Temperature rise condition calculation device, dyeing system, temperature rise condition calculation method and program
The temperature increase condition calculation device uses machine learning to automate the determination of dyeing temperature conditions, addressing the inefficiencies in manual dyeing temperature control and improving the evaluation of newly dyed objects.
Patent Information
- Application Number
- JP2020150522
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2019-09-12
- Filing Date
- 2020-09-08
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2040-09-08
AI Technical Summary
Dyeing processors face a heavy workload in determining appropriate dyeing temperature control for each new type of object, leading to inefficiencies and potential color unevenness, as they need to conduct dyeing tests and estimate heating times manually.
A temperature increase condition calculation device that uses machine learning to determine optimal dyeing temperature conditions based on object type, dye concentration, dyeing machine type, and historical learning data, automatically calculating and outputting these conditions to the dyeing machine.
Reduces the workload of dyeing processors by automating the calculation of optimal dyeing temperature conditions, improving the evaluation of newly dyed objects and reducing color unevenness through precise temperature control.
Smart Images

Figure 0007576947000001 
Figure 0007576947000002 
Figure 0007576947000003
Abstract
Description
[Technical field]
[0001] The present invention relates to a temperature rise condition calculation device, a dyeing system, a temperature rise condition calculation method, and a program. [Background technology]
[0002] 2. Description of the Related Art Dyeing machines that dye objects by controlling the dyeing temperature are known.
[0003] As an example of such a dyeing machine, Patent Document 1 discloses an automatic dyeing machine in which an arithmetic control unit acquires information corresponding to a specific type of dyeing method from information related to control of dyeing temperature that is pre-stored for each type of dyeing method, and controls the dyeing machine body based on the acquired information to dye a fabric using the specific type of dyeing method. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Special Publication No. 6-55992 Summary of the Invention [Problem to be solved by the invention]
[0005] Patent Document 1 does not disclose how the information on the control of the dyeing temperature stored in the automatic dyeing machine is determined, but conventionally, such information has been determined by the dyeing and processing company, which is the user of the automatic dyeing machine. The dyeing and processing company needs to determine appropriate information on the control of the dyeing temperature for all objects to be dyed, including the above-mentioned woven fabrics, each time a new type of object is dyed. For example, in order to reduce color unevenness caused by raising the dyeing temperature in a short time, it is necessary to perform a dyeing test for each object to be dyed, estimate the temperature rise time required to reach the optimal dyeing temperature, or correct the estimated temperature rise time based on a predetermined design standard. This causes a problem of a heavy workload for the dyeing and processing company.
[0006] The present invention has been made in consideration of the above-mentioned circumstances, and aims to reduce the workload of a dyeing machine user. Another aim of the present invention is to enable calculation of optimal conditions for increasing the dyeing temperature per unit time in order to improve the evaluation of a newly dyed object. [Means for solving the problem]
[0007] In order to achieve the above object, the temperature rise condition calculation device according to the present invention includes a temperature rise condition calculation unit and a temperature rise condition output unit. The temperature rise condition calculation unit outputs object information indicating the type of dyed object, dye information indicating the type and concentration of dye used in dyeing, Dyeing machine information indicating the type of dyeing machine used for dyeing; Temperature rise condition information showing the temperature rise condition per unit time of the dyeing temperature of the dye solution when the object is dyed And Based on a trained model generated by machine learning using learning information including the following, a type of object to be newly dyed, a type and concentration of a dye to be used for the new dyeing, , the type of dyeing machine that performs the new dyeing and The temperature rise condition output unit calculates the temperature rise condition per unit time of the dyeing temperature of the dye liquor when newly dyeing from the temperature rise condition calculation unit. Do a new stain Output to the dyeing machine. Effect of the Invention
[0008] According to the present invention, object information, dye information, and temperature rise condition information are Dyeing machine Based on a trained model generated by machine learning using training information including the above, the type of object to be newly dyed, the type and concentration of the dye to be used for the new dyeing, New dyeing machines and The temperature rise condition per unit time of the dyeing temperature of the dye liquor when a new dyeing is performed is calculated from the object information, dye information, and the like, and output to the dyeing machine. Dyeing machine information andIf the temperature rise condition calculation device is obtained, the temperature rise condition can be calculated and output to the dyeing machine. As a result, the workload can be reduced compared to a user of a dyeing machine that does not use the temperature rise condition calculation device according to the present invention. Furthermore, if a trained model is generated by machine learning using learning information suitable for calculating the temperature rise condition per unit time of the dyeing temperature of the dye liquor when newly dyeing, it is possible to increase the evaluation of an object newly dyed with a dye liquor having a dyeing temperature based on the calculated temperature rise condition. As a result, it is possible to calculate the optimal condition for increasing the evaluation of the newly dyed object as the temperature rise condition per unit time of the dyeing temperature. [Brief description of the drawings]
[0009] [Figure 1] FIG. 1 is an explanatory diagram of a dyeing system according to an embodiment of the present invention. [Diagram 2] A block diagram showing the functional configuration of the staining system according to the present embodiment. [Diagram 3] FIG. 1 is a block diagram showing a hardware configuration of a temperature rise condition calculation device according to an embodiment of the present invention. [Figure 4] FIG. 1 is a diagram showing an example of learning information according to an embodiment of the present invention; [Diagram 5] FIG. 1 is a diagram showing an example of a dyeing temperature increase according to the present embodiment. [Figure 6] A flowchart showing a trained model generation process according to the present embodiment. [Figure 7] A flowchart showing a temperature rise condition calculation process according to the present embodiment. [Figure 8] A flowchart showing a learning information generating process according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0010] Hereinafter, a temperature rise condition calculation device, a dyeing system, a temperature rise condition calculation method, and a program according to embodiments of the present invention will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals.
[0011] The temperature rise condition calculation device, the temperature rise condition calculation method, and the program according to the embodiment of the present invention calculate the temperature rise condition per unit time of the dyeing temperature of the dye liquor when a new object is dyed. Also, the dyeing system according to the embodiment of the present invention calculates the temperature rise condition per unit time of the dyeing temperature of the dye liquor when a new object is dyed by the temperature rise condition calculation device, and dyes the object under the calculated temperature rise condition by the dyeing machine.
[0012] FIG. 1 is an explanatory diagram of a dyeing system according to the present embodiment. As shown in FIG. 1, the dyeing system 1 according to the present embodiment includes a dyeing machine 2 that dyes an object, and a learning information storage device 3 that stores learning information used in machine learning for calculating temperature rise conditions. The dyeing system 1 also includes a trained model generation device 4 that generates a trained model (inference model) for calculating temperature rise conditions by machine learning using the learning information, and a temperature rise condition calculation device 5 that calculates temperature rise conditions based on the trained model. In the dyeing system 1, the dyeing machine 2, the learning information storage device 3, the trained model generation device 4, and the temperature rise condition calculation device 5 are connected to each other via a network.
[0013] In the dyeing system 1, the trained model generation device 4 generates a trained model by machine learning using the training information stored in the training information storage device 3. Furthermore, the temperature rise condition calculation device 5 calculates temperature rise conditions for newly dyeing an object based on the trained model generated by the trained model generation device 4, and outputs the calculated temperature rise conditions to the dyeing machine 2. Then, the dyeing machine 2 newly dyes the object under the temperature rise conditions output from the temperature rise condition calculation device 5.
[0014] Fig. 2 is a block diagram showing the functional configuration of the dyeing system according to the present embodiment. As shown in Fig. 2, the dyeing machine 2 includes a temperature rise condition setting unit 201 that sets temperature rise conditions.
[0015] The learning information storage device 3 is, for example, a computer equipped with database management software, that is, a so-called database server. As shown in Fig. 2, the learning information storage device 3 includes a learning information storage unit 301 that stores learning information.
[0016] FIG. 4 is a diagram showing an example of learning information according to the present embodiment. As shown in FIG. 4, the learning information includes object information including information indicating the type of the dyed object, and dye information including information indicating the type and concentration of the dye used for dyeing. The learning information also includes auxiliary information including information indicating the type and concentration of the auxiliary used for dyeing, functional drug information including information indicating the type and concentration of the functional drug used for functionality imparting, and dyeing machine information including information indicating the type of the dyeing machine 2. Furthermore, the learning information includes temperature rise condition information indicating the temperature rise condition when the object was dyed, and evaluation information indicating the evaluation of the object dyed with the dye solution at the dyeing temperature based on the temperature rise condition. That is, the learning information is information including object information, dye information, auxiliary information, functional drug information, dyeing machine information, temperature rise condition information, and evaluation information, and these pieces of information are classified for each dyeing. Therefore, the learning information storage unit 301 stores learning information for each dyeing for all dyeings performed so far.
[0017] For example, in the learning information in the first row of Fig. 4, the "type" of the dyed object is "fabric A", the "type" and "concentration" of the dye used for dyeing are "dye A" and "concentration A1", and the "type" and "concentration" of the auxiliary used for dyeing are "auxiliary A" and "concentration A2". In addition, in the learning information in the first row of Fig. 4, the "type" and "concentration" of the functional agent used for imparting functionality are "functional agent A" and "concentration A3", the "type" of the dyeing machine 2 is "dyeing machine A", the "temperature rise condition" per unit time of the dyeing temperature of the dyeing solution of "dye A" when "fabric A" is dyed is "TA1a, TA1b, ..., TA1k", and the evaluation of "fabric A" dyed with the dyeing solution of "dye A" at the dyeing temperature based on the temperature rise condition "TA1a, TA1b, ..., TA1k" is "○".
[0018] FIG. 5 is a diagram showing an example of the dyeing temperature to be raised according to the present embodiment. In this embodiment, the temperature rise condition is specified by the temperature rise time until the dyeing temperature reaches a predetermined dyeing temperature. For example, the temperature rise condition is specified by the temperature rise time until the temperature rises by 10°C in each section obtained by dividing the dyeing temperature from 20°C to 130°C in increments of 10°C. Here, for example, as shown in FIG. 5, if the vertical axis of the graph is temperature T [°C] and the horizontal axis is time t [min], the dyeing temperature T [°C] is a function T=f(t) of the time t [min] specified by a line drawn on the graph. The function T=f(t) shown in FIG. 5 indicates that the temperature is 20°C at the start of dyeing, the temperature rises steadily from 20°C to 70°C for 5 minutes, and the temperature rises steadily from 70°C to 90°C for 5 minutes. The function T=f(t) also indicates that the temperature rises steadily from 90°C to 110°C for 10 minutes, and the temperature rises steadily from 110°C to 120°C for 10 minutes. In addition, the function T=f(t) indicates that the temperature rises steadily from 120°C to 130°C over a period of 5 minutes, and then the temperature does not change from 130°C for 10 minutes before dyeing is completed.
[0019] Therefore, the temperature rise time from 20°C to 30°C by increasing by 10°C, the temperature rise time from 30°C to 40°C by increasing by 10°C, and the temperature rise time from 40°C to 50°C by increasing by 10°C are each 60 seconds. In addition, the temperature rise time from 50°C to 60°C by increasing by 10°C, and the temperature rise time from 60°C to 70°C by increasing by 10°C are also each 60 seconds. In addition, the temperature rise time from 70°C to 80°C by increasing by 10°C, and the temperature rise time from 80°C to 90°C by increasing by 10°C are each 150 seconds. In addition, the temperature rise time from 90°C to 100°C by increasing by 10°C, and the temperature rise time from 100°C to 110°C are each 300 seconds. The temperature rise time from 110° C. to 120° C. after a 10° C. increase is 600 seconds, and the temperature rise time from 120° C. to 130° C. after a 10° C. increase is 300 seconds.
[0020] Therefore, the temperature rise conditions can be specified by, for example, 60 [sec], 60 [sec], 60 [sec], 60 [sec], 60 [sec], 60 [sec], 150 [sec], 150 [sec], 300 [sec], 300 [sec], 600 [sec], 300 [sec]. Therefore, if the dyeing temperatures shown in Fig. 5 are dyeing temperatures based on the temperature rise conditions indicated by the temperature rise condition information included in the learning information in the first row of Fig. 4, then TA1a = 60 [sec], TA1b = 60 [sec], TA1c = 60 [sec], TA1d = 60 [sec], TA1e = 60 [sec], TA1f = 150 [sec], TA1g = 150 [sec], TA1h = 300 [sec], TA1i = 300 [sec], TA1j = 600 [sec], TA1k = 300 [sec].
[0021] In the present embodiment, the function T=f(t) shown as a broken line in which a plurality of straight lines are connected on a graph in which the vertical axis is temperature T [°C] and the horizontal axis is time t [min] is given as an example of the function of the dyeing temperature, but is not limited thereto. For example, the function of the dyeing temperature may be a function shown as a curve on the above-mentioned graph, or may be a function shown as a line in which straight lines and curves are connected.
[0022] The trained model generating device 4 is, for example, a computer equipped with a GPU (Graphics Processing Unit), that is, a so-called GPU machine. The trained model generating device 4 is not limited to a GPU machine, and may be other computers capable of performing calculations for generating a trained model for calculating a temperature rise condition by machine learning using learning information. For example, the trained model generating device 4 may be a personal computer, a supercomputer, a workstation, or the like equipped with a CPU (Central Processing Unit).
[0023] As shown in FIG. 2, the trained model generating device 4 includes a trained model generating unit 401 that generates a trained model, and a trained model storage unit 402 that stores the trained model. The trained model generated is a mathematical model that indicates the relationship between the type of dyed object, the type and concentration of dye used for dyeing, the type and concentration of auxiliary agent used for dyeing, the type and concentration of functional agent used for imparting functionality, the type of dyeing machine 2, the temperature rise conditions when the object is dyed, and the evaluation of the dyed object. Specifically, the trained model generated is an algorithm for calculating the temperature rise conditions that are predicted to give a high evaluation of the newly dyed object (for example, no color unevenness) from the combination of the type of object, the type and concentration of dye, the type and concentration of auxiliary agent, the type and concentration of functional agent, and the type of dyeing machine 2 in the new dyeing.
[0024] The trained model generation unit 401 acquires all the learning information for each staining performed so far stored in the learning information storage unit 301, and generates a trained model by machine learning using all the acquired learning information. Note that the trained model generation unit 401 acquires all the learning information stored in the learning information storage unit 301, but is not limited to this. For example, the trained model generation unit 401 may acquire a part of the learning information of all the learning information stored in the learning information storage unit 301, and generate a trained model by machine learning using the acquired part of the learning information. Specifically, the trained model generation unit 401 may acquire learning information for each staining performed in a predetermined period (e.g., the past year, half a year, three months, one month, two weeks, one week, etc.) stored in the learning information storage unit 301, and generate a trained model by machine learning using the acquired learning information.
[0025] Here, the machine learning method performed by the trained model generation unit 401 is, for example, a recurrent neural network (RNN), and the format of the learning model is, for example, a general model format of a recurrent neural network such as a long short-term memory (LSTM) or deepRNN. Note that the machine learning method performed by the trained model generation unit 401 is not limited to a recurrent neural network, and may be other neural networks such as a convolutional neural network (CNN) or a probabilistic neural network (PNN), or other methods such as reinforcement learning or association rule learning.
[0026] The temperature rise condition calculation device 5 is, for example, a computer such as a desktop PC (personal computer), a notebook PC, or a tablet PC that is used by a user of the dyeing machine 2, that is, a so-called client machine. When there are multiple users of the dyeing machine 2, the temperature rise condition calculation device 5 is a client machine in the same number as the number of users. For example, as shown in FIG. 1, if there are n users of the dyeing machine 2, n client machines 5A1, 5A2, ..., 5An are provided. Hereinafter, each of the n client machines 5A1, 5A2, ..., 5An will be simply described as a temperature rise condition calculation device 5. Note that the number of client machines does not have to be the same as the number of users. For example, when n ≠ m is established, m client machines 5A1, 5A2, ..., 5Am may be provided for n users.
[0027] As shown in Figure 2, the temperature rise condition calculation device 5 includes a temperature rise condition calculation unit 501 that calculates the temperature rise conditions, a temperature rise condition output unit 502 that outputs the temperature rise conditions to the dyeing machine 2, a learning information generation unit 503 that generates new learning information, and a learning information output unit 504 that outputs the new learning information to the learning information storage device 3.
[0028] When acquiring object information, dye information, auxiliary agent information, functional drug information, and dyeing machine information for new dyeing, the temperature rise condition calculation unit 501 acquires a trained model stored in the trained model storage unit 402 of the trained model generation device 4. Then, based on the acquired trained model, the temperature rise condition calculation unit 501 calculates a temperature rise condition predicted to give a high evaluation to the newly dyed object from a combination of the type of object, type and concentration of dye, type and concentration of functional drug, type and concentration of auxiliary agent, and type of dyeing machine 2 for new dyeing specified from the above-mentioned information.
[0029] For example, if the above-mentioned combination in the new dyeing is a combination included in the learning information obtained by machine learning, the temperature rise condition calculation unit 501 calculates, using the acquired trained model, the same temperature rise condition as the temperature rise condition in the temperature rise condition information included in the learning information for this combination and for which the evaluation information is evaluated as "○". Here, it is assumed that the object information, dye information, auxiliary agent information, functional drug information, and dyeing machine information in the acquired new dyeing are the same as the object information, dye information, auxiliary agent information, functional drug information, and dyeing machine information included in the learning information in the first row of FIG. 4. In this case, since the evaluation information included in the learning information in the first row of FIG. 4 is evaluated as "○", the temperature rise condition calculation unit 501 calculates, using the acquired trained model, the temperature rise conditions "TA1a, TA1b, ..., TA1k" in the temperature rise condition information included in the learning information in the first row of FIG. 4 as the temperature rise conditions in the new dyeing.
[0030] Also, for example, if the above-mentioned combination in the new dyeing is a new combination not included in the learning information obtained by machine learning, the temperature rise condition calculation unit 501 calculates a temperature rise condition that is the same as or similar to the temperature rise condition of the temperature rise condition information included in the learning information with the evaluation of "○" based on the learning information of a combination similar to this combination, for example, the learning information of a combination that is partially common, using the acquired trained model. Here, it is assumed that the object information, auxiliary information, functional drug information, and dyeing machine information in the acquired new dyeing are the same as the object information, auxiliary information, functional drug information, and dyeing machine information included in the learning information in the first and ninth rows of FIG. 4. On the other hand, it is assumed that the dye information in the acquired new dyeing is different from the dye information in the first and ninth rows of FIG. 4, and the "type" and "concentration" of the dye used in the dyeing are "dye C" and "concentration C1".
[0031] In this case, the evaluation of the evaluation information included in the learning information in the first row of Fig. 4 is "○", while the evaluation of the evaluation information included in the learning information in the ninth row of Fig. 4 is "×". Therefore, the temperature rise condition calculation unit 501 calculates, using the acquired trained model, temperature rise conditions that are the same as or similar to the temperature rise conditions "TA1a, TA1b, ..., TA1k" of the temperature rise condition information included in the learning information in the first row of Fig. 4 as temperature rise conditions for new dyeing.
[0032] The temperature rise condition output unit 502 outputs information indicating the temperature rise conditions calculated by the temperature rise condition calculation unit 501 as temperature rise condition information for new dyeing.
[0033] The temperature rise condition setting unit 201 sets the temperature rise condition output by the temperature rise condition output unit 502. For example, when the above-mentioned temperature rise condition "TA1" is output from the temperature rise condition output unit 502, the temperature rise condition setting unit 201 sets "TA1a, TA1b, ..., TA1k". At this time, the dyeing machine 2 adjusts the dyeing temperature so that the temperature rise condition shown in FIG. 5 is achieved from the start of dyeing. When an object is dyed with a dye solution having a dyeing temperature based on the set temperature rise condition, the user of the dyeing machine 2 visually evaluates the dyed object, and generates the above-mentioned evaluation information by giving an evaluation of "○" if no color unevenness occurs and "×" if color unevenness occurs. The user of the dyeing machine 2 also inputs the generated evaluation information to the temperature rise condition calculation device 5.
[0034] When the learning information generation unit 503 acquires evaluation information for new dyeing generated by the user after dyeing is completed, it generates learning information including the object information, dye information, auxiliary agent information, functional drug information, dyeing machine information, and temperature rise condition information already acquired for the new dyeing, as well as the newly acquired evaluation information.
[0035] The learning information output unit 504 outputs the generated learning information for the new staining to the learning information storage device 3 to store it in the learning information storage unit 301. At this time, if the learning information output by the learning information output unit 504 is identical to learning information already stored in the learning information storage unit 301, the learning information storage device 3 may determine that it is duplicated learning information and may not store it in the learning information storage unit 301.
[0036] The trained model generation device 4 irregularly acquires the learning information from the learning information storage unit 301 of the learning information storage device 3, and when new learning information is stored in the learning information storage unit 301, the trained model generation unit 401 generates a new trained model at the request of the user and stores it in the trained model storage unit 402. If learning is frequently performed and the trained model is updated, there is a risk that the accuracy of calculating the temperature rise condition may decrease, and it is necessary to be careful when applying the trained model. For this reason, as in this embodiment, it is preferable that the trained model generation device 4 irregularly acquires the learning information from the learning information storage unit 301 of the learning information storage device 3, but this is not limited thereto, and the trained model generation device 4 may periodically acquire the learning information. As in this embodiment, it is preferable that the trained model generation device 4 generates and stores a new trained model at the request of the user, but this is not limited thereto, and the trained model generation device 4 may automatically generate and store a new trained model when the learning information storage device 3 stores new learning information. In this case, the learned model generation device 4 needs to determine whether the learning information storage device 3 has stored new learning information, for example by obtaining information from the learning information storage device 3 that new learning information has been stored.
[0037] Fig. 3 is a block diagram showing a hardware configuration of a temperature rise condition calculation device according to this embodiment. As shown in Fig. 3, the temperature rise condition calculation device 5 includes a control unit 51 that executes processing according to a control program 59. The control unit 51 includes an arithmetic unit such as a CPU (Central Processing Unit) or a GPU. The control unit 51 functions as a temperature rise condition calculation unit 501, a temperature rise condition output unit 502, a learning information generation unit 503, and a learning information output unit 504 of the temperature rise condition calculation device 5 according to the control program 59.
[0038] Moreover, the temperature rise condition calculation device 5 includes a main storage unit 52 into which a control program 59 is loaded and which is used as a working area for the control unit 51. The main storage unit 52 includes a RAM (Random-Access Memory).
[0039] Moreover, the temperature rise condition calculation device 5 includes an external storage unit 53 that prestores a control program 59. The external storage unit 53 supplies data stored by this program to the control unit 51 in accordance with instructions from the control unit 51, and stores data supplied from the control unit 51. The external storage unit 53 includes a non-volatile memory such as a flash memory, a hard disk, a DVD (Digital Versatile Disc)-RAM, or a DVD-RW (ReWritable).
[0040] Moreover, the temperature rise condition calculation device 5 includes an operation unit 54 that is operated by a user. Information input via the operation unit 54 is supplied to the control unit 51. The operation unit 54 includes information input components such as a keyboard and a mouse.
[0041] Moreover, the temperature rise condition calculation device 5 includes a display unit 55 that displays information input via the operation unit 54 and information output by the control unit 51. The display unit 55 includes an information display device such as an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display.
[0042] The temperature rise condition calculation device 5 also includes a transmission / reception unit 56 that transmits and receives information. The transmission / reception unit 56 includes information communication components such as a network termination device that connects to a network, and a wireless communication device.
[0043] In the temperature rise condition calculation device 5 , the main memory unit 52 , the external memory unit 53 , the operation unit 54 , the display unit 55 and the transmission / reception unit 56 are all connected to the control unit 51 via the internal bus 50 .
[0044] Although not shown in the figures, the learning information storage device 3 and the trained model generation device 4 also have a main memory unit 52, an external memory unit 53, an operation unit 54, a display unit 55 and a transmission / reception unit 56, similar to the temperature rise condition calculation device 5, and are connected to a control unit 51 via an internal bus 50. In the learning information storage device 3, the external memory unit 53 functions as a learning information storage unit 301. Also, in the trained model generation device 4, the control unit 51 functions as a trained model generation unit 401 in accordance with a control program 59, and the external memory unit 53 functions as a trained model storage unit 402.
[0045] FIG. 6 is a flowchart showing a trained model generation process according to the present embodiment. The operation of the trained model generation device 4 generating a trained model will be described with reference to the flowchart shown in FIG. 6. When new learning information is stored in the learning information storage unit 301 of the learning information storage device 3 by the temperature rise condition calculation device 5, the trained model generation unit 401 starts execution of the trained model generation process at the request of the user. First, as shown in FIG. 6, the trained model generation unit 401 acquires all learning information stored in the learning information storage unit 301 (step S101). After acquiring the learning information, the trained model generation unit 401 generates a trained model by machine learning using all the acquired learning information (step S102), stores the generated trained model in the trained model storage unit 402 (step S103), and ends the process. Note that in the present embodiment, the trained model generation unit 401 acquires all learning information stored in the learning information storage unit 301 and generates a trained model by machine learning using all the acquired learning information, but is not limited thereto. For example, as described above, the trained model generation unit 401 may acquire a portion of the learning information among all the learning information stored in the learning information storage unit 301, and generate a trained model by machine learning using the acquired portion of the learning information.
[0046] FIG. 7 is a flowchart showing the temperature rise condition calculation process according to the present embodiment. The operation of the temperature rise condition calculation device 5 for calculating the temperature rise condition for new dyeing will be described using the flowchart shown in FIG. 7. When object information, dye information, auxiliary information, functional drug information, and dyeing machine information for new dyeing generated by the user of the dyeing machine 2 are input to the temperature rise condition calculation device 5, the temperature rise condition calculation unit 501 starts executing the temperature rise condition calculation process. First, as shown in FIG. 7, the temperature rise condition calculation unit 501 acquires object information, dye information, auxiliary information, functional drug information, and dyeing machine information for the new dyeing input by the user (step S201). At this time, the temperature rise condition calculation unit 501 identifies the type of object, type and concentration of dye, type and concentration of auxiliary, type and concentration of functional drug information, and type of dyeing machine 2 for the new dyeing from the acquired information.
[0047] The temperature rise condition calculation unit 501 also acquires the trained model stored in the trained model storage unit 402 of the trained model generation device 4 (step S202). Based on the acquired trained model, the temperature rise condition calculation unit 501 also calculates the temperature rise condition per unit time of the dyeing temperature of the dye solution that is predicted to be highly evaluated for the newly dyed object from the identified type of object, type and concentration of dye, type and concentration of auxiliary, type and concentration of functional drug information, and type of dyeing machine 2 (step S203). The temperature rise condition output unit 502 then outputs the temperature rise condition calculated by the temperature rise condition calculation unit 501 to the dyeing machine 2 (step S204), and ends the process.
[0048] Fig. 8 is a flowchart showing the learning information generation process according to this embodiment. An operation of the temperature rise condition calculation device 5 generating new learning information will be described with reference to the flowchart shown in Fig. 8. When the temperature rise condition output unit 502 outputs the temperature rise condition to the dyeing machine 2, the learning information generation unit 503 starts executing the learning information generation process. First, as shown in Fig. 8, the learning information generation unit 503 determines whether evaluation information about new dyeing generated by a user of the dyeing machine 2 has been input to the temperature rise condition calculation device 5 (step S301).
[0049] If evaluation information is not input (step S301; NO), the learning information generating unit 503 repeats the process of step S301 until evaluation information is input. If evaluation information is input (step S301; YES), the learning information generating unit 503 generates learning information including the object information, dye information, auxiliary agent information, functional drug information, dyeing machine information, and temperature rise condition information already acquired for the new dyeing, and the newly acquired evaluation information (step S302). Then, the learning information output unit 504 outputs the generated new learning information to the learning information storage device 3 to store it in the learning information storage unit 301 (step S303), and ends the process.
[0050] As described above, according to the dyeing system 1 of the present embodiment, the temperature rise condition calculation unit 501 calculates the temperature rise condition per unit time of the dyeing temperature of the dye liquor when newly dyeing from the type of object to be newly dyed and the type and concentration of the dye used for the new dyeing based on the acquired trained model. In addition, the temperature rise condition output unit 502 outputs the calculated temperature rise condition to the dyeing machine 2. Here, the trained model generation unit 401 generates the trained model using training information including at least object information, dye information, temperature rise condition information, and evaluation information. In other words, the training information used in the machine learning for generating the trained model is information including the type of object, the type and concentration of the dye, the temperature rise condition per unit time of the dyeing temperature of the dye liquor, and the evaluation of the dyed object for each dyeing performed so far. Therefore, if the machine-learned learning information contains a combination that is identical or similar to the combination of the type of object to be newly dyed and the type and concentration of dye used for the new dyeing, the temperature rise condition calculation unit 501 can use the acquired trained model to calculate temperature rise conditions that are identical or similar to the temperature rise conditions contained in the learning information that contains these combinations and in which the dyed object was highly rated.
[0051] In this way, the user of the dyeing machine 2 can calculate the temperature rise conditions using the temperature rise condition calculation device 5 and output them to the dyeing machine 2 by acquiring the object information and dye information every time new dyeing is performed. As a result, the workload can be reduced compared to a user of the dyeing machine 2 who does not use the temperature rise condition calculation device 5 according to the present invention. In addition, by doing so, if a trained model is generated by machine learning using learning information suitable for calculating the temperature rise conditions of the dye liquor when newly dyeing, the evaluation of the object newly dyed with the dye liquor having the dyeing temperature based on the calculated temperature rise conditions can be increased. As a result, the optimum condition for increasing the evaluation of the newly dyed object as the temperature rise condition per unit time of the dyeing temperature can be calculated.
[0052] Here, there are known conventional dyeing machines that can select and set one temperature rise condition from among a plurality of registered temperature rise conditions. In such dyeing machines, the number of registered temperature rise conditions is limited due to the size of the storage area of the storage unit that stores each temperature rise condition, so it was necessary to avoid registering temperature rise conditions that are used infrequently. For example, when a new type of object is dyed in a new dyeing, or when a dye with a new blend is used, there may be little demand in the market and the possibility of repeated dyeing is low. In this case, even if a temperature rise condition suitable for a new dyeing is calculated by evaluation in a laboratory, correction using a design standard, etc., if it is found to be a temperature rise condition that is used infrequently after the calculation, not only may the calculated temperature rise condition not be registered, but the existing registered temperature rise condition may be selected for dyeing. For this reason, the user of the dyeing machine has to calculate or determine a temperature rise condition that may not actually be applied in a new dyeing or may not be registered in the dyeing machine every time a new dyeing is performed, which causes a problem of a large redundant workload.
[0053] In contrast, in the dyeing system 1 according to the present embodiment, the user of the dyeing machine can calculate the temperature rise conditions using the temperature rise condition calculation device and output them to the dyeing machine every time new dyeing is performed as described above. Therefore, regardless of the limit on the number of registered temperature rise conditions in the dyeing machine 2, the frequency of subsequent use of the calculated temperature rise conditions, etc., appropriate temperature rise conditions can be automatically calculated and automatically set in the dyeing machine 2 every time new dyeing is performed. As a result, the workload can be reduced compared to a user of the dyeing machine 2 who does not use the temperature rise condition calculation device 5 according to the present invention.
[0054] Moreover, according to the dyeing system 1 of the present embodiment, the trained model generating unit 401 generates a trained model using training information including dyeing machine information. That is, the training information used for machine learning to generate the trained model is information further including the type of dyeing machine 2 for each dyeing for all dyeing performed so far. Therefore, if the machine-learned training information includes a combination that is identical or similar to the combination of the type of object to be newly dyed, the type and concentration of the dye used for the new dyeing, and the type of the dyeing machine 2, the temperature rise condition calculating unit 501 can calculate, using the acquired trained model, a temperature rise condition that is identical or similar to the temperature rise condition included in the training information that includes these combinations and that has a high evaluation of the dyed object.
[0055] In this way, the user of the dyeing machine 2 can obtain object information, dye information, and dyeing machine information each time new dyeing is performed, and can use the temperature rise condition calculation device 5 to calculate the temperature rise conditions and output them to the dyeing machine 2. In addition, in this way, it is easier to give a higher evaluation to an object newly dyed with a dye solution having a dyeing temperature based on the calculated temperature rise conditions than with a temperature rise condition calculation device in which the temperature rise conditions are calculated based on a trained model generated using training information that does not include dyeing machine information.
[0056] In addition, as in this embodiment, in order to make it easier to improve the evaluation of newly dyed objects, it is preferable to generate a trained model using learning information that includes dyeing machine information. However, as long as the learning information includes object information and dye information, it is not necessary to generate a trained model using learning information that includes dyeing machine information.
[0057] Moreover, according to the dyeing system 1 of the present embodiment, the trained model generating unit 401 generates a trained model using training information including auxiliary information. That is, the training information used for machine learning to generate the trained model is information further including the type and concentration of auxiliary for each dyeing for all dyeing performed so far. Therefore, if the machine-learned training information includes a combination that is identical or similar to the combination of the type of object to be newly dyed, the type and concentration of the dye used in the new dyeing, and the type and concentration of the auxiliary, the temperature rise condition calculating unit 501 can calculate, using the acquired trained model, a temperature rise condition that is identical or similar to the temperature rise condition included in the training information that includes these combinations and that has a high evaluation of the dyed object.
[0058] In this way, the user of the dyeing machine 2 can obtain object information, dye information, and auxiliary information each time new dyeing is performed, and can use the temperature rise condition calculation device 5 to calculate the temperature rise conditions and output them to the dyeing machine 2. In addition, in this way, it is easier to give a higher evaluation to an object newly dyed using an auxiliary in a dye liquor with a dyeing temperature based on the calculated temperature rise conditions than with a temperature rise condition calculation device in which the temperature rise conditions are calculated based on a trained model generated using training information that does not include auxiliary information.
[0059] In addition, as in this embodiment, in order to make it easier to evaluate newly dyed objects highly, it is preferable to generate a trained model using learning information that includes auxiliary agent information. However, as long as the learning information includes object information and dye information, it is not necessary to generate a trained model using learning information that includes auxiliary agent information.
[0060] Here, in order to impart flame retardancy to a dyed object, a flame retardant was mixed into the dye solution and dyed in a single bath, and the inventors confirmed through testing that this had an effect on the dyeing speed, etc. In addition, the functional agent used to impart functionality during dyeing is not limited to a flame retardant used to impart flame retardancy, and may be, for example, an antibacterial agent used to impart antibacterial properties, or a water absorbing agent used to impart water absorption properties. Therefore, in order to calculate the temperature rise conditions, it is necessary to take into account the type and concentration of the functional agent, just like the auxiliary agent.
[0061] In contrast, according to the dyeing system 1 of the present embodiment, the trained model generating unit 401 generates a trained model using training information including functional drug information. That is, the training information used for machine learning to generate the trained model is information further including the type and concentration of the functional drug for each dyeing for all dyeing performed so far. Therefore, if the machine-learned training information includes a combination that is identical or similar to the combination of the type of object to be newly dyed, the type and concentration of the dye used for the new dyeing, and the type and concentration of the functional drug, the temperature rise condition calculating unit 501 can calculate, using the acquired trained model, a temperature rise condition that is identical or similar to the temperature rise condition included in the training information that includes these combinations and in which the dyed object was highly rated.
[0062] In this way, the user of the dyeing machine 2 can obtain object information, dye information, and functional drug information each time new dyeing is performed, and can use the temperature rise condition calculation device 5 to calculate the temperature rise conditions and output them to the dyeing machine 2. In addition, in this way, it is easier to improve the evaluation of a newly dyed object by using functional drug information in a dye solution with a dyeing temperature based on the calculated temperature rise conditions, compared to a temperature rise condition calculation device in which the temperature rise conditions are calculated based on a trained model generated using training information that does not include functional drug information.
[0063] In addition, as in this embodiment, in order to make it easier to improve the evaluation of newly dyed objects, it is preferable to generate a trained model using learning information including functional drug information, but as long as the learning information includes object information and dye information, it is not necessary to generate a trained model using learning information including functional drug information.
[0064] Furthermore, according to the dyeing system 1 of the present embodiment, the learning information generating unit 503 generates learning information for the new dyeing when evaluation information for new dyeing is input by the user of the dyeing machine 2. Then, the learning information output unit 504 outputs the generated new learning information to the learning information storage device 3 to store it in the learning information storage unit 301.
[0065] In this way, new learning information including an evaluation of the dyed object when new dyeing is performed under the calculated temperature rise conditions can be generated and fed back as new learning information to be used in machine learning. In addition, in this way, the trained model generation unit 401 can update the trained model by machine learning further using the fed back new learning information. As a result, it is possible to more easily calculate appropriate temperature rise conditions that result in a higher evaluation of the dyed object than a trained model generation device that does not update the trained model by machine learning further using the fed back new learning information.
[0066] Furthermore, according to the dyeing system 1 of this embodiment, the trained model generation unit 401 generates a trained model by machine learning using the learning information stored in the learning information storage unit 301.
[0067] In this way, the trained model generating device 4 can learn the relationship between the type of dyed object, the type and concentration of the dye used in dyeing, the type and concentration of the auxiliary used in dyeing, the type and concentration of the functional agent used to impart functionality, the type of dyeing machine 2, the temperature rise conditions when the object was dyed, and the evaluation of the dyed object. Also, in this way, the trained information storage device 3 can store the trained information for each dyeing for all dyeing performed so far.
[0068] In this embodiment, the trained model generation device 4 includes the trained model generation unit 401 and the trained model storage unit 402, but is not limited thereto. For example, the temperature rise condition calculation device 5 may include the trained model generation unit 401 and the trained model storage unit 402. In this case, the temperature rise condition calculation device 5 needs to have a computational processing capability for generating a trained model by machine learning using the learning information stored in the learning information storage unit 301. For this reason, for example, the temperature rise condition calculation device 5 may be the above-mentioned GPU machine, personal computer, supercomputer, workstation, etc., instead of the client machines 5A1, 5A2, ..., 5An.
[0069] In the present embodiment, the learning information storage device 3 includes the learning information storage unit 301, but is not limited thereto. For example, the trained model generation device 4 may include the learning information storage unit 301. That is, the trained model generation device 4 may be a database server integrated with the learning information storage device 3. Also, for example, the temperature rise condition calculation device 5 may include the learning information storage unit 301. That is, the temperature rise condition calculation device 5 used by the user of the dyeing machine 2 may have the function of the database of the learning information storage device 3. In these cases, the trained model generation device 4 or the temperature rise condition calculation device 5 needs to include a large-capacity storage device having a storage area capable of storing the learning information for each dyeing for all dyeing performed so far.
[0070] In this embodiment, the dyeing system 1 includes a dyeing machine 2, a learning information storage device 3, a trained model generation device 4, and a temperature rise condition calculation device 5, but is not limited to this. For example, the dyeing system 1 may include a dyeing machine 2 and a temperature rise condition calculation device 5, and the temperature rise condition calculation device 5 may further include a learning information storage unit 301, a trained model generation unit 401, and a trained model storage unit 402.
[0071] In this embodiment, the types of objects indicated by the object information are exemplified as "Fabric A," "Fabric B," ..., and "Object N" as shown in FIG. 4. However, the types of objects are not limited to fabrics and may be other dyeable materials such as loose wool, thread, cotton, knitted fabric, and woven fabric.
[0072] In this embodiment, the object information is information including the type of object, but it may also be information including, for example, the width, length, thickness, weight per unit area (so-called basis weight), the type of material yarn and the mixed ratio and thickness of the yarn, etc.
[0073] In this embodiment, the dye information is information including the type and concentration of the dye, but may be information including, for example, the type of dye material and the mixed ratio, etc. The auxiliary information is information including the type and concentration of the auxiliary, but may be information including, for example, the type of auxiliary material and the mixed ratio, etc. The functional drug information is information including the type and concentration of the functional drug, but may be information including, for example, the type of functional drug material and the mixed ratio, etc.
[0074] In addition, as in the present embodiment, in order to easily calculate an appropriate temperature rise condition that will give a high evaluation to the dyed object, the auxiliary information is preferably information including the concentration of the auxiliary, but the auxiliary information may be information that does not include the concentration of the auxiliary. That is, the learning information used in the machine learning to generate the trained model may be information including the type of object, the type and concentration of the dye, the type of auxiliary, the temperature rise condition per unit time of the dyeing temperature of the dye solution, and the evaluation of the dyed object for each dyeing performed so far. In this case, if the machine-learned learning information includes a combination that is identical or similar to the combination of the type of object to be newly dyed, the type and concentration of the dye, and the type of auxiliary used in the new dyeing, the temperature rise condition calculation unit 501 can calculate, using the acquired trained model, a temperature rise condition that is identical or similar to the temperature rise condition included in the learning information that includes these combinations and gave a high evaluation to the dyed object.
[0075] In addition, as in the present embodiment, in order to easily calculate an appropriate temperature rise condition that will give a high evaluation to the dyed object, the functional drug information is preferably information including the concentration of the functional drug, but the functional drug information may be information that does not include the concentration of the functional drug. That is, the learning information used in the machine learning to generate the trained model may be information including the type of object, the type and concentration of the dye, the type of functional drug, the temperature rise condition per unit time of the dyeing temperature of the dye solution, and the evaluation of the dyed object for each dyeing performed so far. In this case, if the machine-learned learning information includes a combination that is identical or similar to the combination of the type of object to be newly dyed, the type and concentration of the dye used in the new dyeing, and the type of functional drug, the temperature rise condition calculation unit 501 can calculate, using the acquired trained model, a temperature rise condition that is identical or similar to the temperature rise condition included in the learning information that includes these combinations and gave a high evaluation to the dyed object.
[0076] In this embodiment, the dyeing machine information includes the type of dyeing machine 2. However, the dyeing machine information may further include, for example, a bath ratio, which is the weight ratio of dye to the object to be dyed, a pass time, which is the time it takes for the object to be dyed to pass through the dyeing machine 2, and the pressure of the nozzle through which the dye liquid is sprayed.
[0077] In this embodiment, the learning information is information that includes object information, dye information, auxiliary information, functional drug information, dyeing machine information, temperature rise condition information, and evaluation information. However, for example, the learning information may be information that further includes customer information indicating the name, industry, purchase quantity, etc. of the customer who purchases the dyed object.
[0078] In this embodiment, the evaluation information is information showing a two-level evaluation of "○" or "×", but may be information showing an evaluation of three or more levels. For example, it may be information showing an evaluation of four levels of "excellent", "good", "fair", and "poor".
[0079] In this embodiment, after new dyeing is performed, the user of the dyeing machine 2 visually evaluates the dyed object and inputs the generated evaluation information to the temperature rise condition calculation device 5, but this is not limited to this. For example, the dyed object may be automatically evaluated by the dyeing machine 2 or a newly installed evaluation device, and the generated evaluation information may be automatically input to the temperature rise condition calculation device 5. In this case, the dyeing machine 2 or the newly installed evaluation device must have a function of automatically evaluating the dyed object by image analysis processing. For example, the dyeing machine 2 or the evaluation device may be equipped with a camera and an image determination unit, and the camera may capture the dyed object, and the image determination unit may determine whether or not there is uneven dyeing based on the color of each pixel specified from the image of the object after dyeing acquired, or determine whether or not the object is dyed with a preset color. In addition, when the evaluation of the dyed object is automated, the dyeing machine 2 may output the generated evaluation information to the temperature rise condition calculation device 5 when generating evaluation information indicating an evaluation of "x", and then suspend dyeing until acquiring newly calculated temperature rise conditions based on a trained model updated by machine learning using the new learning information fed back. In addition, at this time, the dyeing machine 2 may also output request information for outputting new temperature rise conditions when outputting the evaluation information to the temperature rise condition calculation device 5. In this way, the dyeing machine 2 can also automate the process of resetting new temperature rise conditions and resuming dyeing.
[0080] In addition, as in the present embodiment, in order to easily calculate appropriate temperature rise conditions that will give a high evaluation to the dyed object, the learning information is preferably information including evaluation information, but as long as the learning information includes object information, dye information, and temperature rise condition information, it may be information that does not include evaluation information. That is, the learning information used in machine learning to generate the trained model may be information including the type of object, the type and concentration of dye, and the temperature rise condition per unit time of the dyeing temperature of the dye solution for each dyeing performed so far for all dyeing performed so far. In this case, if the trained model generation unit 401 generates a trained model using only the learning information in which the evaluation of the dyed object was high, and the combination that is the same as or similar to the combination of the type of object to be newly dyed and the type and concentration of the dye used for the new dyeing is included in the machine-learned learning information, the temperature rise condition calculation unit 501 can calculate, by the acquired trained model, a temperature rise condition that is the same as or similar to the temperature rise condition included in the learning information including these combinations.
[0081] The core part of the temperature rise condition calculation device 5, which includes the control unit 51, the main memory unit 52, the external memory unit 53, the operation unit 54, the display unit 55, the transmission / reception unit 56, the internal bus 50, etc., can be realized by using a normal computer system, not a dedicated system. For example, the temperature rise condition calculation device 5 that executes the above-mentioned processing may be configured by distributing a computer program stored in a recording medium readable by the temperature rise condition calculation device 5, such as a flexible disk or a DVD-ROM (Read-Only Memory), and installing the computer program on a computer. Alternatively, the temperature rise condition calculation device 5 may be configured by storing the computer program in a storage device of a server device on a communication network such as the Internet, and downloading the computer program by a normal computer system.
[0082] Furthermore, when the functions of the temperature rise condition calculation device 5 are realized by sharing between an OS (operating system) and an application program, or by cooperation between the OS and an application program, only the application program portion may be stored in a recording medium or storage device.
[0083] It is also possible to superimpose a computer program on a carrier wave and provide it via a communication network. For example, the computer program may be posted on a bulletin board system (BBS) on the communication network and provided via the network. The computer program may then be started and executed under the control of the OS in the same way as other application programs, thereby executing the above-mentioned processing.
[0084] In addition, the configurations of the temperature rise condition calculation device 5, the dyeing system 1, the temperature rise condition calculation method, and the program according to the present embodiment are merely examples, and can be changed and modified as desired as long as the problem to be solved by the present invention can be solved.
[0085] The present invention allows various embodiments and modifications without departing from the broad spirit and scope of the present invention. The above-described embodiments are for the purpose of explaining the present invention and do not limit the scope of the present invention. In other words, the scope of the present invention is indicated by the claims, not the embodiments. Various modifications made within the scope of the claims and the scope of the invention equivalent thereto are considered to be within the scope of the present invention.
[0086] This application is based on Japanese Patent Application No. 2019-165897, filed on September 12, 2019. The entire specification, claims, and drawings of Japanese Patent Application No. 2019-165897 are incorporated herein by reference. [Explanation of symbols]
[0087] 1 Dyeing system, 2 Dyeing machine, 3 Learning information storage device, 4 Learned model generation device, 5 Heating condition calculation device, 5A1, 5A2, ..., 5An Client machine, 50 Internal bus, 51 Control unit, 52 Main memory unit, 53 External memory unit, 54 Operation unit, 55 Display unit, 56 Transmitting / receiving unit, 59 Control program, 201 Heating condition setting unit, 301 Learning information storage unit, 401 Learned model generation unit, 402 Learned model storage unit, 501 Heating condition calculation unit, 502 Heating condition output unit, 503 Learning information generation unit, 504 Learning information output unit.
Claims
1. a temperature rise condition calculation unit that calculates the temperature rise condition per unit time of the dyeing temperature of the dye liquor when newly dyeing from the type of object to be newly dyed, the type and concentration of the dye used in the new dyeing, and the type of dyeing machine that will perform the new dyeing, based on a trained model generated by machine learning using learning information including object information indicating the type of dyed object, dye information indicating the type and concentration of the dye used in the dyeing, dyeing machine information indicating the type of dyeing machine that performed the dyeing, and temperature rise condition information indicating the temperature rise condition per unit time of the dyeing temperature of the dye liquor when the object is dyed; a temperature rise condition output unit that outputs the temperature rise condition calculated by the temperature rise condition calculation unit to a dyeing machine that performs new dyeing; A temperature rise condition calculation device comprising:
2. The learning information further includes auxiliary information indicating the type and concentration of an auxiliary used in dyeing the object, The temperature rise condition calculation unit calculates a temperature rise condition when newly dyeing from the type of object to be newly dyed, the type and concentration of dye used for the new dyeing, the type of dyeing machine to perform the new dyeing, and the type and concentration of auxiliary agent to be used for the new dyeing, based on the trained model. The temperature rise condition calculation device according to claim 1 .
3. The learning information further includes functional agent information indicating the type and concentration of a functional agent used to impart functionality when the object is dyed, The temperature rise condition calculation unit calculates a temperature rise condition when the object is newly dyed based on the learned model from the type of object to be newly dyed, the type and concentration of the dye used for the new dyeing, the type of dyeing machine to perform the new dyeing, and the type and concentration of the functional agent used to impart functionality during the new dyeing. The temperature rise condition calculation device according to claim 1 .
4. The learning information further includes functional agent information indicating the type and concentration of a functional agent used to impart functionality when dyeing the object, The temperature rise condition calculation unit calculates a temperature rise condition for new dyeing based on the learned model from the type of object to be newly dyed, the type and concentration of dye used for the new dyeing, the type of dyeing machine to perform the new dyeing, the type and concentration of auxiliary agent used for the new dyeing, and the type and concentration of functional agent used for imparting functionality during the new dyeing. The temperature rise condition calculation device according to claim 2 .
5. Further comprising a trained model generation unit that generates the trained model by machine learning using the learning information. The temperature rise condition calculation device according to any one of claims 1 to 4.
6. a learning information storage unit for storing learning information including object information indicating the type of the dyed object, dye information indicating the type and concentration of the dye used in the dyeing, dyeing machine information indicating the type of dyeing machine used in the dyeing, and temperature rise condition information indicating the temperature rise condition per unit time of the dyeing temperature of the dye solution when the object is dyed; a trained model generation unit that generates a trained model by machine learning using the training information stored in the training information storage unit; A temperature rise condition calculation unit that calculates a temperature rise condition per unit time of the dyeing temperature of the dye liquor when newly dyeing based on the type of object to be newly dyed, the type and concentration of the dye used for the new dyeing, and the type of dyeing machine to perform the new dyeing, based on the trained model generated by the trained model generation unit; a temperature rise condition output unit that outputs the temperature rise conditions calculated by the temperature rise condition calculation unit; a dyeing machine that performs new dyeing at a dyeing temperature based on the temperature rise conditions output by the temperature rise condition output unit; A dyeing system comprising:
7. a temperature rise condition calculation step of calculating the temperature rise condition per unit time of the dyeing temperature of the dye liquor when newly dyeing from the type of object to be newly dyed, the type and concentration of the dye used in the new dyeing, and the type of dyeing machine that will perform the new dyeing, based on a trained model generated by machine learning using learning information including object information indicating the type of the dyed object, dye information indicating the type and concentration of the dye used in the dyeing, dyeing machine information indicating the type of dyeing machine that performed the dyeing, and temperature rise condition information indicating the temperature rise condition per unit time of the dyeing temperature of the dye liquor when the object is newly dyed; a temperature rise condition output step of outputting the temperature rise condition calculated in the temperature rise condition calculation step to a dyeing machine that performs new dyeing; A method for calculating temperature rise conditions, including:
8. Computer, a temperature rise condition calculation unit that calculates the temperature rise condition per unit time of the dyeing temperature of the dye liquor when the object is newly dyed from the type of object to be newly dyed, the type and concentration of the dye used in the new dyeing, and the type of dyeing machine that will perform the new dyeing, based on a trained model generated by machine learning using learning information including object information indicating the type of the dyed object, dye information indicating the type and concentration of the dye used in the dyeing, dyeing machine information indicating the type of dyeing machine that performed the dyeing, and temperature rise condition information indicating the temperature rise condition per unit time of the dyeing temperature of the dye liquor when the object is newly dyed; a temperature rise condition output unit that outputs the temperature rise condition calculated by the temperature rise condition calculation unit to a dyeing machine that performs new dyeing; A program that functions as a
Citation Information
Patent Citations
Wet cloth thermal molding process real-time temperature estimation method
CN108038256A
Dyeing apparatus and dyeing method
JP1993098557A
Collision sensor
JP1994055992A
Method for dyeing fiber material
JP2009249797A
Method for treating fibrous material
JP2010242232A
