CN109074052B - Unsteady detection device, unsteady detection system, and unsteady detection method - Google Patents
Unsteady detection device, unsteady detection system, and unsteady detection method Download PDFInfo
- Publication number
- CN109074052B CN109074052B CN201680084571.5A CN201680084571A CN109074052B CN 109074052 B CN109074052 B CN 109074052B CN 201680084571 A CN201680084571 A CN 201680084571A CN 109074052 B CN109074052 B CN 109074052B
- Authority
- CN
- China
- Prior art keywords
- tact
- unsteady
- state
- unit
- detection device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 87
- 238000004519 manufacturing process Methods 0.000 claims abstract description 50
- 238000012544 monitoring process Methods 0.000 claims abstract description 47
- 238000000605 extraction Methods 0.000 claims abstract description 41
- 239000000284 extract Substances 0.000 claims abstract description 20
- 238000003860 storage Methods 0.000 claims description 53
- 238000000034 method Methods 0.000 claims description 23
- 238000003384 imaging method Methods 0.000 claims description 18
- 239000013598 vector Substances 0.000 claims description 15
- 230000006835 compression Effects 0.000 claims description 13
- 238000007906 compression Methods 0.000 claims description 13
- 238000009826 distribution Methods 0.000 claims description 7
- 230000002123 temporal effect Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000005484 gravity Effects 0.000 claims description 2
- 238000000513 principal component analysis Methods 0.000 claims description 2
- 230000010365 information processing Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 14
- 230000015654 memory Effects 0.000 description 14
- 238000005259 measurement Methods 0.000 description 4
- 230000007704 transition Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
- General Factory Administration (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
An unsteady state detection device (1) that detects whether or not a monitored object is in an unsteady state includes: an element extraction unit (12) that extracts elements that represent the features of a continuous image group for each production beat, which is a predetermined unit of work, from the continuous image group that is a plurality of image data that are continuously captured including a monitoring target; and a determination unit (18) that determines whether the tact of the determination target in the monitoring target is in a non-steady state or a steady state, based on the elements of each tact extracted by the element extraction unit (12).
Description
Technical Field
The present invention relates to an unsteady detection device, an unsteady detection system, and an unsteady detection method for detecting an unsteady state.
Background
Conventionally, a sensor such as a camera is installed at a site of a monitoring target to be inspected or maintained, and whether the monitoring target is in a stable state without an abnormality or in an unstable state with some abnormality is determined based on sensor information such as an image. Patent document 1 discloses a technique of generating a cluster of similar images in a steady state from feature amounts extracted from a plurality of images in a steady state that have been acquired in the past, and determining that a monitoring target represented by a newly acquired image is in an unstable state when a feature amount extracted from the newly acquired image does not belong to the cluster.
Patent document 1: japanese patent laid-open publication No. 2006-330797
Disclosure of Invention
The technique described in patent document 1 is effective in the case where the monitoring target for detecting the unstable state does not move in the stable state, that is, the same image in the stable state. However, in a manufacturing site or the like where a person, an article, a machine, or the like is moving in a steady state, there is a problem that clusters of similar images cannot be generated, and therefore, an unstable state cannot be detected.
The present invention has been made in view of the above circumstances, and an object of the present invention is to provide an unsteady state detection device capable of detecting an unsteady state when a monitored object that moves in a steady state is included.
In order to solve the above problems and achieve the object, the present invention includes: an element extraction unit that extracts an element indicating a feature of a continuous image group for each production beat, which is a predetermined unit of work, from the continuous image group that is a plurality of image data that are continuously captured including a monitoring target; and a determination unit that determines whether the tact to be determined is in a non-steady state or a steady state in the monitoring target, based on the elements of each tact extracted by the element extraction unit. The element extraction unit extracts a 1 st element indicating a feature of each image data from each image data to be monitored, and extracts a 2 nd element indicating a feature of a 1 st element changing with time from the 1 st element in 1 tact. When the 2 nd element is represented by a vector, the determination unit determines whether the tact to be determined is in the non-steady state or the steady state, using a data set representing distribution information of vectors representing the 2 nd element of a plurality of tacts determined to be in the steady state.
ADVANTAGEOUS EFFECTS OF INVENTION
The unsteady state detection device according to the present invention has an effect of being able to detect an unsteady state when a monitoring object that moves in a steady state is included.
Drawings
Fig. 1 is a block diagram showing a configuration example of an unsteady state detection device according to embodiment 1.
Fig. 2 is a flowchart showing a process of detecting an unsteady state in the unsteady state detection device according to embodiment 1.
Fig. 3 is a diagram showing 2 elements extracted by the element extraction unit according to embodiment 1.
Fig. 4 is a diagram schematically showing the relationship between the cluster information stored in the cluster information storage unit and the 2 nd element of the beat to be determined read from the 2 nd element storage unit in embodiment 1.
Fig. 5 is a diagram showing an example of image information in which the display generation unit according to embodiment 1 highlights a difference between the image data of the monitoring target at the production beat determined by the determination unit to be in the non-steady state and the image data of the monitoring target at the production beat determined to be in the steady state.
Fig. 6 is a diagram showing another example of image information in which the display generation unit according to embodiment 1 highlights a difference between the image data of the beat determined by the determination unit to be in the non-steady state and the image data of the beat determined to be in the steady state.
Fig. 7 is a diagram showing an example of a case where a processing circuit of the instability detection apparatus according to embodiment 1 is configured by a CPU and a memory.
Fig. 8 is a diagram showing a configuration example of the unsteady state detection system according to embodiment 2.
Detailed Description
Hereinafter, an unsteady state detection device, an unsteady state detection system, and an unsteady state detection method according to embodiments of the present invention will be described in detail with reference to the accompanying drawings. The present invention is not limited to the present embodiment.
Fig. 1 is a block diagram showing a configuration example of an unsteady state detection device 1 according to embodiment 1 of the present invention. The instability detection apparatus 1 is, for example, a programmable display. In the present embodiment, a case will be described as an example where the unsteady state detection device 1 detects an unsteady state in a production line for a predetermined 1 tact that is an arbitrary operation unit of a manufacturing process. The 1 tact may be 1 manufacturing process of a line to be monitored, or may include a plurality of manufacturing processes. The use of the unsteady detection device 1 is not limited to the production line.
As data used by the unsteady state detection device 1 to detect an unsteady state, image data captured by the imaging device 2 is used. The instability detection apparatus 1 detects 1 tact of a manufacturing process based on information acquired from an external apparatus 3 such as a programmable controller that controls manufacturing equipment in a production line or a measuring instrument that detects a predetermined event in the production line. The unsteady state detection device 1 receives settings such as a determination threshold value required for the unsteady state detection process described later from the operator 4.
The structure of the instability detection apparatus 1 will be described. The instability detection apparatus 1 includes: a data acquisition unit 11 that acquires image data from the imaging device 2; an element extraction unit 12 that extracts a 1 st element indicating a feature of a frequency of each image data from the image data acquired by the data acquisition unit 11 by using an image compression technique, and extracts a 2 nd element indicating a feature of a 1 st element changing with time from the 1 st element of 1 beat received from a 1 st element division unit 15 described later by using an image compression technique; and a 1 st element storage unit 13 that stores the 1 st element extracted by the element extraction unit 12.
Further, the unsteady state detection device 1 includes: an external device connection interface 14 that transmits and receives data and the like to and from the external device 3 and detects 1 tact of a unit of work to be monitored based on information from the external device 3; and a 1 st element division unit 15 that divides and reads the 1 st element of 1 tact from the 1 st element storage unit 13 for every 1 tact notified from the external device connection interface 14, and delivers the 1 st element of 1 tact to the element extraction unit 12.
Further, the unsteady state detection device 1 includes: a 2 nd element storage unit 16 that stores the 2 nd element extracted by the element extraction unit 12; a cluster information storage unit 17 that stores cluster information including a data set or the like indicating distribution information in the case of the 2 nd element indicating a tempo which was determined to be in a steady state in the past by a vector; and a determination unit 18 that determines whether the tact to be determined is in a non-steady state or a steady state in the monitoring target, using the elements of each tact extracted by the element extraction unit 12, that is, the 2 nd element of the tact to be determined stored in the 2 nd element storage unit 16 and the cluster information stored in the cluster information storage unit 17.
Further, the unsteady state detection device 1 includes: an operation receiving unit 19 that receives an operation from the operator 4 and sets a determination threshold value used in the determination process of the determination unit 18 in the determination unit 18; a display generation unit 20 that generates display information including the determination result based on the determination result of the determination unit 18; a display unit 21 that displays the display information generated by the display generation unit 20; and an image information storage unit 22 that stores the 1 st element used when the 2 nd element is extracted by the element extraction unit 12. The 1 st element storage unit 13, the 2 nd element storage unit 16, the cluster information storage unit 17, and the image information storage unit 22 are collectively referred to as a storage unit 23.
Next, an unstable state detection method of the unstable state detection device 1 for detecting whether or not the monitoring target is in an unstable state, that is, a process of detecting an unstable state will be described. Fig. 2 is a flowchart showing a process of detecting an unsteady state in the unsteady state detection device 1 according to embodiment 1.
First, in the non-stationary detection device 1, the data acquisition unit 11 acquires image data, which is data of an image captured by the imaging device 2 including a monitoring target, from the imaging device 2 (step S1). The imaging device 2 is, for example, a digital camera. The data acquisition unit 11 acquires a continuous image group as a plurality of image data from the imaging device 2. For example, when the image capturing device 2 continuously captures 30 still images for 1 second, the data acquisition unit 11 acquires image data of a still image from the image capturing device 2 every time the image capturing device 2 captures a still image.
The element extraction unit 12 performs frequency decomposition on each image data to be monitored acquired by the data acquisition unit 11 using an image compression technique, and extracts the 1 st element that is an element representing the feature of the frequency of each image data (step S2). The element extraction unit 12 can extract the 1 st element from the image data using an existing method such as principal component analysis or wavelet transform as an image compression technique.
Fig. 3 is a diagram showing 2 elements extracted by the element extraction unit 12 according to embodiment 1. In fig. 3, the solid line indicated by (1) such as the 1 st and 2 nd images on the axis in the time direction is the 1 st element extracted from each image data of the monitoring target by the element extraction unit 12, and is an element indicating the frequency of the feature constituting the frequency of each image. Here, the lapse of time is shown by the number of sheets such as the 1 st sheet and the 2 nd sheet. In fig. 3, a broken line indicated by (2) on the axis in the frequency direction is a 2 nd element extracted from the 1 st element by the element extraction unit 12 as described later, and is an element showing a temporal change in frequency element, which is a transition that is a feature of a temporal change in the 1 st element. In fig. 3, the axis in the amplitude direction represents the magnitude of the frequency element, i.e., the amplitude. As the non-stationary detection device 1, a range associated with movement of a person, an article, a manufacturing apparatus, or the like in a production line is set as a monitoring target of non-stationary state detection, and the content of image data, which is a still image, differs for each shooting time. Therefore, the 1 st element indicating the feature of the frequency extracted from the image data by the element extraction unit 12 shows a transition of the feature of the different frequency for the 1 st and 2 nd sheets, that is, a transition of the feature of the different frequency for the time when the still image is captured. In a production line of a monitoring target, generally, a person, an article, or a manufacturing apparatus repeats the same operation every 1 tact. Therefore, if the case is the steady state, the 1 st element extracted from the image data of 1 beat in each beat shows the same feature in the same time band in each beat.
Each time the element extraction unit 12 extracts the 1 st element from the image data, the 1 st element extracted is stored in the 1 st element storage unit 13 (step S3).
The external device connection interface 14 detects 1 tact of a work unit of a line to be monitored, which is detected in an unstable state, based on information acquired from the external device 3 (step S4). The 1 tact is a work unit of 1 or more manufacturing processes in a production line as a monitoring target. The external device connection interface 14 detects a unit of work repeated in the production line to be monitored as 1 tact. For example, when the external device 3 is a programmable controller, the external device connection interface 14 detects 1 tact from information of a processing range of the programmable controller. Alternatively, for example, when the external device 3 is a measuring device that detects a predetermined event in a production line, the external device connection interface 14 detects 1 tact based on information on an interval between the detection of the event. Specifically, in the case where the measuring device is a sensor for detecting the flow of an article, the external device connection interface 14 detects 1 tact at intervals at which the sensor detects the flow of a specific article in the manufacturing process. Each time the external device connection interface 14 detects 1 tact, it notifies the 1 st element dividing unit 15 of the fact that 1 tact is detected.
The 1 st element division unit 15 reads the 1 st element stored in the 1 st element storage unit 13 from the 1 st element storage unit 13 every time a notification that 1 tact, which is a unit of work, is detected is received from the external device connection interface 14. That is, the 1 st element dividing unit 15 divides the 1 st element extracted and continued by the element extracting unit 12 into 1 beat (step S5). The 1 st element division unit 15 delivers the 1 st element of 1 tact read from the 1 st element storage unit 13 to the element extraction unit 12.
The element extraction unit 12 extracts, as the 2 nd element, an element that shows a feature of a temporal change of the 1 st element at a predetermined frequency or at a predetermined frequency interval, by using an image compression technique for the 1 st element of 1 tact acquired from the 1 st element division unit 15 (step S6). The method of extracting the 2 nd element in the element extracting unit 12 is the same as that for extracting the 1 st element described above.
The element extraction unit 12 extracts the 2 nd element from the 1 st element, thereby obtaining information of a broken line shown in fig. 3 (2). In fig. 3, only 1 broken line is shown as the 2 nd element, and this is schematically shown for easy understanding of the 2 nd element. The element extraction unit 12 actually extracts the 2 nd element from the 1 st element at a plurality of frequencies.
Each time the element extraction unit 12 extracts the 2 nd element from the 1 st element, the 2 nd element extracted is stored in the 2 nd element storage unit 16 (step S7). The element extraction unit 12 also stores the 1 st element of the 1 st tact used in extracting the 2 nd element in the image information storage unit 22 (step S8).
The determination unit 18 reads the 2 nd element of the tact to be determined from the 2 nd element storage unit 16, and determines whether or not the tact to be determined is in an unstable state in the monitoring target with reference to the cluster information of the cluster information storage unit 17 (step S9). The determination unit 18 may set the data amount of the 2 nd element for 1 tact, periodically check the 2 nd element storage unit 16, and read the data amount of the 2 nd element for 1 tact after the 2 nd element storage unit 16 stores the data amount.
Here, the cluster information stored in the cluster information storage unit 17 will be described. Fig. 4 is a diagram schematically showing the relationship between the cluster information stored in the cluster information storage unit 17 and the 2 nd element of the tempo to be determined read from the 2 nd element storage unit 16 in embodiment 1.
The cluster information includes a steady-state data group 41 as distribution information of the 2 nd element of a plurality of tacts determined as a steady state in the past, and center coordinates 42 of the steady-state data group 41. In general, the 2 nd element extracted by the element extraction unit 12 may be expressed by a formula such as a formula of 2 nd order or a formula of 3 rd order, and the feature of the formula may be expressed by vector information using a coefficient of each order of the obtained formula. The steady state data group 41 shows the distribution of points represented by vectors of the 2 nd elements of a plurality of tacts determined to be in a steady state in the past. The center coordinates 42 show the coordinate position of the center obtained from the distribution state of the point represented by the vector of the 2 nd element of the plurality of tacts determined to be in the steady state in the past. The 2 nd element 43 is a point indicated by a vector represented by the 2 nd element of the determination target tact read from the 2 nd element storage unit 16. Further, the center coordinate 42 described above may be used as the center of gravity of the steady-state data group 41.
The determination unit 18 is set in advance by the operator 4 via the operation receiving unit 19 with a determination threshold for determining whether or not the tact to be determined is in an unstable state. When the distance between the center coordinate 42 shown in fig. 4 and the 2 nd element 43 of the tact to be judged is equal to or greater than the judgment threshold, the judgment unit 18 judges that the tact to be judged is in an unstable state in the monitoring target (step S9: Yes). When determining that the tempo of the determination target is in the unstable state, the determination unit 18 notifies the display generation unit 20 of the determination result that the tempo of the determination target is in the unstable state.
When the beat to be determined is in the non-steady state as a result of determination, the display generation unit 20 acquires, from the image information storage unit 22, the 1 st element of 1 beat in the past beat determined to be in the steady state and the 1 st element of 1 beat in the beat to be determined to be in the non-steady state in the current determination. The display generation unit 20 restores the image data of the steady state tempo based on the 1 st element of the tempo determined as the steady state in the past, and restores the image data of the unsteady state tempo based on the 1 st element of the tempo determined as the unsteady state in the determination at this time. The display generation unit 20 detects a difference between the image data of the steady state tempo and the image data of the non-steady state tempo, and generates image information in which the difference is emphasized for an image displayed by superimposing the image data of the steady state tempo and the image data of the non-steady state tempo. The display generation unit 20 generates display information including the result of determination of a character or the like indicating that the tempo being determined is in an unstable state and image information, and controls the display unit 21 to display the display information (step S10). The display generation unit 20 may detect a difference between the image data of the steady state tempo and the image data of the unsteady state tempo, and generate image information in which the difference is emphasized and displayed for the image in which the image data of the unsteady state tempo is displayed.
Fig. 5 is a diagram showing an example of image information in which the display generation unit 20 according to embodiment 1 emphasizes and displays a difference between image data of a monitoring target in a production beat determined to be in an unstable state by the determination unit 18 and image data of a monitoring target in a production beat determined to be in a stable state. The instability detection apparatus 1 can detect an unstable state when, for example, the invader 51 is near the production line. Fig. 6 is a diagram showing another example of image information in which the display generation unit 20 according to embodiment 1 highlights a difference between image data of a beat determined to be in an unstable state and image data of a beat determined to be in a stable state by the determination unit 18. The instability detection apparatus 1 can detect an unstable state when there is an abnormal product 61 such as a broken product among products flowing on a certain production line that is moving all the time, for example.
The determination unit 18 may output the determination result to the external device 3 via the external device connection interface 14 when the beat of the determination target is determined to be in the unstable state in the monitoring target (step S9: Yes). The determination unit 18 may acquire the display information generated by the display generation unit 20 from the display generation unit 20 and output the acquired display information to the external device 3 via the external device connection interface 14.
When the distance between the center coordinate 42 and the 2 nd element 43 of the tact to be determined shown in fig. 4 is smaller than the determination threshold, the determination unit 18 determines that the tact to be determined is in a stable state in the monitoring target (step S9: No). When determining that the tempo of the determination target is in the steady state, the determination unit 18 notifies the display generation unit 20 of the determination result that the tempo of the determination target is in the steady state. The display generation unit 20 may generate display information including a result of determination such as a character indicating that the tempo of the determination target is in a stable state, and display the display information on the display unit 21.
The determination unit 18 clusters the 2 nd element of the tempo to be determined in the steady state (step S11). Specifically, the determination unit 18 stores information of the vector of the 2 nd element based on the tempo to be determined which is determined to be in the stable state in the cluster information storage unit 17. The determination unit 18 edits the cluster information stored in the cluster information storage unit 17, and adds information of the vector of the 2 nd element based on the tempo of the determination target determined to be in the stable state to the stable state data group 41. The determination unit 18 includes the 2 nd element of the tact determined to be in the steady state at this time in the steady-state data group 41 shown in fig. 4, and recalculates the center coordinates 42 if necessary. Thereby, the determination unit 18 can set the cluster information stored in the cluster information storage unit 17 to the latest state.
In the unsteady state detection device 1, the case where the image data is used as the information for detecting the state of the manufacturing process has been described, but the information for detecting the state of the manufacturing process is not limited to the image data. The instability detection apparatus 1 may use measurement data such as a numerical value obtained from a measurement device such as a pressure gauge for measuring the pressure of a press machine or the like provided in a manufacturing process, or a flow meter for measuring the air flowing through a piston operating under air pressure, that is, a value of a measurement device for measuring the operating state of the manufacturing equipment. The non-stationary detection device 1 may also use log data of each device used in the manufacturing process as information for detecting the state of the manufacturing process. The data acquiring unit 11 acquires measurement data such as the above-described numerical values or log data.
Further, the cluster information storage unit 17 stores the steady state data group 41 using the information of the 2 nd element of the tact that was previously determined as the steady state, and updates the steady state data group 41 using the information of the 2 nd element of the tact that was newly determined as the steady state, but the amount of data may become excessive. Therefore, the determination unit 18 may delete the information of the 2 nd element from the steady-state data group 41 in the order of the acquisition timing when the capacity of the steady-state data group 41 reaches a certain amount, or may delete the information of the 2 nd element after the lapse of a certain period from the steady-state data group 41.
The element extraction unit 12 stores the 1 st element of the 1 st tact used when the 2 nd element is extracted in the image information storage unit 22, but may store the image data restored from the 1 st element in the image information storage unit 22. In this case, the capacity of the image information storage unit 22 needs to be increased, but the configuration of the display generation unit 20 can be simplified because the image data can be restored from the 1 st element without using the display generation unit 20.
Further, the operator 4 sets the determination threshold value for the determination unit 18 via the operation receiving unit 19, but in order to set the determination threshold value to a numerical value, the operator 4 needs to be familiar with a device to be detected unstably in the manufacturing process. Therefore, the operator 4 may change the determination threshold value with reference to the image information in the unsteady state displayed on the display unit 21. Further, the operator 4 may operate the determination unit 18 via the operation receiving unit 19 for the 2 nd element of the beat erroneously detected as the unsteady state due to the inappropriate value set as the determination threshold value, and select the 2 nd element of the beat to be determined as the steady state data group 41 to perform clustering in the clustering information storage unit 17. The operator 4 may dynamically change the determination threshold value according to the determination result of the determination unit 18, or may set a hysteresis without setting the determination threshold value to a unique value.
Next, a hardware configuration of the instability detection apparatus 1 will be described. In the unsteady state detection device 1, the data acquisition unit 11 is implemented by an interface circuit capable of receiving image data and the like. The external device connection interface 14 is implemented by an interface circuit capable of transmitting and receiving data to and from the external device 3. The operation receiving unit 19 is implemented by a device such as a mouse or a keyboard. The display unit 21 is implemented by a display such as an lcd (liquid Crystal display). The storage unit 23 including the 1 st element storage unit 13, the 2 nd element storage unit 16, the cluster information storage unit 17, and the image information storage unit 22 is implemented by a memory. The element extraction unit 12, the 1 st element division unit 15, the determination unit 18, and the display generation unit 20 are implemented by a processing circuit. The processing circuit may be dedicated hardware, or may be a cpu (central processing unit) and a memory for executing a program stored in the memory.
Fig. 7 is a diagram showing an example of a case where a processing circuit of the instability detection apparatus 1 according to embodiment 1 is configured by a CPU91 and a memory 92. When the processing circuit is constituted by the CPU91 and the memory 92, the functions of the element extracting unit 12, the 1 st element dividing unit 15, the determining unit 18, and the display generating unit 20 are realized by software, firmware, or a combination of software and firmware. The software or firmware is described as a program and is stored in the memory 92. In the processing circuit, the CPU91 reads and executes a program stored in the memory 92, thereby realizing each function.
The CPU91 may be a processing device, an arithmetic device, a microprocessor, a microcomputer, a processor, or a dsp (digital Signal processor). Examples of the memory 92 include nonvolatile or volatile semiconductor memories such as ram (random Access memory), rom (read Only memory), flash memory, eprom (erasable Programmable rom), and eeprom (electrically eprom), magnetic disks, flexible disks, optical disks, compact disks, mini disks, and dvd (digital versatile disc). The memory implementing the storage unit 23 may be the memory 92.
As described above, according to the present embodiment, in the unsteady state detection device 1, with respect to a monitoring target in 1 beat which is a unit of work accompanied by an operation such as a production line, the 1 st element indicating the feature of the frequency of each image data is extracted from each image data of a continuous image group obtained by imaging the monitoring target by using the image compression technique, the 2 nd element indicating the feature of the 1 st element changing with time is extracted from the 1 st element in 1 beat by using the image compression technique, and whether the beat of the determination target is in the unsteady state or in the steady state is determined using the cluster information including the 2 nd element of the beat of the determination target and the data group including the 2 nd element of the beat determined as the steady state in the past. Thus, the unsteady state detection device 1 can detect an unsteady state with respect to a monitoring target that operates in a steady state. In addition, when the monitoring target that operates in a steady state is targeted, the instability detection apparatus 1 performs processing by the image compression technique in 2 stages, and thereby can detect an unstable state with a smaller amount of information than a case where image data obtained by imaging the monitoring target is directly used.
In embodiment 2, a case where the instability detection apparatus 1 detects an unstable state in a plurality of monitoring targets will be described.
Fig. 8 is a diagram showing a configuration example of the unsteady state detection system 6 according to embodiment 2. The unsteady state detection system 6 includes the unsteady state detection device 1 and a plurality of external devices 3, and is a system in which the unsteady state detection device 1 and each of the external devices 3 are connected via a network 5. In embodiment 1, the unsteady state detection apparatus 1 is connected to 1 imaging apparatus 2, and detects the production tempo in an unsteady state for 1 production line of monitoring objects imaged by the imaging apparatus 2. However, in the non-stationary detection device 1, if there is a margin in the processing capacity of the element extraction unit 12, the capacity of the storage unit 23, and the like, a plurality of production lines can be monitored. When there are a plurality of monitoring targets, the plurality of imaging devices 2 output image data obtained by imaging a predetermined monitoring target by each imaging device to the unsteady state detection device 1. In fig. 8, the imaging device 2 may be included in the external device 3, for example, a programmable controller, and the unsteady state detection device 1 may be configured as a production management device that manages a production line. In this case, the instability detection apparatus 1 can extract and analyze the chronological transition of data controlled during operation in each production line or the operation state as an element, i.e., a waveform. Thus, the operator 4 can quantify fluctuations, unevenness, waste, and the like between the respective manufacturing processes based on the detection state of the tact in the unsteady state performed by the unsteady state detection device 1 of the unsteady state detection system 6, and can perform optimization of the respective manufacturing processes.
In the non-stationary detection system 6, the processing itself of the non-stationary detection device 1 for detecting the non-stationary state for each line to be monitored is the same as that in embodiment 1.
As described above, according to the present embodiment, the unsteady state detection device 1 detects an unsteady state with respect to a plurality of monitoring targets. Thus, the unstable state detection device 1 for detecting the amount of the object to be monitored does not need to be provided, and a system for detecting an unstable state with respect to a plurality of objects to be monitored can be realized at low cost.
The configurations described in the above embodiments are merely examples of the contents of the present invention, and may be combined with other known techniques, and some of the configurations may be omitted or modified without departing from the scope of the present invention.
Description of the reference numerals
The system comprises an unsteady detection device 1, an imaging device 2, an external device 3, an operator 4, a network 5, an unsteady detection system 6, a data acquisition part 11, an element extraction part 12, an element storage part 1 at 13, an external device connection interface 14, an element division part 1 at 15, an element storage part 2 at 16, a cluster information storage part 17, a judgment part 18, an operation receiving part 19, a display generation part 20, a display part 21, an image information storage part 22, and a storage part 23.
Claims (13)
1. An unsteady state detection device is characterized by comprising:
an element extraction unit that extracts an element indicating a feature of a continuous image group for each production beat, which is a predetermined unit of work, from the continuous image group that is a plurality of image data that are continuously captured including a monitoring target; and
a determination unit that determines whether the tact to be determined is in a non-steady state or a steady state in the monitoring target based on the elements of each tact extracted by the element extraction unit,
the element extraction unit extracts a 1 st element indicating a feature of each image data from each image data to be monitored, extracts a 2 nd element indicating a feature of a temporal change of the 1 st element from the 1 st element in 1 tact,
when the 2 nd element is represented by a vector, the determination unit determines whether the beat to be determined is in the non-steady state or the steady state, using a data set representing distribution information of vectors representing the 2 nd element of the plurality of beats determined to be in the steady state.
2. The unsteady detection device of claim 1,
the element extraction unit extracts the 1 st element from each image data of a monitoring target using an image compression technique, and extracts the 2 nd element from the 1 st element in 1 beat using the image compression technique.
3. The unsteady detection device of claim 2,
the image compression technique is principal component analysis or wavelet transform.
4. The unsteady detection device of any one of claims 1 to 3,
the determination unit determines that the tempo of the determination target is in an abnormal state when a distance between a position of a center coordinate or a center of gravity of the data group and a position indicated by a vector of a 2 nd element indicating the tempo of the determination target is greater than or equal to a determination threshold value.
5. The unsteady detection device of any one of claims 1 to 3,
a 1 st element dividing section for dividing and reading a 1 st element of 1 tact from the plurality of 1 st elements extracted by the element extracting section,
the element extracting section extracts the 2 nd element from the 1 st element of the 1 st tact divided by the 1 st element dividing section.
6. The unsteady detection device of any one of claims 1 to 3,
has a storage unit for storing information of the data group,
the determination unit causes the storage unit to store information indicating the vector of the 2 nd element of the tact determined as a steady state, and adds the information to the data group.
7. The unsteady detection device of claim 6,
the information processing apparatus includes a display generation unit that generates display information including a determination result indicating that the tempo of the determination target is in an unstable state, and controls display of the display information when the determination unit determines that the tempo of the determination target is in the unstable state.
8. The unsteady detection device of claim 7,
the element extraction unit causes the storage unit to store the 1 st element of the 1 st tact used in extracting the 2 nd element,
the display generation unit restores the image data of the monitoring target at each tact based on the 1 st element of 1 tact determined as the steady state tact and the 1 st element of 1 tact determined as the non-steady state tact stored in the storage unit, and generates the display information including image information indicating a difference in the restored image data of the monitoring target at each tact.
9. The unsteady detection device of any one of claims 1 to 3,
the 1 tact is a processing range of 1 or more manufacturing processes on the line to be monitored, and is a programmable controller that controls manufacturing equipment in the line.
10. The unsteady detection device of any one of claims 1 to 3,
the 1 tact is an interval at which a measuring instrument that detects a predetermined event in the production line detects the event, and is one or more manufacturing processes on the production line that is the monitoring target.
11. An unsteady detection system, comprising:
the unsteady detection device of claims 1 to 10; and
a plurality of imaging devices each outputting image data obtained by imaging a predetermined object under monitoring when there are a plurality of objects under monitoring,
the unsteady detection device and the plurality of imaging devices are connected via a network, and the unsteady detection device determines whether each tact is in an unsteady state or a steady state for each monitoring target.
12. An unsteady state detection method for an unsteady state detection device that detects whether or not a monitored object is in an unsteady state,
the unsteady detection method is characterized by comprising:
an element extraction step of extracting an element indicating a feature of a continuous image group for each production beat, which is a predetermined unit of work, from the continuous image group that is a plurality of image data that are continuously captured including a monitoring target; and
a determination step of determining whether the tact to be determined in the monitoring target is in an unstable state or in a stable state based on the elements of each tact extracted in the element extraction step,
the element extracting step includes:
a 1 st element extraction step of extracting a 1 st element indicating a feature of each image data from each image data of a monitoring target; and
a 2 nd element extraction step of extracting a 2 nd element representing a feature of a temporal change of the 1 st element from the 1 st element of 1 tact,
in the determining step, when the 2 nd element is represented by a vector, it is determined whether the tact to be determined is in a non-steady state or a steady state using a data set representing distribution information of vectors representing the 2 nd element of a plurality of tacts determined as being in a steady state.
13. The unsteady detection method according to claim 12,
in the 1 st element extraction step, the 1 st element is extracted from each image data of a monitoring target using an image compression technique; and
in the 2 nd element extraction step, the 2 nd element is extracted from the 1 st element of 1 tact using the image compression technique.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2016/062364 WO2017183107A1 (en) | 2016-04-19 | 2016-04-19 | Unsteadiness detection device, unsteadiness detection system, and unsteadiness detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109074052A CN109074052A (en) | 2018-12-21 |
| CN109074052B true CN109074052B (en) | 2020-01-03 |
Family
ID=59854938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201680084571.5A Active CN109074052B (en) | 2016-04-19 | 2016-04-19 | Unsteady detection device, unsteady detection system, and unsteady detection method |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP6195688B1 (en) |
| CN (1) | CN109074052B (en) |
| WO (1) | WO2017183107A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113189935B (en) * | 2021-04-29 | 2022-09-30 | 浙江陀曼云计算有限公司 | Non-invasive production beat prediction method and system based on time sequence power data |
| CN114554088B (en) * | 2022-02-16 | 2023-04-18 | 广州市斯睿特智能科技有限公司 | High-speed beat detection system |
| CN114637264B (en) * | 2022-03-15 | 2024-05-17 | 广州明珞装备股份有限公司 | Motion stability analysis method, system, device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4641450B2 (en) * | 2005-05-23 | 2011-03-02 | 日本電信電話株式会社 | Unsteady image detection method, unsteady image detection device, and unsteady image detection program |
| CN102591321A (en) * | 2010-12-28 | 2012-07-18 | 三菱电机株式会社 | Monitor control system |
| JP2012204455A (en) * | 2011-03-24 | 2012-10-22 | Mitsubishi Electric Corp | Mounting failure analysis system and process abnormality monitoring system |
| CN102825605A (en) * | 2012-09-13 | 2012-12-19 | 昆山市工业技术研究院有限责任公司 | Material delivering robot with visual detecting function |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08185204A (en) * | 1994-12-27 | 1996-07-16 | Yazaki Corp | Production management system for assembly product by plural sequencers |
| JP2005313294A (en) * | 2004-04-30 | 2005-11-10 | Mitsuba Corp | Production support system, and production support method |
| JP2007243846A (en) * | 2006-03-10 | 2007-09-20 | Matsushita Electric Ind Co Ltd | Image extraction analyzer, image extraction analyzing system, and image extraction analysis method |
| JP2013191185A (en) * | 2012-03-15 | 2013-09-26 | Mitsubishi Electric Corp | Abnormality detector |
| JP2013246729A (en) * | 2012-05-28 | 2013-12-09 | Nec Corp | Similar time series data search system |
| JP5684941B1 (en) * | 2014-07-31 | 2015-03-18 | 株式会社日立パワーソリューションズ | Abnormal sign diagnostic apparatus and abnormal sign diagnostic method |
| JP5946573B1 (en) * | 2015-08-05 | 2016-07-06 | 株式会社日立パワーソリューションズ | Abnormal sign diagnosis system and abnormality sign diagnosis method |
-
2016
- 2016-04-19 JP JP2017503977A patent/JP6195688B1/en active Active
- 2016-04-19 WO PCT/JP2016/062364 patent/WO2017183107A1/en active Application Filing
- 2016-04-19 CN CN201680084571.5A patent/CN109074052B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4641450B2 (en) * | 2005-05-23 | 2011-03-02 | 日本電信電話株式会社 | Unsteady image detection method, unsteady image detection device, and unsteady image detection program |
| CN102591321A (en) * | 2010-12-28 | 2012-07-18 | 三菱电机株式会社 | Monitor control system |
| JP2012204455A (en) * | 2011-03-24 | 2012-10-22 | Mitsubishi Electric Corp | Mounting failure analysis system and process abnormality monitoring system |
| CN102825605A (en) * | 2012-09-13 | 2012-12-19 | 昆山市工业技术研究院有限责任公司 | Material delivering robot with visual detecting function |
Also Published As
| Publication number | Publication date |
|---|---|
| JP6195688B1 (en) | 2017-09-13 |
| JPWO2017183107A1 (en) | 2018-04-26 |
| CN109074052A (en) | 2018-12-21 |
| WO2017183107A1 (en) | 2017-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10788320B2 (en) | Defect detecting device, defect detecting method, and computer-readable recording medium | |
| CN109074052B (en) | Unsteady detection device, unsteady detection system, and unsteady detection method | |
| CN107924184B (en) | Monitoring device, control method of monitoring device, and recording medium | |
| JP2013033459A (en) | Abnormality monitoring system and abnormality monitoring method | |
| JPWO2018104985A1 (en) | Anomaly analysis method, program and system | |
| JP6164311B1 (en) | Information processing apparatus, information processing method, and program | |
| JP6398383B2 (en) | Abnormality diagnosis device | |
| CN107924182B (en) | Monitoring device, control method of monitoring device, and recording medium | |
| EP3349003A1 (en) | Rotating machine abnormality detection device, rotating machine abnormality detection method, and rotating machine | |
| JP2019159786A (en) | Information processing device, information processing method, and program | |
| JP6409375B2 (en) | Parameter classification device | |
| US10866163B2 (en) | Anomaly monitoring device and method for producing anomaly signs according to combinations of sensors based on relationship of sensor fluctuations | |
| JP2013191185A (en) | Abnormality detector | |
| JP6225079B2 (en) | Air conditioner operation detection method and system | |
| KR102337155B1 (en) | System and method of monitoring by visualizing IoT data | |
| US9746961B2 (en) | Background signal processing system and background signal processing method | |
| JP2021096801A (en) | Monitoring apparatus and monitoring program | |
| WO2023105725A1 (en) | Time series data processing method | |
| TWI797017B (en) | Overheat prediction system, overheat prediction method and non-transitory computer-readable storage medium | |
| KR20210070671A (en) | System and method of monitoring by analyzing IoT data | |
| JP6396820B2 (en) | Communication signal monitoring device, feature amount processing device, and analysis method | |
| US20210048336A1 (en) | Abnormal-sound determination criterion generation device, abnormal-sound criterion generation method, abnormal-sound sensing device, and storage medium | |
| KR20170086350A (en) | Apparatus for detecting abnormal operation of machinery and method using the same | |
| KR20190047878A (en) | Apparatus and method for detecting trouble of sensor based on signal | |
| JP2020038594A (en) | Abnormality detecting apparatus, abnormality detecting method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |