, the historical spray quantity data and the historical predicted spray quantity data; the spray quantity prediction model is trained according to the training loss function to obtain the trained spray quantity prediction model.

[0012] Further, according to the historical ambient temperature data, the historical average temperature of the precast box beam, the size characteristic vector, the historical spraying amount data and the historical predicted spraying amount data, the loss function of the spraying amount prediction model is determined, including: according to the formula Determine the loss function of the spray rate prediction model ,in, is the size characteristic vector of the j-th precast box girder, is the standard size characteristic vector of precast box girder, for The transposed vector of is the historical average temperature of the j-th prefabricated box girder at the first historical moment of curing, is the historical ambient temperature data of the first historical moment of health preservation, is the historical spraying volume data of the jth prefabricated box girder at the first historical moment of curing, is the historical predicted spraying volume data of the jth prefabricated box girder at the hth first historical moment of curing, H is the number of the first historical moment of curing, M is the number of prefabricated box girders, h≤H, j≤M, and h, j, H and M are all positive integers.

[0013] Further, according to the predicted moving speed data and the predicted spraying amount data, the number of round trips of the spray curing equipment configured for the multiple prefabricated box beams at the current curing moment is determined, including: obtaining the length of the prefabricated box beam and the spraying speed of the spray curing equipment; according to the formula Determine the number of round trips of the spray curing equipment configured for the j-th prefabricated box girder at the current curing time ,in, is the predicted spraying amount data of the j-th prefabricated box girder at the current curing moment, The predicted moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the current curing moment, is the spray speed of the spray health equipment, is the length of the j-th precast box girder.

[0014] Technical effect: According to the present invention, the moving speed prediction model and the spraying volume prediction model are used to predict the moving speed and spraying volume of the spraying equipment according to the current environmental data and prefabricated box girder data, so that the prefabricated box girder can be properly maintained, which helps to improve the quality of the prefabricated box girder. The moving speed and the number of round trips of the spray curing equipment can be controlled according to the environmental conditions and prefabricated box girder in the prefabricated box girder site, thereby improving the efficiency and quality of the spray curing of the prefabricated box girder. When determining whether to start the spray curing equipment, it can be determined based on two conditions. By comparing the environmental data and the preset environmental data, the spraying equipment can be started in time under the corresponding environmental conditions, which helps to improve the curing effect of the prefabricated box girder and reduce quality problems caused by environmental factors. When determining the loss function of the moving speed prediction model, the influence of historical environmental data and historical prefabricated box girder data on the moving speed can be used to determine the influence of the above data on the error of the historical predicted moving speed data, and thus weights are set based on the influence and the relative difference between the historical moving speed data and the historical predicted moving speed data, and based on the characteristic that the shorter the time interval with the current moment, the higher the accuracy, and the closer the environmental data at the current moment is to the environmental data at the first historical moment, the closer the moving speed is, and the greater the reference value of the error of the historical predicted moving speed data, and thus weights are set. The errors output by the moving speed prediction model of each prefabricated box girder at each first historical moment are weightedly summed to obtain a loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and improving the accuracy of the moving speed prediction model. When determining the loss function of the spray volume prediction model, the influence of historical ambient temperature data and historical prefabricated box girder average temperature on the spray volume can be used to determine the influence of the above data on the error of historical predicted spray volume data, and thus based on the influence and the relative difference between historical spray volume data and historical predicted spray volume data, and based on the characteristic that the shorter the time interval with the current moment, the higher the accuracy, and the more similar the size feature vector is to the standard size feature vector, the more similar the spray volume is, and the greater the reference value of the error of historical predicted spray volume data, the weight is set, and thus the errors output by the spray volume prediction model of each prefabricated box girder at each first historical moment are weightedly summed to obtain the loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and improving the accuracy of the spray volume prediction model. When determining the round trip data of the spray curing equipment configured for multiple prefabricated box girders at the current curing moment, the round trip data of the spray curing equipment configured for multiple prefabricated box girders at the current curing moment can be determined by predicting the moving speed data and the predicted spraying volume data. This can enable each prefabricated box girder to obtain sufficient moisture during the curing process, thereby improving the curing effect, reducing quality problems caused by insufficient spraying, and improving the accuracy, reliability and scientificity of the round trip data.

[0015] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and not limiting of the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can derive other embodiments based on these drawings without inventive efforts.

[0017] Figure 1 A block diagram of a control system of a mobile spray curing device for prefabricated box girders according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying 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 making creative efforts shall fall within the scope of protection of the present invention.

[0019] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0020] Figure 1A block diagram of a control system of a mobile spray curing equipment for prefabricated box girders according to an embodiment of the present invention is exemplarily shown, wherein the system comprises: an environmental data module for acquiring environmental data at the current moment of curing through sensors arranged in the prefabricated box girder yard, wherein the environmental data comprises environmental temperature data, environmental humidity data and environmental light data; a device starting module for determining whether to start the spray curing equipment based on the environmental data and preset environmental data; a prefabricated box girder data module for acquiring prefabricated box girder data at the current moment of curing through sensors arranged at multiple sampling points of the prefabricated box girder if it is determined to start the spray curing equipment, wherein the prefabricated box girder data comprises prefabricated box girder temperature data and prefabricated box girder humidity data; a predicted moving speed data module for inputting the environmental data and the prefabricated box girder data into a trained moving speed prediction model to obtain the spray curing equipment configured for multiple prefabricated box girders at the current moment of curing. Predicted moving speed data; a shooting module, used to shoot the prefabricated box girder through a binocular camera at the current time of curing to obtain a high-definition prefabricated box girder image and an infrared prefabricated box girder image, wherein the binocular camera includes a high-definition camera and an infrared camera, the high-definition prefabricated box girder image is obtained by shooting the high-definition camera, and the infrared prefabricated box girder image is obtained by shooting the infrared camera; a predicted spray amount data module, used to input the high-definition prefabricated box girder image and the infrared prefabricated box girder image into a trained spray amount prediction model to obtain predicted spray amount data of multiple prefabricated box girders; a round trip number data module, used to determine the round trip number data of the spray curing equipment configured for multiple prefabricated box girders at the current time of curing according to the predicted moving speed data and the predicted spray amount data; an equipment operation module, used to operate the spray curing equipment at the current time of curing according to the round trip number data and the predicted moving speed data.

[0021] According to an embodiment of the present invention, the control system for mobile spray curing equipment for precast box girders uses a travel speed prediction model and a spray volume prediction model to predict the travel speed and spray volume of the spray equipment based on current environmental data and precast box girder data, ensuring proper curing of the precast box girders and helping to improve their quality. The travel speed and number of round trips of the spray curing equipment can be controlled based on the environmental conditions within the precast box girder yard and the precast box girders, improving the efficiency and quality of the spray curing of the precast box girders.

[0022] According to one embodiment of the present invention, in the environmental data module, sensors are installed and set in advance in the prefabricated box girder yard to monitor the environmental temperature data, environmental humidity data and environmental light data in the prefabricated box girder yard in real time.

[0023] According to one embodiment of the present invention, in the starting equipment module, the preset environmental data is a threshold value determined based on the need for spray curing of prefabricated box girders. For example, when the ambient temperature is below 5°C or 10°C, spray curing is not required and insulation measures need to be taken. The preset ambient temperature data is 5°C or 10°C, and the present invention does not impose any restrictions on this.

[0024] According to one embodiment of the present invention, determining whether to start the spray health-care equipment according to the environmental data and the preset environmental data includes: obtaining a first condition C1 and a second condition C2 according to formula (1),

[0025] (1),

[0026] in, To maintain the current ambient temperature data, To preset the ambient temperature data, To maintain the current environmental humidity data, To preset the ambient humidity data, To maintain the current ambient light data, is the preset ambient light data; when any one of the first condition C1 and the second condition C2 is met, it is determined to start the spray health equipment.

[0027] According to one embodiment of the present invention, in the first condition C1 of formula (1), Indicates that when the ambient temperature data at the current curing time is greater than or equal to the preset ambient temperature data, and the ambient humidity data at the current curing time is less than the preset ambient humidity data, the ambient temperature in the precast box girder yard is suitable and the ambient humidity is low, and the precast box girder needs to be sprayed for curing. For example, when the ambient temperature data at the current curing time is not less than 5°C and the ambient humidity data is less than 60%, the precast box girder needs to be sprayed for curing. In the second condition C2, It means that when the ambient temperature data at the current moment of curing is greater than or equal to the preset ambient temperature data, the ambient humidity data at the current moment of curing is greater than or equal to the preset ambient humidity data, and the ambient light data at the current moment of curing is greater than or equal to the preset ambient light data, the ambient temperature in the prefabricated box girder yard is suitable and the ambient humidity is high, but the light is too strong. The increase in light intensity will cause the concrete surface temperature to rise rapidly and a large amount of water to evaporate. Therefore, the prefabricated box girder needs to be sprayed for curing.

[0028] In this way, whether to start the spray curing equipment can be determined based on two conditions. By comparing the environmental data and the preset environmental data, the spray equipment can be started in time under the corresponding environmental conditions, which helps to improve the curing effect of prefabricated box girders and reduce quality problems caused by environmental factors.

[0029] According to one embodiment of the present invention, in the prefabricated box girder data module, sensors are set at multiple sampling points of the prefabricated box girder to monitor the temperature and humidity of the prefabricated box girder in real time. The temperature data and humidity data obtained at the multiple sampling points are averaged respectively to obtain the prefabricated box girder temperature data and the prefabricated box girder humidity data.

[0030] According to one embodiment of the present invention, in the predicted moving speed data module, the environmental data and prefabricated box girder data are input into a trained moving speed prediction model. The moving speed prediction model can be a neural network model, which is trained based on a large amount of historical data through machine learning or deep learning technology. It can analyze the predicted moving speed data of the spray curing equipment configured for multiple prefabricated box girders at the current curing moment.

[0031] According to one embodiment of the present invention, the training step of the moving speed prediction model includes: screening out the first historical moment of starting the spray curing equipment from the curing historical moments; obtaining historical environmental data, historical prefabricated box girder data and historical moving speed data corresponding to multiple first historical moments of curing, wherein the historical environmental data includes historical environmental temperature data, historical environmental humidity data and historical environmental lighting data, and the historical prefabricated box girder data includes historical prefabricated box girder temperature data and historical prefabricated box girder humidity data; processing the historical environmental data and the historical prefabricated box girder data through the moving speed prediction model to obtain the historical predicted moving speed data of the spray curing equipment configured for multiple prefabricated box girders at multiple first historical moments of curing; determining the loss function of the moving speed prediction model based on the historical environmental data, the historical prefabricated box girder data, the historical moving speed data and the historical predicted moving speed data; training the moving speed prediction model based on the training loss function to obtain the trained moving speed prediction model.

[0032] According to one embodiment of the present invention, the moment at which the spray curing equipment was activated is searched and determined within the curing history. This moment is referred to as the first historical moment. The higher the ambient temperature and ambient light data, and the lower the ambient humidity, the more rapid the need for comprehensive spray curing of the precast box girders. That is, the faster the movement of the spray curing equipment, thereby reducing the impact of environmental factors on the precast box girders. The greater the difference between the precast box girder temperature data and the ambient temperature data, the more rapid the need for comprehensive spray curing to reduce the precast box girder temperature, and the faster the movement of the spray curing equipment. Similarly, the lower the humidity of the precast box girder, the faster the movement of the spray curing equipment. A movement speed prediction model can predict the predicted movement speed data of the spray curing equipment configured for multiple precast box girders at the current curing moment based on the relationship between the aforementioned environmental data, precast box girder data, and the movement speed of the spray curing equipment. A loss function is determined based on the relative difference between the historical predicted movement speed data and the historical movement speed data recorded by historical monitoring. A trained movement speed prediction model is obtained by applying feedback adjustment to the loss function.

[0033] According to one embodiment of the present invention, the loss function of the moving speed prediction model is determined based on the historical environmental data, the historical prefabricated box girder data, the historical moving speed data and the historical predicted moving speed data, including: determining the loss function of the moving speed prediction model according to formula (2): ,

[0034] (2),

[0035] in, To maintain the current ambient temperature data, is the historical ambient temperature data of the first historical moment of health preservation, To maintain the current environmental humidity data, The historical environmental humidity data for the hth historical moment of health preservation, To maintain the current ambient light data, The historical ambient light data for the hth historical moment of health preservation, is the historical precast box girder temperature data of the jth precast box girder at the first historical moment of curing, is the historical prefabricated box girder humidity data of the jth prefabricated box girder at the hth first historical moment, is the standard value of the temperature difference between the prefabricated box girder and the environment, is the standard moisture data of precast box beams, The historical moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the first historical moment of curing is: The historical predicted moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the h-th first historical moment of curing, H is the number of the first historical moments of curing, M is the number of prefabricated box girders, h≤H, j≤M, and h, j, H and M are all positive integers.

[0036] According to one embodiment of the present invention, in formula (2), The relative error between the historical moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the h-th first historical moment of curing and the historical predicted moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the h-th first historical moment of curing. It is the ratio of the difference between the historical prefabricated box girder temperature data of the jth prefabricated box girder at the hth first historical moment of curing and the historical ambient temperature data at the hth first historical moment of curing, to the standard value of the temperature difference between the prefabricated box girder and the environment. The larger the ratio, the greater the difference between the historical prefabricated box girder temperature data of the jth prefabricated box girder at the hth first historical moment of curing and the historical ambient temperature data at the hth first historical moment of curing, and the faster the moving speed of the spray curing equipment. It is the ratio of the historical precast box girder humidity data of the j-th precast box girder at the h-th first historical moment of curing to the standard humidity data of the precast box girder. The smaller the ratio, the smaller the historical precast box girder humidity data and the faster the moving speed of the spray curing equipment. It means that the difference between the historical prefabricated box girder temperature data and the historical ambient temperature data is positively correlated with the moving speed of the spray curing equipment, and the historical prefabricated box girder humidity data is negatively correlated with the moving speed of the spray curing equipment. For example, when the difference between the historical prefabricated box girder temperature data and the historical ambient temperature data is larger, the prefabricated box girder is more likely to crack due to the temperature difference, and it is necessary to speed up the cooling of the prefabricated box girder. The faster the moving speed of the spray curing equipment is, and the smaller the historical prefabricated box girder humidity data is, the prefabricated box girder is more likely to crack due to dryness, and it is necessary to speed up the moisturizing of the prefabricated box girder. Therefore, the difference-related data between the historical prefabricated box girder temperature data and the historical ambient temperature data is placed in the numerator position, indicating that the difference between the historical prefabricated box girder temperature data and the historical ambient temperature data is larger relative to the standard value of the temperature difference between the prefabricated box girder and the environment, that is, The larger the value of , the greater the impact on the error of the historical predicted moving speed data. The historical precast box girder humidity data related data are placed in the denominator, indicating that the historical precast box girder humidity data is smaller than the standard humidity data of the precast box girder, that is, The smaller the value of , the greater the impact on the error of historical predicted moving speed data. is the weight of the hth first historical moment, which is used to reasonably weight the relative errors at different moments in the loss function. The accuracy of the historical predicted mobile speed data of the hth first historical moment output by the mobile speed prediction model is usually higher than the accuracy of the historical predicted mobile speed data of the h+1th first historical moment. That is, the longer the time interval between a certain first historical moment and the current moment, the less accurate the prediction result. To improve training efficiency, the higher the weight is set, and vice versa, the more accurate the prediction result, the lower the weight is. is the similarity between the ambient temperature data at the current time of health preservation and the historical ambient temperature data at the hth historical time of health preservation. It is the similarity between the current environmental humidity data of health preservation and the historical environmental humidity data of the first historical moment of health preservation. The similarity between the current ambient light data and the hth historical ambient light data is calculated. To achieve similar speed monitoring results, the closer the current ambient light data is to the first historical ambient light data, the closer the historical speed data is to the current predicted speed. This increases its reference value and, therefore, its weight.

[0037] According to one embodiment of the present invention, using 、 、 、 and The training loss function is obtained by taking a weighted average of the relative errors in the predicted movement speed data of each precast box girder at each first historical moment. During the training of the movement speed prediction model, the loss function is backpropagated and some internal model parameters are adjusted to reduce the loss value of the movement speed prediction model, thereby improving the accuracy of the movement speed prediction model and obtaining the trained movement speed prediction model.

[0038] In this way, the influence of historical environmental data and historical prefabricated box girder data on the moving speed can be used to determine the influence of the above data on the error of historical predicted moving speed data, and thus weights are set based on the influence and the relative difference between the historical moving speed data and the historical predicted moving speed data, and based on the characteristic that the shorter the time interval with the current moment, the higher the accuracy, and the closer the environmental data at the current moment is to the environmental data at the first historical moment, the closer the moving speed is, and the greater the reference value of the error of the historical predicted moving speed data, and thus weights are set. The errors output by the moving speed prediction model of each prefabricated box girder at each first historical moment are weightedly summed to obtain a loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and improving the accuracy of the moving speed prediction model.

[0039] According to one embodiment of the present invention, a binocular camera device is used in the imaging module. This device consists of two types of cameras: a high-definition camera for capturing high-definition images of precast box girders, which can reflect their appearance and visible features, such as their length and width. An infrared camera is used to capture infrared images of the precast box girders, which can reflect their temperature distribution.

[0040] According to one embodiment of the present invention, in the spray volume prediction data module, the high-definition prefabricated box girder image and the infrared prefabricated box girder image are input into a trained spray volume prediction model. The spray volume prediction model can be a neural network model, which is trained based on a large amount of historical data through machine learning or deep learning technology, and can analyze the predicted spray volume data of multiple prefabricated box girders.

[0041] According to one embodiment of the present invention, the training step of the spray volume prediction model includes: screening out the first historical moment of starting the spray curing equipment from the curing historical moments; obtaining the historical spray volume data and historical infrared prefabricated box girder images of multiple prefabricated box girders at multiple first historical moments of curing; determining the historical prefabricated box girder average temperature of multiple prefabricated box girders at multiple first historical moments of curing according to the pixel values ​​of the pixel points of the historical infrared prefabricated box girder images; performing feature extraction processing on the prefabricated box girder area in the high-definition prefabricated box girder image through the size feature encoding layer of the trained image recognition neural network model , obtain size feature vectors of multiple prefabricated box girders; process the high-definition prefabricated box girder images and the historical infrared prefabricated box girder images through a spray amount prediction model to obtain historical predicted spray amount data of multiple prefabricated box girders at multiple first historical moments of curing; determine the loss function of the spray amount prediction model according to the historical ambient temperature data, the historical average temperature of the prefabricated box girders, the size feature vectors, the historical spray amount data and the historical predicted spray amount data; train the spray amount prediction model according to the training loss function to obtain the trained spray amount prediction model.

[0042] According to one embodiment of the present invention, the pixel values ​​of pixels in historical infrared precast box girder images represent the temperature values ​​of the precast box girder. All temperature values ​​are averaged to obtain the historical average temperature of the precast box girder. The image recognition neural network model can be a convolutional neural network model. The image recognition neural network model uses a dimension feature encoding layer to extract features from the precast box girder images in the high-definition precast box girder images, obtaining dimension feature vectors for each precast box girder. The closer the dimensions of the precast box girder are to the standard dimensions, the more consistent the required spray volume. The greater the difference between the average temperature of the precast box girder and the ambient temperature data, the greater the required spray volume. A moving speed prediction model can predict the predicted spray volume data for the precast box girder based on the relationship between the dimension feature vectors, the average temperature of the precast box girder, and the spray volume. A loss function is determined based on the relative difference between the historical spray volume data and the historical predicted spray volume data. Feedback adjustment of the loss function is performed to obtain a trained spray volume prediction model.

[0043] According to one embodiment of the present invention, the loss function of the spraying amount prediction model is determined based on the historical ambient temperature data, the historical average temperature of the precast box girder, the size characteristic vector, the historical spraying amount data and the historical predicted spraying amount data, including: determining the loss function of the spraying amount prediction model according to formula (3): ,

[0044] (3),

[0045] in, is the size characteristic vector of the j-th precast box girder, is the standard size characteristic vector of precast box girder, for The transposed vector of is the historical average temperature of the j-th prefabricated box girder at the first historical moment of curing, is the historical ambient temperature data of the first historical moment of health preservation, is the historical spraying volume data of the jth prefabricated box girder at the first historical moment of curing, is the historical predicted spraying volume data of the jth prefabricated box girder at the hth first historical moment of curing, H is the number of the first historical moment of curing, M is the number of prefabricated box girders, h≤H, j≤M, and h, j, H and M are all positive integers.

[0046] According to one embodiment of the present invention, in formula (3), It is the relative error between the historical spraying volume data of the j-th prefabricated box girder at the first historical moment of curing at the h-th time and the historical predicted spraying volume data of the j-th prefabricated box girder at the first historical moment of curing at the h-th time. It is the relative difference between the historical average temperature of the j-th precast box girder at the h-th first historical moment of curing and the historical ambient temperature data at the h-th first historical moment of curing. The larger the relative difference, the greater the difference between the historical average temperature of the precast box girder and the historical ambient temperature data, and the more spraying amount is required. That is, the relative difference is positively correlated with the spraying amount of the spray curing equipment, that is, The larger the value of , the greater the impact on the error of historical predicted spray volume data. is the weight of the hth first historical moment, which is used to reasonably weight the relative errors at different moments in the loss function. The accuracy of the historical predicted spraying volume data of the hth first historical moment output by the spraying volume prediction model is usually higher than the accuracy of the historical predicted spraying volume data of the h+1th first historical moment. That is, the longer the time interval between a certain first historical moment and the current moment, the less accurate the prediction result. In order to improve the training efficiency, the higher the weight is set, and vice versa, the more accurate the prediction result is, the lower the weight is. is the similarity between the size feature vector of the j-th prefabricated box girder and the standard size feature vector of the prefabricated box girder. The closer the similarity is to 1, the more the size of the prefabricated box girder conforms to the standard size, thereby achieving a similar spray volume monitoring effect. That is, if the size feature vector of the j-th prefabricated box girder is more similar to the standard size feature vector of the prefabricated box girder, the closer the size of the prefabricated box girder is to the standard size, the greater its reference value is, and therefore, the higher its weight is.

[0047] According to one embodiment of the present invention, using 、 and The relative errors of the predicted spray volume data for each precast box girder at each first historical moment are weighted averaged to obtain the training loss function. During the training of the spray volume prediction model, the loss function is back-propagated and some internal parameters of the model are adjusted to reduce the loss function value, thereby improving the accuracy of the spray volume prediction model and obtaining the trained spray volume prediction model.

[0048] In this way, the influence of historical ambient temperature data and historical prefabricated box girder average temperature on the spray volume can be used to determine the influence of the above data on the error of historical predicted spray volume data, and thus based on the influence and the relative difference between the historical spray volume data and the historical predicted spray volume data, and based on the characteristic that the shorter the time interval with the current moment, the higher the accuracy, and the more similar the size feature vector is to the standard size feature vector, the more similar the spray volume is, and the greater the reference value of the error of historical predicted spray volume data, the weight is set, thereby performing a weighted summation on the errors output by the spray volume prediction model of each prefabricated box girder at each first historical moment to obtain a loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and improving the accuracy of the spray volume prediction model.

[0049] According to one embodiment of the present invention, in the round trip number data module, the round trip number data of the spray curing equipment configured for multiple prefabricated box girders at the current curing moment is determined based on the predicted moving speed data and the predicted spray volume data.

[0050] According to one embodiment of the present invention, the number of round trips of the spray curing equipment configured for the multiple prefabricated box beams at the current curing time is determined based on the predicted moving speed data and the predicted spraying amount data, including: obtaining the length of the prefabricated box beam and the spraying speed of the spray curing equipment; determining the number of round trips of the spray curing equipment configured for the j-th prefabricated box beam at the current curing time according to formula (4) ,

[0051] (4),

[0052] in, is the predicted spraying amount data of the j-th prefabricated box girder at the current curing moment, The predicted moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the current curing moment, is the spray speed of the spray health equipment, is the length of the j-th precast box girder.

[0053] According to one embodiment of the present invention, in formula (4), It is the ratio of the predicted spray volume data of the j-th prefabricated box girder at the current curing time to the spray speed of the spray curing equipment, indicating the time required for the spraying to end. The larger the ratio, the longer the time required for the spraying to end. It is the ratio of the length of the j-th prefabricated box girder to the predicted moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the current curing moment, indicating the time required for the j-th prefabricated box girder to be sprayed from the beginning to the end at the current curing moment. The ratio of the time required for spraying to end to the time required for spraying from the beginning to the end is rounded up. The larger the rounded value is, the more times the spraying health care equipment will go back and forth when the spraying ends. For example, If it is 4.3, the number of times the spray health care equipment goes back and forth is 5 times.

[0054] In this way, the number of round trips of the spray curing equipment configured for multiple prefabricated box girders at the current curing moment can be determined by predicting the moving speed data and the predicted spray volume data. This allows each prefabricated box girder to obtain sufficient moisture during the curing process, thereby improving the curing effect, reducing quality problems caused by insufficient spraying, and improving the accuracy, reliability, and scientificity of the round trip data.

[0055] According to one embodiment of the present invention, in the operating equipment module, the spray curing equipment will operate according to the round trip number data and spray on the prefabricated box girder according to the predicted moving speed data, meeting the curing requirements.

[0056] According to the control system of the mobile spray curing equipment for prefabricated box girders according to the embodiment of the present invention, the moving speed prediction model and the spray volume prediction model are used to predict the moving speed and spray volume of the spray equipment according to the current environmental data and the prefabricated box girder data, so that the prefabricated box girder can be properly cured, which helps to improve the quality of the prefabricated box girder. The moving speed and the number of round trips of the spray curing equipment can be controlled according to the environmental conditions in the prefabricated box girder yard and the prefabricated box girder, thereby improving the efficiency and quality of the spray curing of the prefabricated box girder. When determining whether to start the spray curing equipment, it can be determined based on two conditions. By comparing the environmental data and the preset environmental data, the spray equipment can be started in time under the corresponding environmental conditions, which helps to improve the curing effect of the prefabricated box girder and reduce quality problems caused by environmental factors. When determining the loss function of the moving speed prediction model, the influence of historical environmental data and historical prefabricated box girder data on the moving speed can be used to determine the influence of the above data on the error of the historical predicted moving speed data, and thus weights are set based on the influence and the relative difference between the historical moving speed data and the historical predicted moving speed data, and based on the characteristic that the shorter the time interval with the current moment, the higher the accuracy, and the closer the environmental data at the current moment is to the environmental data at the first historical moment, the closer the moving speed is, and the greater the reference value of the error of the historical predicted moving speed data, and thus weights are set. The errors output by the moving speed prediction model of each prefabricated box girder at each first historical moment are weightedly summed to obtain a loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and improving the accuracy of the moving speed prediction model. When determining the loss function of the spray volume prediction model, the influence of historical ambient temperature data and historical prefabricated box girder average temperature on the spray volume can be used to determine the influence of the above data on the error of historical predicted spray volume data, and thus based on the influence and the relative difference between historical spray volume data and historical predicted spray volume data, and based on the characteristic that the shorter the time interval with the current moment, the higher the accuracy, and the more similar the size feature vector is to the standard size feature vector, the more similar the spray volume is, and the greater the reference value of the error of historical predicted spray volume data, the weight is set, and thus the errors output by the spray volume prediction model of each prefabricated box girder at each first historical moment are weightedly summed to obtain the loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and improving the accuracy of the spray volume prediction model. When determining the round trip data of the spray curing equipment configured for multiple prefabricated box girders at the current curing moment, the round trip data of the spray curing equipment configured for multiple prefabricated box girders at the current curing moment can be determined by predicting the moving speed data and the predicted spraying volume data. This can enable each prefabricated box girder to obtain sufficient moisture during the curing process, thereby improving the curing effect, reducing quality problems caused by insufficient spraying, and improving the accuracy, reliability and scientificity of the round trip data.

[0057] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0058] Those skilled in the art will appreciate that the embodiments of the present invention described above and shown in the accompanying drawings are intended to be illustrative only and are not intended to limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and illustrated in the embodiments. Any variations or modifications may be made to the embodiments of the present invention without departing from the principles described.

Claims

1. A control system for a mobile spray curing equipment for prefabricated box beams, characterized in that: include: An environmental data module is used to obtain environmental data at the current time of curing through sensors set in the prefabricated box girder yard, wherein the environmental data includes environmental temperature data, environmental humidity data and environmental light data; a starting equipment module is used to determine whether to start the spray curing equipment based on the environmental data and preset environmental data; a prefabricated box girder data module is used to obtain prefabricated box girder data at the current time of curing through sensors set at multiple sampling points of the prefabricated box girder if it is determined to start the spray curing equipment, wherein the prefabricated box girder data includes prefabricated box girder temperature data and prefabricated box girder humidity data; a predicted moving speed data module is used to input the environmental data and the prefabricated box girder data into a trained moving speed prediction model to obtain predicted moving speed data of the spray curing equipment configured for multiple prefabricated box girders at the current time of curing; a shooting module is used to obtain the predicted moving speed data of the spray curing equipment configured for multiple prefabricated box girders at the current time of curing at the current time of curing At a certain moment, the prefabricated box girder is photographed by a binocular camera to obtain a high-definition prefabricated box girder image and an infrared prefabricated box girder image, wherein the binocular camera includes a high-definition camera and an infrared camera, the high-definition prefabricated box girder image is obtained by photographing the high-definition camera, and the infrared prefabricated box girder image is obtained by photographing the infrared camera; a predicted spray quantity data module is used to input the high-definition prefabricated box girder image and the infrared prefabricated box girder image into a trained spray quantity prediction model to obtain predicted spray quantity data of multiple prefabricated box girders; a round trip number data module is used to determine the round trip number data of the spray curing equipment configured for multiple prefabricated box girders at the current curing moment according to the predicted moving speed data and the predicted spray quantity data; an equipment operation module is used to operate the spray curing equipment according to the round trip number data and the predicted moving speed data at the current curing moment.

2. The control system of the mobile spray curing equipment for prefabricated box beams according to claim 1 is characterized in that: Determine whether to start the spray health care equipment according to the environmental data and the preset environmental data, including: according to the formula The first condition C1 and the second condition C2 are obtained, wherein, To maintain the current ambient temperature data, To preset the ambient temperature data, To maintain the current environmental humidity data, To preset the ambient humidity data, To maintain the current ambient light data, is the preset ambient light data; when any one of the first condition C1 and the second condition C2 is met, it is determined to start the spray health equipment.

3. The control system of the mobile spray curing equipment for prefabricated box beams according to claim 1 is characterized in that: The training steps of the moving speed prediction model include: screening out the first historical moment of starting the spray curing equipment from the curing historical moments; obtaining historical environmental data, historical prefabricated box girder data and historical moving speed data corresponding to multiple first historical moments of curing, wherein the historical environmental data include historical environmental temperature data, historical environmental humidity data and historical environmental lighting data, and the historical prefabricated box girder data include historical prefabricated box girder temperature data and historical prefabricated box girder humidity data; processing the historical environmental data and the historical prefabricated box girder data through the moving speed prediction model to obtain the historical predicted moving speed data of the spray curing equipment configured for multiple prefabricated box girders at multiple first historical moments of curing; determining the loss function of the moving speed prediction model based on the historical environmental data, the historical prefabricated box girder data, the historical moving speed data and the historical predicted moving speed data; training the moving speed prediction model based on the loss function of the moving speed prediction model to obtain the trained moving speed prediction model.

4. The control system of the mobile spray curing equipment for prefabricated box beams according to claim 3 is characterized in that: Determine the loss function of the moving speed prediction model based on the historical environmental data, the historical prefabricated box girder data, the historical moving speed data and the historical predicted moving speed data, including: according to the formula Determine the loss function of the moving speed prediction model ,in, To maintain the current ambient temperature data, is the historical ambient temperature data of the first historical moment of health preservation, To maintain the current environmental humidity data, The historical environmental humidity data for the hth historical moment of health preservation, To maintain the current ambient light data, The historical ambient light data for the hth historical moment of health preservation, is the historical precast box girder temperature data of the jth precast box girder at the first historical moment of curing, is the historical prefabricated box girder humidity data of the jth prefabricated box girder at the hth first historical moment, is the standard value of the temperature difference between the prefabricated box girder and the environment, is the standard moisture data of precast box beams, The historical moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the first historical moment of curing is: The historical predicted moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the h-th first historical moment of curing, H is the number of the first historical moments of curing, M is the number of prefabricated box girders, h≤H, j≤M, and h, j, H and M are all positive integers.

5. The control system of the mobile spray curing equipment for prefabricated box beams according to claim 4 is characterized in that: The training steps of the spray volume prediction model include: selecting the first historical moment of starting the spray curing equipment from the curing historical moments; obtaining historical spray volume data and historical infrared prefabricated box girder images of multiple prefabricated box girders at multiple first historical moments of curing; determining the historical average temperature of multiple prefabricated box girders at multiple first historical moments of curing according to the pixel values ​​of the pixel points of the historical infrared prefabricated box girder images; performing feature extraction processing on the prefabricated box girder area in the high-definition prefabricated box girder image through the size feature encoding layer of the trained image recognition neural network model, and obtaining multiple prefabricated box girders. The size characteristic vector of the beam; the high-definition prefabricated box beam image and the historical infrared prefabricated box beam image are processed by a spray quantity prediction model to obtain the historical predicted spray quantity data of multiple prefabricated box beams at multiple first historical moments of curing; the loss function of the spray quantity prediction model is determined according to the historical ambient temperature data, the historical average temperature of the prefabricated box beam, the size characteristic vector, the historical spray quantity data and the historical predicted spray quantity data; the spray quantity prediction model is trained according to the loss function of the spray quantity prediction model to obtain the trained spray quantity prediction model.

6. The control system of the mobile spray curing equipment for prefabricated box beams according to claim 5, characterized in that: According to the historical ambient temperature data, the historical average temperature of the precast box beam, the size characteristic vector, the historical spray volume data and the historical predicted spray volume data, the loss function of the spray volume prediction model is determined, including: according to the formula Determine the loss function of the spray rate prediction model ,in, is the size characteristic vector of the j-th precast box girder, is the standard size characteristic vector of precast box girder, for The transposed vector of is the historical average temperature of the j-th prefabricated box girder at the first historical moment of curing, is the historical ambient temperature data of the first historical moment of health preservation, is the historical spraying volume data of the jth prefabricated box girder at the first historical moment of curing, is the historical predicted spraying volume data of the jth prefabricated box girder at the hth first historical moment of curing, H is the number of the first historical moment of curing, M is the number of prefabricated box girders, h≤H, j≤M, and h, j, H and M are all positive integers.

7. The control system of the mobile spray curing equipment for prefabricated box beams according to claim 1 is characterized in that: According to the predicted moving speed data and the predicted spraying amount data, the back-and-forth number of times of the spray curing equipment configured for the multiple prefabricated box beams at the current curing moment is determined, including: obtaining the length of the prefabricated box beam and the spraying speed of the spray curing equipment; according to the formula Determine the number of round trips of the spray curing equipment configured for the j-th prefabricated box girder at the current curing time ,in, is the predicted spraying amount data of the j-th prefabricated box girder at the current curing moment, The predicted moving speed data of the spray curing equipment configured for the j-th prefabricated box girder at the current curing moment, is the spray speed of the spray health equipment, is the length of the j-th precast box girder.

Images