Sanitary earthenware manufacturing system and sanitary earthenware manufacturing method

Abstract

To improve accuracy of sanitary earthenware.SOLUTION: A sanitary earthenware manufacturing system is constituted to manufacture sanitary earthenware after a calcination step. The sanitary earthenware manufacturing system has a control part which generates three-dimensional data of a model before calcination from three-dimensional data of a product model using a learning model. The learning model is trained using a database containing shape information for sanitary earthenware after calcination and shape information for sanitary earthenware before calcination. The database has shape information for one or more pieces of calcined sanitary earthenware, for shape information for one piece of un-calcined sanitary earthenware.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The disclosed embodiments relate to a sanitary ware manufacturing system and a sanitary ware manufacturing method. [Background technology]

[0002] Conventionally, there is known a manufacturing method for sanitary ware in which tests are performed on specimens of raw materials for the sanitary ware to determine drying shrinkage and changes in deformation over time, and to specify the shape at the completion of a drying process (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6571580 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, the test is performed on a specimen of the raw material of the sanitary ware, so the specified shape at the end of the drying process depends on the test results by the worker. Therefore, for example, there is a risk that the degree of completion of the sanitary ware will vary greatly due to the variation in the skill of the worker. In other words, the conventional technology has room for improvement in terms of improving the accuracy of the sanitary ware.

[0005] An object of one aspect of an embodiment is to provide a sanitary ware manufacturing system and a sanitary ware manufacturing method that improve the accuracy of sanitary ware. [Means for solving the problem]

[0006] A sanitary ware manufacturing system according to one aspect of the embodiment manufactures sanitary ware through a firing process. The sanitary ware manufacturing system includes a control unit that generates three-dimensional data of a pre-fired model from three-dimensional data of a product model using a learning model. The learning model is trained using a database having shape information of the fired sanitary ware and shape information of the pre-fired sanitary ware. The database has shape information of one or more fired sanitary ware pieces for each piece of pre-fired sanitary ware shape information.

[0007] This allows the sanitary ware manufacturing system to generate three-dimensional data of the pre-fired model from three-dimensional data of a product model, which is the shape of the sanitary ware product. Therefore, the sanitary ware manufacturing system can suppress variation in the degree of completion of the sanitary ware and improve the accuracy of the sanitary ware. In addition, the sanitary ware manufacturing system can automatically generate three-dimensional data of the pre-fired model, making it easy to create three-dimensional data of the pre-fired model.

[0008] Additionally, the shape information of the sanitary ware before firing is 3D scan data of the sanitary ware before firing.

[0009] This allows the sanitary ware manufacturing system to generate three-dimensional data of the pre-fired model based on accurate shape information of the sanitary ware before firing, thereby improving the accuracy of the sanitary ware.

[0010] Furthermore, firing information at the time of firing is linked to at least one of the shape information of the sanitary ware before firing and the shape information of the sanitary ware after firing.

[0011] This allows the sanitary ware manufacturing system to manufacture a pre-fired model that takes into account firing information for when manufacturing sanitary ware, thereby improving the accuracy of the sanitary ware.

[0012] The learning model also generates three-dimensional data of a pre-fired model for the three-dimensional data of the sanitary ware product model stored in the database.

[0013] As a result, the sanitary ware manufacturing system can manufacture pre-fired models with high accuracy, thereby improving the accuracy of the sanitary ware. Also, the sanitary ware manufacturing system can reduce the work of workers who correct the pre-fired models.

[0014] In addition, the learning model generates three-dimensional data of a pre-fired model for three-dimensional data of a sanitary ware product model that is not stored in the database.

[0015] This allows the sanitary ware manufacturing system to generate three-dimensional data of a pre-fired model corresponding to the sanitary ware product model from the three-dimensional data of a new sanitary ware product model. Therefore, the sanitary ware manufacturing system can manufacture a pre-fired model with high accuracy, improving the accuracy of the sanitary ware. In addition, the sanitary ware manufacturing system can reduce the work of workers who modify the pre-fired model. Effect of the Invention

[0016] According to one aspect of the embodiment, the precision of the sanitary ware can be improved. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a schematic cross-sectional view showing a production mold for manufacturing sanitary ware. [Diagram 2] FIG. 2 is a schematic cross-sectional view of the production mold taken along the line II-II of FIG. [Diagram 3] FIG. 3 is a diagram showing an example of a production mold that is generated by being transferred from the master mold. [Figure 4] FIG. 4 is a diagram showing how a master mold is generated. [Diagram 5] FIG. 5 is a diagram showing an outline of a sanitary ware manufacturing system. [Figure 6] FIG. 6 is a block diagram showing a design apparatus according to the embodiment. [Figure 7]FIG. 7 is a diagram illustrating an example of the database. [Figure 8] FIG. 8 is a flowchart illustrating the manufacturing process of the sanitary ware according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] The sanitary ware manufacturing system and the method for manufacturing sanitary ware disclosed in the present application will be described in detail below with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments shown below. It should be noted that the drawings are schematic, and the dimensional relationships and ratios of each element may differ from reality. The drawings may also include parts with different dimensional relationships and ratios. The sanitary ware manufacturing system is a system for manufacturing sanitary ware. In the sanitary ware manufacturing system, each process for manufacturing sanitary ware is carried out.

[0019] Sanitary ware includes toilet bowls, urinals, washbasins, etc. Sanitary ware is manufactured by pouring slip into a mold, removing the part of the slip that has adhered to the surface of the mold from the mold, and firing the part.

[0020] When manufacturing sanitary ware, for example, a plurality of production molds 1 are used, as shown in Figs. 1 and 2. Fig. 1 is a schematic cross-sectional view showing the production mold 1 for manufacturing sanitary ware. Fig. 2 is a schematic cross-sectional view of the production mold 1 as viewed from the II-II cross section direction of Fig. 1. When manufacturing sanitary ware, for example, slip is poured into a space formed by combining four production molds 1a-1d. It should be noted that the number of production molds 1 for manufacturing sanitary ware is not limited to four. The number of production molds 1 for manufacturing sanitary ware is two or more.

[0021] The production mold 1 is a mold to which the master mold 2 is transferred, as shown in Fig. 3. Fig. 3 is a diagram showing an example of the production mold 1 produced by transfer from the master mold 2. The master mold 2 is a mold for producing the production mold 1. By producing the production mold 1 by transferring the master mold 2, a plurality of the same production molds 1 can be produced.

[0022] The master mold 2 is produced, for example, by processing a block raw material with an electric cutting tool 3 based on three-dimensional data of an intermediate model for a sanitary ware product, as shown in Fig. 4. Fig. 4 is a diagram showing the state in which the master mold 2 is produced. The block raw material is, for example, a resin material. For example, the block raw material is a composite material mainly made of resin containing chemical wood or the like.

[0023] The intermediate model is a model before firing, and is a model that takes into account the shrinkage of the base material compared to the final model (product model) of the sanitary ware product after firing. The shrinkage of the base material includes deformation due to gravity. The intermediate model is a model that is different from the final model for the sanitary ware product. The intermediate model is a model that reflects the shrinkage of the base material due to firing. In other words, the intermediate model is a model that shows the shape of the product before firing. The final model is a model that shows the shape of the product after firing.

[0024] The three-dimensional data of the intermediate model is generated using a learning model, which will be described in detail later. The three-dimensional data of the intermediate model is created as CAD (Computer Aided Design) data. The intermediate model is created by a design device 4 (see FIG. 5).

[0025] The electric cutting tool 3 is provided in a processing machine 5 (see FIG. 5). The processing machine 5 is controlled based on CAM (Computer Aided Manufacturing) data created from CAD data. The processing machine 5 processes a block of raw material using the electric cutting tool 3 to generate a master mold 2. The processing machine 5 is an NC (Numerical Control) machine tool or an MC (Machining Center).

[0026] The three-dimensional data of the final model is created using CAD (Computer Aided Design). The three-dimensional data of the final model is designed by a designer (user).

[0027] The three-dimensional data of the intermediate model and the three-dimensional data of the final model are stored in a server 6. The server 6 is connected to the design device 4 so as to be able to communicate wirelessly or wired via a network N1, for example, as shown in FIG. 5. FIG. 5 is a diagram showing an outline of a sanitary ware manufacturing system 7. The network N1 is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet, and is composed of one or more networks.

[0028] The server 6 is communicatively connected to a processing machine 5 having an electric cutting tool 3 via a network N2, wirelessly or by wire. The network N2 is, for example, a LAN or a WAN such as the Internet, and is composed of one or more networks.

[0029] Next, the design device 4 will be described with reference to Fig. 6. Fig. 6 is a block diagram showing the design device 4 according to the embodiment.

[0030] The design device 4 includes a communication unit 10, a storage unit 11, and a control unit 12. Note that the design device 4 is connected to an input device such as a keyboard, a monitor, and the like.

[0031] The communication unit 10 is, for example, a device for communicating data with the server 6. The communication unit 10 is, for example, a communication module capable of wired communication or wireless communication. The wireless communication is performed by, for example, Wi-Fi (registered trademark), LTE (Long Term Evolution), BLE (Bluetooth (registered trademark) Low Energy), Zigbee (registered trademark), UWB (Ultra Wide Band), etc.

[0032] The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory. The storage unit 11 stores a learning model. The learning model may be learned (generated) by the design device 4 or may be generated by another device.

[0033] The control unit 12 is a computer. The control unit 12 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs stored in the storage unit 11 using a RAM as a working area. The control unit 12 can also be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0034] The control unit 12 generates an intermediate model using a technique related to AI (Artificial Intelligence). The control unit 12 generates the intermediate model using a learning model. Specifically, when the three-dimensional data of the final model is input, the control unit 12 generates three-dimensional data of the intermediate model using the learning model.

[0035] The learning model is generated by machine learning and is trained using a database having shape information of the sanitary ware after firing and shape information of the sanitary ware before firing.

[0036] The database includes shape information of different sanitary ware after firing and shape information of different sanitary ware before firing, as shown in Fig. 7. Fig. 7 is a diagram showing an example of the database.

[0037] For example, in the database, shape information before firing of one sanitary ware is linked to shape information after firing of one or more sanitary wares. For example, in the database, shape information A1 before firing of one sanitary ware A is linked to shape information a1-an after firing of two or more sanitary wares A. This is because even when the same intermediate model is fired, the shape of the sanitary ware after firing differs depending on the environment during firing. In addition, for sanitary wares B, C, etc. that are different from sanitary ware A, two or more pieces of shape information b1-bn, c1-cn after firing are linked to shape information B1, C1 before firing of one sanitary ware B, C, respectively.

[0038] The shape information of the sanitary ware before firing is 3D scan data acquired by scanning an intermediate model, which is the sanitary ware before firing, with a 3D scanner. The shape information of the sanitary ware before firing may be 3D scan data of the master mold 2 or the production mold 1. The shape information of the sanitary ware before firing may be three-dimensional data of the intermediate model created by an operator. The shape information of the sanitary ware before firing may be three-dimensional data of the master mold 2 created by an operator.

[0039] The shape information of the fired sanitary ware is 3D scan data obtained by scanning the fired sanitary ware with a 3D scanner.

[0040] The control unit 12 uses the learning model to generate an intermediate model for a final model of sanitary ware that is not stored in the database. For example, when three-dimensional data of the final model of sanitary ware V that is not stored in the database is input, the control unit 12 uses the learning model to generate three-dimensional data of an intermediate model of sanitary ware V. For example, sanitary ware V is a new sanitary ware (sanitary ware with a new product number). The control unit 12 generates three-dimensional data of the intermediate model of sanitary ware V using a learning model learned from pre-fired shape information of sanitary ware different from sanitary ware V and post-fired shape information of sanitary ware different from sanitary ware V.

[0041] The learning model generates three-dimensional data of an intermediate model of sanitary ware V corresponding to three-dimensional data of a final model of sanitary ware V, for example, based on pre-fired shape information A1-C1 of multiple sanitary ware A-C and post-fired shape information a1-an, b1-bn, and c1-cn of multiple sanitary ware A-C.

[0042] That is, without having three-dimensional data of the intermediate model of the sanitary ware V, the control unit 12 generates three-dimensional data of the intermediate model of the sanitary ware V by using a learning model from the three-dimensional data of the final model of the sanitary ware V. As a result, a master mold 2 of the intermediate model of the sanitary ware V is produced based on the three-dimensional data of the intermediate model of the sanitary ware V.

[0043] Furthermore, the control unit 12 may use the learning model to generate three-dimensional data of an intermediate model for the three-dimensional data of the final model of the sanitary ware stored in the database. For example, when three-dimensional data of the final model of sanitary ware B stored in the database is input, the control unit 12 uses the learning model to generate three-dimensional data of the intermediate model of sanitary ware B. As a result, a master mold 2 for the intermediate model of sanitary ware B is produced based on the three-dimensional data of the intermediate model of sanitary ware B. For example, when a new master mold 2 for sanitary ware B is produced, the master mold 2 is produced based on the three-dimensional data of the intermediate model generated using the learning model.

[0044] In this way, the control unit 12 uses the learning model to generate three-dimensional data of an intermediate model of the sanitary ware relative to the three-dimensional data of the final model of the sanitary ware.

[0045] The master mold 2 may be modified based on the results of prototype evaluation of the sanitary ware using the production mold 1. In this case, the production mold 1 is generated using the modified master mold 2 to manufacture the intermediate model. The database stores shape information of the sanitary ware before and after firing, before and after the master mold 2 is modified.

[0046] Next, a method for manufacturing sanitary ware executed by the sanitary ware manufacturing system 7 according to the embodiment will be described with reference to the flowchart in Fig. 8. Fig. 8 is a flowchart illustrating the manufacturing process for sanitary ware according to the embodiment. The processes described below include a development process.

[0047] In the first design process (S100), a final model of the sanitary ware product is designed by CAD. That is, three-dimensional data of the final model is created using CAD. In other words, the final model is digitized. The three-dimensional data of the final model is stored in the server 6. The first design process is a development process.

[0048] Next, in the second design process (S101), three-dimensional data of an intermediate model of the sanitary ware is designed by the learning model. Specifically, from the three-dimensional data of the final model, three-dimensional data of an intermediate model corresponding to the three-dimensional data of the final model is created by the learning model. The three-dimensional data of the intermediate model is stored in the server 6. The second design process and subsequent processes are manufacturing processes.

[0049] Next, in the master mold fabrication step (S102), the master mold 2 is fabricated. Three-dimensional data of an intermediate model of the sanitary ware is read from the server 6. The read three-dimensional data of the intermediate model is converted into CAM data. Based on the converted CAM data, the block raw material is processed by the processing machine 5. In this way, the master mold 2 is fabricated.

[0050] Next, in the production mold fabrication step (S103), the production mold 1 is fabricated. The production mold 1 is fabricated by being transferred from the master mold 2.

[0051] Next, in the manufacturing process (S104), a sanitary ware product is manufactured. The sanitary ware is manufactured using the production mold 1. Specifically, an intermediate model is made using the production mold 1, and the intermediate model is fired to manufacture the sanitary ware product. That is, the manufacturing process includes a firing process.

[0052] Furthermore, by 3D scanning the intermediate model, information on the shape of the sanitary ware before firing is obtained and saved in a database, and by 3D scanning the sanitary ware product, information on the shape of the sanitary ware after firing is obtained and saved in a database.

[0053] In a sanitary ware manufacturing system according to a comparative example that does not use a learning model, three-dimensional data of an intermediate model is generated by an operator, and an intermediate model is manufactured. The intermediate model thus manufactured is then fired to produce a prototype, which is then evaluated, and the master mold 2 is modified. For example, such prototype evaluation is repeated to produce a final master mold 2, and the sanitary ware is manufactured. As a result, when manufacturing an intermediate model corresponding to a final model of sanitary ware, there is often a large variation in the degree of completion of the sanitary ware due to variations in the skills of the operators, etc.

[0054] The sanitary ware manufacturing system 7 manufactures sanitary ware through a firing process. The sanitary ware manufacturing system 7 includes a control unit 12. The control unit 12 generates three-dimensional data of an intermediate model from three-dimensional data of a final model using a learning model. The learning model is trained using a database having shape information of sanitary ware after firing and shape information of sanitary ware before firing. The database has shape information of one or more fired sanitary ware pieces for each piece of shape information of unfired sanitary ware.

[0055] This allows the sanitary ware manufacturing system 7 to generate three-dimensional data of the intermediate model from three-dimensional data of the final model, which is the shape of the sanitary ware product. As a result, the sanitary ware manufacturing system 7 can reduce variation in the degree of completion of the sanitary ware and improve the accuracy of the sanitary ware. In addition, the sanitary ware manufacturing system 7 can automatically generate three-dimensional data of the intermediate model, making it easy to create three-dimensional data of the intermediate model.

[0056] The shape information of the sanitary ware before firing is 3D scan data of the sanitary ware before firing.

[0057] This allows the sanitary ware manufacturing system 7 to generate three-dimensional data of the intermediate model based on accurate shape information of the sanitary ware before firing, thereby enabling the sanitary ware manufacturing system 7 to improve the accuracy of the sanitary ware.

[0058] The learning model generates three-dimensional data of an unfired model for three-dimensional data of a sanitary ware product model that is not stored in the database.

[0059] This allows the sanitary ware manufacturing system 7 to generate three-dimensional data of an intermediate model that corresponds to the final model of the sanitary ware from the three-dimensional data of the new final model of the sanitary ware. As a result, the sanitary ware manufacturing system 7 can manufacture an intermediate model with high accuracy, improving the accuracy of the sanitary ware. In addition, the sanitary ware manufacturing system 7 can reduce the work of workers who modify the intermediate model.

[0060] The learning model generates three-dimensional data of an intermediate model for the three-dimensional data of the final model of the sanitary ware stored in the database.

[0061] As a result, the sanitary ware manufacturing system 7 can manufacture accurate intermediate models, thereby improving the accuracy of the sanitary ware. In addition, the sanitary ware manufacturing system 7 can reduce the work of workers who correct the intermediate models.

[0062] At least one of the shape information of the sanitary ware before firing and the shape information of the sanitary ware after firing may be linked to firing information. The firing information includes firing conditions, type of slip (raw material), manufacturing method, conditions during the manufacturing process, and environmental information. The environmental information includes information such as the temperature when drying the intermediate model, the humidity when drying the intermediate model, the temperature during molding, and the humidity during molding. In this case, the firing information is also linked to the three-dimensional data of the final model, and three-dimensional data of the intermediate model is generated by the learning model.

[0063] This enables the sanitary ware manufacturing system 7 to manufacture an intermediate model that takes into account firing information when manufacturing sanitary ware, thereby improving the accuracy of the sanitary ware.

[0064] Further advantages and modifications may readily occur to those skilled in the art. Thus, the invention in its broader aspects is not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications may be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and equivalents thereof. [Explanation of symbols]

[0065] 1 Production type 2 Master mold 3 Electric cutting tools 4 Design equipment 5 Processing machinery 6 Server 7 Sanitary ware manufacturing system 10. Communications Department 11 Storage section 12 Control section

Claims

1. A sanitary ware manufacturing system for manufacturing sanitary ware through a firing process, comprising: a control unit that generates three-dimensional data of a pre-fired model from three-dimensional data of a product model using a learning model; the learning model is trained using a database having shape information of the sanitary ware after firing and shape information of the sanitary ware before firing, a database having shape information of one or more fired sanitary ware pieces for one piece of pre-fired sanitary ware shape information.

2. 2. The sanitary ware manufacturing system according to claim 1, wherein the shape information of the sanitary ware before being fired is 3D scan data of the sanitary ware before being fired.

3. The sanitary ware manufacturing system according to claim 1 , wherein firing information at the time of firing is linked to at least one of the shape information of the sanitary ware before firing and the shape information of the sanitary ware after firing.

4. 2. The sanitary ware manufacturing system according to claim 1, wherein the learning model generates three-dimensional data of a pre-fired model for the three-dimensional data of a sanitary ware product model stored in the database.

5. The sanitary ware manufacturing system according to claim 1 , wherein the learning model generates three-dimensional data of a pre-fired model for three-dimensional data of a sanitary ware product model that is not stored in the database.

6. A method for manufacturing sanitary ware by carrying out a firing process, comprising the steps of: A step of generating three-dimensional data of a pre-fired model from three-dimensional data of a product model using a learning model, the learning model is trained using a database having at least shape information of the sanitary ware after firing and shape information of the sanitary ware before firing, a manufacturing method for sanitary ware, wherein the database has shape information of two or more sanitary ware after firing for one piece of shape information of the sanitary ware before firing.

Images