JP2020027329A - Facility diagnostic system and facility diagnostic method - Google Patents

Abstract

To provide a facility diagnostic system capable of more properly diagnosing disorder of manufacturing facilities.SOLUTION: A facility diagnostic system comprises: an operation information acquisition part 11 which acquires respective pieces of operation information on a plurality of manufacturing facilities; a disorder diagnostic part 12 which diagnoses, based upon the operation information, disorder of at least one of the plurality of manufacturing facilities; an output part 13 which outputs the diagnostic result of the disorder diagnostic part 12; and a feedback information acquisition part 14 which acquires feedback information responsive to the diagnostic result. Variance among the plurality of respective manufacturing facilities can be taken into consideration by using the feedback information, so the disorder of at least the one manufacturing facility which really needs to be maintained can be diagnosed.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a facility diagnosis system and a facility diagnosis method.

  Patent Document 1 discloses that a feeder of a mounting machine in a plurality of factories is monitored, use is prohibited when a specific parameter such as the number of times of supply or the number of times of supply error exceeds a threshold, and the feeder whose use is prohibited is repaired or inspected at a maintenance center. It is shown to be.

JP 2004-140162 A

  However, even when a specific parameter such as the number of times of supply or the number of times of supply error exceeds the threshold, the mounting machine is not malfunctioning, and repair or inspection of the mounting machine (hereinafter, referred to as maintenance) may not always be necessary. . When maintenance is performed on manufacturing equipment, such as a mounting machine, which is not malfunctioning and does not require maintenance, not only wasteful work is performed, but also parts are wasted, resulting in wasted cost (loss cost). turn into.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a facility diagnosis system and a facility diagnosis method that can more appropriately diagnose a malfunction of a manufacturing facility.

  In order to achieve the above object, a facility diagnosis system according to an aspect of the present invention includes an operation information acquisition unit that acquires operation information of each of a plurality of manufacturing facilities, and based on the operation information, A malfunction diagnosis unit that diagnoses malfunction of at least one of the manufacturing facilities, an output unit that outputs a diagnosis result of the malfunction diagnosis unit, and a feedback information acquisition unit that acquires feedback information on the diagnosis result.

  Each of these specific embodiments may be realized by an apparatus, a method, an integrated circuit, a computer program, or a recording medium, or may be realized by any combination of the apparatus, the method, the integrated circuit, the computer program, and the recording medium. You may.

  ADVANTAGE OF THE INVENTION According to the equipment diagnosis system etc. of this invention, malfunction of a manufacturing equipment can be diagnosed more appropriately.

1 is a diagram illustrating an example of a configuration of a facility diagnosis system according to Embodiment 1. FIG. FIG. 2 is a diagram illustrating an example of a detailed configuration of a malfunction diagnosis unit illustrated in FIG. 1. FIG. 3 is a diagram illustrating a configuration of a diagnostic model illustrated in FIG. 2 and a learning method. 5 is a flowchart showing a flow of an operation of the equipment diagnosis system according to the first embodiment. 5 is a flowchart showing a flow of operation of the equipment diagnosis system including a process of updating a diagnosis model in the first embodiment. FIG. 9 is a diagram illustrating an example of a configuration of a facility diagnosis system according to a second embodiment. FIG. 13 is a diagram illustrating a facility diagnosis system according to an example of the second embodiment. It is a top view of the mounting machine shown in FIG. FIG. 9 is a perspective view of the tape feeder shown in FIG. FIG. 9 is a side view illustrating a configuration of the tape feeder illustrated in FIG. 8. FIG. 8 is a diagram showing an example of the subjective data shown in FIG. 7. FIG. 8 is a diagram illustrating an example of maintenance performance data illustrated in FIG. 7.

  In order to achieve the above object, a facility diagnosis system according to an aspect of the present invention includes an operation information acquisition unit that acquires operation information of each of a plurality of manufacturing facilities, and based on the operation information, A malfunction diagnosis unit that diagnoses malfunction of at least one of the manufacturing facilities, an output unit that outputs a diagnosis result of the malfunction diagnosis unit, and a feedback information acquisition unit that acquires feedback information on the diagnosis result.

  According to this, the malfunction of the manufacturing equipment can be diagnosed more appropriately.

  Further, a maintenance unit may be provided for executing maintenance of the at least one manufacturing facility diagnosed as malfunction by the malfunction diagnosis unit.

  Further, a maintenance work instruction unit for instructing the maintenance unit to perform maintenance of the at least one manufacturing facility diagnosed as malfunction by the malfunction diagnosis unit may be provided.

  Further, a maintenance work instruction unit for instructing a user to perform maintenance of the at least one manufacturing facility diagnosed as malfunction by the malfunction diagnosis unit may be further provided.

  Further, the feedback information may include at least one of information on a maintenance result of the at least one manufacturing facility by the maintenance unit and information on a maintenance result by a checker.

  Further, the feedback information may include information on whether or not the malfunction diagnosis by the malfunction diagnosis unit is correct.

  Further, the malfunction diagnosis unit may have a diagnosis model, and the diagnosis model may be updated based on the feedback information.

  The diagnostic model may be created by learning using operation result data including operation information of each of the plurality of manufacturing facilities.

  Further, the apparatus may further include a facility collection instruction section for instructing a collection person who collects the at least one manufacturing facility diagnosed as malfunction by the malfunction diagnosis section.

  Further, the manufacturing facility may include at least one element of a surface mounting apparatus or a plurality of elements constituting the surface mounting apparatus.

  Further, the diagnostic model may be one of a plurality of diagnostic models, and the plurality of diagnostic models may be provided corresponding to a plurality of customers.

  Note that these general or specific aspects may be realized by a recording medium such as an apparatus, a method, an integrated circuit, a computer program or a computer-readable CD-ROM, and an apparatus, a system, a method, and an integrated circuit. , A computer program and a recording medium.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Each of the embodiments described below shows one specific example of the present invention. Numerical values, shapes, materials, constituent elements, arrangement positions and connection forms of constituent elements, use procedures, communication procedures, and the like shown in the following embodiments are merely examples, and do not limit the present invention. In addition, among the components in the following embodiments, components not described in the independent claims that indicate the highest concept of the present invention are described as arbitrary components. In addition, each drawing is not necessarily strictly illustrated. In each of the drawings, substantially the same configuration is denoted by the same reference numeral, and redundant description will be omitted or simplified.

(Embodiment 1)
Hereinafter, the equipment diagnosis system according to the first embodiment will be described with reference to the drawings.

[Configuration of Equipment Diagnosis System 10]
FIG. 1 is a diagram illustrating an example of a configuration of a facility diagnosis system 10 according to the first embodiment. The equipment diagnosis system 10 according to the present embodiment can diagnose a malfunction of a manufacturing equipment. As shown in FIG. 1, the equipment diagnosis system 10 includes an operation information acquisition unit 11, a malfunction diagnosis unit 12, an output unit 13, and a feedback information acquisition unit 14.

[Operation information acquisition unit 11]
The operation information acquisition unit 11 acquires operation information of each of a plurality of manufacturing facilities. The operation information acquisition unit 11 is realized by, for example, a computer including a processor (microprocessor), a memory, a communication interface, and the like. In the present embodiment, the operation information acquisition unit 11 periodically collects or acquires operation information (operation data) of the manufacturing equipment.

  Here, the manufacturing facility is a mounting facility, and includes at least one element of the surface mounting apparatus or a plurality of elements constituting the surface mounting apparatus. The manufacturing equipment is not limited to these cases, but may be any device or device for manufacturing a mounting board, a component, or the like in a factory, as long as it can acquire operation data indicating one or more parameters during operation. .

  The operation information is production performance characteristic data of one mounting facility, and is log data such as a correction amount, a suction learning value, a component suction event, and an error occurrence event. When acquiring the operation information, the operation information acquisition unit 11 acquires or stores the date and time (sampling date and time) when the operation information, that is, each data of the production result system characteristic data is acquired. The correction amount is a correction amount of the suction position when the mounting equipment picks up the electronic component. This correction amount, that is, the suction correction amount, is calculated for each component recognition result. Further, the suction learning value is an offset amount when a component is picked up from the feeder by the suction nozzle. The adsorption learning value is changed by learning a specified offset value from the recognition results obtained a plurality of times. The component suction frequency is the number of times the component has been suctioned from each feeder. The component suction frequency is obtained from the log data of the component suction event. Note that the component suction frequency is the number of times components are sucked from the component supply device for each component supply device (feeder), and may be, for example, the number of times that a total number of components have been suctioned since the component supply device was manufactured, The number of times the component is sucked in an arbitrary period may be used. The start date of the number of component suction times is not limited to these examples, and may be determined according to the application. The error occurrence count is the number of times that the suction nozzle in the mounting equipment has failed in picking up the component. The number of error occurrences is obtained from the log data of the error occurrence event. The start date of the number of occurrences of the error may be determined according to the application, similarly to the start date of the number of times of picking up components. The production performance characteristic data is hereinafter also referred to as operation data.

  Note that the operation information is not limited to the production performance characteristic data of one mounting facility, but may further include profile system characteristic data of one mounting facility. The profile feature data includes the component mounting date and time (time stamp), which is the date and time when the component (reel) was mounted on the feeder, the component dimensions, the component vendor supplied from the feeder, the maintenance date and time of the mounting equipment, and the Includes past failure locations, sprocket offset in mounting equipment, and height of feeder cover in mounting equipment. In the following, the subjective data and the production performance characteristic data excluding the component vendor are also referred to as maintenance performance data.

[Disease diagnosing unit 12]
The malfunction diagnosis unit 12 diagnoses a malfunction of at least one of the plurality of manufacturing facilities based on the operation information acquired by the operation information acquisition unit 11. The malfunction diagnosis unit 12 is realized by, for example, a computer including a processor (microprocessor), a memory, a communication interface, and the like. In the present embodiment, the malfunction diagnosis unit 12 estimates the malfunction level of the unit (element) configuring each of the plurality of mounting facilities from the operation information acquired by the operation information acquisition unit 11 using the diagnosis model 121. Then, the malfunction of at least one manufacturing facility is diagnosed. Here, the unit may be, for example, a tape feeder constituting a mounting facility, or may be a recognition camera, a mounting head, or the like as another unit. Further, it may be a component such as a gear or a motor constituting the tape feeder.

  FIG. 2 is a diagram showing an example of a detailed configuration of the malfunction diagnosis unit 12 shown in FIG. FIG. 3 is a diagram showing a configuration and a learning method of the diagnostic model 121 shown in FIG. The malfunction diagnosis unit 12 includes a diagnosis model 121, a pattern comparison unit 123, and a level determination unit 124, as shown in FIG.

<Diagnostic model 121>
The diagnostic model 121 is created by learning operation result data indicating operation information of each of a plurality of manufacturing facilities. The diagnostic model 121 is updated based on the feedback information.

  In the present embodiment, the diagnostic model 121 determines whether the behavior of a unit configuring each of the plurality of mounting facilities indicated by the characteristic data included in the operation information of each of the plurality of manufacturing facilities to be monitored is in a normal state. It is a model that can show. The diagnostic model 121 includes, for example, a normal behavior pattern 1211, a normal correlation pattern 1212, and a preprocessing unit 1213 as shown in FIG.

The preprocessing unit 1213 performs a process of accumulating production performance characteristic data such as operation performance data acquired by the operation information acquisition unit 11. Thus, the normal behavior pattern 1211 can be learned or additionally learned (updated) by using at least a certain amount of data for one day or one week. The preprocessing unit 1213 obtains the number of times of component suction from the log data of the component suction event acquired by the operation information acquisition unit 11 and accumulates the number as the production performance characteristic data. Similarly, the preprocessing unit 1213 obtains the number of times of error occurrence from the log data of the error occurrence event acquired by the operation information acquisition unit 11 and accumulates the number as the production performance characteristic data.

  The normal behavior pattern 1211 uses at least one day's worth or one week's worth of production result type feature data, and a pattern showing how the production result type feature data changes if the unit is in normal behavior is statistical. It is created by dynamic machine learning. For example, the normal behavior pattern 1211 may be a probability pattern obtained from, for example, logistic regression analysis. In addition, the normal behavior pattern 1211 is additionally learned, that is, updated based on subjective data that is feedback information on a diagnosis result in which a fixed amount is accumulated.

  The subjective data is obtained by a user or the like subjectively determining the validity of information on whether or not the malfunction diagnosis by the malfunction diagnosis unit 12 is correct. Note that, based on the subjective data, the threshold described later may be changed without changing the normal behavior pattern 1211. This allows the variation of each unit to be reflected on the basis of subjective data by a person involved in the maintenance of the unit, so that the unit requiring maintenance can be more accurately estimated. Note that the unit-to-unit variation is a difference depending on how the unit is used, and means that the necessity of maintenance is different even if the same correction amount, error occurrence number, or component suction number is indicated. Further, the subjective data may include visual inspection data indicating a result of visually inspecting the maintenance target.

  The normal correlation pattern 1212 indicates what kind of fluctuations occur in the normal behavior of the unit when it is divided into components, offsets, and the like, using production performance feature data and profile feature data. It is a pattern. The normal correlation pattern 1212 is also created by performing statistical machine learning, and is a probability pattern obtained from, for example, logistic regression analysis. Further, the normal correlation pattern 1212 is additionally learned or updated based on subjective data and maintenance performance data, which are feedback information on the diagnosis result, accumulated in a certain amount.

  The maintenance result data includes at least one of information on a maintenance result of a unit diagnosed as malfunctioning by the malfunction diagnosis unit 12 and information on a maintenance result by a checker. The information on the maintenance result includes, for example, maintenance execution date and time, a past failure location, a maintenance execution item, and the like, and the maintenance execution item includes, for example, a sprocket offset and a height of a feeder cover. In addition, information on the maintenance result includes the serial number of the unit, the date and time when the unit was accepted, the maintenance staff and execution date and time, the status before maintenance, the execution items at the time of maintenance, the adjustment and measurement results, and the date and time when the unit was returned. You may. Thus, the variation of each unit can be reflected on the basis of the actual maintenance data, so that a malfunctioning unit requiring maintenance can be more accurately estimated. The confirmer is not limited to the user who manages one manufacturing facility, but may be a person of a service company that performs maintenance such as a service person.

<Pattern comparison unit 123>
The pattern comparing unit 123 compares the created diagnostic model 121, which is a learning model, with the feature data included in the operation information of the manufacturing facility to be compared. More specifically, the pattern comparison unit 123 compares whether or not the feature data included in the operation information of the unit to be compared is included in the normal range indicated by the normal behavior pattern 1211 and the normal correlation pattern 1212. When the feature data is not included in the normal range as a result of the comparison, the pattern comparison unit 123 outputs the difference to the level determination unit 124 as an index.

<Level determination unit 124>
As a result of the comparison by the pattern comparing unit 123, when the feature data is not included in the normal range, the level determining unit 124 estimates the malfunction level depending on whether the difference exceeds a predetermined threshold. The level determination unit 124 determines that the malfunction level is an abnormal level or a normal level depending on whether or not the threshold level is exceeded. Note that, even when the level does not exceed the threshold value (first threshold value), the level determination unit 124 sets the level at which an abnormality may occur (that is, the abnormality grace level) or the normal level depending on whether or not the threshold value is exceeded. It may be determined that there is.

[Output unit 13]
The output unit 13 outputs a diagnosis result of the malfunction diagnosis unit 12. The output unit 13 is realized by, for example, a computer including a processor (microprocessor), a memory, a communication interface, and the like.

  More specifically, the output unit 13 may be a transmission unit that transmits a diagnosis result of at least one manufacturing facility diagnosed by the malfunction diagnosis unit 12 as malfunction to a user who manages one manufacturing facility. In this case, the output unit 13 may be a server that transmits a diagnosis result by e-mail or the like. The output unit 13 may be a display unit such as a display that displays a diagnosis result of at least one manufacturing facility diagnosed by the malfunction diagnosis unit 12 as malfunctioning.

[Feedback information acquisition unit 14]
The feedback information acquisition unit 14 acquires feedback information for a diagnosis result. The feedback information acquisition unit 14 is realized by, for example, a computer including a processor (microprocessor), a memory, a communication interface, and the like.

  Here, the feedback information may include, for example, at least one of information on a maintenance result of the unit diagnosed as malfunction by the malfunction diagnosis unit 12 and information on a maintenance result by the user. Further, the feedback information may further include information for which the validity is subjectively determined, such as information on whether or not the malfunction diagnosis by the malfunction diagnosis unit 12 is correct.

  The maintenance result of the unit diagnosed as malfunction by the malfunction diagnosis unit 12 is, for example, maintenance result data. As described above, the maintenance performance data includes, for example, the serial number of the unit, the date and time when the unit was accepted, the maintenance staff and the execution date and time, the status before maintenance, the items to be performed during maintenance, the adjustment and measurement results, and the return of the unit. Date and time may be included. As described above, the maintenance result data includes information indicating a result of the maintenance performed on each unit to be maintained.

[Operation of Equipment Diagnosis System 10]
The operation of the equipment diagnosis system 10 configured as described above will be described below.

  FIG. 4 is a flowchart showing a flow of the operation of the equipment diagnosis system 10 according to the first embodiment.

  First, the facility diagnosis system 10 acquires operation information of each of a plurality of manufacturing facilities (S11).

  Next, the equipment diagnosis system 10 diagnoses a malfunction of at least one of the plurality of manufacturing facilities based on the operation information acquired in step S11 (S12). In the present embodiment, the equipment diagnosis system 10 estimates a malfunction level of a unit (element) configuring each of the plurality of mounting equipments, for example, using the diagnosis model 121 based on the operation information acquired in step S11.

  Next, the equipment diagnosis system 10 outputs the diagnosis result diagnosed in step S11 (S13). For example, the equipment diagnosis system 10 transmits a diagnosis result of at least one manufacturing equipment diagnosed by the malfunction diagnosis unit 12 as malfunction to a user who manages one manufacturing equipment.

  Next, the equipment diagnosis system 10 acquires feedback information on the diagnosis result (S14). In the present embodiment, when a certain amount of feedback information is accumulated for at least one day or one week, the equipment diagnosis system 10 updates the diagnostic model 121 using the accumulated feedback information. Hereinafter, the flow of the operation of the equipment diagnostic system 10 including the process of updating the diagnostic model 121 will be described.

  FIG. 5 is a flowchart showing the flow of the operation of the equipment diagnostic system 10 including the processing up to the update of the diagnostic model 121 in the first embodiment. The same elements as those in FIG. 4 are denoted by the same reference numerals, and detailed description will be omitted.

  That is, in step S15, the facility diagnosis system 10 determines whether the acquired feedback information has exceeded a predetermined amount (S15). In the present embodiment, the facility diagnosis system 10 determines whether or not a certain amount of feedback information is accumulated for at least one day or one week.

  Next, the equipment diagnosis system 10 updates the diagnosis model 121 based on the acquired feedback information (S16). In the present embodiment, the diagnostic model 121 is updated using the feedback information accumulated in a certain amount. Thereby, the unit-to-unit variation due to a difference in the usage method or the like can be reflected in the diagnostic model 121 using the feedback information, so that the unit requiring maintenance can be more accurately estimated.

[Effects]
As described above, the equipment diagnosis system 10 of the present embodiment not only diagnoses a malfunction of at least one of the plurality of manufacturing facilities based on the operation information of the plurality of manufacturing facilities, but also provides feedback information. To get. By using the acquired feedback information, it is possible to take into account the variation of each of the plurality of manufacturing facilities due to a difference in the method of use. As a result, it is possible to more accurately diagnose a malfunction of at least one manufacturing facility that really requires maintenance, and it is possible to more appropriately diagnose a malfunction of the manufacturing facility.

  Here, the equipment diagnosis system 10 of the present embodiment uses the diagnosis model 121 created in advance to perform malfunction diagnosis of the manufacturing equipment from the operation information of each of the plurality of monitoring target manufacturing equipment. The diagnostic model 121 created in advance is created by performing statistical machine learning in advance using operation data of a plurality of manufacturing facilities. The diagnostic model 121 created in advance corresponds to a learning model common to a plurality of manufacturing facilities, such as learning by treating elements having differences for each manufacturing facility as constants.

  Further, the diagnostic model 121 is updated (additional learning) using the feedback information accumulated in a certain amount. Thus, it is possible to reflect the variation of each of the plurality of manufacturing facilities due to the difference in the usage method or the like to the diagnostic model 121 using the feedback information. As a result, it is possible to more accurately diagnose a malfunction of a manufacturing facility that really requires maintenance. The updated diagnostic model 121 is created by performing statistical machine learning using feedback information such as subjective data and actual maintenance data. The updated diagnostic model 121 is manufactured by performing additional learning by substituting a part treated as a constant of the diagnostic model 121 created in advance using data or a value indicating an element having a difference for each manufacturing facility. This corresponds to a learning model optimized for each facility.

(Embodiment 2)
In the first embodiment, the description has been given based on the minimum configuration of the equipment diagnosis system. However, the present invention is not limited to this. The apparatus may further include a configuration for performing maintenance of the manufacturing facility diagnosed as malfunctioning. This case will be described as a second embodiment. In the following, a description will be given mainly of points different from the first embodiment.

[Configuration of Equipment Diagnosis System 20]
FIG. 6 is a diagram illustrating an example of a configuration of the equipment diagnosis system 20 according to the second embodiment. The same components as those in FIG. 1 are denoted by the same reference numerals, and detailed description thereof will be omitted. As shown in FIG. 6, the equipment diagnosis system 20 includes an operation information acquisition unit 11, a malfunction diagnosis unit 12, an output unit 13, a feedback information acquisition unit 14, a facility collection instruction unit 25, and a maintenance work instruction unit 26. And a maintenance unit 27. The equipment diagnosis system 20 is different from the equipment diagnosis system 10 in the first embodiment in that the configuration of an equipment collection instruction unit 25, a maintenance work instruction unit 26, and a maintenance unit 27 is added, and malfunction diagnosis is performed. The configuration of the unit 22 is different.

[Disease diagnosing unit 22]
The malfunction diagnosis unit 22 diagnoses malfunction of at least one of the plurality of manufacturing facilities based on the operation information acquired by the operation information acquisition unit 11. More specifically, the malfunction diagnosis unit 22 estimates the malfunction level of a unit (element) constituting each of the plurality of mounting facilities from the operation information acquired by the operation information acquisition unit 11 using the diagnosis model 121. Diagnosing a malfunction of at least one manufacturing facility.

  Here, the malfunction diagnosis unit 22 according to the second embodiment uses a different diagnosis model 121 than the malfunction diagnosis unit 12 according to the first embodiment. That is, the diagnostic model 121 is one of a plurality of diagnostic models provided for a plurality of customers. More specifically, first, the diagnostic model 121 is a pre-created common learning learned using operation result data indicating operation information of each of a plurality of manufacturing facilities so as to correspond to a plurality of customers in common. Model. The diagnostic model 121 is updated by learning using operation result data indicating operation information of each of a plurality of manufacturing facilities belonging to the sixteen customers so as to correspond to one customer. Model. The diagnosis model 121 is further updated based on feedback information on the diagnosis results of the plurality of manufacturing facilities belonging to the one customer, and becomes an optimized learning model.

  The other configuration is the same as that of the malfunction diagnosis unit 12 according to the first embodiment, and a description thereof will not be repeated.

[Equipment recovery instruction section 25]
The equipment recovery instructing unit 25 instructs a collector who collects at least one manufacturing equipment diagnosed as malfunctioning by the malfunction diagnosis unit 22.

  In the present embodiment, the equipment recovery instructing unit 25 is configured to notify the recoverer who recovers the at least one unit based on the diagnosis result of the unit constituting each of the at least one manufacturing equipment diagnosed by the malfunction diagnosis unit 12 as malfunctioning. To instruct. Here, the collecting person is a person in charge of the sales company that sells the at least one unit or a person who is requested to collect by the sales company. The sales company may be a manufacturer of the at least one manufacturing facility or unit, or may be a company that sells the at least one manufacturing facility or unit.

[Maintenance work instruction unit 26]
The maintenance work instructing unit 26 instructs the maintenance unit 27 to perform maintenance on at least one manufacturing facility diagnosed as malfunction by the malfunction diagnosis unit 22. Further, the maintenance work instructing unit 26 may instruct a user to perform maintenance of at least one manufacturing facility diagnosed as malfunction by the malfunction diagnosis unit 22.

  In the present embodiment, the maintenance work instructing unit 26 instructs maintenance of the at least one unit based on the diagnosis result of the unit configuring each of the at least one manufacturing facility diagnosed by the malfunction diagnosis unit 12 as malfunctioning. When the maintenance on the at least one unit is performed by the maintenance unit 27, the maintenance work instruction unit 26 may instruct the maintenance unit 27 to perform maintenance on the at least one unit. When maintenance on the at least one unit is performed by a user or the like, the maintenance work instruction unit 26 may instruct the user to perform maintenance on the at least one unit.

[Maintenance unit 27]
The maintenance unit 27 performs maintenance of at least one manufacturing facility diagnosed as malfunction by the malfunction diagnosis unit 22.

  More specifically, the maintenance unit 27 controls the automatic maintenance device, and when the maintenance of the at least one unit can be performed, causes the automatic maintenance device to perform the maintenance. Here, the automatic maintenance device is a device that performs an inspection by measuring various states of a unit that configures the at least one manufacturing facility, and that repairs or replaces the unit. The automatic maintenance device may perform only inspection among inspection, repair, and replacement, and repair and replacement may be performed by a user such as a maintenance person.

[Effects]
As described above, the facility diagnosis system 20 of the present embodiment, based on the operation information of each of the plurality of manufacturing facilities belonging to the one customer, manufactures at least one of the plurality of manufacturing facilities belonging to the one customer. In addition to diagnosing equipment malfunctions, obtain feedback information. Further, by using the feedback information on the diagnosis results of the plurality of manufacturing facilities belonging to the one customer, it is possible to consider the variation of each of the plurality of manufacturing facilities belonging to the one customer. As a result, of the plurality of manufacturing facilities belonging to the one customer, it is possible to more accurately diagnose a malfunction of at least one of the manufacturing facilities that requires truly maintenance, and to more appropriately diagnose the malfunction of the manufacturing facility. Diagnose.

  In addition, the equipment diagnosis system 20 of the present embodiment uses the diagnosis model 121 created in advance to perform malfunction diagnosis of the manufacturing equipment from the operation information of each of the plurality of monitoring target manufacturing equipments belonging to the one customer. The diagnostic model 121 created in advance is created by performing statistical machine learning in advance using operation data of a plurality of manufacturing facilities belonging to the one customer. The diagnostic model 121 created in advance corresponds to a learning model common to a plurality of manufacturing facilities belonging to the one customer.

  Further, the diagnostic model 121 is updated (additional learning) by using feedback information on diagnostic results of a plurality of manufacturing facilities belonging to the one customer accumulated in a certain amount. Thus, using the feedback information on the diagnosis results of the plurality of manufacturing facilities belonging to the one customer, it is possible to reflect the variation of each of the plurality of manufacturing facilities due to a difference in use method or the like in the diagnostic model 121. As a result, out of the plurality of manufacturing facilities belonging to the one customer, it is possible to more accurately diagnose a malfunction of the manufacturing facility that truly requires maintenance. The updated diagnosis model 121 is created by performing statistical machine learning using feedback information such as subjective data and maintenance result data on the diagnosis results of a plurality of manufacturing facilities belonging to the one customer. The updated diagnostic model 121 corresponds to a learning model optimized for each manufacturing facility belonging to the one customer.

(Example)
As an example of a specific mode of the equipment diagnosis system 20 according to Embodiment 2, an equipment diagnosis system 20A in the surface mounting industry will be described with reference to FIG.

  FIG. 7 is a diagram illustrating an equipment diagnosis system 20A according to an example of the second embodiment.

  The equipment diagnosis system 20A in the surface mounting industry is configured to diagnose malfunction of a plurality of units constituting a surface mounting machine as a manufacturing equipment. The equipment diagnosis system 20A shown in FIG. 7 includes an equipment diagnosis device 10A, a server 13A, and a mail server 13B. Further, as shown in FIG. 7, the equipment diagnosis system 20A includes a mail server 25A, an automatic maintenance device 27A, a mounting machine 202, an LNB 203, a server 204, a database 205, an input device 206, a data collection device 207 and an input device 208 may be provided. These devices are physically arranged in one of a plurality of areas such as an area belonging to the diagnostic provider 201A, a cloud 201B, an area belonging to the sales company 201C, and an area belonging to the factory 201D.

<Diagnosis provider 201A>
The diagnosis provider 201A is a company that provides a result of diagnosing a malfunction in a plurality of units constituting the surface mounter. In the area to which the diagnostic provider 201A belongs, the equipment diagnostic device 10A, the server 13A, and the mail server 13B are physically arranged.

  The equipment diagnosis device 10A includes, for example, all the components that constitute the equipment diagnosis system 10. In the present embodiment, the facility diagnostic apparatus 10A uses the diagnostic model 121 to execute a server diagnosis based on the operation data of the mounting machine 202 collected at the factory 201D, and diagnoses the malfunction of each of the plurality of units constituting the mounting machine 202 on the server. 13A.

  In the diagnostic model 121 in this embodiment, operation result data indicating operation information of the mounting machine 202 which is a manufacturing apparatus belonging to the factory 201D is learned so as to correspond to one customer. That is, the diagnostic model 121 is a model that can indicate whether or not a plurality of units included in the mounting machine 202 are in a normal state. The diagnostic model 121 is created by learning using the operation result data as a reference recommended by the manufacturer of the mounting machine 202. For this reason, the equipment diagnosis apparatus 10A compares the diagnosis model 121 with the characteristic data obtained from the operation result data of the mounting machine 202 that is the monitoring target manufacturing equipment, and indicates whether the difference exceeds a predetermined threshold. The diagnostic result is output to the server 13A.

  After that, the diagnostic model 121 is updated based on feedback information on the diagnostic result of the mounting machine 202 belonging to the factory 201D. In the present embodiment, for example, when the feedback information for the diagnosis result of one unit is subjective data, and it indicates that the diagnosis result of the one unit is NG, the predetermined threshold is changed. On the other hand, for example, when the feedback information for the diagnosis result of one unit is subjective data and it is indicated that the diagnosis result of the one unit is OK, the actual malfunction location of the one unit and the behavior data thereof Are used as teacher data, and the diagnostic model 121 is additionally learned (updated). Thereby, the accuracy of malfunction diagnosis can be improved.

  Further, for example, when the feedback information for the diagnosis result of one unit is the maintenance result data, the diagnostic model 121 is additionally learned using the maintenance result data including the actual malfunction location of the one unit and its behavior data as the teacher data. (Update. Thereby, the accuracy of malfunction diagnosis can be improved. Further, for example, the feedback information on the diagnosis result of one unit may be the subjective data and the maintenance result data.

  The server 13A creates a report such as a malfunction candidate unit list from the diagnosis result output from the equipment diagnosis apparatus 10A. The server 13A creates a report such as a malfunction candidate unit list by collecting and listing the units determined to be malfunctioning in the diagnosis result.

  The mail server 13B transmits a report such as the malfunction candidate unit list created by the server 13A to the mail server 25A. As a result, the malfunction candidate unit can be transmitted to the user who manages or maintains the mounting machine 202 in the factory 201D.

<Cloud 201B>
The cloud 201B is a virtual server that cooperates with various devices via the Internet. The cloud 201B provides on-demand use of IT resources such as a database via the Internet.

  The database 205 is managed by the cloud 201B. The database 205 stores operation data of the mounting machine 202 collected in the factory 201D. Further, the database 205 also stores the maintenance result data of the mounting machine 202. The database 205 may store feedback information such as an evaluation of a user who manages or maintains the mounting machine 202 in the factory 201D with respect to the malfunction candidate unit list created by the server 13A.

<Factory 201D>
The factory 201D is a company or the like that manufactures electronic components and the like using manufacturing equipment. In the area to which the factory 201D belongs, the mail server 25A, the mounting machine 202, the LNB 203, the server 204, and the input device 206 are physically arranged.

  The mounting machine 202 is an example of a manufacturing facility and is a surface mounting machine. The mounting machine 202 is composed of a plurality of units as a plurality of elements.

  Here, an example of the configuration of the mounting machine 202 will be described with reference to FIGS. FIG. 8 is a plan view of the mounting machine 202 shown in FIG.

  In the mounting machine 202, a board fixing portion (conveyor rail) for fixing a circuit board 314 on which electronic components (not shown) are mounted is provided at the center of the base 313. The base 313 is provided with a pair of component mounting stages 315 symmetrically with respect to the board fixing portion.

  The component mounting stage 315 includes a plurality of rows of tape feeders 310 that continuously supply electronic components, and enables various types of electronic components to be sucked at the component supply position. The component mounting stage 315 includes a suction head 316 that holds an electronic component at a component supply position and mounts the electronic component on the circuit board 314.

  The suction head 316 is supported by the XY robot 317. The XY robot 317 is movable in each of the XY directions in FIG. 8, and moves the suction head 316 to a component supply position or above the circuit board 314. The XY robot 317 has an X-axis beam 318, and the suction head 316 is supported by the X-axis beam 318 so as to be movable in the X direction. The X-axis beam 318 is movable in the Y direction along the Y-axis beam 319.

  A nozzle change section 320 is provided between the component mounting stage 315 and the board fixing section. The nozzle change unit 320 is provided with a nozzle holder 221, a component recognition unit 322, and a waste tray 323.

  The nozzle holder 221 stores component suction nozzles 324 for various electronic components to be mounted on the suction head 316. The suction head 316 can replace the component suction nozzle 324 with the nozzle change unit 320. The component recognition unit 322 includes an optical sensor such as a line sensor, and recognizes the attitude (component position, rotation angle, and the like) of the electronic component that is being sucked by the component suction nozzle 324 of the suction head 316. If the electronic component being sucked by the component suction nozzle 324 of the suction head 316 has a wrong type or a defect in the discard tray 323, the electronic component is discarded.

  Next, the configuration of the tape feeder 310 will be described.

  FIG. 9 is a perspective view of the tape feeder 310 shown in FIG. FIG. 10 is a side view showing the configuration of the tape feeder 310 shown in FIG.

  The tape feeder 310 is held on a trolley (not shown), and is detachable from the mounting machine 202 by an operator operating the trolley. A tape reel 325 shown in FIG. 9 is mounted on the tape feeder 310, and a tape 326 shown in FIG. The tape feeder 310 has a function of performing a feeding operation of the tape 326 inside the outer frame 32 shown in FIG. 10 to feed electronic components housed at a constant pitch to the tape 326 to the supply port 328.

  A tape feed mechanism 329 is provided at a tip end in the outer frame 327. The tape feed mechanism 329 includes a sprocket 332 having a pin formed on an outer periphery for engaging a feed hole formed at an equal pitch in the feed direction of the tape 326. The tape feed mechanism 329 is a drive motor 333 that is a rotation drive unit of the sprocket 332, a transmission mechanism that transmits the rotation drive of the drive motor 333 to the sprocket 332, and a control unit that controls the rotation drive of the drive motor 333. A feeder control unit 335 is provided.

  When the drive motor 333 is controlled to rotate intermittently according to the storage pitch of the electronic components, the sprocket 332 performs index rotation, and the tape 326 wound on the tape reel 325 is moved from the rear end to the outer frame 327. It is pulled in and pitch-fed to the tip. As a result, the electronic components stored in the tape 326 are sequentially supplied to the supply port 328 at the pickup position.

  The supply port 328 is formed by being opened at a part of a tape guide 337 that is mounted on the upper part of the outer frame 327 and guides the feeding of the tape 326. A part of the tape guide 337 is a folded portion of the cover tape 338 peeled off from the surface of the tape 326, and the cover tape peeling mechanism 39 peels off the cover tape 338 from the surface of the tape 326. Thus, the electronic component is supplied to the supply port 328 in an exposed state, and is picked up by the component suction nozzle 324 positioned above the supply port 328.

  The gear unit 340 is configured by a gear train of a drive gear 343, a first transmission gear 345, a second transmission gear 346, a third transmission gear 347, and a final gear 342. The drive gear 343 is attached to the output shaft of the drive motor 333. The first transmission gear 345 meshes with the drive gear 343. A second transmission gear 346 is coaxially fixed to the first transmission gear 345, and the second transmission gear 346 meshes with the third transmission gear 347. The third transmission gear 347 meshed with the second transmission gear 346 also meshes with the final gear 342 fixed to the rotation shaft of the sprocket 332.

  In the tape feeder 310, when the electronic components stored in the tape 326 at the same pitch are sequentially supplied to the supply port 328, the stop position of the tape 326 or the sprocket 332 for each pitch feed is set so that the feed position does not vary. Must be precisely adjusted.

  Therefore, the cause of the malfunction in the mounting machine 202 configured as described above is, for example, as follows. Examples include dirt of the supply port 328, wear and play of the tip of the sprocket 332, set and shift of the drive motor 333, and play of the tape feeder 310, shift of the feed position, and deterioration of the motor torque.

  Hereinafter, returning to FIG. 7, the description will be continued.

  The LNB 203 is also called a line network box, and is a device that collects data obtained when the mounting machine 202 is operating. The LNB 203 is realized by, for example, a computer including a processor (microprocessor), a memory, a communication interface, and the like. The LNB 203 collects operation data of the mounting machine 202 and transmits it to the server 204.

  The server 204 stores the operation data of the mounting machine 202 transmitted from the LNB 203 in the database 205. Further, the server 204 stores the subjective data as feedback information for the diagnosis result of the mounting machine 202 transmitted from the LNB 203 in the database 205.

  The mail server 25A receives the report such as the malfunction candidate unit list created by the server 13A. Thus, a user who manages or maintains the mounting machine 202 in the factory 201D receives the malfunction candidate unit, and can check whether the malfunction candidate unit is really malfunctioning in the mounting machine 202. If the user confirms that the unit was really malfunctioning, he or she contacts the person in charge of the sales company 201C and arranges to have the unit (the unit malfunctioning) confirmed to be malfunctioning collected. After maintenance, the unit is returned.

  The input device 206 is a device to which subjective data is input by a user's input. The input device 206 is realized by, for example, a computer including a processor (microprocessor), a memory, a communication interface, and the like.

  Here, the subjective data indicates the result of confirming whether or not the malfunction candidate unit is really malfunctioning in the mounting machine 202 and subjectively determines the validity of the malfunction candidate unit. In this embodiment, the subjective data is input for each unit.

  FIG. 11 is a diagram showing an example of the subjective data shown in FIG.

  For example, as shown in FIG. 11, the subjective data includes a unit serial number that uniquely identifies a unit, a malfunction determination person and a determination date and time, a malfunction determination result, and information indicating a physical state. The malfunction determination person and determination date and time indicate the name of the person (user) who made the malfunction determination of the unit indicated by the unit serial number and the date and time thereof based on the malfunction candidate unit list. The malfunction determination result indicates whether or not the result of checking the actual unit of the unit indicated by the unit serial number indicates that the determination as a malfunction candidate was correct.

  The actual state includes different information depending on whether the condition is abnormal or not. In the case of a malfunction, the information of the actual unit of the unit indicated by the unit serial number includes a) a malfunctioning portion, b) a malfunction phenomenon, and c) other special information. On the other hand, if there was no malfunction, a) there was no problem with the actual unit of the unit indicated by the unit serial number; ) Number of feeds, c) maintenance counter, and d) information indicating the error rate.

<Distributor 201C>
The sales company 201C is a company that sells or maintains the mounting machine 202 or a plurality of units that constitute the mounting machine 202. In the area to which the sales company 201C belongs, the automatic maintenance device 27A, the data collection device 207, and the input device 208 are physically arranged.

  The person in charge of the sales company 201C receives the notification, collects the malfunctioning unit, and returns the unit after maintenance.

  The automatic maintenance device 27A performs inspection by measuring various states of the malfunctioning unit, and performs maintenance of the malfunctioning unit by repairing or replacing the unit. Note that the automatic maintenance device 27A may perform only inspection among inspection, repair, and replacement, and repair and replacement may be performed by a maintenance person.

  The data collection device 207 is a device that collects maintenance result data that is data relating to maintenance performed on the malfunctioning unit. If the data collection device 207 can collect a part or all of the maintenance result data of the malfunctioning unit from the automatic maintenance device 27A, the data collection device 207 may collect the part or all. In addition, when the maintenance staff has performed maintenance on the malfunctioning unit, the data collection device 207 collects the maintenance result data input to the input device 208 by the maintenance staff. Further, the data collection device 207 stores the collected maintenance result data in the database 205. The data collection device 207 is realized by, for example, a computer including a processor (microprocessor), a memory, a communication interface, and the like.

  The input device 208 is realized by, for example, a computer including a processor (microprocessor), a memory, a communication interface, and the like. The input device 208 is a device to which a maintenance result is input by an input of a maintenance person or the like. The input device 208 transmits the input maintenance result to the data collection device 207 as maintenance result data. The input device 208 may be configured to receive subjective data by a person in charge of the sales company 201C such as a person in charge of maintenance.

  Here, as described above, the maintenance performance data is data that is input when performing maintenance for each maintenance target unit, and is data relating to maintenance performed for a malfunctioning unit. In the present embodiment, the maintenance result data is also input for each unit. Since the subjective data is as described above, the description is omitted here.

  FIG. 12 is a diagram showing an example of the maintenance result data shown in FIG.

  For example, as shown in FIG. 12, the maintenance result data includes a unit serial number, an acceptance date and time, a maintenance person and execution date and time, a state before maintenance, a maintenance execution item, an output result of the automatic maintenance device, and a shipment. It contains information indicating the date and time and the mounting machine number.

  The unit serial number indicates an identification number for uniquely identifying a malfunctioning unit. The acceptance date and time indicates the date and time when the actual unit of the unit indicated by the unit serial number was accepted as a malfunctioning unit. The person in charge of maintenance and the date and time of maintenance indicate the name of the person in charge of maintenance of the unit indicated by the unit serial number and the date and time. The pre-maintenance state indicates a state before the actual maintenance of the unit indicated by the unit serial number is performed (at the time of acceptance). The maintenance execution item indicates an item for which maintenance has been performed, for example, an inspected item and an adjusted item. The output result of the automatic maintenance device indicates a maintenance execution item by the automatic maintenance device 27A. The shipment date and time indicates the date and time when the unit indicated by the unit serial number was shipped for return to the user. The mounting machine number is a serial number that uniquely identifies the mounting machine 202 that has constituted the malfunction unit.

  According to the above embodiment, it is possible to diagnose malfunction of each of the plurality of units constituting the mounting machine 202 belonging to the factory 201D based on the operation information of the mounting machine 202 belonging to the factory 201D of the one customer. . Further, by using the feedback information on the diagnosis result of each of the plurality of units configuring the mounting machine 202, it is possible to consider the variation of each of the plurality of units configuring the mounting machine 202 belonging to the factory 201D of the customer. As a result, it is possible to more accurately diagnose a malfunction of at least one of the plurality of units constituting the mounting machine 202 that requires truly maintenance.

  The equipment diagnosis apparatus 10A according to the present embodiment performs malfunction diagnosis of a plurality of units configuring the mounting machine 202 from the operation information of the monitoring target mounting machine 202 using the diagnostic model 121 created in advance. The diagnostic model 121 created in advance is created by performing statistical machine learning in advance using operation data of the mounting machine 202 belonging to the factory 201D of the customer. The diagnostic model 121 created in advance corresponds to a learning model common to a plurality of units configuring the mounting machine 202 belonging to the factory 201D of the one customer.

  Further, the diagnostic model 121 is updated (additional learning) using feedback information on diagnostic results of a plurality of units constituting the mounting machine 202 belonging to the factory 201D of the one customer stored in a certain amount. As a result, using the feedback information on the diagnosis results of the plurality of units included in the mounting machine 202 belonging to the factory 201D of the one customer, the variation of each of the plurality of units due to a difference in use method is reflected in the diagnosis model 121. be able to. As a result, out of a plurality of units constituting the mounting machine 202 belonging to the factory 201D of the one customer, it is possible to more accurately diagnose a malfunction of a unit that truly requires maintenance. The updated diagnostic model 121 is statistically machine-learned using feedback information, such as subjective data and maintenance performance data, on the diagnostic results of a plurality of units included in the mounting machine 202 belonging to the one customer's factory 201D. Created by: The updated diagnostic model 121 corresponds to a learning model optimized for each of a plurality of units constituting the mounting machine 202 belonging to the factory 201D of the one customer.

  As described above, in the equipment diagnosis system 20A, 1) operation data of the mounting machine 202 (a plurality of constituent units) which is a customer apparatus is collected, and 2) the AI, that is, the equipment diagnosis apparatus 10A is obtained from the collected operation data. Diagnose the malfunction of the customer's equipment and 3) send the diagnosis result to the customer. Also, in the equipment diagnosis system 20A, 4) when the transmitted diagnosis result is confirmed by the customer and feedback information as subjective data is input, 5) feedback information as subjective data is collected, and AI teacher data is collected. Used as In the equipment diagnosis system 20A, 6) at least one of the plurality of units constituting the mounting machine 202 diagnosed as malfunctioning is collected by the sales company 201C or the like, and maintenance is performed manually or automatically. 7) Maintenance result data, which is the result of manual or automatic maintenance, is collected and used as AI teacher data. By performing the data flows 1) to 7) for each customer, it is possible to more accurately diagnose a malfunction of at least one unit that really needs maintenance.

(Possibility of other embodiments)
As described above, the equipment diagnosis system of the present invention has been described in the embodiment, but there is no particular limitation on a subject or an apparatus on which each processing is performed. It may be processed by a processor or the like (described below) incorporated in a specific device located locally. Alternatively, the processing may be performed by a cloud server or the like that is arranged in a different place from the local device. In the embodiment, the diagnostic model 121 is described as being statistically machine-learned, but is not limited thereto. The diagnostic model 121 may be learned using a learning method other than statistical machine learning such as deep learning.

  Note that the present invention is not limited to the above embodiment. For example, another embodiment that is realized by arbitrarily combining the components described in this specification and excluding some of the components may be an embodiment of the present invention. Further, the gist of the present invention with respect to the above-described embodiment, that is, modified examples obtained by performing various modifications conceivable by those skilled in the art without departing from the meaning indicated by the words described in the claims are also included in the present invention. It is.

  The present invention further includes the following cases.

  (1) The above device is, specifically, a computer system including a microprocessor, a ROM, a RAM, a hard disk unit, a display unit, a keyboard, a mouse, and the like. The RAM or the hard disk unit stores a computer program. Each device achieves its function by the microprocessor operating according to the computer program. Here, the computer program is configured by combining a plurality of instruction codes indicating instructions to the computer in order to achieve a predetermined function.

  (2) Some or all of the constituent elements of the above-described device may be configured by one system LSI (Large Scale Integration: large-scale integrated circuit). The system LSI is an ultra-multifunctional LSI manufactured by integrating a plurality of components on one chip, and is specifically a computer system including a microprocessor, a ROM, a RAM, and the like. . The RAM stores a computer program. When the microprocessor operates according to the computer program, the system LSI achieves its function.

  (3) A part or all of the constituent elements of the above-described device may be constituted by an IC card or a single module that is detachable from each device. The IC card or the module is a computer system including a microprocessor, a ROM, a RAM, and the like. The IC card or the module may include the above super multifunctional LSI. When the microprocessor operates according to the computer program, the IC card or the module achieves its function. The IC card or the module may have tamper resistance.

  (4) The present invention may be the method described above. Further, these methods may be a computer program that is realized by a computer, or may be a digital signal formed by the computer program.

  (5) Further, the present invention provides a computer-readable recording medium for reading the computer program or the digital signal, for example, a flexible disk, a hard disk, a CD-ROM, an MO, a DVD, a DVD-ROM, a DVD-RAM, a BD ( (Blu-ray (registered trademark) Disc), a semiconductor memory, or the like. Further, the digital signal may be recorded on these recording media.

  In the present invention, the computer program or the digital signal may be transmitted via an electric communication line, a wireless or wired communication line, a network represented by the Internet, a data broadcast, or the like.

  In addition, the present invention may be a computer system including a microprocessor and a memory, wherein the memory stores the computer program, and the microprocessor operates according to the computer program.

  Further, the program or the digital signal is recorded on the recording medium and transferred, or the program or the digital signal is transferred via the network or the like, thereby being implemented by another independent computer system. You may do it.

  INDUSTRIAL APPLICABILITY The present invention can be used for an equipment diagnosis system and an equipment diagnosis method for more appropriately diagnosing a malfunction of a manufacturing equipment, and in particular, appropriately diagnoses a malfunction in a mounting machine and a plurality of units constituting the mounting machine in the surface mounting industry. For the equipment diagnosis system and equipment diagnosis method.

10, 20, 20A Equipment diagnostic system 10A Equipment diagnostic device 11 Operation information acquisition unit 12, 22, Malfunction diagnosis unit 13 Output unit 13A, 204 server 13B, 25A Mail server 14 Feedback information acquisition unit 25 Equipment collection instruction unit 26 Maintenance work instruction unit 27 Maintenance Unit 27A Automatic Maintenance Device 121 Diagnostic Model 123 Pattern Comparison Unit 124 Level Judgment Unit 202 Mounting Machine 203 LNB
205 Database 206, 208 Input device 207 Data collection device 1211 Normal behavior pattern 1212 Normal correlation pattern 1213 Preprocessing unit

Claims (12)

An operation information acquisition unit for acquiring operation information of each of a plurality of manufacturing facilities;
A malfunction diagnosis unit that diagnoses malfunction of at least one manufacturing facility of the plurality of manufacturing facilities based on the operation information;
An output unit that outputs a diagnosis result of the malfunction diagnosis unit;
A feedback information acquisition unit that acquires feedback information for the diagnosis result,
Equipment diagnostic system. further,
A maintenance unit that performs maintenance of the at least one manufacturing facility that has been diagnosed as malfunctioning by the malfunction diagnosis unit,
The facility diagnosis system according to claim 1. further,
A maintenance work instructing unit that instructs the maintenance unit to perform maintenance of the at least one manufacturing facility diagnosed as malfunction by the malfunction diagnosis unit,
The equipment diagnosis system according to claim 2. further,
The apparatus further includes a maintenance work instructing unit that instructs a user on maintenance of the at least one manufacturing facility diagnosed as malfunctioning from the malfunction diagnosis unit,
The facility diagnosis system according to claim 1. The feedback information includes information on a maintenance result of the at least one manufacturing facility by the maintenance unit, and at least one of information on a maintenance result by a confirmer,
The equipment diagnosis system according to claim 2. The feedback information includes information on whether or not the malfunction diagnosis by the malfunction diagnosis unit is correct.
The equipment diagnosis system according to any one of claims 1 to 5. The malfunction diagnosis unit has a diagnosis model,
The diagnostic model is updated based on the feedback information.
The equipment diagnosis system according to any one of claims 1 to 6. The diagnostic model is created by being learned using operation result data including operation information of each of the plurality of manufacturing facilities,
The facility diagnosis system according to claim 7. further,
An equipment recovery instructing unit that instructs a recoverer to recover the at least one manufacturing facility diagnosed as malfunctioning by the malfunction diagnosis unit,
An equipment diagnosis system according to any one of claims 1 to 8. The manufacturing facility includes at least one element of a surface mounting device or a plurality of elements constituting the surface mounting device,
The equipment diagnosis system according to claim 1. The diagnostic model is one of a plurality of diagnostic models,
The plurality of diagnostic models are provided corresponding to a plurality of customers,
The facility diagnosis system according to claim 7. Acquires operation information for each of multiple manufacturing facilities,
Based on the acquired operation information, diagnose a malfunction of at least one of the plurality of manufacturing facilities,
Output the diagnostic result,
Obtaining feedback information on the diagnosis result,
Equipment diagnosis method.

Images