JP2019098303A - Spray condition information calculation device and spray condition information calculation method - Google Patents

Abstract

To provide a spray condition information calculation device and a spray condition information calculation method capable of reducing irregularities of installation due to spray.SOLUTION: A spray condition information calculation device includes an acquisition part which acquires spray state information including a spray pressure of liquid injected on a scraping process, a spray angle and a spray flow rate and adhesion performance information which expresses adhesion performance for an object of coating material installed by spraying the coating material onto an objective surface after the scraping process is performed in an environment according to the spray state information, a learning part which learns spray condition information which expresses such a spray pressure of liquid, spray angle and spray flow rate that adhesive performance for an object of the coating material arrives at a predetermined standard value by using the spray state information and the adhesive performance information and an output part for outputting a value which expresses the spray pressure, the spray angle and the spray flow rate based on the learning result.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a spray condition information calculation device and a spray condition information calculation method.

  Conventionally, the construction method by spraying is utilized in kelen and painting. For example, the surface treatment is performed on the object to be installed, such as a wall surface, by a kering operation, and the coating operation is performed. For example, in Patent Document 1, a vehicle is coated, and the relationship between the physical properties of the paint sprayed on the vehicle and the amount of air supplied to the hand gun is stored in advance, and is used for coating by referring to this. It controls the amount of air according to the paint.

JP, 2013-059757, A

  However, in general, depending on the construction technology and experience of the workers, the properties of the material to be sprayed, etc., the construction method by spraying causes unevenness in construction and can not always be performed under optimal conditions, so maintenance of construction quality and There is a problem that improvement may be difficult. In Patent Document 1, the amount of air supplied to the hand gun can be controlled according to the physical properties of the paint. However, since the construction by spraying can not necessarily be optimized only by the amount of air, Patent Document 1 has room for improvement.

  This invention is made in view of such a situation, The objective is to provide the spraying condition information arithmetic unit which can reduce the nonuniformity of the construction by spraying, and the spraying condition information arithmetic method.

  In order to solve the problems described above, according to the present invention, the kelen process is performed in the environment according to the spray state information including the spray pressure, the spray angle, and the spray flow rate of the liquid sprayed in the kelen process and the spray state information. An acquisition unit for acquiring adhesion performance information representing adhesion performance of the coating material to the object, which is constructed by spraying the coating material on the target surface after the removal, the spraying state information and the adhesion performance A learning unit for learning spray condition information representing a spray pressure, a spray angle, and a spray flow rate of a liquid such that the adhesion performance of the coating material to the object reaches a predetermined reference value using information; And an output unit that outputs a value indicating a spray pressure, a spray angle, and a spray flow rate based on the result.

  Further, the present invention is the spraying condition information computing method in the spraying condition information computing device, wherein the acquiring unit includes spraying condition information including spraying pressure, spraying angle and spraying flow rate of the liquid to be sprayed in the kelen process, and the spraying. Acquire adhesion performance information that represents the adhesion performance of the coating material to the object, applied by spraying the coating material onto the target surface after the keren process is performed in the environment according to the state information And a learning unit using the spray state information and the adhesion performance information to set the spray pressure, the spray angle, and the spray flow rate of the liquid such that the adhesion performance of the coating material to the object reaches a predetermined reference value. Learns spray condition information, and the output unit outputs a value indicating the spray pressure, the spray angle, and the spray flow rate based on the learning result. A condition information calculation method spraying to.

  As described above, according to the present invention, since the spray condition information of the liquid in the kelen process is learned so that the adhesion performance of the coating material reaches a predetermined reference value, and the learning result is output. Preferred spraying conditions can be determined. Thus, by performing the application of the coating material according to the determined spray conditions, it is possible to carry out the execution that meets a certain standard, and reduce the unevenness of the construction due to the spray that does not satisfy the standard. It becomes easy to maintain and improve the quality.

It is a figure which shows the application procedure of the resin coating film by embodiment of this invention. It is a schematic block diagram explaining the function of spraying condition information operation device. 5 is a flow chart for explaining the operation of the spray condition information arithmetic device 10. It is a figure which shows an example of the adhesion test result. It is a figure which shows an example of 3 layer neural network.

Hereinafter, a spray condition information calculation apparatus according to an embodiment of the present invention will be described with reference to the drawings. Here, before the description of the spray condition information calculation device, the spray construction in the present embodiment will be described. In the present embodiment, in the case of the spray construction, a case where a resin coating is applied to a construction target surface using a spray device will be described as an example.
FIG. 1 is a view showing a procedure of applying a resin coating film according to the embodiment of the present invention.
In this embodiment, the construction method of the resin coating film uses the construction method of constructing the concrete structure 1 by applying the polyurea resin coating film 3 after curing the concrete surface 2a which is the surface of the concrete 2 Be
The construction target surface is a concrete surface 2a. The application method of the resin coating 3 includes a keren process by a water jet keren operation and a resin spraying process.
The water jet kelen work is carried out by using a water jet nozzle 4 and carrying out high-pressure water injection to work the concrete surface 2a (keren process). A resin spraying process is implemented by the operation | work which sprays the resin coating film 3 using the spraying nozzle 5 on the concrete surface covered by the keling process.
In the resin spraying step, a spraying method in which a polyurea resin is sprayed to the surface of a concrete structure with a thickness of several millimeters is used. By carrying out the resin spraying method after the water jet kelen work, the impact resistance and durability of the structure 1 such as concrete can be improved.

  As the resin coating film 3, a synthetic resin composed of a polyurethane resin or a polyurea resin is used, which is a compound formed by a chemical reaction of an isocyanate and a curing agent comprising at least one of a polyol and an amine. can do.

  Here, the adhesion performance of the resin coating film 3 to the concrete surface 2a differs depending on the state after rolling of the construction surface (concrete surface 2a) in the keren process. Therefore, it is necessary to carry out squeeze so that the adhesion performance of the resin coating film 3 satisfies a certain standard. In this kelen, the condition of the surface that has been squeezed may change depending on various conditions such as the properties of the structure 1 and the concrete surface 2 a and the way of spraying water jetted from the water jet, but in the present embodiment, the water Focusing on the spray pressure, spray angle and spray flow rate of water jetted from the jet, it was decided to obtain these suitable conditions by the spray control support device.

FIG. 2 is a schematic block diagram for explaining the function of the spray condition information calculation device.
The spraying condition information arithmetic device 10 is configured to include an input unit 11, a learning unit 12, and an output unit 13.
The input unit 11 sprays the coating material on the target surface after the keren process is performed according to the spray condition and the spray state information including the spray pressure, the spray angle, and the spray flow rate of the liquid to be sprayed in the keren process. The adhesion performance information indicating the adhesion performance of the applied coating material to the object is acquired. This liquid is, for example, water.

Further, the input unit 11 is data of spray state information including a spray pressure, a spray angle, and a spray flow rate of the liquid to be sprayed in the kelen process, of data input via any input device such as a touch panel, a keyboard, or a mouse. Acquire by accepting input. Although this spray state information is described through the input device, for example, a pressure sensor that measures the pressure of the liquid jetted by the water jet, the angle between the liquid jetted from the water jet and the jet target object If it is possible to obtain data from a flow rate sensor that measures the spray flow rate of the liquid jetted from the water jet, these data may be acquired as a result of calculation of the spray angle which is the above.
The spray angle, which is the angle between the liquid jetted from the water jet and the jet target, is determined by the angle of the spray direction of the water jet with respect to the normal direction of the working surface. For example, with regard to the angle at which the jet direction of the water jet is directed, a posture sensor is provided on the water jet and measurement is performed to acquire the angle of the water jet with respect to the horizontal plane. The angle between the surface to be sprayed and the horizontal direction can be measured or read out from construction drawing data. And the angle of the spraying direction of the water jet with respect to the normal direction of the working surface can be determined by finding the relative angle between the angle of the jetting direction of these water jets and the angle of the surface to be sprayed. .

The coating material is, for example, a synthetic resin used as a paint for forming the resin coating film 3 described above. The adhesion performance information is for the application target surface of the resin coating 3 after the resin coating 3 formed by spraying the coating material is cured with respect to the application target surface subjected to rolling in the kelen process. Adhesion strength is evaluated and measured as adhesion performance. The input unit 11 acquires adhesion performance information indicating the adhesion performance of the measured resin coating film 3.
The adhesion performance is measured, for example, by checking the adhesion strength of the resin coating when the resin coating 3 is sprayed after the construction target surface is covered with high-pressure water jetted with a water jet and the resin coating 3 is sprayed. It is performed by evaluating the adhesion performance of the film. The input unit 11 accepts data input as this adhesion value as the evaluation value.

  The learning unit 12 uses the spray state information and the adhesion performance information to represent the spray pressure, the spray angle, and the spray flow rate of the liquid such that the adhesion performance of the coating material to the object reaches a predetermined reference value. Learn information For example, the learning unit is configured by a combination of a CPU (Central Processing Unit) such as a computer and a storage device (for example, a hard disk, RAM (Random Access Memory), ROM (Read Only Memory)). The function as the learning unit 12 is realized by executing a program based on the stored learning algorithm.

The learning unit 12 uses an adhesion result information that represents the adhesion performance of the coating film formed on the surface that has been squeezed by the squeeze process, with respect to the spray pressure, the spray angle, and the splay flow rate of the liquid sprayed in the squealing process Make the network learn.
In the learning unit 12, a learning model after learning is performed is stored as a learned model. The learned model is used to output data indicating a spray pressure, a spray angle, and a spray flow which will be described later.

This learning is performed by reinforcement learning, but may be machine learning or the like.
For example, a neural network can be used as a learning model. The neural network includes a first layer for calculating the spray pressure, a second layer for calculating the spray angle, and a third layer for calculating the spray flow rate.

The learning unit 12 further includes a reward calculation unit 121 and a function updating unit 122.
The reward calculation unit 121 calculates a reward based on the spray state information input from the input unit 11 and the adhesion performance information input from the input unit 11.
The reward calculation unit 121 acquires adhesion performance information input from the input unit 11 and calculates a reward for reinforcing and learning the learning model in the learning unit 12.
The data used as a reward here is, for example, the value of adhesion performance. Reinforcement learning can update the learner of the learning model so that the highest reward can be obtained, for example, when the adhesion performance reference value (1.5 N / mm ² ) is exceeded.
The function update unit 122 updates the function for calculating the spray condition information based on the spray state information acquired via the input unit 11 and the reward calculated by the reward calculation unit 121.

  The output unit 13 outputs values indicating the spray pressure, the spray angle, and the spray flow rate based on the learning result. The output unit 13 is, for example, a liquid crystal display device, and may output the value to be output by displaying it on the screen, or output it to an external device (for example, a spray device) to be used as a setting value. May be

  Such a spray condition information calculation device 10 may be configured by, for example, a personal computer or a tablet, or may be provided in the spray device.

Next, the operation of the above-described spray condition information arithmetic device 10 will be described using the flowchart of FIG.
The input unit 11 acquires spray state information by obtaining information obtained from the input device or various sensors (step S101). The worker sprays water on the wall surface etc. which is the construction target surface by the spraying pressure, spraying angle, and spraying flow rate of water jetted from the water jet according to the spraying state information. Thereby, the kelen process is implemented. When a kerening process is carried out and the coating material is sprayed onto the construction target surface, the adhesion performance is evaluated after a predetermined curing time has elapsed. When the adhesion performance is evaluated, the input unit 11 acquires adhesion performance information indicating the evaluation result (step S102). As the evaluation result, for example, a value representing adhesion strength (N / mm ² ) is input as adhesion performance.

When the adhesion performance is acquired, the reward calculation unit 121 calculates the remuneration based on the blowing state information and the adhesion performance information (step S103).
For example, the reward calculation unit 121, for example, increases the reward as the adhesion performance is higher, and calculates the reward so as to reduce the reward as the adhesion performance is lower. Further, the reward calculation unit 121 may store in advance a reference value representing the adhesion performance, and may determine the remuneration based on the relationship between the reference value and the adhesion performance information. For example, if the adhesion strength represented by the adhesion performance information is less than the reference value, the reward is increased as the reference value is approached, and if the adhesion strength represented by the adhesion performance information becomes equal to or more than the reference value, the reward is further increased. It can be calculated.
Next, the function update unit 122 updates the function for calculating the spray condition information based on the spray state information input from the input unit 11 and the reward calculated by the reward calculation unit 121 (step S104). ).

As described above, the spray condition information calculation device 10 learns spray condition information.
When learning is performed, the output unit 13 of the spray condition information calculation device 10 outputs the spray condition information. For example, when the output unit 13 is a display device, this output may be displayed on the screen of the display device, or when it is an interface for outputting data to another device, the spray condition information May be output as data. For example, when the output unit 13 is a display device, “spray pressure 吹 き 付 け MPa, spray angle 度 degree, flow rate L L / min” or the like is displayed on the screen as the spray condition information. The operator visually recognizes this and sets it as the setting value of the water jet spray device so as to become the pressure and flow rate at which water is jetted from the water jet so as to become spray state information corresponding to the spray condition information (or The operation of the valve or the like is performed, and the injection is performed while maintaining the injection angle at the angle indicated by the spray state information.
When the spray condition information is output as data from the interface, for example, the pressure and the pressure to the spray device can be output by outputting the spray condition information to the spray device that controls the pressure and flow rate of the water jetted from the water jet. The flow rate can be set.

  Here, at the start of learning in the learning unit 12 (at the start of the learning algorithm), the correlation between the spray condition information and the adhesion performance is in an unknown state, but the adhesion performance is learned so as to satisfy a predetermined performance. As you move forward, gradually identify features and interpret correlations. Then, the learning unit 12 can bring the condition representing the correlation between the blowing condition information and the adhesion performance closer to the optimum solution as the learning progresses.

In the case where the water jet cleaning operation is performed on a certain construction target surface using such a spray condition information calculation device 10, spray condition information can be determined on the assumption that the following conditions are optimum.
Spray pressure: 150MPa ± 20MPa
Blow-off angle: 20 ° ± 5 ° from the normal of the working surface
Spray flow rate: 6 L / min ± 0.5 L / min
And, the adhesion performance when the resin coating film 3 is sprayed to the surface to be applied after the kelen process is performed according to the spraying condition information is the adhesion performance when the film thickness of the resin coating film 3 is 2 mm. It was confirmed that the reference value (1.5 N / mm ² ) was exceeded.
The adhesion test results are shown in FIG. In the drawing, the adhesion test results focusing on the relationship between the water spray pressure and the adhesion performance among the spray condition information are illustrated. In this figure, the horizontal axis represents the spray pressure of water in the kelen process, and the vertical axis represents the adhesion performance. Here, it was possible to confirm that all of the adhesion performance (adhesion strength) exceeded the reference value (1.5 N / mm ² ) when the spraying pressure was between 100 MPa and 200 MPa.

  Thus, for the required film thickness (for example, 2 mm), the spraying conditions that satisfy the adhesion performance are based on the spraying pressure, spraying angle, spraying flow rate, and these various amounts are each at three levels (for example, pressure In this case, a three-layer neural network can be constructed as shown in FIG. 5 by dividing the pressure into a pressure larger than the average spraying pressure, an average spraying pressure, and a pressure smaller than the average spraying pressure. Reinforcement learning of the actual adhesion performance makes bonus addition to the level of each technology level, and it becomes an artificial intelligence by deep learning by selecting and recording the optimal route, and performing optimal spray construction become able to.

In the embodiment described above, by using the above-described spray condition information calculation device 10, it is possible to standardize the spray or to optimize the spray. For example, when the property of the construction target surface is different from before, or when using a coating material that has not been used before, it is not possible to grasp the spray condition information meeting the adhesion performance criteria Even if this is the case, it is possible to obtain spray condition information that meets the standard of the adhesion performance by advancing the learning by the spray condition information calculation device 10.
Further, in the present embodiment, when using artificial intelligence for the spray condition information calculation device 10, the optimum spray construction method is applied not only to the construction for forming a resin coating film, but also by coating the machine surface or the vehicle surface. It can apply also in the spray factory etc which form the paint film.
In addition, by forming the resin coating film 3 in accordance with the spraying condition information that satisfies the adhesion strength, it is possible to reduce waste that would otherwise spray the coating material more than necessary, and a water jet is required. Since the above operation can be reduced, the electricity cost for operating the water jet can be reduced.

  Each part of the spray condition information calculation device 10 in the above-described embodiment may be realized by a computer. In that case, a program for realizing this function may be recorded in a computer readable recording medium, and the program recorded in the recording medium may be read and executed by a computer system. Here, the “computer system” includes an OS and hardware such as peripheral devices. The term "computer-readable recording medium" refers to a storage medium such as a flexible disk, a magneto-optical disk, a ROM, a portable medium such as a ROM or a CD-ROM, or a hard disk built in a computer system. Furthermore, “computer-readable recording medium” dynamically holds a program for a short time, like a communication line in the case of transmitting a program via a network such as the Internet or a communication line such as a telephone line. It may also include one that holds a program for a certain period of time, such as volatile memory in a computer system that becomes a server or a client in that case. Further, the program may be for realizing a part of the functions described above, or may be realized in combination with the program already recorded in the computer system. It may be realized using a programmable logic device such as an FPGA (Field Programmable Gate Array).

  The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes design and the like within the scope of the present invention.

DESCRIPTION OF SYMBOLS 10 Spray condition information arithmetic unit 11 Input part 12 Learning part 13 Output part 121 Reward calculation part 122 Function update part

Claims (3)

The coating material is sprayed on the target surface after the keren process is performed in the environment according to the spray state information including the spray pressure, the spray angle, and the spray flow rate of the liquid sprayed in the keling process and the spray state information An acquisition unit configured to acquire adhesion performance information indicating adhesion performance of the coating material to the object,
Spray condition information representing a spray pressure, a spray angle and a spray flow rate of the liquid such that the adhesion performance of the coating material to the object reaches a predetermined reference value using the spray state information and the adhesion performance information A learning unit to learn,
An apparatus for calculating spray condition information, comprising: an output unit that outputs a value indicating a spray pressure, a spray angle, and a spray flow rate based on the learned result. The spray condition information calculation device according to claim 1, wherein the coating material is a resin. A spraying condition information computing method in a spraying condition information computing device, comprising:
With respect to the target surface after the kerning process has been performed in the environment according to the spraying condition information including the spraying pressure, spraying angle and spraying flow rate of the liquid sprayed by the acquiring unit in the keling process, and the spraying condition information Acquiring adhesion performance information indicating the adhesion performance of the coating material to a target object, which is applied by spraying the coating material;
The learning unit uses the spray state information and the adhesion performance information to represent the spray pressure, the spray angle, and the spray flow rate of the liquid such that the adhesion performance of the coating material to the object reaches a predetermined reference value. Learn spray condition information,
An output unit outputs a value indicating a spray pressure, a spray angle, and a spray flow rate based on the learning result. Spray condition information calculation method.

Images