JP2021082637A - Rework condition learning device, rework condition determination device, and rework device - Google Patents

Abstract

To provide a rework condition learning device for learning a set value which is a condition of re-machining to be performed on a rework object, and also provide a rework condition determination device using the same, and a rework device.SOLUTION: Disclosed is a rework condition learning device for learning a set value which is a condition for re-machining a rework object. This learning device includes: a set value input part into which a set value associated with a rework object for each device for re-machining is inputted; a good/defective determination result input part into which a good/defective determination result of a good or defective article of the rework object reworked by the set value inputted into the set value input part is inputted; and a learning part for leaning the set value which makes the good article for each rework object based on the set value and the good/defective determination result.SELECTED DRAWING: Figure 1

Description

The present invention relates to a rework condition learning device for learning a set value which is a condition for reworking to be performed on a rework target, a rework condition determining device using the rework condition learning device, and a rework device.

Conventionally, some rework devices (repair devices) that perform rework on a rework target heat solder to remove electronic components from the substrate to be reworked (see, for example, Patent Documents 1 and 2). .. Further, some rework devices (repair devices) attach an alternative electronic component after removing the electronic component from the substrate (see, for example, Patent Document 3).

On the other hand, there is a model in which a learning model by machine learning using AI (Artificial Intelligence) or the like is applied to a rework device (repair device) (see, for example, Patent Document 4). Patent Document 4 discloses that a learning model (sequential learning) is used for determining a non-defective product and a defective product, and discloses that a rework device (repair device) displays a defective part and a defective content as a determination result. Has been done.

Japanese Unexamined Patent Publication No. 2018-148532 Japanese Unexamined Patent Publication No. 2005-223000 Japanese Unexamined Patent Publication No. 2006-179556 Japanese Unexamined Patent Publication No. 2008-185395

However, in the conventional rework device, it is necessary to input the set value which is the condition of the rework to remove or attach the target part for each rework target to be reworked, and the yield depends on the skill of the person who inputs it. There was a problem that it had an impact.

The present invention has been made to solve the above-mentioned problems, and is a rework condition learning device that learns a set value which is a condition of rework performed on a rework target for each rework target. It is an object of the present invention to obtain a rework condition determination device and a rework device using the above.

The rework condition learning device according to the present invention, the rework condition determining device and the rework device using the rework condition learning device are set as the reworking conditions for removing or attaching the target parts to the reworking target in the reworking condition learning device. The value is learned, and for each device to be reworked, a set value input unit for inputting the set value associated with the rework target and the setting input to the set value input unit are used. The rework target is based on the good / bad judgment result input unit in which the good / bad judgment result of the good or bad product of the rework target reprocessed according to the value is input, and the set value and the good / bad judgment result. It is characterized in that it is provided with a learning unit for learning the set value, which is a good product for each.

The rework condition learning device according to the present invention is a rework condition learning device that learns a set value which is a removal condition for removing the target part from a rework target to which the target part is attached by soldering to the work target. For each device to be reworked, the set value input unit for inputting the set value associated with the rework target and the rework reworked by the set value input to the set value input unit. Based on the good / bad judgment result input unit in which the good / bad judgment result of the target non-defective product or defective product is input, and the set value and the good / bad judgment result, the set value that becomes a good product for each rework target is set. It is characterized by having a learning unit for learning.

The rework condition learning device according to the present invention is a rework condition learning device that learns a set value which is an attachment condition for attaching a new target part to a rework target from which the target part has been removed, and is a rework condition learning device for each device that performs rework. In addition, a set value input unit in which the set value is input, which is associated with the rework target, and a non-defective product or a defective product of the reprocess target reprocessed by the set value input in the set value input unit. A good / bad judgment result input unit for inputting a good / bad judgment result, and a learning unit for learning the set value which is a good product for each rework target based on the set value and the good / bad judgment result. It is characterized by being prepared.

The rework condition determining device according to the present invention is a rework condition learning device that learns a set value which is a removal condition for removing the target part from a rework target to which the target part is attached by soldering to the work target. For each device to be reworked, the set value input unit for inputting the set value associated with the rework target and the rework reworked by the set value input to the set value input unit. Based on the good / bad judgment result input unit in which the good / bad judgment result of the target non-defective product or defective product is input, and the set value and the good / bad judgment result, the set value that becomes a good product for each rework target is set. It is a rework condition determination device using the learning result of the rework condition learning device provided with the learning unit to be learned, and the rework target input unit into which the information of the rework target is input and the learning result of the learning unit are input. It is characterized in that it is provided with a rework condition determination unit for determining the set value at which the rework target is a non-defective product whose information is input to the rework target input unit.

The rework condition determining device according to the present invention is a rework condition learning device that learns a set value which is an attachment condition for attaching a new target part to a rework target from which the target part has been removed, and is a device for performing rework. In addition, a set value input unit in which the set value is input, which is associated with the rework target, and a non-defective product or a defective product of the reprocess target reprocessed by the set value input in the set value input unit. A good / bad judgment result input unit for inputting a good / bad judgment result, and a learning unit for learning the set value which is a good product for each rework target based on the set value and the good / bad judgment result. It is a rework condition determination device using the learning result of the rework condition learning device provided, and the reworking is performed by using the reworking target input unit in which the information of the reworking target is input and the learning result of the learning unit. It is characterized by including a rework condition determining unit for determining the set value at which the rework target for which information is input is a non-defective product in the target input unit.

The rework device according to the present invention is a rework condition learning device that learns a set value which is a removal condition for removing the target part from a rework target to which the target part is attached by soldering to the work target, and is a rework condition learning device. For each device that performs the reworking, the set value input unit for inputting the set value associated with the rework target and the rework target reworked by the set value input to the set value input unit. Based on the good / bad judgment result input unit in which the good / bad judgment result of the good product or the defective product is input, and the set value and the good / bad judgment result, the set value that becomes a good product is learned for each rework target. It is a rework condition determination device using the learning result of the rework condition learning device provided with the learning unit, and uses the rework target input unit into which the information of the rework target is input and the learning result of the learning unit. A rework device using a rework condition determination device including a rework condition determination unit for determining the set value for which information is input to the rework target input unit and the rework target is a non-defective product. Removal unit that controls the removal unit so as to remove the target component under the conditions input to the removal unit, the condition setting unit that is input to the set value determined by the rework condition determination unit, and the condition setting unit. It is characterized by having a part.

The rework device according to the present invention is a rework condition learning device that learns a set value which is an attachment condition for attaching a new target part to a rework target from which the target part has been removed, and is a rework condition learning device for each device to be reworked. A set value input unit in which the set value is input, which is associated with the rework target, and a good or defective product of the reprocess target reprocessed by the set value input in the set value input unit. It is provided with a good / bad judgment result input unit for inputting a defective judgment result, and a learning unit for learning the set value which is a good product for each rework target based on the set value and the good / bad judgment result. It is a rework condition determination device using the learning result of the rework condition learning device, and the rework target input unit in which the information of the rework target is input and the rework target input unit using the learning result of the learning unit are used. A rework device using a rework condition determination device including a rework condition determination unit for determining the set value at which the information is input to the unit and the rework target is a non-defective product. The condition setting unit in which the set value determined by the rework condition determination unit is input and the soldering unit are controlled so as to solder a new target component under the conditions input to the condition setting unit. It is characterized by being provided with a soldering control unit.

According to the present invention, it is possible to obtain a rework condition learning device capable of learning a set value which is a non-defective product for each rework target, a rework condition determining device using the rework condition learning device, and a rework device.

It is a functional block diagram of the rework condition learning apparatus which concerns on Embodiment 1 of this invention. It is a flowchart explaining operation (rework condition learning method) of the rework condition learning apparatus which concerns on Embodiment 1 of this invention. It is a functional block diagram of the rework condition learning apparatus, the rework condition determination apparatus, and the rework apparatus which concerns on Embodiment 1 of this invention. It is a flowchart explaining operation (rework condition determination method) of the rework condition determination apparatus which concerns on Embodiment 1 of this invention. It is a flowchart explaining operation (rework method) of the rework apparatus which concerns on Embodiment 1 of this invention. It is a flowchart explaining operation (rework method) of the rework apparatus which concerns on Embodiment 1 of this invention. It is a functional block diagram of the rework condition learning apparatus which concerns on Embodiment 2 of this invention. It is a flowchart explaining operation (rework condition learning method) of the rework condition learning apparatus which concerns on Embodiment 2 of this invention. It is a functional block diagram of the rework condition learning apparatus which concerns on Embodiment 3 of this invention. It is a flowchart explaining operation (good or bad method) of the rework condition learning apparatus which concerns on Embodiment 3 of this invention. It is a functional block diagram of the rework condition learning apparatus, the rework condition determination apparatus, and the rework apparatus which concerns on Embodiment 3 of this invention. It is a functional block diagram of the rework condition learning apparatus which concerns on Embodiment 4 of this invention. It is a flowchart explaining operation (rework condition learning method) of the rework condition learning apparatus which concerns on Embodiment 4 of this invention. It is a functional block diagram of the rework condition learning apparatus, the rework condition determination apparatus, and the rework apparatus which concerns on Embodiment 4 of this invention. It is a functional block diagram of the rework condition learning apparatus, the rework condition determination apparatus, and the rework apparatus which concerns on Embodiment 4 of this invention. It is a flowchart explaining operation (rework condition determination method) of the rework condition determination apparatus which concerns on Embodiment 4 of this invention. It is a flowchart explaining operation (rework method) of the rework apparatus which concerns on Embodiment 4 of this invention. It is a flowchart explaining operation (rework method) of the rework apparatus which concerns on Embodiment 4 of this invention. It is a functional block diagram of the rework condition learning apparatus which concerns on Embodiment 5 of this invention. It is a flowchart explaining operation (rework condition learning method) of the rework condition learning apparatus which concerns on Embodiment 5 of this invention. It is a functional block diagram of the rework condition learning apparatus which concerns on Embodiment 6 of this invention. It is a flowchart explaining operation (good or bad method) of the rework condition learning apparatus which concerns on Embodiment 6 of this invention. It is a functional block diagram of the rework condition learning apparatus, the rework condition determination apparatus, and the rework apparatus which concerns on Embodiment 6 of this invention. It is a functional block diagram of the rework condition learning apparatus, the rework condition determination apparatus, and the rework apparatus which concerns on Embodiment 6 of this invention.

The present application is a rework condition learning device that learns a set value that is a condition for reworking to remove or attach a target part to a rework target 1, a rework condition determination device and a rework device (rework condition learning) using the set value. It relates to a method, a method for determining rework conditions using the method, and a rework method). The set values that are the conditions for reworking are the set values that are the removal conditions for removing the target part from the rework target 1 and the setting values that are the mounting conditions for attaching a new target part to the rework target from which the target part has been removed. It is a value. Specifically, the former is a set value which is a removal condition for removing the target part from the rework target 1 in which the target part is attached to the work target by soldering. The latter is a set value which is an attachment condition for attaching a new target component to the rework target 1 from which the soldered target component has been removed.

A rework condition learning device that learns the set value, which is a removal condition for removing the target part, from the former rework target 1 to which the target part is attached by soldering to the machining target, a rework condition determination device using this, and a rework condition determination device. The rework device (rework condition learning method, rework condition determination method and rework method using the rework condition learning method) will be described in the first to third embodiments.

The latter, a rework condition learning device that learns the set value that is the mounting condition for attaching a new target part to the rework target 1 from which the soldered target part has been removed, a rework condition determination device and a rework device that use this. (Rework condition learning method, rework condition determination method and rework method using the same) will be described in the fourth to sixth embodiments. It should be noted that the fourth to sixth embodiments include not only the case of learning only the set value which is the attachment condition but also the case of learning the set value which is the removal condition corresponding to the former.

That is, the rework device is a device that performs rework. Rework (rework) is rework (rework) in which the target part is removed from the rework target 1 to which the target part is attached by soldering to the work target, or rework target in which the soldered target part is removed. It refers to at least one of reworking in which a new target part is attached to 1.

Embodiment 1.
Hereinafter, the rework condition learning device according to the first embodiment of the present invention, the rework condition determining device and the rework device using the rework condition learning device will be described with reference to FIGS. 1 to 6. In the figure, the same reference numerals indicate the same or corresponding parts, and detailed description thereof will be omitted. In FIG. 3, the rework target 1 is, for example, a substrate 1 such as a printed circuit board, and includes a single-layer substrate and a multilayer substrate. A printed wiring board, a printed wiring board, a printed circuit board, or a printed circuit board may be obtained by soldering wiring or parts (target parts) to the printed circuit board. A printed circuit board with wiring may be simply called a printed wiring board or a printed wiring board. In this case, it can be said that the rework target 1 (board 1) includes the printed wiring board and the printed wiring board. The substrate 1 may be referred to as a processing target. Further, the rework target 1 (board 1) is targeted by the first solder information (first solder condition) of the first solder printed on the rework target 1, the parts to be soldered, and the soldering. It can be said that the parts are composed of members to which they are fixed.

The target parts include electronic parts and analog parts, and the leads and terminals are fixed to the processing target by soldering by reflow. The members to which the target component is fixed are the above-mentioned printed circuit board, printed wiring board, and printed wiring board, and solder is formed on the surface by printing or the like. Leads and terminals of the target component include those that are inserted into through holes formed in the substrate 1 and fixed by soldering. In summary, the rework target 1 includes a work target, which is a substrate 1, to which a target component is attached by soldering.

In FIGS. 1 and 3, the rework condition learning device 2 has a setting condition input unit 3, a good / bad determination result input unit 4, and a learning unit 5. In FIG. 3, the rework portion 6 (removal portion 6a in the first embodiment) removes the target component from the rework target 1 to which the target component is attached by soldering to the machining target. The removing portion 6a has, for example, a heating portion (blower portion) and a removing portion (adsorption portion). The heating unit heats the joint portion of the target component of the rework target 1 with hot air or the like. The removing unit removes the target part from the rework target 1 by sucking the target part with a suction nozzle or the like. The removing portion 6a may include a cooling portion for cooling the rework target 1 heated by the heating portion. The rework condition learning device 2 learns a set value which is a removal condition for removing the target part from the rework target 1 to which the target part is attached by soldering to the machining target, and builds a learning model.

Subsequently, in FIGS. 1 and 3, the good / bad determination result input unit 4 is a non-defective product or non-defective product of the rework target 1 that has been reworked according to the set value (set value as the removal condition) input to the set value input unit 3. The quality judgment result of a non-defective product is input. In the quality / defect determination result input unit 4, the quality / defect determination result initially input is, for example, an visual inspection (by a person or a machine) of a printed circuit board (printed circuit board) which is a rework target 1 after being reprocessed. It is a data of the results of inspections including inspections). That is, the result of the visual inspection (inspection including inspection by a person or a machine) may be converted into data and associated with the processed set value (set value input to the set value input unit 3) of the rework target 1. The visual inspection referred to here is an inspection (determination) of the quality of the rework target 1 to which the target component is attached by soldering to the machining target from the appearance after the target component is removed. The learning unit 5 learns a set value that is a non-defective product for each rework target 1 based on the set value and the good / bad determination result. Based on the set value input to the setting condition input unit 3 and the good / bad judgment result input to the good / bad judgment result input unit 4, the learning unit 5 sets a set value to be a good product for each rework target 1. It is something to learn.

Machine learning such as AI may be applied to the learning unit 5 (rework condition learning device 2). The learning unit 5 (rework condition learning device 2) constructs and accumulates a learning model. Preferably, the learning unit 5 may learn by associating the same rework target 1 with a different set value as a non-defective product for each rework device 10 as an error for each rework device 10. Further, as a removal condition, the set value input unit 3 includes the first solder information of the first solder formed on the rework target 1, the soldered target component, and the member to which the target component is fixed by soldering. The set value associated with the rework target 1 defined in the first combination of the heating condition and the cooling condition is input.

Here, the heating condition is a condition for heating the joint portion of the target component of the rework target 1 by the heating portion (blower portion) of the removing portion 6a. For example, the heating temperature, the heating time, the wind speed of hot air, and the like. In order to prevent damage to electronic components due to thermal shock, a profile that uses multi-step heating is often used as the heating temperature profile. The risk of component damage can be reduced by gradually raising the temperature in several stages in the temperature range up to the maximum heating temperature. For example, 150 ° C. for 20 seconds, 180 ° C. for 20 seconds, etc. can be exemplified up to 230 ° C. The cooling condition is a condition in which the cooling portion of the removing portion 6a cools the rework target 1 heated by the heating portion of the removing portion 6a. For example, cooling temperature, cooling time, wind speed of cold air, and the like. It can be said that this is mainly a condition for cooling the portion that was the joint portion of the target part of the rework target 1. Rapid cooling is often performed to stabilize the soldering quality. For example, the temperature lowering rate is about 2 ° C. to 4 ° C./sec. As the heating condition and cooling condition, the temperature and humidity around the rework device 10 or the temperature and humidity of the space (room) in which the rework device 10 is installed may be added to the conditions.

In this case, the set value input unit 3 further adds the first solder information of the first combination to the composition of the first solder, the flux type added to the first solder, and the first solder. The set value associated with the rework target 1 distinguished by at least one of the obtained flux content and the area of the first solder may be input. Similarly, the set value input unit 3 inputs the set value associated with the rework target 1 in which the target component is distinguished by the outer shape or the type of electrode surface treatment in the first combination. It may be. Similarly, the set value input unit 3 is associated with the rework target 1 in which the member is distinguished by at least one of the thickness, the material, the number of layers, the specific gravity, and the type of surface treatment in the first combination. The set value may be input.

That is, the first set value input unit 3 is among the first combination of the first solder information, the soldered target component, the member to which the target component is fixed by soldering, the heating condition, and the cooling condition. , The first solder information and the target component are the same, and the set values when the member conditions, heating conditions, and cooling conditions are changed are input respectively. Further, the second set value input unit 3 is among the first combination of the first solder information, the soldered target component, the member to which the target component is fixed by soldering, the heating condition, and the cooling condition. , The first solder information and the member are the same, and the set values when the conditions of the target parts, the heating conditions, and the cooling conditions are changed are input respectively. Further, the third set value input unit 3 is among the first combination of the first solder information, the soldered target component, the member to which the target component is fixed by soldering, the heating condition, and the cooling condition. , The target parts and members are the same, and the set values when the first solder information (first solder condition), heating condition, and cooling condition are changed are input respectively.

Here, a case where the conditions of the member (rework target 1 for removing the target part) changes and a case where the conditions of the target part change will be described. The change in the conditions of the member means that the thickness, material, number of layers, specific gravity, and type of surface treatment of the member are different as described above. When the member is the substrate 1, the thickness means the specifications of the plate thickness (conductor foil thickness, conductor foil area, number of laminated sheets). In the case of the substrate 1, the material means the base material of the substrate and the conductor type of the conductor foil. Further, changing the conditions of the target component means that the volume, the electrode shape, and the electrode surface treatment are different. Since the shape and size of the target component can be known from the volume and the electrode shape, the volume and the electrode shape of the target component can be said to be information on the outer shape of the target component.

Next, a case where the first solder information (condition of the first solder) is changed will be described. As described above, the first solder information includes the composition of the first solder, the flux type (flux type) added to the first solder, and the content of the flux added to the first solder, for example. This means that the areas of the printed first solders are different. The composition of the first solder may include the flux type (flux type) and the flux content. Further, the printed first solder area refers to the area of the first solder printed on the surface of the rework target 1. The area of the printed first solder also means the printing amount of the printed first solder, and can be said to be the volume of the printed first solder in consideration of the thickness of the first solder. Further, the information (condition) of the printed area of the first solder (the amount of the printed first solder printed) is the information on the position of the printed first solder on the surface of the rework target 1. It may be included, and the information (condition) of the printed area of the first solder (printed amount of the printed first solder) is printed on the surface of the rework target 1 of the first solder. The location information itself may be used.

So far, the case where two of the first combination of the first solder information, the part to be soldered, the member to which the target part is fixed by soldering, the heating condition, and the cooling condition are fixed has been described. , All combinations may be covered, or among the first combination of the first solder information, the target part to be soldered, the member to which the target part is fixed by soldering, the heating condition, and the cooling condition. One may be fixed. That is, the set value input unit 3 has the composition of the first solder printed on the rework target 1, the flux type added to the first solder, the flux content added to the first solder, and the first. At least one of the soldering areas, the outer shape of the part to be soldered, or the surface treatment of the electrodes, the thickness, material, number of layers, specific gravity, and type of surface treatment of the member to which the target part is fixed by soldering. At least one of the above, at least one of the heating conditions or the cooling conditions, and the set value (set value as the removal condition) associated with the rework target 1 defined in the first combination is input. It can be said that.

This is the composition of the solder printed on the rework target 1, the flux type added to the solder, the flux content added to the solder, at least one from the solder area, the outer shape of the part to be soldered, or One of the electrode surface treatments (volume of the target part to be soldered, electrode shape, at least one from the electrode surface treatment), thickness, material, number of layers, specific gravity, surface treatment of the member to which the target part is fixed by soldering The above-mentioned set value is input, which is associated with at least one of the above types and is associated with the rework target 1 defined by at least one first combination of heating conditions or cooling conditions. As a result, the set values that can be supported can be greatly increased. The set value is used to remove the target part from the rework target 1 to which the target part is attached by soldering to the work target by using the removal portion 6a (rework portion 6).

Next, the operation of the rework condition learning device according to the first embodiment (the rework condition learning method according to the first embodiment) will be described with reference to FIG. In FIG. 2, in step 1, the set value (removal condition) associated with the rework target 1 is set in the set value input unit 3 for each device (specifically, the rework device 10 described later) that performs rework (rework). It is a processing step in which the setting value) is input. In step 2, the quality / defect determination of the non-defective product or the defective product of the rework target 1 reprocessed by the set value (set value as the removal condition) input to the set value input unit 3 in the good / bad judgment result input unit 4 is performed. This is a processing step in which the result is input. In step 1 and step 2, the order of processing does not matter. It may be at the same time. In step 3, based on the set value input to the setting condition input unit 3 and the good / bad judgment result input to the good / bad judgment result input unit 4, the learning unit 5 becomes a good product for each rework target 1. This is a processing step for learning the set value. Preferably, step 3 incorporates a processing step in which the learning unit 5 is made to learn by associating each reworking device 10 with a different set value that is a non-defective product even for the same reworking target 1 as an error for each reworking device 10. Good.

In the operation of the rework condition learning device according to the first embodiment (the rework condition learning method according to the first embodiment), as in the rework condition learning device according to the first embodiment, preferably, step 1 is a set value. In the input unit 3, the removal conditions are defined by the first combination of the first solder information, the soldered target part, the member to which the target part is fixed by soldering, the heating condition, and the cooling condition. This is a step in which a set value associated with the processing target 1 is input. The conditions of the target parts, the conditions of the members, and their combinations are the same as those of the rework condition learning device according to the first embodiment.

In FIG. 3, the rework condition determination device 7 uses the learning result (learning model) of the rework condition learning device 2 shown in FIGS. 1 and 3 (the rework condition determination device according to the first embodiment). The rework condition determination device 7 has a rework target input unit 8 and a rework condition determination unit 9. In FIG. 3, the rework target input unit 8 inputs information on the rework target 1 that is the target to be newly machined (soldering is removed). The rework condition determination unit 9 uses the learning result (learning model) of the learning unit 5 to set a set value (set value as a removal condition) in which the rework target 1 for which information is input to the rework target input unit 8 is a good product. ) Is determined.

Next, the operation of the rework condition determination device according to the first embodiment (the rework condition determination method according to the first embodiment) will be described with reference to FIG. In FIG. 4, step 11 is a processing step in which information on the rework target 1 to be newly reworked (removing the target part) is input to the rework target input unit 8. Step 12 is a processing step in which the rework condition determination unit 9 uses the learning result (learning model) of the learning unit 5. In step 13, the rework condition determination unit 9 uses the learning result (learning model) of the learning unit 5 to input information to the rework target input unit 8, and the rework target 1 is a good product (removal condition). (Set value as) is determined.

In FIG. 3, the rework device 10 uses the rework condition determining device 7 shown in FIG. 3 (rework device according to the first embodiment). The rework device 10 has a removal unit 6a (rework unit 6), a condition setting unit 11, and a removal control unit 12a (rework control unit 12). The condition setting unit 11 inputs the set value determined by the rework condition determination unit 7. The removal control unit 12a controls the removal unit 6a so as to remove the target part from the rework target 1 under the conditions input to the condition setting unit 11. The removal control unit 12a controls the removal unit 6a so that the new rework target 1 can be reworked (the target part can be removed) under the removal conditions determined by the set value.

Next, the operation of the rework device according to the first embodiment (the rework method according to the first embodiment) will be described with reference to FIG. In FIG. 5, step 21 is a processing step in which the set value determined by the rework condition determination unit 7 is input to the condition setting unit 11. Step 24 is a processing step of performing removal. Specifically, step 24 is a processing step in which the removal control unit 12a controls the removal unit 6a so as to remove the target component from the rework target 1 under the conditions input to the condition setting unit 11. That is, step 24 is a processing step of causing the removal unit 6a to rework (remove the target part) the new rework target 1 under the removal conditions determined by the set value.

In the rework condition learning device according to the first embodiment, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the first embodiment, the rework condition determination method and the rework method using the same), the rework condition As mentioned in the explanation of the learning device (rework condition learning method), the learning unit 5 (in step 3) sets different rework devices 10 to be good products even if they are the same rework target 1. It may be learned by associating it as an error for each rework device 10. The error for each rework device 10 can be used in the rework condition determination device and the rework device (the rework condition determination method and the rework method according to the first embodiment) as follows.

First, in the rework condition determination device (step 12), the learning result of the learning unit 5 is used to determine a set value at which the rework target 1 whose information is input to the rework target input unit 8 is a good product, and the rework condition is determined. The determination unit 9 uses the learning result of the learning unit 5 to identify the presence or absence of an error associated with the determined set value. Then, as shown in FIG. 6, in the rework device 10, the removal control unit 12a has an error associated with the condition (process of step 21) input to the condition setting unit 11, and has been corrected by the condition setting unit 11. At (YES in the process of step 22), the removal unit 6a is controlled so as to remove the soldering (process of step 24) by using the set value which is the reference value corrected for the error (process of step 23). On the other hand, the removal control unit 12a has the condition input to the condition setting unit 11 even if there is an error associated with the condition (process of step 21) input to the condition setting unit 11 (the process of step 22 is NO). The removal unit 6a is controlled so as to remove the target component in step 24 (process in step 24).

When going directly from step 22 to step 24, if there is no error associated with the condition (process of step 21) input to the condition setting unit 11, the process of the flowchart shown in FIG. 5 is performed. That is, when the error is not corrected by the condition setting unit 11, it is directly from step 22 (step 21) regardless of the presence or absence of the error associated with the condition (process of step 21) input to the condition setting unit 11. You will go to step 24.

Further, the set value (set value as the removal condition) which becomes the reference value corrected for the error may be individually prepared, or the learning result (learning model) of the learning unit 5 may be used. That is, the learning unit 5 of the rework condition learning device learns by associating each rework device 10 with a different set value that is a good product even if it is the same rework target 1 as an error for each device, and corrects the error. Determine the setting value to be. Then, the removal control unit 12a of the rework device 10 has an error associated with the condition input to the condition setting unit 11, and when the condition setting unit 11 has corrected the error, the setting becomes the reference value determined by the learning unit 5. Using the value (the set value as the reference value may be acquired via the rework condition determining device 7), the removal unit 6a is controlled so as to remove the target component.

As described above, the rework condition learning device according to the first embodiment, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the first embodiment, the rework condition determination method and the rework method using the same) have been described. It is possible to learn and use the set values that are good products for each rework target 1. The set value is a removal condition for removing the target part from the rework target 1 to which the target part is attached by soldering to the processing target.

Embodiment 2.
Hereinafter, the rework condition learning device according to the second embodiment of the present invention, the rework condition determining device and the rework device using the rework condition learning device will be described with reference to FIGS. 7 and 8. The description will be focused on the parts different from those of the first embodiment. In the figure, the same reference numerals indicate the same or corresponding parts, and detailed description thereof will be omitted. The major difference between the first embodiment and the second embodiment is that the learning unit 5 has a set value (set value as a removal condition) that is a non-defective product for each rework target 1 and image data to be reworked (excluding soldering). It is to learn by associating it with a picture of the part where it was done. There is no significant difference in the rework device 10 between the first embodiment and the second embodiment.

In FIG. 7, the good / bad determination result input unit 4 determines the good / bad of the non-defective product or the defective product of the rework target 1 reprocessed by the set value (set value as the removal condition) input to the set value input unit 3. The result is input. Further, the good / bad determination result input unit 4 inputs the image data of the rework target (photograph of the unsoldered portion, etc.) after removing the target part in the rework target 1 associated with the good / bad judgment result. It is a thing. Based on the set value input to the setting condition input unit 3 and the good / bad judgment result input to the good / bad judgment result input unit 4, the learning unit 5 sets a set value to be a good product for each rework target 1. It is something to learn. Further, the learning unit 5 learns by associating the set value, which is a non-defective product, with the image data to be reprocessed for each reprocessing object 1.

In this way, the rework condition learning device according to the second embodiment associates the set value that becomes a non-defective product for each rework target 1 with the image data to be reprocessed, so that the determined rework target 1 is a non-defective product. Since the image data to be reprocessed corresponding to the set value to be reprocessed can be easily specified, the determined image at the time of completion when the reprocessed object 1 is reprocessed with the set value to be a non-defective product (the target part is removed). Can be easily obtained. The image data to be reprocessed may be determined by determining the learning result (learning model) of the learning unit 5 when the rework condition determining unit 9 determines the set value. The rework condition determination device 7 may include a display unit that displays (determined) image data to be reprocessed obtained from the learning result (learning model) of the learning unit 5, including the outside.

Next, the operation of the rework condition learning device according to the second embodiment (the rework condition learning method according to the second embodiment) will be described with reference to FIG. In FIG. 8, in step 1, the set value (setting as a removal condition) associated with the rework target 1 is set in the set value input unit 3 for each device for removing the solder (specifically, the rework device 10 described later). Value) is an input processing step. In step 1 and the next step 2A, the order of processing does not matter. It may be at the same time.

In FIG. 8, in step 2A, the non-defective product or defective product of the rework target 1 reprocessed by the set value (set value as the removal condition) input to the set value input unit 3 in the good / bad determination result input unit 4. The processing step in which the good / bad judgment result is input, and further, the rework target image data (solder) after removing the target part in the rework target 1 associated with the good / bad judgment result in the good / bad judgment result input unit 4. This is a processing step in which (such as a photo of the removed part) is input. In step 3A, the learning unit 5 becomes a good product for each rework target 1 based on the set value input to the setting condition input unit 3 and the good / bad judgment result input to the good / bad judgment result input unit 4. A processing step for learning the set value, and a processing step for causing the learning unit 5 to learn the set value that is a good product for each reprocessing target 1 and the image data to be reprocessed in association with each other. Similar to step 3 of the first embodiment, in step 3A, in step 3A, the learning unit 5 is associated with each rework device 10 having different setting values that are good products even if the same rework target 1 is used, as an error for each rework device 10. A processing step to be trained may be incorporated.

As described above, the rework condition learning device according to the second embodiment, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the second embodiment, the rework condition determination method and the rework method using the same) have been described. It is possible to learn and use the set values that are good products for each rework target 1. Furthermore, it is also possible to obtain image data to be reprocessed (with the target component removed) that was actually reprocessed in the past.

Embodiment 3.
Hereinafter, the rework condition learning device according to the third embodiment of the present invention, the rework condition determining device and the rework device using the rework condition learning device will be described with reference to FIGS. 9, 10, and 11. The description will be focused on the parts different from the first and second embodiments. In the figure, the same reference numerals indicate the same or corresponding parts, and detailed description thereof will be omitted. The major difference between the second embodiment and the third embodiment is that in the second embodiment, the learning unit 5 sets a non-defective product (set value as a removal condition) for each rework target 1 and a rework target image. The learning was performed in association with data (such as a photograph of a portion where the solder was removed), but further, in the third embodiment, a new rework target image data input unit 13 is further provided. There are no major differences in the rework device 10 between the first embodiment, the second embodiment, and the third embodiment. There is no big difference between the second embodiment and the third embodiment with respect to the rework condition determining device 7.

In FIGS. 9 and 10, the new rework target image data input unit 13 is for inputting the new rework target image data of the rework target 1 from which the solder is newly removed, that is, the target part is removed. is there. The setting value input unit 3 inputs a setting value associated with the reprocessing target 1 of the new reprocessing target image data. Using the learning result (learning model), the learning unit 5 uses the feature amount of the new reprocessing target image data input to the new reprocessing target image data input unit 13 to determine similar reprocessing target image data (good / bad determination). The result input unit 4) is determined, and the quality judgment result of the reprocessing target 1 of the new reprocessing target image data is determined from the quality judgment result associated with the determined reprocessing target image data. Is what you do. The good / bad judgment result input unit 4 inputs the good / bad judgment result of the good or bad product of the rework target 1 newly removed from the soldering, which is judged by the learning unit 5 using the learning result (learning model). Is.

The learning unit 5 extracts the feature amount from the new rework target image data and newly removes the soldering, that is, learns by associating it with the feature amount of the rework target image data of the rework target 1 from which the target part is removed. By doing so, it is possible to improve the classification accuracy. That is, although not shown, it can be said that the learning unit 5 has a feature amount extraction unit (feature amount extraction function) that extracts a feature amount from the new rework target image data or the rework target image data. This feature amount extraction unit (feature amount extraction function) may be formed in the setting condition input unit 3. The feature amount extraction unit (feature amount extraction function) may be formed in the quality determination result input unit 4. In this way, machine learning such as AI in the learning unit 5 (rework condition learning device 2) captures features by learning using a large amount of sample data and its correct label, and makes predictions and decisions for new data. It can be said that it is something to do.

Next, the operation of the rework condition learning device according to the third embodiment (the rework condition learning method according to the third embodiment) will be described with reference to FIG. In FIG. 10, step 31 is a processing step in which the new rework target image data of the rework target 1 that has been newly soldered is input to the new rework target image data input unit 13. Further, in the set value input unit 3, the set value associated with the reprocess target 1 of the new reprocess target image data is input. This may also be collectively referred to as step 13.

In FIG. 10, in step 32, the learning result (learning model) was used in the learning unit 5, and the newly reworked target image data input unit 13 was input to the learning unit 5, and the solder was newly removed, that is, the target component was removed. Similar rework target image data (input to the good / bad judgment result input unit 4) is determined from the feature amount of the new rework target image data of the removed rework target 1, and the determined rework target image is determined. This is a processing step for determining the quality determination result of the reprocessing target 1 of the new reprocessing target image data from the quality determination result associated with the data. In step 33, the quality / defect determination result input unit 4 receives the quality / defect determination result of the non-defective product or the defective product of the rework target 1 newly removed from the soldering, which is determined by the learning unit 5 using the learning result (learning model). This is the processing step to be input.

The rework condition learning device according to the third embodiment (the rework condition learning method according to the third embodiment) is a rework target image of the rework target 1 associated with the good / bad judgment result in the good / bad judgment result input unit 4. As the data is input and the learning progresses by associating the set value that is a good product for each reprocessing target 1 with the image data to be reprocessed in the learning unit 5, the quality judgment result is not associated with the "image". Good / bad judgment is also made for the data (in the third embodiment, the image data in which the soldering is newly removed, that is, the image data referred to as the "new reprocessing target image data" of the reprocessing target 1 from which the target component is removed) ". The accuracy with which the result can be judged is improved.

"Image data" to which the quality judgment result is not associated (in the third embodiment, the image referred to as "new rework target image data" of the rework target 1 in which the soldering is newly removed, that is, the target part is removed. Using the good / bad determination result determined by the learning unit 5 for "data)", the rework condition determination device and the rework device shown in FIG. 11 can determine the set value and remove the soldering using the set value. .. Of course, it is also possible to determine the set value and remove the target part from the rework target 1 using the set value, which is the operation described in the first and second embodiments.

As described above, the rework condition learning device according to the third embodiment, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the third embodiment, the rework condition determination method and the rework method using the same) have been described. It is possible to learn and use the set value (set value as a removal condition) that is a good product for each rework target 1. Further, it is possible to obtain the image data to be reprocessed (without soldering) actually processed in the past, and it is possible to carry out a new quality determination using the image data to be reprocessed.

The rework condition learning device according to the first to third embodiments, the rework condition determination device and the rework device using the same (the rework condition learning method according to the first to third embodiments, the rework condition using the same). The determination method and the rework method) include the removal condition learning device according to the first to third embodiments, and the removal condition determination device and the removal device using the removal condition learning device (the removal condition learning according to the first to third embodiments). It may be read as a method, a method for determining removal conditions using the method, and a removal method).

The rework condition learning device according to the fourth to sixth embodiments, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the sixth embodiment, the rework condition determination method and the rework method using the same). ) Is newly added to the rework target 1 from which the target part has been removed, as shown in FIG. 14 (FIG. 23) described later, in the set value input unit 3 (step 1) in the first to third embodiments. The setting value including the mounting condition for mounting the target component (that is, the setting value as the mounting condition in addition to the setting value as the removal condition) is input.

Of course, the rework condition learning device according to the fourth to sixth embodiments, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the sixth embodiment, the rework condition determination method using the rework condition learning device, and the rework condition determination method using the same). In the rework method), as shown in FIG. 15 (FIG. 25) described later, the setting value input unit 3 (step 1) sets the mounting conditions for attaching a new target component to the rework target 1 from which the target component has been removed. Only the set value including the set value (set value as the mounting condition) may be input.

Therefore, for example, the rework condition learning device according to the fourth to sixth embodiments learns the set value which is the mounting condition for attaching a new target component to the rework target 1 from which the target component has been removed. , The following configuration can be considered. For each device (rework device 10) to be reworked, a set value input unit 3 for inputting a set value associated with the rework target 1 and a set value input to the set value input unit 3 (as a mounting condition). Reworking based on the good / bad judgment result input unit 4 in which the good / bad judgment result of the good or bad product of the rework target 1 reworked according to (the set value of) is input, and the set value and the good / bad judgment result. Each target 1 is provided with a learning unit 5 that learns a set value that is a non-defective product.

In the description of the fourth to sixth embodiments, the configuration of FIG. 15 (FIG. 24) of FIGS. 14 and 15 (FIGS. 23 and 24), which will be described later, will be mainly described for the sake of simplicity. The configuration obtained by subtracting FIG. 15 (FIG. 24) from FIG. 14 (FIG. 23) is the same as that of the first to third embodiments. Further, in any case, in the fourth to sixth embodiments, the good / bad determination result input unit 4 is a new target according to the set value (set value as the mounting condition) input to the set value input unit 3. It is desirable to input the good / bad judgment result including the good / bad judgment result of the rework target 1 to which the part is attached. In addition, detailed description of parts common to the first to third embodiments (mostly parts related to removal conditions) may be omitted.

Embodiment 4.
Hereinafter, the rework condition learning device according to the fourth embodiment of the present invention, the rework condition determining device and the rework device using the rework condition learning device will be described with reference to FIGS. 12 to 18. In the figure, the same reference numerals indicate the same or corresponding parts, and detailed description thereof will be omitted. In FIGS. 14 and 15, the rework target 1 is, for example, a substrate 1 such as a printed circuit board, and includes a single-layer substrate and a multilayer substrate. A printed wiring board, a printed wiring board, a printed circuit board, or a printed circuit board may be obtained by soldering wiring or parts (target parts) to the printed circuit board. A printed circuit board with wiring may be simply called a printed wiring board or a printed wiring board. In this case, it can be said that the rework target 1 (board 1) includes the printed wiring board and the printed wiring board. The substrate 1 may be referred to as a processing target. Further, the rework target 1 (board 1) is the second solder information (second solder condition) of the second solder printed on the rework target 1, the target component for soldering, and the target component by soldering. It can be said that it is composed of members to which is fixed.

The new target parts include electronic parts and analog parts, and the leads and terminals are fixed to the rework target by soldering by reflow. The members to which the target component is fixed are the above-mentioned printed circuit board, printed wiring board, and printed wiring board, and solder is formed on the surface by printing or the like. Leads and terminals of the target component include those that are inserted into through holes formed in the substrate 1 and fixed by soldering.

In FIGS. 12, 14, and 15, the rework condition learning device 2 has a setting condition input unit 3, a good / bad determination result input unit 4, and a learning unit 5. In FIGS. 14 and 15, the rework portion 6 (in the fourth embodiment, the soldered portion 6b) attaches a new target component to the rework target 1 from which the target component has been removed. Note that FIG. 14 illustrates a rework device 10 having not only a soldering portion 6b but also a removing portion 6a (described in the first to third embodiments) as the rework portion 6. The soldering portion 6b can be soldered to a new target component such as a soldering iron portion, a local soldering portion, or a reflow furnace. The rework condition learning device 2 learns a set value which is a removal condition for removing the target part from the rework target 1 to which the target part is attached by soldering to the machining target, and builds a learning model.

The local soldering unit includes at least one molten solder tank, a molten solder supply path, and at least one solder jet nozzle (rectifying nozzle). A soldering device using one jet nozzle (rectifying nozzle) may be called a point dip type. Further, a soldering device using a plurality of jet nozzles (rectifying nozzles) may be referred to as a multi-dip type.

The reflow furnace can be used in a tunnel-shaped furnace, a reflow heating unit that sends a gas such as oxygen into the furnace, a gas reflow heating unit that blows air from the reflow ventilation unit, a reflow heating unit that heats the inside of the furnace, and a soldering point. It is provided with a reflow transfer unit (for example, a conveyor) that conveys the rework target 1 on which the second solder is printed. The gas concentration (for example, oxygen concentration) in the furnace, the temperature in the furnace, and the amount of air blown into the furnace are adjusted (controlled) by the reflow blower unit and the reflow heating unit. Further, the transfer speed of the rework target 1 in the furnace is adjusted (controlled) by the reflow transfer unit.

In such a case (when the soldering portion 6b is a reflow furnace), the soldering portion 6b may have a solder printing function for printing a second solder. Then, the soldering control unit 12b, which will be described later, controls the soldering unit 6b before the soldering unit 6b solders the new target component to the second object 1 to be reprocessed by the solder printing function. Have the solder printed.

Subsequently, in FIGS. 12, 14, and 15, the good / bad determination result input unit 4 is the rework target 1 that has been reworked according to the set value (set value as the mounting condition) input to the set value input unit 3. The quality judgment result of a non-defective product or a defective product is input. In the quality / defect determination result input unit 4, the quality / defect determination result initially input is, for example, an visual inspection (by a person or a machine) of a printed circuit board (printed circuit board) which is a rework target 1 after being reprocessed. It is a data of the results of inspections including inspections). That is, the result of the visual inspection (inspection including inspection by a person or a machine) may be converted into data and associated with the processed set value (set value input to the set value input unit 3) of the rework target 1. The visual inspection referred to here is an inspection (determination) of the quality of the rework target 1 after attaching a new target part to the rework target 1 from which the target part has been removed. The learning unit 5 learns a set value that is a non-defective product for each rework target 1 based on the set value and the good / bad determination result. Based on the set value input to the setting condition input unit 3 and the good / bad judgment result input to the good / bad judgment result input unit 4, the learning unit 5 sets a set value to be a good product for each rework target 1. It is something to learn.

Machine learning such as AI may be applied to the learning unit 5 (rework condition learning device 2). The learning unit 5 (rework condition learning device 2) constructs and accumulates a learning model. Preferably, the learning unit 5 may learn by associating the same rework target 1 with a different set value as a non-defective product for each rework device 10 as an error for each rework device 10. Further, as a mounting condition, the set value input unit 3 is a second combination of a new target component and the second solder information of the second solder for mounting the new target component on the rework target 1. The set value associated with the rework target 1 defined in is input.

In this case, the set value input unit 3 further adds the second solder information of the second combination to the composition of the second solder, the flux type added to the second solder, and the second solder. The set value associated with the rework target 1 distinguished by at least one of the obtained flux content and the area of the second solder may be input. Similarly, the set value input unit 3 inputs the set value associated with the rework target 1 in which the target component is distinguished by the outer shape or the type of electrode surface treatment in the second combination. It may be. Similarly, the set value input unit 3 is associated with the rework target 1 in which the member is distinguished by at least one of the thickness, the material, the number of layers, the specific gravity, and the type of surface treatment in the second combination. The set value may be input.

That is, the first set value input unit 3 is the second of the second combination of the second solder information, the target component to be soldered, and the member to which the new target component is fixed by soldering. It means that the solder information and the target parts are the same, and the set values when the conditions of the members are changed are input respectively. Further, the second set value input unit 3 is the second solder of the second combination of the second solder information, the target component to be soldered, and the member to which the target component is fixed by soldering. It means that the information and members are the same, and the set values are input when the conditions of the target parts change. Further, in the third set value input unit 3, among the second combination of the second solder information, the target component to be soldered, and the member to which the target component is fixed by soldering, the target component and the member are It refers to the same one in which the set values when the second solder information (second solder condition) changes are input respectively.

Here, a case where the conditions of the member (rework target 1 to which the target part is newly attached) changes and a case where the conditions of the target part change will be described. The change in the conditions of the member means that the thickness, material, number of layers, specific gravity, and type of surface treatment of the member are different as described above. When the member is the substrate 1, the thickness means the specifications of the plate thickness (conductor foil thickness, conductor foil area, number of laminated sheets). In the case of the substrate 1, the material means the base material of the substrate and the conductor type of the conductor foil. Further, changing the conditions of the target component means that the volume, the electrode shape, and the electrode surface treatment are different. Since the shape and size of the target component can be known from the volume and the electrode shape, the volume and the electrode shape of the target component can be said to be information on the outer shape of the target component.

Next, a case where the second solder information (condition of the second solder) is changed will be described. As described above, the second solder information includes the composition of the second solder, the flux type (flux type) added to the second solder, and the content of the flux added to the second solder, for example. This means that the areas of the second solders to be printed are different. The composition of the second solder may include the flux type (flux type) and the flux content. The area of the second solder to be printed refers to the area of the second solder printed on the surface of the rework target 1. The area of the second solder to be printed also means the printing amount of the second solder to be printed, and can be said to be the volume of the second solder to be printed in consideration of the thickness of the second solder. Further, the information (condition) of the area of the second solder to be printed (the amount of the second solder to be printed) is the information on the position of the second solder to be printed on the surface of the rework target 1. It may be included, and the information (condition) of the area of the second solder to be printed (the amount of the second solder to be printed) is printed on the surface of the second solder to be reprocessed 1. The location information itself may be used.

So far, the case where two of the second combination of the second solder information, the target part to be soldered, and the member to which the target part is fixed by soldering is fixed has been described, but all combinations are covered. Alternatively, one of the second combination of the second solder information, the target component for soldering, and the member to which the target component is fixed by soldering may be fixed. That is, the set value input unit 3 has the composition of the second solder printed on the rework target 1, the flux type added to the second solder, the flux content added to the second solder, and the second solder. At least one of the soldering areas, the outer shape of the part to be soldered, or the surface treatment of the electrodes, the thickness, material, number of layers, specific gravity, and type of surface treatment of the member to which the target part is fixed by soldering. It can be said that the set value (set value as the mounting condition) associated with the rework target 1 defined in the second combination of at least one of the above is input.

This is at least one from the composition of the solder printed on the rework target 1, the flux type added to the solder, the flux content added to the solder, the area of the solder, the outer shape of the part to be soldered, or One of the electrode surface treatments (volume of the target part to be soldered, electrode shape, at least one from the electrode surface treatment), thickness, material, number of layers, specific gravity, surface treatment of the member to which the target part is fixed by soldering The above-mentioned set value associated with the rework target 1 defined by at least one second combination from the type of the above is input. As a result, the set values that can be supported can be greatly increased. The set value is used to attach a new target component to the rework target 1 from which the target component has been removed by using the soldering section 6b (rework section 6).

The conditions of the soldering iron portion, the local soldering portion, and the reflow furnace may be added to the second combination of the set values (set values as the mounting conditions). For example, in the case of a soldering iron portion, at least one of the tip shapes of the trowel including the soldering temperature and the diameter of the trowel in the soldering iron can be considered for each rework target 1 to be soldered (reprocessed). In the case of the local soldering part, for each rework target 1 to be soldered (reworked), the moving speed of the nozzle forming a jet of solder (second solder), the gap between the rework target 1 and the tip of the nozzle. At least one of the dimensions and the jet height of the solder (second solder) is conceivable. In the case of a reflow furnace, at least the gas concentration in the furnace, the temperature in the furnace, the amount of air blown into the furnace, and the transport speed of the rework target 1 in the furnace for each rework target 1 to be soldered (reworked). One can be considered.

Next, the operation of the rework condition learning device according to the fourth embodiment (the rework condition learning method according to the fourth embodiment) will be described with reference to FIG. In FIG. 13, in step 21, the set value (as an attachment condition) associated with the rework target 1 is set in the set value input unit 3 for each device (specifically, the rework device 10) that performs rework (rework). This is a processing step in which the set value) is input. In step 22, the quality / defect determination of the non-defective product or the defective product of the rework target 1 reprocessed by the set value (set value as the mounting condition) input to the set value input unit 3 in the good / bad determination result input unit 4 is performed. This is a processing step in which the result is input. In step 21 and step 22, the order of processing does not matter. It may be at the same time. In step 23, the learning unit 5 becomes a good product for each rework target 1 based on the set value input to the setting condition input unit 3 and the good / bad judgment result input to the good / bad judgment result input unit 4. This is a processing step for learning the set value. Preferably, step 23 incorporates a processing step in which the learning unit 5 is made to learn by associating each rework device 10 with a different set value that is a non-defective product even for the same rework target 1 as an error for each rework device 10. Good.

In the operation of the rework condition learning device according to the fourth embodiment (the rework condition learning method according to the fourth embodiment), similarly to the rework condition learning device according to the fourth embodiment, preferably, step 11 is a set value. The input unit 3 is associated with the rework target 1 defined in the second combination of the second solder information, the soldered target part, and the member to which the target part is fixed by soldering as mounting conditions. In addition, it is a step in which the set value is input. The conditions of the target parts, the conditions of the members, and their combinations are the same as those of the rework condition learning device according to the fourth embodiment.

In the fourth to sixth embodiments, the second solder and the second solder information are the same as the first solder and the first solder information in the first to third embodiments, respectively. But it may be. Similarly, the target component and the new target component may be of the same type or specifications. That is, the new target part may be a substitute for the target part. Therefore, the new target part may be referred to as a substitute target part.

In FIGS. 14 and 15, the rework condition determining device 7 uses the learning result (learning model) of the rework condition learning device 2 shown in FIGS. 12 and 14 and 15 (rework according to the fourth embodiment). Conditioning device). The rework condition determination device 7 has a rework target input unit 8 and a rework condition determination unit 9. In FIGS. 14 and 15, the information of the rework target 1 to be newly machined (soldered) is input to the rework target input unit 8. The rework condition determination unit 9 uses the learning result (learning model) of the learning unit 5 to set a set value (set value as an attachment condition) in which the rework target 1 for which information is input to the rework target input unit 8 is a good product. ) Is determined.

Next, the operation of the rework condition determination device according to the fourth embodiment (the rework condition determination method according to the fourth embodiment) will be described with reference to FIG. In FIG. 16, step 211 is a processing step in which information on the rework target 1 to be newly reworked (attaching the target component) is input to the rework target input unit 8. Step 212 is a processing step in which the rework condition determination unit 9 uses the learning result (learning model) of the learning unit 5. In step 213, the rework condition determination unit 9 uses the learning result (learning model) of the learning unit 5 to input information to the rework target input unit 8, and the rework target 1 is a good product (mounting condition). (Set value as) is determined.

In FIGS. 14 and 15, the rework device 10 uses the rework condition determination device 7 shown in FIGS. 14 and 15 (the rework device according to the first embodiment). The rework device 10 has a soldering unit 6b (rework unit 6), a condition setting unit 11, and a soldering control unit 12b (rework control unit 12). Note that FIG. 14 illustrates a rework device 10 having not only the soldering control unit 12b but also the removal control unit 12a (described in the first to third embodiments) as the rework control unit 12. .. The condition setting unit 11 inputs the set value determined by the rework condition determination unit 7. The soldering control unit 12b controls the soldering unit 6b so as to newly attach the target component to the rework target 1 under the conditions input to the condition setting unit 11. The soldering control unit 12b controls the soldering unit 6b so that the new rework target 1 can be reworked (the target component is mounted) under the mounting conditions determined by the set values.

Next, the operation of the rework device according to the fourth embodiment (the rework method according to the fourth embodiment) will be described with reference to FIG. In FIG. 17, step 221 is a processing step in which the set value determined by the rework condition determination unit 7 is input to the condition setting unit 11. Step 224 is a processing step of mounting implementation. Specifically, step 224 is a processing step of controlling the soldering unit 6b so that the soldering control unit 12b is soldered under the conditions input to the condition setting unit 11. That is, step 224 is a processing step of causing the soldering portion 6b to reprocess the new target component 1 (attach a new target component) under the mounting conditions determined by the set value.

In the rework condition learning device according to the fourth embodiment, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the fourth embodiment, the rework condition determination method and the rework method using the same), the rework condition As mentioned in the explanation of the learning device (rework condition learning method), the learning unit 5 (in step 23) sets different rework devices 10 to be good products even if they are the same rework target 1. It may be learned by associating it as an error for each rework device 10. The error for each rework device 10 can be used in the rework condition determination device and the rework device (the rework condition determination method and the rework method according to the fourth embodiment) as follows.

First, in the rework condition determination device (step 212), the learning result of the learning unit 5 is used to determine a set value at which the rework target 1 whose information is input to the rework target input unit 8 is a good product, and the rework condition is determined. The determination unit 9 uses the learning result of the learning unit 5 to identify the presence or absence of an error associated with the determined set value. Then, as shown in FIG. 18, in the rework device 10, the soldering control unit 12b has an error associated with the condition (process of step 221) input to the condition setting unit 11, and the condition setting unit 11 corrects the error. When completed (process in step 222 is YES), the soldering unit 6b is controlled so as to perform soldering (processing in step 224) using a set value that serves as a reference value after correcting the error (processing in step 223). ). On the other hand, the soldering control unit 12b is input to the condition setting unit 11 even if there is an error associated with the condition (process of step 221) input to the condition setting unit 11 (process of step 222 is NO). The soldering portion 6b is controlled so as to attach the target component under the conditions (process of step 224).

When going directly from step 222 to step 224, if there is no error associated with the condition (process of step 221) input to the condition setting unit 11, the process of the flowchart shown in FIG. 17 is performed. That is, when the error is not corrected by the condition setting unit 11, it is directly from step 222 (step 221) regardless of the presence or absence of the error associated with the condition (process of step 221) input to the condition setting unit 11. You will go to step 224.

Further, the set value (set value as the mounting condition) which becomes the reference value corrected for the error may be individually prepared, or the learning result (learning model) of the learning unit 5 may be used. That is, the learning unit 5 of the rework condition learning device learns by associating each rework device 10 with a different set value that is a good product even if it is the same rework target 1 as an error for each device, and corrects the error. Determine the setting value to be. Then, the soldering control unit 12b of the rework device 10 has an error associated with the condition input to the condition setting unit 11, and when the condition setting unit 11 has corrected the error, the soldering control unit 12b becomes the reference value determined by the learning unit 5. Using the set value (the set value as the reference value may be acquired via the rework condition determining device 7), the soldering unit 6b is controlled so as to attach a new target component.

As described above, the rework condition learning device according to the fourth embodiment, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the fourth embodiment, the rework condition determination method and the rework method using the same) have been described. It is possible to learn and use the set values that are good products for each rework target 1. The set value is an attachment condition for attaching a new target component to the rework target 1 from which the target component has been removed.

Embodiment 5.
Hereinafter, the rework condition learning device according to the fifth embodiment of the present invention, the rework condition determining device and the rework device using the rework condition learning device will be described with reference to FIGS. 19 and 20. The description will be focused on the parts different from those of the fourth embodiment. In the figure, the same reference numerals indicate the same or corresponding parts, and detailed description thereof will be omitted. The major difference between the fourth embodiment and the fifth embodiment is that the learning unit 5 performs the rework target image data (soldering) and the set value (set value as the mounting condition) that is a non-defective product for each rework target 1. It is to learn by associating it with a picture of a soldering part. There is no major difference in the rework device 10 between the fourth embodiment and the fifth embodiment.

In FIG. 19, the good / bad determination result input unit 4 determines the good / bad of the non-defective product or the defective product of the rework target 1 reprocessed by the set value (set value as the mounting condition) input to the set value input unit 3. The result is input. Further, in the good / bad judgment result input unit 4, the image data of the rework target (photograph of the soldered part, etc.) after the new target component in the rework target 1 associated with the good / bad judgment result is attached. It is what is entered. Based on the set value input to the setting condition input unit 3 and the good / bad judgment result input to the good / bad judgment result input unit 4, the learning unit 5 sets a set value to be a good product for each rework target 1. It is something to learn. Further, the learning unit 5 learns by associating the set value, which is a non-defective product, with the image data to be reprocessed for each reprocessing object 1.

As described above, since the rework condition learning device according to the fifth embodiment associates the set value that becomes a non-defective product for each rework target 1 with the image data to be reprocessed, the determined rework target 1 is a non-defective product. Since the image data to be reprocessed corresponding to the set value to be reprocessed can be easily specified, the determined reprocessed object 1 is reprocessed with the set value to be a non-defective product (when a new target part is attached) at the time of completion. Image can be easily obtained. The image data to be reprocessed may be determined by determining the learning result (learning model) of the learning unit 5 when the rework condition determining unit 9 determines the set value. The rework condition determination device 7 may include a display unit that displays (determined) image data to be reprocessed obtained from the learning result (learning model) of the learning unit 5, including the outside.

Next, the operation of the rework condition learning device according to the fifth embodiment (the rework condition learning method according to the fifth embodiment) will be described with reference to FIG. In FIG. 20, in step 21, the set value (set value as the mounting condition) associated with the rework target 1 for each device (specifically, the rework device 10) for soldering to the set value input unit 3 is set. Is the processing step in which is input. In step 21 and the next step 22A, the order of processing does not matter. It may be at the same time.

In FIG. 20, in step 22A, the non-defective product or defective product of the rework target 1 reprocessed by the set value (set value as the mounting condition) input to the set value input unit 3 in the good / bad determination result input unit 4. The process step in which the good / bad judgment result is input, and the image data to be reworked after the target parts in the rework target 1 associated with the good / bad judgment result are attached to the good / bad judgment result input unit 4. This is a processing step in which (such as a photograph of the soldered part) is input. In step 23A, the learning unit 5 becomes a good product for each rework target 1 based on the set value input to the setting condition input unit 3 and the good / bad judgment result input to the good / bad judgment result input unit 4. A processing step for learning the set value, and a processing step for causing the learning unit 5 to learn the set value that is a good product for each reprocessing target 1 and the image data to be reprocessed in association with each other. Similar to step 23 of the fourth embodiment, in step 23A, in step 23A, the learning unit 5 is associated with each rework device 10 having different setting values that are good products even if the same rework target 1 is used, as an error for each rework device 10. A processing step to be trained may be incorporated.

As described above, the rework condition learning device according to the fifth embodiment, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the fifth embodiment, the rework condition determination method and the rework method using the same) have been described. It is possible to learn and use the set values that are good products for each rework target 1. Furthermore, it is also possible to obtain image data to be reprocessed (with the target component removed) that was actually reprocessed in the past.

Embodiment 6.
Hereinafter, the rework condition learning device according to the sixth embodiment of the present invention, the rework condition determining device and the rework device using the rework condition learning device will be described with reference to FIGS. 21 to 24. The description will be focused on the parts different from the fourth and fifth embodiments. In the figure, the same reference numerals indicate the same or corresponding parts, and detailed description thereof will be omitted. The major difference between the fifth embodiment and the sixth embodiment is that in the fifth embodiment, the learning unit 5 sets a non-defective product (set value as an attachment condition) for each rework target 1 and a rework target image. The learning was performed in association with data (such as a photograph of a soldered portion), but further, in the sixth embodiment, the new rework target image data input unit 13 is further provided. There are no major differences in the rework device 10 between the fourth embodiment, the fifth embodiment, and the sixth embodiment. There are no major differences in the rework condition determining device 7 between the fifth embodiment and the sixth embodiment.

In FIGS. 21 and 22, the new rework target image data input unit 13 is newly soldered, that is, the new rework target image data of the rework target 1 to which the target part is attached is input. is there. The setting value input unit 3 inputs a setting value associated with the reprocessing target 1 of the new reprocessing target image data. Using the learning result (learning model), the learning unit 5 uses the feature amount of the new reprocessing target image data input to the new reprocessing target image data input unit 13 to determine similar reprocessing target image data (good / bad determination). The result input unit 4) is determined, and the quality judgment result of the reprocessing target 1 of the new reprocessing target image data is determined from the quality judgment result associated with the determined reprocessing target image data. Is what you do. The good / bad judgment result input unit 4 inputs the good / bad judgment result of the good or bad product of the rework target 1 newly soldered, which is judged by the learning unit 5 using the learning result (learning model). Is.

The learning unit 5 extracts the feature amount from the new rework target image data and newly solders it, that is, learns in association with the feature amount of the rework target image data of the rework target 1 to which the target part is attached. By doing so, it is possible to improve the classification accuracy. That is, although not shown, it can be said that the learning unit 5 has a feature amount extraction unit (feature amount extraction function) that extracts a feature amount from the new rework target image data or the rework target image data. This feature amount extraction unit (feature amount extraction function) may be formed in the setting condition input unit 3. The feature amount extraction unit (feature amount extraction function) may be formed in the quality determination result input unit 4. In this way, machine learning such as AI in the learning unit 5 (rework condition learning device 2) captures features by learning using a large amount of sample data and its correct label, and makes predictions and decisions for new data. It can be said that it is something to do.

Next, the operation of the rework condition learning device according to the sixth embodiment (the rework condition learning method according to the sixth embodiment) will be described with reference to FIG. In FIG. 22, step 231 is a processing step in which the new rework target image data of the newly soldered rework target 1 is input to the new rework target image data input unit 13. Further, in the set value input unit 3, the set value associated with the reprocess target 1 of the new reprocess target image data is input. This may also be collectively referred to as step 213.

In FIG. 22, in step 232, the learning result (learning model) was used in the learning unit 5 to newly solder the target component, which was input to the new rework target image data input unit 13. Similar rework target image data (input to the good / bad judgment result input unit 4) is determined from the feature amount of the new rework target image data of the rework target 1 attached, and the determined rework target image is determined. This is a processing step for determining the quality determination result of the reprocessing target 1 of the new reprocessing target image data from the quality determination result associated with the data. In step 233, the good / bad judgment result of the good or bad product of the rework target 1 newly soldered, which is determined by the learning unit 5 using the learning result (learning model), is sent to the good / bad judgment result input unit 4. This is the processing step to be input.

The rework condition learning device according to the sixth embodiment (the rework condition learning method according to the sixth embodiment) is a rework target image of the rework target 1 associated with the good / bad judgment result in the good / bad judgment result input unit 4. As the data is input and the learning progresses by associating the set value that is a good product for each reprocessing target 1 with the image data to be reprocessed in the learning unit 5, the quality judgment result is not associated with the "image". Good / bad judgment is also made for the data (in the third embodiment, the image data is newly soldered, that is, the image data referred to as the "new rework target image data" of the rework target 1 to which the target part is attached). The accuracy with which the result can be judged is improved.

"Image data" to which the quality determination result is not associated (in the sixth embodiment, an image referred to as "new rework target image data" of the rework target 1 to which the target part is newly soldered, that is, the target part is attached. Using the good / bad determination result determined by the learning unit 5 for "data)", the rework condition determination device and the rework device shown in FIGS. 23 and 24 determine the set value and solder using the set value. be able to. Of course, it is also possible to determine the set value and attach a new target component to the rework target 1 using the set value, which is the operation described in the fourth and fifth embodiments.

The difference (relationship) between the rework condition determination device and the rework device shown in FIG. 23 and the rework condition determination device and the rework device shown in FIG. 24 is the same as the difference (relationship) between FIGS. 14 and 15. That is, FIG. 23 illustrates a rework device 10 having not only the soldering portion 6b but also the removing portion 6a (described in the first to third embodiments) as the rework portion 6. FIG. 23 illustrates a rework device 10 having not only the soldering control unit 12b but also the removal control unit 12a (described in the first to third embodiments) as the rework control unit 12.

As described above, the rework condition learning device according to the sixth embodiment, the rework condition determination device and the rework device using the rework condition learning device (the rework condition learning method according to the sixth embodiment, the rework condition determination method and the rework method using the same) have been described. It is possible to learn and use the set values (set values as mounting conditions) that are good products for each rework target 1. Further, it is possible to obtain image data to be reprocessed (soldered) that has actually been reprocessed in the past, and it is possible to perform new quality determination using the image data to be reprocessed.

Further, in the configuration shown in FIG. 15 (FIG. 25), the rework condition learning device according to the fourth to sixth embodiments, the rework condition determination device and the rework device using the rework condition learning device (rework according to the sixth embodiment). The condition learning method, the rework condition determination method and the rework method using the same, are the soldering condition learning device according to the fourth to sixth embodiments, the soldering condition determination device and the soldering device (implementation). It may be read as the soldering condition learning method according to the sixth embodiment, the soldering condition determination method and the soldering method using the soldering condition learning method).

The rework condition learning device according to the first to sixth embodiments is a rework condition learning device 2 that learns a set value that is a condition for reworking the rework target 1, and is a device that performs rework (rework device). For each 10), the set value input unit 3 in which the set value is input, which is associated with the rework target 1, and the non-defective product of the reprocess target 1 reprocessed by the set value input in the set value input unit 3 or A good / bad judgment result input unit 4 in which a good / bad judgment result of a defective product is input, and a learning unit 5 that learns a set value that becomes a good product for each rework target 1 based on a set value and a good / bad judgment result. It is characterized by having.

The rework condition determination device and the rework device according to the first to sixth embodiments use the rework condition learning device according to the first to sixth embodiments. The reworking condition is at least one of the removal condition of the target part and the attachment condition of the target part. Reworking is at least one of the removal of the target component soldered by the first solder and the attachment of the target component by soldering the second solder. The rework device 10 is at least one of a device for removing the target component by releasing the soldering and a device for attaching a new target component by soldering.

1 Rework target, 2 Rework condition learning device, 3 Setting condition input unit,
4 Good / bad judgment result input unit, 5 learning unit, 6 rework unit, 6a removal unit,
6b Soldering part, 7 Rework condition determination device, 8 Rework target input part,
9 Rework condition determination unit, 10 Rework device, 11 Condition setting unit,
12 Rework control unit, 12a Removal control unit, 12b Soldering control unit,
13 New rework target image data input unit.

Claims (35)

It is a rework condition learning device that learns the set value which is the removal condition for removing the target part from the rework target to which the target part is attached by soldering to the work target.
For each device to be reworked, the set value input unit for inputting the set value associated with the rework target and the rework reworked by the set value input to the set value input unit. Based on the good / bad judgment result input unit in which the good / bad judgment result of the target non-defective product or defective product is input, and the set value and the good / bad judgment result, the set value that becomes a good product for each rework target is set. A rework condition learning device characterized by having a learning unit for learning. The set value input unit is, as the removal condition, the first solder information of the first solder formed on the rework target, the soldered target component, and a member to which the target component is fixed by soldering. The rework condition learning apparatus according to claim 1, wherein the set value associated with the rework target defined in the first combination of the heating condition and the cooling condition is input. In the set value input unit, the first solder information of the first combination is added to the composition of the first solder, the flux type added to the first solder, and the first solder. The rework according to claim 2, wherein the set value associated with the rework target, which is distinguished by at least one of the obtained flux content and the area of the first solder, is input. Condition learning device. In the set value input unit, the set value in which the target component is associated with the rework target whose outer shape or the type of electrode surface treatment is distinguished from the first combination is input. The rework condition learning device according to claim 2 or 3, wherein the rework condition learning device is characterized. The set value input unit is associated with the rework target in which the member is distinguished by at least one of thickness, material, number of layers, specific gravity, and type of surface treatment in the first combination. The rework condition learning device according to any one of claims 2 to 4, wherein the set value is input. The set value input unit has, as the removal conditions, the composition of the first solder formed on the processing target, the flux type added to the first solder, and the flux content added to the first solder. , At least one of the areas of the first solder, the outer shape of the target component soldered, or the surface treatment of the electrode, the thickness, material, and layer of the member to which the target component is fixed by soldering. The set value associated with the processing target defined in the first combination of number, specific gravity, at least one of the types of surface treatment, at least one of the heating conditions or the cooling conditions is input. The rework condition learning device according to claim 1, wherein the rework condition learning device is characterized. The first to sixth aspects of the present invention, wherein the learning unit learns by associating each device with a different set value, which is a non-defective product even if the rework target is the same, as an error for each device. The rework condition learning device according to any one of the items. In the good / bad determination result input unit, the image data of the rework target after removing the target part in the rework target associated with the good / bad judgment result is further input.
The learning unit further relates to any one of claims 1 to 7, wherein the learning unit learns by associating the set value, which is a non-defective product for each reprocessing target, with the processing target image data. The rework condition learning device described. Further equipped with a new rework target image data input section,
In the new rework target image data input unit, the new rework target image data of the rework target that has been newly soldered is input, and the new rework target image data is input.
The set value input unit is input with the set value associated with the rework target of the new rework target image data.
Using the learning result, the learning unit determines similar reprocessing target image data from the feature amount of the new reprocessing target image data input to the new reprocessing target image data input unit, and determines the determination. From the good / bad judgment result associated with the rework target image data, the good / bad judgment result of the rework target of the new rework target image data is determined.
The rework according to claim 8, wherein the good / bad determination result input unit inputs the good / bad determination result of the non-defective product or the defective product to be reprocessed, which is determined by the learning unit using the learning result. Condition learning device. A rework condition determination device using the learning result of the rework condition learning device according to any one of claims 1 to 9.
Using the rework target input unit into which the information of the rework target is input and the learning result of the learning unit, the set value in which the rework target in which the information is input to the rework target input unit is a good product. A rework condition determination device including a rework condition determination unit for determining. A rework condition determination device using the learning result of the rework condition learning device according to claim 7.
Using the rework target input unit into which the information of the rework target is input and the learning result of the learning unit, the set value in which the rework target in which the information is input to the rework target input unit is a good product. A rework condition determination device, comprising a rework condition determination unit for determining the presence or absence of the error associated with the determined set value. A rework device using the rework condition determination device according to claim 10 or 11.
The removal unit of the device, the condition setting unit in which the set value determined by the rework condition determination unit is input, and the removal unit are controlled so as to remove the target component under the conditions input to the condition setting unit. A rework device characterized by having a removal control unit. A rework device using the rework condition determination device according to claim 10.
The removal unit of the device, the condition setting unit in which the set value determined by the rework condition determination unit is input, and the removal unit are controlled so as to remove the target component under the conditions input to the condition setting unit. Equipped with a removal control unit
The removal control unit controls the removal control unit so as to remove the target component under the conditions input to the condition setting unit even when there is the error associated with the condition input to the condition setting unit. A rework device characterized by this. A soldering apparatus using the rework condition determining apparatus according to claim 11.
The removal unit of the device, the condition setting unit in which the set value determined by the rework condition determination unit is input, and the removal unit are controlled so as to remove the target component under the conditions input to the condition setting unit. Equipped with a removal control unit
The removal unit has the error associated with the condition input to the condition setting unit, and when the error has been corrected by the condition setting unit, the setting value serving as a reference value for correcting the error is used. A rework device characterized by controlling the removal portion so as to remove the target component. The set value input unit is characterized in that the set value including the mounting condition for attaching a new target component to the rework target from which the target component has been removed is input. The rework condition learning device according to any one of the following items. It is a rework condition learning device that learns the set value which is the mounting condition for attaching a new target part to the rework target from which the target part has been removed.
For each device to be reworked, the set value input unit for inputting the set value associated with the rework target and the rework reworked by the set value input to the set value input unit. Based on the good / bad judgment result input unit in which the good / bad judgment result of the target non-defective product or defective product is input, and the set value and the good / bad judgment result, the set value that becomes a good product for each rework target is set. A rework condition learning device characterized by having a learning unit for learning. The good / bad determination result input unit is the good / bad determination result including the determination result of the non-defective product or the defective product of the rework target to which the new target part is attached by the set value input to the set value input unit. The rework condition learning device according to claim 15 or 16, wherein is input. As the mounting condition, the set value input unit is of the second solder information of the new target component and the second solder information for mounting the new target component to the rework target. The rework condition learning device according to any one of claims 15 to 17, wherein the set value associated with the rework target defined in combination is input. In the set value input unit, the second solder information of the second combination is added to the composition of the second solder, the flux type added to the second solder, and the second solder. The rework according to claim 18, wherein the set value associated with the rework target, which is distinguished by at least one of the flux content and the area of the second solder, is input. Condition learning device. In the set value input unit, the set value in which the target component is associated with the rework target whose outer shape or the type of electrode surface treatment is distinguished in the second combination is input. The rework condition learning device according to claim 18 or 19. In the set value input unit, in the second combination, the member to which the new target component is fixed by soldering is distinguished by at least one of the thickness, the material, the number of layers, the specific gravity, and the type of surface treatment. The rework condition learning device according to any one of claims 18 to 20, wherein the set value associated with the rework target is input. The set value input unit has, as the mounting conditions, the composition of the second solder for mounting the new target component on the rework target, the flux type added to the second solder, and the second solder. The flux content added to the solder, at least one of the areas of the second solder, the outer shape of the new target component to be soldered, or the surface treatment of the electrode, whichever is new by soldering. It is characterized in that the set value associated with the rework target defined by the combination of at least one of the thickness, material, number of layers, specific gravity, and surface treatment type of the member to which the part is fixed is input. The rework condition learning device according to any one of claims 15 to 17. The 15th to 22nd claims, wherein the learning unit learns by associating each device with a different set value, which is a good product even if the rework target is the same, as an error for each device. The rework condition learning device according to any one of the items. Further, the good / bad determination result input unit is input with the image data of the rework target after the target component is newly attached in the rework target associated with the good / bad determination result.
The learning unit further relates to any one of claims 17 to 23, wherein the learning unit further learns by associating the set value, which is a non-defective product for each reprocessing target, with the processing target image data. The rework condition learning device described. Further equipped with a new rework target image data input section,
The new rework target image data input unit is input with the newly soldered new rework target image data.
The set value input unit is input with the set value associated with the rework target of the new rework target image data.
Using the learning result, the learning unit determines similar reprocessing target image data from the feature amount of the new reprocessing target image data input to the new reprocessing target image data input unit, and determines the determination. From the good / bad judgment result associated with the rework target image data, the good / bad judgment result of the rework target of the new rework target image data is determined.
The rework according to claim 24, wherein the good / bad determination result input unit inputs the good / bad determination result of the non-defective product or the defective product to be reprocessed, which is determined by the learning unit using the learning result. Condition learning device. A rework condition determination device using the learning result of the rework condition learning device according to any one of claims 15 to 25.
Using the rework target input unit into which the information of the rework target is input and the learning result of the learning unit, the set value in which the rework target in which the information is input to the rework target input unit is a good product. A rework condition determination device including a rework condition determination unit for determining. A rework condition determination device using the learning result of the rework condition learning device according to claim 23.
Using the rework target input unit into which the information of the rework target is input and the learning result of the learning unit, the set value in which the rework target in which the information is input to the rework target input unit is a good product. A rework condition determination device, comprising a rework condition determination unit for determining the presence or absence of the error associated with the determined set value. A rework device using the rework condition determination device according to claim 26 or 27.
Soldering is performed on the soldering unit of the device, the condition setting unit in which the set value determined by the rework condition determination unit is input, and the new target component under the conditions input in the condition setting unit. A rework device including a soldering control unit that controls the soldering unit as described above. A rework device using the rework condition determination device according to claim 26.
Soldering is performed on the soldering unit of the device, the condition setting unit in which the set value determined by the rework condition determination unit is input, and the new target component under the conditions input in the condition setting unit. It is provided with a soldering control unit that controls the soldering unit as described above.
The soldering control unit so as to solder a new target component under the conditions input to the condition setting unit even if there is the error associated with the conditions input to the condition setting unit. A rework device characterized by controlling the soldering control unit. A rework device using the rework condition determination device according to claim 27.
Soldering is performed on the soldering unit of the device, the condition setting unit in which the set value determined by the rework condition determination unit is input, and the new target component under the conditions input in the condition setting unit. It is provided with a soldering control unit that controls the soldering unit as described above.
The soldering control unit has the error associated with the condition input to the condition setting unit, and when the condition setting unit has corrected the error, the soldering control unit uses the set value which is a reference value for correcting the error. , A rework device characterized in that the soldered portion is controlled so as to solder a new target component. It is a rework condition learning device that learns the set value which is the removal condition for removing the target part from the rework target to which the target part is attached by soldering to the work target.
For each device to be reworked, the set value input unit for inputting the set value associated with the rework target and the rework reworked by the set value input to the set value input unit. Based on the good / bad judgment result input unit in which the good / bad judgment result of the target non-defective product or defective product is input, and the set value and the good / bad judgment result, the set value that becomes a good product for each rework target is set. The learning unit includes a learning unit for learning, and the learning unit corrects the error by associating each device with a different set value, which is a good product even if the rework target is the same, as an error for each device. It is a rework condition determination device using the learning result of the reflow condition learning device, which is characterized by determining the set value which is the reference value.
Using the rework target input unit into which the information of the rework target is input and the learning result of the learning unit, the set value in which the rework target in which the information is input to the rework target input unit is a good product. It is a rework device using a rework condition determination device, which is characterized by having a rework condition determination unit for determining the above.
The removal unit of the device, the condition setting unit in which the set value determined by the rework condition determination unit is input, and the removal unit are controlled so as to remove the target component under the conditions input to the condition setting unit. Equipped with a removal control unit
The removal unit has the error associated with the condition input to the condition setting unit, and when the error has been corrected by the condition setting unit, the setting value serving as a reference value for correcting the error is used. A rework device characterized by controlling the removal portion so as to remove the target component. It is a rework condition learning device that learns the set value which is the mounting condition for attaching a new target part to the rework target from which the target part has been removed.
For each device to be reworked, the set value input unit for inputting the set value associated with the rework target and the rework reworked by the set value input to the set value input unit. Based on the good / bad judgment result input unit in which the good / bad judgment result of the target non-defective product or defective product is input, and the set value and the good / bad judgment result, the set value that becomes a good product for each rework target is set. The learning unit includes a learning unit for learning, and the learning unit corrects the error by associating each device with a different set value, which is a good product even if the rework target is the same, as an error for each device. It is a rework condition determination device using the learning result of the rework condition learning device, which is characterized by determining the set value which is the reference value.
Using the rework target input unit into which the information of the rework target is input and the learning result of the learning unit, the set value in which the rework target in which the information is input to the rework target input unit is a good product. It is a rework device using a rework condition determination device, which is characterized by having a rework condition determination unit for determining the above.
Soldering is performed on the soldering unit of the device, the condition setting unit in which the set value determined by the rework condition determination unit is input, and the new target component under the conditions input in the condition setting unit. It is provided with a soldering control unit that controls the soldering unit as described above.
The soldering control unit has the error associated with the condition input to the condition setting unit, and when the condition setting unit has corrected the error, the soldering control unit uses the set value which is a reference value for correcting the error. , A rework device characterized in that the soldered portion is controlled so as to solder a new target component. The soldering unit has a solder printing function, and the soldering control unit controls the soldering unit to perform the soldering before the soldering unit solders a new target component. The reworking apparatus according to any one of claims 28 to 30, and 32, wherein printing is performed on the reworked object by a printing function. A rework condition learning device that learns a set value that is a condition for reworking to remove or attach a target part to a reworking target, and is associated with the reworking target for each device that performs the reworking. In addition, the set value input unit in which the set value is input and the quality determination result of the non-defective product or defective product to be reprocessed by the set value input in the set value input unit are input. A rework condition characterized by including a good / bad determination result input unit and a learning unit that learns the set value that is a good product for each rework target based on the set value and the good / bad determination result. Learning device. The rework condition learning device according to claim 34, wherein the device is at least one of a device for removing the target component by releasing soldering and a device for attaching a new target component by soldering.

Images