JP2017109279A - Processing equipment, processing method, and processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the abnormality determination precision of a robot.SOLUTION: An abnormality determination part 36 detects whether or not time-series data outputted by a sensor 24 for detecting the situations of a robot have deviated a normal range determined on the basis of a predetermined threshold value th. And, the abnormality determination part 36 adjusts the threshold value to th'(=th+Δ). It is decided that the robot is abnormal, in the case where the data having deviated the normal range deviates the range which is determined on the basis of the threshold value th'after adjusted.SELECTED DRAWING: Figure 5

Description

  The present invention relates to a processing apparatus, a processing method, and a processing program.

  Conventionally, various methods are known as methods for detecting an abnormality in a working robot (see, for example, Patent Documents 1 to 4). For example, after defining an abnormal value and setting a probability distribution model (normal distribution, chi-square distribution, etc.) of an abnormal value, a value with a low probability of appearing (for example, μ ± 3σ when μ is averaged) is a threshold value For example, a method of determining an abnormality when a threshold value is exceeded is known.

  However, in the case of time-series data, since the number of data points obtained in one operation is large, data exceeding the threshold value frequently occurs within one operation time, and there is a possibility that the abnormality determination is excessively performed. For example, if the threshold is (μ ± 3σ), the data falls within the threshold with a probability of 99.7%, but conversely, the data exceeds the threshold with a probability of approximately 3 per 1000 times. In this case, the probability that one point or more of the 1000 points of time series data exceeds the threshold is 95%.

  For this reason, conventionally, the threshold value is increased (for example, μ ± 5σ), or, for example, it is determined that the threshold is normal until 5 points out of 1000 exceed the threshold value, so that abnormal determination is not performed excessively. . In addition, a method has been proposed in which a moving average method is introduced for a time series of abnormal values, and only high-frequency components of time series abnormal values are filtered, so that only a change point having a large change is determined to be abnormal ( For example, see Patent Document 5).

JP 2009-70071 A Japanese Patent Laid-Open No. 3-48728 JP-A-8-54915 JP-A-11-129145 JP 2005-4658 A

  However, although the method of increasing the threshold value suppresses excessive abnormality determination, there is a possibility that the abnormality may be missed. Further, in a method in which data exceeding a threshold value is not determined to be abnormal until a predetermined number or more appears, a difference between the data and the threshold value is not taken into account, and thus a serious abnormality may be missed. Further, in Patent Document 5, since it is necessary for a person to determine a parameter (window width), it is difficult to determine an appropriate value as a parameter value.

  In one aspect, an object of the present invention is to provide a processing device, a processing method, and a processing program capable of improving the abnormality determination accuracy of a working unit.

  In one aspect, the processing device detects whether or not the time-series data output from a sensor that detects the status of a working unit that performs work on an object deviates from a range determined based on a predetermined threshold. A detection unit that counts the number of times that data that deviates from the range is continuously detected when data that deviates from the range is detected, and a threshold value according to the number of times that the counting unit has counted. A determination unit configured to determine that the working unit is abnormal when the data that has been adjusted and deviated from the range deviates from a range determined based on the adjusted threshold value;

  The abnormality determination accuracy of the working unit can be improved.

It is a figure showing roughly the composition of the working device concerning one embodiment. Fig.2 (a)-FIG.2 (f) are figures which show the flow of the operation | work which peels the release paper of a double-sided tape. It is a figure which shows an example of the change of the output value of a sensor. It is a figure which shows roughly the hardware constitutions of a processing apparatus. It is a functional block diagram of a processing apparatus. It is a flowchart which shows a threshold value and adjustment value setting process. FIG. 7A is a diagram showing the average μ and the threshold value, and FIG. 7B is a diagram showing an example in which the learning data deviates from the normal range. It is a figure which shows an example of the data structure of an adjustment value table. It is a flowchart which shows an abnormality determination process. FIG. 10A and FIG. 10B are diagrams for explaining the processing in step S42 in FIG. It is a figure which shows a modification.

  Hereinafter, an embodiment of a working device will be described in detail with reference to FIGS.

  FIG. 1 is a diagram for explaining the overall configuration of a work apparatus 100 according to an embodiment. As shown in FIG. 1, the working device 100 includes a robot 22 as a working unit, a controller 14, a camera 12, a processing device 10, and the like.

  The robot 22 is an industrial robot, for example. The robot 22 includes, for example, a stage 25 and a manipulator 26. The manipulator 26 performs work using the action unit 28. The action unit 28 is, for example, a hand mechanism or tweezers. The stage 25 supports the manipulator 26. The robot 22 is controlled by the controller 14. The controller 14 operates the robot 22 based on a teaching data sequence in a time series of a series of operations. Here, for example, the teaching data string may be acquired from the outside via the input / output interface 97 illustrated in FIG. 4 or may be stored in the HDD 96 or the like in advance.

  Here, as an example, the robot 22 of the present embodiment executes an operation of peeling the release paper of the double-sided tape along the flow as shown in FIGS. 2 (a) to 2 (f). For example, as shown in FIG. 2A, a double-sided tape 115 as an object is attached on a stage 110, and the double-sided tape 115 has an adhesive portion 112 and a release paper 114. Shall. Then, the robot 22 performs an operation of peeling the release paper 114 using the tweezers-like action unit 28. In this case, the action unit 28 is operated by the manipulator 26, and the sensor 24 detects distortion of the manipulator 26.

  First, the robot 22 touches the stage 110 with the tip of the action portion 28 as shown in FIG. Next, as shown in FIGS. 2C and 2D, the robot 22 inserts the tip of the action part 28 between the release paper 114 and the adhesive part 112, and uses the action part 28 to release the release paper. Pick 114. Then, as shown in FIG. 2E, the robot 22 peels the release paper 114 from the adhesive portion 112 using the action unit 28, and designates the peeled release paper 114 as shown in FIG. 2F. Move to location and discard.

  Returning to FIG. 1, the sensor 24 is provided in the manipulator 26 and detects the status of work performed by the robot 22. The sensor 24 is a strain sensor that detects strain of the manipulator 26, for example. It is assumed that a plurality of sensors 24 are provided for the manipulator 26. As the sensor 24, for example, a 3-axis or 6-axis force sensor may be used. In this case, the sensor 24 detects the force vector and / or torque of the action point. The sensor 24 may be a load sensor, a pressure sensor, an acceleration sensor, a microphone, or the like. FIG. 3 shows an example of a change in the output value of the sensor 24. In FIG. 3, the horizontal axis represents time (time) from the start of work of the robot 22, and the vertical axis represents the output value (sensor value) of the sensor 24. As shown in FIG. 3, the output value (the waveform shown by the solid line) of the sensor 24 changes while the robot 22 performs operations such as insertion, release paper knob, peeling, moving, and discarding. In FIG. 3, the range between the upper and lower sides of the broken line indicates a threshold value used in abnormality determination described later.

  Returning to FIG. 1, it is assumed that the camera 12 is a two-dimensional image sensor such as a CCD (Charge Coupled Device) sensor or a CMOS (Complimentary Metal Oxide Semiconductor) sensor. However, the present invention is not limited to this, and the camera 12 may be a one-dimensional image sensor.

  The processing device 10 determines whether the work status of the robot 22 is normal (normal or abnormal) based on the image data acquired by the camera 12, the data detected by the sensor 24, the coordinate position of the action unit 28, and the like. FIG. 4 shows a hardware configuration of the processing apparatus 10. As shown in FIG. 4, the processing apparatus 10 includes a CPU (Central Processing Unit) 90, a ROM (Read Only Memory) 92, a RAM (Random Access Memory) 94, a storage unit (here, an HDD (Hard Disk Drive)) 96, An input / output interface 97, a display unit 93, an input unit 95, a portable storage medium drive 99, and the like are provided. Each component of the processing apparatus 10 is connected to a bus 98. The display unit 93 includes a liquid crystal display or the like, and the input unit 95 includes a keyboard, a mouse, an input button, and the like. In the processing device 10, the CPU 90 executes a program (including a processing program) stored in the ROM 92 or the HDD 96 or a program (including a processing program) read from the portable storage medium 91 by the portable storage medium drive 99. Thereby, the function of each part shown in FIG. 5 is implement | achieved.

  FIG. 5 is a functional block diagram of the processing apparatus 10. The processing device 10 functions as a value setting unit 30, an abnormality determination unit 36, and an output unit 38 as a setting unit when the CPU 90 executes a program.

  Prior to the robot 22 performing the work, the value setting unit 30 causes the robot 22 to perform the same operation as the work, and acquires values detected by the sensors during the operation as learning data. And the value setting part 30 sets the threshold value used in the abnormality determination part 36 based on learning data, or sets the adjustment value for adjusting a threshold value. Details of the threshold value and adjustment value setting method will be described later.

  The abnormality determination unit 36 acquires time-series data (output values) detected by each sensor while the robot 22 is working, and based on the output values, the quality of the work of the robot 22 (work Whether or not an abnormality has occurred. Details of the abnormality determination process by the abnormality determination unit 36 will be described later. The determination result by the abnormality determination unit 36 is notified to the output unit 38.

  When the abnormality determination unit 36 determines that an abnormality has occurred in the robot 22, the output unit 38 outputs that the abnormality has occurred via the display unit 93 or the like.

  Next, processing (threshold and adjustment value setting processing, abnormality determination processing) of each unit in FIG. 5 will be described in detail.

(Threshold and adjustment value setting processing)
FIG. 6 shows a flowchart of threshold value and adjustment value setting processing executed by the value setting unit 30. The process of FIG. 6 is a process executed before operating the robot 22 for the first time. Note that the process of FIG. 6 may be executed at predetermined time intervals (for example, during maintenance).

  In the process of FIG. 6, first, in step S10, the value setting unit 30 acquires learning data. Specifically, the value setting unit 30 causes the robot 22 to perform the same operation as the operation before the robot 22 performs the operation, and the values (output values) detected by the sensors during the operation. ) As learning data. The value setting unit 30 acquires a large number of learning data.

  Next, in step S12, the value setting unit 30 assumes a probability model. Here, as an example, a normal distribution is assumed. Note that the assumed probability model may be another model such as a chi-square distribution.

Next, in step S14, the value setting unit 30 creates a threshold value. Assuming that the probability model is assumed in step S12, it is possible to treat a region having a low probability of data appearance as abnormal, so that a value defining the region can be used as a threshold for determining whether or not the region is abnormal. Become. When the time is k, the average of the learning data at time k is μ _k , and the standard deviation of the learning data at time k is σ _k , in the method using the 3σ management width, the threshold th _k is th _k = μ _k. ± 3σ _k can be set. FIG. 7A shows μ _k and th _k (= μ _k ± 3σ _k ) in a section of k = 900 to 920 msec as an example. Incidentally, if the range between the values _{μ k -3σ k ~μ k + 3σ} k output from the sensor 24, will be determined robot 22 from normal. Hereinafter, the range between _{μ k -3σ k ~μ k + 3σ} k is referred to as "normal range".

Next, in step S16, the value setting unit 30 acquires all data that deviates continuously i (i = 1, 2, 3,...) Times from the created threshold th _k . Even if th _k is calculated using learning data as in step S14 described above, there is stochastically data that deviates from the range (normal range) determined by the threshold th _k in the set of learning data. Therefore, the value setting unit 30 extracts data that deviates from the normal range from a large number of learning data, and what number of data the extracted data continuously deviates from the normal range (ie, continuous The number of deviations i) is specified, and the data is classified for each i. For example, in FIG. 7B, the data indicated by the symbols P _a and P _b are classified as “data of i = 1” because there is no data that deviates from the normal range immediately before. The data indicated by the symbol P _c is classified as “i = 2 data” because there is one data (P _b ) that deviates from the normal range immediately before.

  Next, in step S18, the value setting unit 30 calculates an amount (deviation amount) in which each of the deviating learning data deviates from the normal range.

Next, in step S20, the value setting unit 30 specifies the maximum deviation amount for each _i and sets it as the adjustment value Δi. In this case, the value setting unit 30 identifies the largest deviation amount among the “i = 1 data” and sets the identified largest deviation amount as the adjustment value Δ ₁ . Further, the value setting unit 30 identifies the data having the maximum deviation amount among the “i = 2 data”, and sets the identified maximum deviation amount as the adjustment value Δ ₂ . The same applies to Δ ₃ , Δ ₄ ,. Note that if “i = m data” does not exist, Δ _m = 0.

Next, in step S22, the value setting unit 30 transmits the threshold value th _k created in step S14 and the adjustment value Δ _i set in step S20 to the abnormality determination unit 36. The adjustment value Δ _i is transmitted to the abnormality determination unit 36 in the form of an adjustment value table as shown in FIG. The adjustment value table in FIG. 8 stores the number of consecutive departures i and the adjustment value Δi.

With the above processing, all processing in FIG. 6 is completed. With the processing in FIG. 6, the value setting unit 30 can automatically set the threshold th _k and the adjustment value Δ _i from the learning data.

In the above description, the case where the threshold value th _k and the adjustment value Δ _i are set using the learning data acquired in step S10 has been described. However, the present invention is not limited to this. For example, the learning data acquired in step S10 may be used only when the threshold value th _k is set, and the data (test data) acquired separately from step S10 may be used in the processing after step S16.

(Abnormality judgment processing)
FIG. 9 shows a flowchart of the abnormality determination process. The abnormality determination unit 36 and the output unit 38 continuously execute the process of FIG. 9 from the start to the end of the work of the robot 22.

  When the processing of FIG. 9 is started, first, in step S30, the abnormality determination unit 36 sets (initializes) the time k to 0 and sets (initializes) the number of consecutive departures i to 0.

  Next, in step S <b> 32, the abnormality determination unit 36 determines whether the time k is smaller than the time N. The time N means the time required for the robot 22 to work. Here, if the robot 22 performs the same work, the time N required for the work is constant. In step S32, it can be said that it is determined whether one operation is completed by determining whether k is smaller than N. If the determination in step S32 is negative, the entire process of FIG. 9 is terminated. If the determination is affirmative, the abnormality determination unit 36 proceeds to step S34.

After the transition to step S34, the abnormality determination section 36 acquires data x _k output from the sensor 24 at time k.

Next, in step S36, the abnormality determination unit 36 determines whether or not the data x _k deviates from the normal range (μ _k −3σ _{k to} μ _k + 3σ _k ) determined by the threshold value. If the determination in step S36 is negative, the process proceeds to step S50, where the abnormality determination unit 36 sets (initializes) i to 0, increments k by 1 (k = k + 1), and performs step S32. Return to. On the other hand, if the determination in step S36 is affirmative, the abnormality determination unit 36 proceeds to step S38.

In step S38, the abnormality determination unit 36 increments i by 1 (i = i + 1). That is, the abnormality determination unit 36 counts up the number of consecutive departures i. Next, in step S40, the abnormality determination unit 36 acquires the adjustment value Δ _i from the adjustment value table and adjusts the threshold th _k (calculates the adjusted threshold th ′ _ik ). For example, when the adjustment value Δ ₁ is acquired, the threshold value th ′ _1k after adjustment is th ′ _1k = μ _k ± 3σ _k ± Δ ₁ (in the same order of signs). In this case, the normal range is μ _k −3σ _k −Δ _{1 to} μ _k + 3σ _k + Δ ₁ . Further, when the adjustment value Δ ₂ is acquired, the adjusted threshold th ′ _2k is th ′ _2k = μ _k + 3σ _k + Δ ₂ (in the same order of signs). In this case, the normal range is μ _k −3σ _k −Δ _{2 to} μ _k + 3σ _k + Δ ₂ .

Next, in step S42, the abnormality determination unit 36 determines whether or not x _k is out of the normal range determined by the adjusted threshold th ′ _ik . For example, in the case of the data x _a and x _b (i = 1 data) shown in FIGS. _10A and _10B , it is larger than th _1k ′ = (μ _k + 3σ _k + Δ ₁ ). In this case, the determination in step S42 is affirmed. Further, for example, in the case of the data x _c shown in FIG. 10B (data of i = 2), if the data x _c is larger than th ′ _2k (= μ _k + 3σ _k + Δ ₂ ), the step The determination in S42 is affirmed. In the example of FIG. 10 (a), FIG. 10 (b), when the data x _c, the determination in step S42 is affirmative, data x _a, in the case of x _b, the determination in step S42 is negative .

  If the determination in step S42 is negative, it is normal and the process proceeds to step S48. In step S48, the abnormality determination unit 36 increments k by 1 (k = k + 1), and returns to step S32. On the other hand, if the determination in step S42 is affirmative, the process proceeds to step S44.

  In step S44, the abnormality determination unit 36 determines that there is an abnormality. Next, in step S46, the output unit 38 outputs an abnormality. In this case, the output unit 38 outputs that an abnormality has occurred via the display unit 93 or the like. Thereafter, the abnormality determination unit 36 increments k by 1 (k = k + 1) in step S48, and then returns to step S32.

  The above process is repeated until the determination in step S32 is denied. When the determination in step S32 is denied, the entire process in FIG. 9 ends. By performing the processing of FIG. 9 as described above, when there is data that deviates from the normal range, it is not immediately determined that there is an abnormality, and therefore it is possible to suppress the abnormality determination from being performed excessively. In addition, in order to make an abnormality determination based on whether or not the data that deviates from the normal range deviates from the adjusted threshold value corresponding to the number of consecutive departures i, an appropriate abnormality determination that considers the amount of data deviation is performed. Can do.

As can be seen from the above description, whether or not the output value output from the sensor 24 that detects the condition of the robot 22 including the abnormality determination unit 36 deviates from the normal range determined based on the predetermined threshold th _k . A function as a detection unit for detecting the above is realized. Further, when the data detected by the counting unit including the abnormality determination unit 36 and the detection unit that counts the number of consecutive deviations i deviates from the range determined based on the adjusted threshold th ′ _ik , the abnormality of the robot 22 is detected. A function as a determination unit for determination is realized.

As described above in detail, according to the present embodiment, the abnormality determination unit 36 determines that the time-series data output from the sensor 24 that detects the status of the robot 22 is determined based on the predetermined threshold th _k. It is detected whether it deviated from. Then, the abnormality determination unit 36 sets the threshold value th ′ _ik (=) according to the number of times that data that deviates from the normal range is continuously detected when the data deviates from the normal range (continuous deviation number i). th _k + Δ _i ), and when the data deviating from the normal range deviates from the range determined based on the adjusted threshold th ′ _ik , it is determined that the robot 22 is abnormal. As described above, in this embodiment, the abnormality determination unit 36 does not immediately determine that there is an abnormality even if there is data that deviates from the normal range determined by the threshold th _k, and the threshold adjusted according to the number of consecutive departures i. Therefore, it is determined that there is an abnormality when deviating from the range determined by the above, so that it is possible to suppress excessive abnormality determination and improve abnormality determination accuracy. For example, according to the present embodiment, it is possible to detect an abnormality that is overlooked when the threshold value is uniformly increased to μ ± 5σ. Further, according to the present embodiment, it is possible to suppress overlooking of data that should be determined as abnormal as compared to a case where a method that does not determine that data is abnormal until a predetermined number of data deviates from the normal range is employed. .

Further, in this embodiment, the value setting unit 30 causes the robot 22 to perform the same operation as the work prior to the work of the robot 22, acquires data output from the sensor 24 as learning data, and based on the learning data to set the adjustment value Δ _i. Thereby, the value setting unit 30 can automatically set an appropriate adjustment value based on the learning data.

In the present embodiment, the value setting unit 30 classifies the learning data that deviates from the normal range based on the number of consecutive deviations _i, and sets the adjustment value Δ _i based on the classified learning data. Thus, it is possible to set an appropriate adjustment value Δ _i corresponding to the number of consecutive departures i.

In the present embodiment, the value setting unit 30 sets the maximum value among the deviation amounts of the learning data classified based on the number of consecutive deviations i as the adjustment value Δ _i . Accordingly, it is possible to automatically set an appropriate adjustment value that can suppress excessive abnormality determination based on the learning data.

In the above embodiment, the value setting unit 30 has been described with respect to the case where the maximum value among the deviation amounts of the learning data classified based on the number of consecutive deviations i is the adjustment value Δ _i , but is not limited thereto. It is not a thing. For example, an average value of deviation amounts of learning data classified based on the number of consecutive deviations i may be used as the adjustment value Δ _i . Alternatively, for example, a statistical value calculated from the deviation amount of the learning data classified based on the number of consecutive deviations i may be used as the adjustment value Δ _i .

  In the above embodiment, the case where the processing apparatus 10 has the function of the value setting unit 30 has been described. However, the present invention is not limited to this. For example, as shown in FIG. 11, the cloud server 85 connected to the work device 100 (processing device 10) via the network 80 may have the same function as the value setting unit 30. In this case, the processing device 10 may provide the learning data to the cloud server 85, and the cloud server 85 may calculate a threshold value or an adjustment value based on the learning data and provide the calculated value to the abnormality determination unit 36 of the processing device 10. Good. Note that the cloud server 85 may calculate and provide threshold values and adjustment values used by the plurality of work devices 100 as illustrated in FIG. 11.

  Further, the cloud server 85 may have the functions (value setting unit 30, abnormality determination unit 36, output unit 38) of the processing apparatus 10 of the above embodiment. In this case, the cloud server 85 acquires the data acquired by the work apparatus 100 via the network 80, determines an abnormality by the same method as the above embodiment based on the acquired data, and determines the determination result as the work apparatus 100. May be transmitted. The work device 100 and the cloud server 85 may be installed in different countries.

  The above processing functions can be realized by a computer. In that case, a program describing the processing contents of the functions that the processing apparatus should have is provided. By executing the program on a computer, the above processing functions are realized on the computer. The program describing the processing contents can be recorded on a computer-readable recording medium (except for a carrier wave).

  When the program is distributed, for example, it is sold in the form of a portable recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) on which the program is recorded. It is also possible to store the program in a storage device of a server computer and transfer the program from the server computer to another computer via a network.

  The computer that executes the program stores, for example, the program recorded on the portable recording medium or the program transferred from the server computer in its own storage device. Then, the computer reads the program from its own storage device and executes processing according to the program. The computer can also read the program directly from the portable recording medium and execute processing according to the program. Further, each time the program is transferred from the server computer, the computer can sequentially execute processing according to the received program.

  The above-described embodiment is an example of a preferred embodiment of the present invention. However, the present invention is not limited to this, and various modifications can be made without departing from the scope of the present invention.

In addition, the following additional remarks are disclosed regarding description of the above embodiment.
(Additional remark 1) The detection part which detects whether the time-sequential data which the sensor which detects the condition of the working part which performs work with respect to a target object deviated from the range defined based on a predetermined threshold value,
A counter that counts the number of times data that deviates from the range is detected continuously when data deviating from the range is detected;
A threshold value is adjusted according to the number of times counted by the counting unit, and when the data that deviates from the range deviates from a range determined based on the adjusted threshold value, a determination unit that determines that the working unit is abnormal,
A processing apparatus comprising:
(Supplementary Note 2) Prior to the work, the work unit performs the same operation as the work, acquires time-series data output from the sensor as learning data, and uses it for threshold adjustment based on the learning data The processing apparatus according to appendix 1, further comprising a setting unit that sets an adjustment value.
(Supplementary Note 3) The setting unit
When learning data deviating from a range determined based on the predetermined threshold is detected, the detected learning data is classified and classified based on the number of times data deviating from the range is continuously detected. The processing apparatus according to appendix 2, wherein an adjustment value corresponding to the number of times is set based on the learning data.
(Additional remark 4) The said setting part calculates the deviation amount from the said predetermined threshold value of each learning data classified based on the said frequency | count, and sets the calculated maximum value of the said deviation amount as an adjustment value according to the said frequency | count And
The processing apparatus according to appendix 3, wherein the determination unit adjusts the threshold value so that the range is expanded by an amount corresponding to the adjustment value.
(Additional remark 5) The acquisition part which acquires the time-sequential data which the sensor which detects the condition of the working part which performs work with respect to a target object outputs from an external device,
A detection unit for detecting whether the time-series data acquired by the acquisition unit deviates from a range determined based on a predetermined threshold;
A counter that counts the number of times data that deviates from the range is detected continuously when data deviating from the range is detected;
A threshold value is adjusted according to the number of times counted by the counting unit, and when the data that deviates from the range deviates from a range determined based on the adjusted threshold value, a determination unit that determines that the working unit is abnormal,
A processing apparatus comprising:
(Additional remark 6) The processing apparatus of Additional remark 5 further provided with the transmission part which transmits the determination result of the said determination part with respect to the said external device.
(Supplementary note 7) Detecting whether or not the time-series data output by the sensor that detects the status of the working unit that performs work on the object deviates from a range determined based on a predetermined threshold,
When detecting data that deviates from the range, the number of times that data that deviates from the range is continuously detected is counted,
The threshold is adjusted according to the counted number of times, and when the data that deviates from the range deviates from the range determined based on the adjusted threshold, it is determined that the working unit is abnormal.
A processing method characterized in that a computer executes the processing.
(Supplementary Note 8) Prior to the work, the working unit performs the same operation as the work, acquires time-series data output from the sensor as learning data, and uses it for threshold adjustment based on the learning data The processing method according to appendix 7, wherein the computer executes the process of setting an adjustment value.
(Supplementary Note 9) In the processing to be set,
When learning data deviating from a range determined based on the predetermined threshold is detected, the detected learning data is classified and classified based on the number of times data deviating from the range is continuously detected. The processing method according to appendix 8, wherein an adjustment value corresponding to the number of times is set based on the learning data.
(Supplementary Note 10) In the setting process, a deviation amount from the predetermined threshold value of each of the learning data classified based on the number of times is calculated, and the calculated maximum value of the deviation amount is used as an adjustment value according to the number of times. Set,
The processing method according to claim 9, wherein in the determination process, the threshold value is adjusted so that the range is expanded by an amount corresponding to the adjustment value.
(Additional remark 11) The time series data which the sensor which detects the condition of the work part which performs work with respect to a target object outputs are acquired from an external device,
Detecting whether or not the acquired time-series data deviates from a range determined based on a predetermined threshold;
When detecting data that deviates from the range, the number of times that data that deviates from the range is continuously detected is counted,
The threshold is adjusted according to the counted number of times, and when the data that deviates from the range deviates from the range determined based on the adjusted threshold, it is determined that the working unit is abnormal.
A processing method characterized in that a computer executes the processing.
(Supplementary note 12) The processing method according to supplementary note 11, wherein the computer further executes a process of transmitting a determination result obtained in the determination process to the external device.
(Supplementary Note 13) Detecting whether time-series data output from a sensor that detects the status of a working unit that performs work on an object deviates from a range determined based on a predetermined threshold value,
When detecting data that deviates from the range, the number of times that data that deviates from the range is continuously detected is counted,
The threshold is adjusted according to the counted number of times, and when the data that deviates from the range deviates from the range determined based on the adjusted threshold, it is determined that the working unit is abnormal.
A processing program for causing a computer to execute processing.
(Supplementary Note 14) Prior to the work, the work unit performs the same operation as the work, acquires time-series data output from the sensor as learning data, and uses it for threshold adjustment based on the learning data The processing program according to appendix 13, wherein the computer is caused to execute processing for setting an adjustment value.
(Supplementary Note 15) In the processing to be set,
When learning data deviating from a range determined based on the predetermined threshold is detected, the detected learning data is classified and classified based on the number of times data deviating from the range is continuously detected. The processing program according to appendix 14, wherein an adjustment value corresponding to the number of times is set based on the learning data.
(Supplementary Note 16) In the setting process, a deviation amount from the predetermined threshold of each learning data classified based on the number of times is calculated, and the calculated maximum value of the deviation amount is used as an adjustment value according to the number of times. Set,
The processing program according to appendix 15, wherein the determination includes adjusting the threshold value so that the range is expanded by an amount corresponding to the adjustment value.
(Supplementary Note 17) Obtaining time-series data output from an external device output from a sensor that detects the status of a working unit that performs work on an object,
Detecting whether or not the acquired time-series data deviates from a range determined based on a predetermined threshold;
When detecting data that deviates from the range, the number of times that data that deviates from the range is continuously detected is counted,
The threshold is adjusted according to the counted number of times, and when the data that deviates from the range deviates from the range determined based on the adjusted threshold, it is determined that the working unit is abnormal.
A processing program for causing a computer to execute processing.
(Additional remark 18) The processing program of Additional remark 17 characterized by making the said computer further perform the process which transmits the determination result obtained by the said determination process with respect to the said external device.

10 processing device 30 value setting unit (setting unit)
36 Abnormality determination unit (detection unit, counting unit, determination unit)

Claims (8)

A detection unit that detects whether or not time-series data output by a sensor that detects the status of a working unit that performs work on an object deviates from a range determined based on a predetermined threshold;
A counter that counts the number of times data that deviates from the range is detected continuously when data deviating from the range is detected;
A threshold value is adjusted according to the number of times counted by the counting unit, and when the data that deviates from the range deviates from a range determined based on the adjusted threshold value, a determination unit that determines that the working unit is abnormal,
A processing apparatus comprising:   Prior to the work, the work unit performs the same operation as the work, acquires time-series data output from the sensor as learning data, and sets an adjustment value used for threshold adjustment based on the learning data The processing apparatus according to claim 1, further comprising: a setting unit that performs processing. The setting unit
When learning data deviating from a range determined based on the predetermined threshold is detected, the detected learning data is classified and classified based on the number of times data deviating from the range is continuously detected. The processing apparatus according to claim 2, wherein an adjustment value corresponding to the number of times is set based on the learning data. The setting unit calculates a deviation amount from the predetermined threshold for each of the learning data classified based on the number of times, and sets the calculated maximum value of the deviation amount as an adjustment value according to the number of times,
The processing apparatus according to claim 3, wherein the determination unit adjusts the threshold value so that the range is expanded by an amount corresponding to the adjustment value. An acquisition unit for acquiring, from an external device, time-series data output by a sensor that detects the status of a working unit that performs work on an object;
A detection unit for detecting whether the time-series data acquired by the acquisition unit deviates from a range determined based on a predetermined threshold;
A counter that counts the number of times data that deviates from the range is detected continuously when data deviating from the range is detected;
A threshold value is adjusted according to the number of times counted by the counting unit, and when the data that deviates from the range deviates from a range determined based on the adjusted threshold value, a determination unit that determines that the working unit is abnormal,
A processing apparatus comprising:   The processing device according to claim 5, further comprising a transmission unit that transmits a determination result of the determination unit to the external device. Detecting whether or not the time-series data output by a sensor that detects the status of a working unit that performs work on an object deviates from a range determined based on a predetermined threshold;
When detecting data that deviates from the range, the number of times that data that deviates from the range is continuously detected is counted,
The threshold is adjusted according to the counted number of times, and when the data that deviates from the range deviates from the range determined based on the adjusted threshold, it is determined that the working unit is abnormal.
A processing method characterized in that a computer executes the processing. Detecting whether or not the time-series data output by a sensor that detects the status of a working unit that performs work on an object deviates from a range determined based on a predetermined threshold;
When detecting data that deviates from the range, the number of times that data that deviates from the range is continuously detected is counted,
The threshold is adjusted according to the counted number of times, and when the data that deviates from the range deviates from the range determined based on the adjusted threshold, it is determined that the working unit is abnormal.
A processing program for causing a computer to execute processing.

Images