Patent Application
20240385613
The present invention relates to a life estimation method, a life estimation device, and a computer program.
An injection molding machine includes an injection device that melts and injects a molding material and a mold clamping device. The injection device includes a heating cylinder that has a nozzle at its tip and a screw that is provided in the heating cylinder to be rotatable in a circumferential direction and an axial direction. The screw is driven in a rotational direction and the axial direction by a driving mechanism. The driving mechanism includes a ball screw that converts the rotational driving force of an injection servo motor into the driving force of the screw in the axial direction and transmits the driving force (for example, Patent Document 1).
[Patent Document 1] Japanese Patent Laid-Open Publication No. 2019-166702
Meanwhile, the scheduled inspection time of the ball screw is displayed on the basis of the usage conditions and usage time of the injection molding machine. However, the degree of damage to the ball screw differs depending on the injection molding machine even when the scheduled inspection time comes. As a result, the injection molding machine is rarely inspected even when the scheduled inspection time comes.
An object of the present invention is to provide a life estimation method, a life estimation device, and a computer program that can accumulate physical quantity data indicating a state of a predetermined part constituting an industrial machine and calculate a failure time or failure probability of the predetermined part.
According to an aspect of the present invention, there is provided a life estimation method including: acquiring physical quantity data indicating a state of a predetermined part constituting an industrial machine; storing the acquired physical quantity data and time data indicating an acquisition time of the physical quantity data in association with each other; calculating a function for estimating a parameter value correlated with a life of the predetermined part over time on the basis of the acquired physical quantity data and the time data; and calculating a failure time or a failure probability of the predetermined part using the calculated function.
According to another aspect of the present invention, there is provided a life estimation device including: an acquisition unit acquiring physical quantity data indicating a state of a predetermined part constituting an industrial machine; a storage unit storing the acquired physical quantity data and time data indicating an acquisition time of the physical quantity data in association with each other; and a calculation unit calculating a function for estimating a parameter value correlated with a life of the predetermined part over time on the basis of the acquired physical quantity data and the time data and calculating a failure time or a failure probability of the predetermined part using the calculated function.
According to still another aspect of the present invention, there is provided a computer program causing a computer to execute a process including: acquiring physical quantity data indicating a state of a predetermined part constituting an industrial machine; storing the acquired physical quantity data and time data indicating an acquisition time of the physical quantity data in association with each other; calculating a function for estimating a parameter value correlated with a life of the predetermined part over time on the basis of the acquired physical quantity data and the time data; and calculating a failure time or a failure probability of the predetermined part using the calculated function.
According to the above, it is possible to accumulate physical quantity data indicating the state of a predetermined part constituting an industrial machine and to calculate the failure timing or failure probability of the predetermined part.
Hereinafter, specific examples of an injection molding machine (life estimation device), a life estimation method, and a computer program according to embodiments of the present invention will be described with reference to the drawings. At least some of the embodiments described below may be combined arbitrarily. In addition, the present invention is not limited to these examples, but is indicated by the claims. The present invention is intended to include all changes within the meaning and range equivalent to the claims.
The mold clamping device 2 includes a fixed platen 22 that is fixed on a bed 20, a mold clamping housing 23 that is provided to be slidable on the bed 20, and a movable platen 24 that similarly slides on the bed 20. The fixed platen 22 and the mold clamping housing 23 are connected by a plurality of tie bars, for example, four tie bars 25. The movable platen 24 is configured to be slidable between the fixed platen 22 and the mold clamping housing 23. A mold clamping mechanism 26 is provided between the mold clamping housing 23 and the movable platen 24. The mold clamping mechanism 26 is configured as, for example, a toggle mechanism. Further, the mold clamping mechanism 26 may be configured by a direct-pressure-type mold clamping mechanism, that is, a mold clamping cylinder. A fixed mold 28 and a movable mold 27 are provided in the fixed platen 22 and the movable platen 24, respectively. When the mold clamping mechanism 26 is driven, the mold 21 is opened and closed.
The injection device 3 is provided on a base 30. The injection device 3 includes a heating cylinder 31 that has a nozzle 31a at its tip and a screw 32 that is disposed in the heating cylinder 31 so as to be rotatable in a circumferential direction and an axial direction. A heater for melting the molding material is provided inside the heating cylinder 31 or on the outer periphery of the heating cylinder 31. The screw 32 is driven by the driving device 5 in a rotational direction and the axial direction.
A hopper 33 into which the molding material is put is provided in the vicinity of a rear end potion of the heating cylinder 31. In addition, the injection molding machine 1 includes a nozzle touch device 34 that moves the injection device 3 in a front-rear direction (a left-right direction in
The control device 4 is a computer that controls the operations of the mold clamping device 2 and the injection device 3 and includes, for example, a processor (calculation unit) 41, a storage unit 42, an operation unit 43, an acquisition unit 44, and a display unit 45 as a hardware configuration. In addition, the control device 4 may be a server device that is connected to a network. Further, the control device 4 may be configured by a plurality of computers to perform distributed processing, may be implemented by a plurality of virtual machines installed in one server, or may be implemented using a cloud server.
The processor 41 includes arithmetic circuits, such as a central processing unit (CPU), a multi-core CPU, a graphics processing unit (GPU), general-purpose computing on graphics processing units (GPGPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), and a neural processing unit (NPU), internal storage devices, such as a read only memory (ROM) and a random access memory (RAM), I/O terminals, a timer, and the like. The processor 41 executes a computer program (program product) 42a stored in the storage unit 42, which will be described below, to implement a control method according to Embodiment 1.
The storage unit 42 is a non-volatile memory such as a hard disk, an electrically erasable programmable ROM (EEPROM), or a flash memory. The storage unit 42 stores a computer program 42a for causing a computer to execute a process of calculating the failure time and failure probability of a ball screw 51.
The computer program 42a according to Embodiment 1 may be recorded on a recording medium 6 in a computer-readable manner. The storage unit 42 stores the computer program 42a read from the recording medium 6 by a reading device. The recording medium 6 is a semiconductor memory such as a flash memory. Further, the recording medium 6 may be an optical disc such as a compact disc (CD)-ROM, a digital versatile disc (DVD)-ROM, or a Blu-ray (registered trademark) disc (BD). Furthermore, the recording medium 6 may be a flexible disk, a magnetic disk, such as a hard disk, a magneto-optical disk, or the like. Moreover, the computer program 42a according to Embodiment 1 may be downloaded from an external server that is connected to a communication network and then stored in the storage unit 42.
The operation unit 43 is an input device such as a touch panel, a soft key, a hard key, a keyboard, or a mouse.
The acquisition unit 44 performs AD conversion on a rotation angle signal output from an encoder 50d, which will be described below, and an acceleration signal output from an acceleration sensor 5a and acquires rotation angle data and acceleration data.
The display unit 45 is a liquid crystal panel, an organic EL display, electronic paper, a plasma display, or the like. The display unit 45 displays various types of information corresponding to the image data given from the processor 41.
Setting values for determining molding conditions, such as an injection start time point, resin temperature in the mold, nozzle temperature, cylinder temperature, hopper temperature, mold clamping force, an injection speed, injection acceleration, injection peak pressure, and an injection stroke, are set in the injection molding machine 1. In addition, setting values for determining molding conditions, such as cylinder tip resin pressure, a reverse prevention ring seating state, holding pressure switching pressure, a holding pressure switching speed, a holding pressure switching position, a holding pressure completion position, a cushion position, metering back pressure, and metering torque, are set in the injection molding machine 1. Further, setting values for determining molding conditions, such as a metering completion position, a retraction speed of the screw 32, cycle time, mold closing time, injection time, holding pressure time, metering time, and mold opening time, are set in the injection molding machine 1. Then, the injection molding machine 1 in which these setting values have been set operates according to the setting values.
The ball screw 51 includes a ball screw shaft 51a and a nut 51b that is fitted to the ball screw shaft 51a. A base end portion of the ball screw shaft 51a is rotatably supported by a first plate 52 via a bearing 52a, the first plate 52 having a hole portion and a bearing seat. A large pulley 50c is provided in the base end portion of the ball screw shaft 51a. The small pulley 50a and the large pulley 50c are connected by a timing belt 50b, and the rotational force of the small pulley 50a is transmitted to the large pulley 50c at a reduced speed such that the ball screw shaft 51a is rotated.
Hereinafter, a direction (the right side in
A load cell 53 is provided on a forward-direction-side surface of the nut 51b, and a forward-direction-side surface of the load cell 53 is fixed to a second plate 54. A plurality of through holes are formed in the second plate 54, and guide shafts 55 are inserted into the through holes. The second plate 54 is guided by the guide shafts 55 and is moved in the forward and backward direction. A third plate 56 is provided on a forward-direction side of the first plate 52, and one end portion and the other end portion of the guide shaft 55 are supported by the first plate 52 and the third plate 56, respectively. When the ball screw shaft 51a is rotated, the nut 51b, the load cell 53, and the second plate 54 are moved integrally along the guide shaft 55 in the forward and backward direction.
The second plate 54 is provided with a hole portion and a bearing seat, and an output shaft 58 is supported by the hole portion via a bearing 54a. A plasticizing pulley 57 is provided on the output shaft 58. The plasticizing pulley 57 is connected to a pulley that is attached to a motor (not illustrated) for rotating the screw 32 through a timing belt (not illustrated). A rotation center of the output shaft 58 is matched with a rotation center of the ball screw shaft 51a. A recessed portion into which the tip of the ball screw shaft 51a is inserted when the nut 51b is moved forward or backward is formed in the output shaft 58. In addition, one end of the screw 32 is fixed to the output shaft 58 such that the central axes thereof are matched with each other. A through hole through which the screw 32 is inserted is formed in the third plate 56. One end of the heating cylinder 31 is fixed to the third plate 56 such that the screw 32 inserted through the through hole of the third plate 56 can be moved in the heating cylinder 31 in the axial direction.
Further, the acceleration sensor 5a that detects the vibration of the nut 51b is attached to the nut 51b of the ball screw 51. The acceleration sensor 5a outputs the detected acceleration signal to the control device 4. The processor 41 of the control device 4 performs AD conversion on the acceleration signal output from the acceleration sensor 5a to acquire acceleration data, using the acquisition unit 44. The control device 4 can estimate the life of the ball screw 51 on the basis of the acceleration data.
An outline of a molding process cycle is as follows, and the control device 4 performs a process of sequentially moving a forward and backward movement range of the nut 51b in the repeated molding process cycle. During injection molding, a mold closing process, a mold clamping process, an injection unit advancement process, an injection process, a metering process, an injection unit retraction process, a mold opening process, and an ejection process that are well known are sequentially performed.
Then, the calculation unit stores the acquired acceleration data and time data indicating the time when the acceleration data was acquired in the storage unit 42 in association with each other (Step S112). The time data is obtained from a timer.
Then, the calculation unit calculates a first function for estimating a change in an acceleration peak value correlated with the life of the ball screw 51 over time on the basis of the acceleration data and the time data stored in the storage unit 42 (Step S113). The acceleration peak value is an example of a parameter value correlated with the life of the ball screw 51.
For example, the first function is represented by the following expression:
where
The processor 41 calculates the coefficients a, b, and c at which a mean squared error is minimized to calculate the first function.
Then, as represented by a broken line in
Furthermore, the processor 41 calculates a third function for estimating changes in values obtained by subtracting the standard deviation of the normal distribution from parameter values at a plurality of time points over time (Step S115). A method for calculating the third function is the same as the method for calculating the second function.
Next, the processor 41 calculates the failure time and failure probability of the ball screw 51 using the first function (Step S116). Similarly, the processor 41 calculates the failure time and failure probability of the ball screw 51 using the second function (Step S117). Further, the processor 41 calculates the failure time and failure probability of the ball screw 51 using the third function (Step S118).
In addition, the processor 41 calculates the time point when the acceleration peak value calculated using the second function reaches the predetermined failure determination threshold value as the failure time when the failure probability is 16% (second probability).
Further, the processor 41 calculates the time point when the acceleration peak value calculated using the third function reaches the predetermined failure determination threshold value as the failure time when the failure probability is 84% (third probability).
Furthermore, the example in which the failure time is estimated from the intersection points of the first function, the second function, and the third function and the failure determination threshold value has been described above. However, as illustrated in
Then, the processor 41 displays, for example, a measured value graph 45a and estimated value graphs 45b, 45c, and 45d on the display unit 45 (Step S119) and ends the process.
The horizontal axis indicates the operating time corresponding to the time elapsed, and the vertical axis indicates the degree of failure corresponding to the acceleration peak value. The measured value graph 45a is a graph illustrating the measured value of a change in the acceleration peak value over time which is based on the acceleration data and the time data stored in the storage unit 42. The estimated value graphs 45b, 45c, and 45d are graphs illustrating changes in the acceleration peak values calculated by the first function, the second function, and the third function over time, respectively.
Further, the processor 41 displays a threshold value line image 45f showing the failure determination threshold value on the display unit 45. Furthermore, the processor 41 displays a normal distribution image 45e showing the time elapsed from the current time and the failure probability of the ball screw 51.
The operator of the injection molding machine 1 can visually recognize the current actual state, failure time, and failure probability of the ball screw 51 from the measured value graph 45a and the estimated value graphs 45b, 45c, and 45d displayed on the display unit 45.
As described above, according to the injection molding machine 1 of Embodiment 1, it is possible to accumulate the acceleration data indicating the state of the ball screw 51 of the injection molding machine 1 and to calculate the failure time and failure probability of the ball screw 51.
Specifically, it is possible to calculate the first function indicating the relationship between time and the acceleration peak value using the maximum likelihood estimation method and to calculate the time point when the acceleration peak value calculated using the first function reaches the predetermined failure determination threshold value as the failure time when the failure probability is 50%.
In addition, it is possible to calculate the time point when the acceleration peak value calculated using the second function reaches the predetermined failure determination threshold value as the failure time when the failure probability is 16%.
Further, it is possible to calculate the time point when the acceleration peak value calculated using the third function reaches the predetermined failure determination threshold value as the failure time when the failure probability is 84%.
Furthermore, it is possible to display the current state of the ball screw 51 using the measured value graph 45a and the estimated value graphs 45b, 45c, and 45d.
In addition, in Embodiment 1, the example has been described in which the failure time and failure probability of the ball screw 51 are estimated on the basis of the vibration of the ball screw 51. However, physical quantity data indicating the current or torque of the injection servo motor 50 may be used. The processor 41 may calculate a function indicating a change in the peak value of the current or torque over time on the basis of the physical quantity data indicating the current or torque of the injection servo motor 50 and calculate the failure time and failure probability of the ball screw 51 using the same method as that in Embodiment 1. Further, a configuration may be adopted in which the failure time and failure probability of the ball screw 51 are calculated on the basis of the concentration of iron powder included in a lubricant for the ball screw 51.
Furthermore, in Embodiment 1, the example has been described in which the failure time and failure probability of the ball screw 51 are calculated. However, a configuration may be adopted in which the failure time and failure probability of the mold clamping device 2 and the injection device 3 are calculated.
Moreover, a configuration may be adopted in which physical quantity data indicating the state of a predetermined part constituting an industrial machine is acquired and the failure time and failure probability of the predetermined part are calculated.
In addition, in Embodiment 1, the second function and the third function for estimating the values obtained by adding and subtracting the standard deviation from the average value of the acceleration peak values are given as an example. However, the present invention is not limited thereto. A configuration may be adopted in which a function for estimating a value obtained by adding or subtracting any predetermined deviation to or from the average value of the acceleration peak values is calculated and the failure time and the failure probability are estimated using the function.
An injection molding machine 1 according to Embodiment 2 differs from the injection molding machine according to Embodiment 1 in that the failure time and failure probability are calculated for each part of the ball screw shaft 51a. Since the other configurations of the injection molding machine 1 are the same as those of the injection molding machine 1 according to Embodiment 1, the same portions are denoted by the same reference numerals, and a detailed description thereof will be omitted.
Then, the calculation unit stores the acquired acceleration data, the acquired position data, and time data indicating the time when the acceleration data and the position data were acquired in the storage unit 42 in association with one another (Step S212). The time data is obtained from the timer.
Then, the calculation unit calculates the first function for estimating a change in the acceleration peak value correlated with the life of the ball screw 51 over time for each part of the ball screw shaft 51a on the basis of the acceleration data, the position data, and the time data stored in the storage unit 42 (Step S213).
Then, the processor 41 calculates the second function for estimating a change in the value obtained by adding the standard deviation of the normal distribution to the acceleration peak value calculated using the first function over time for each part of the ball screw shaft 51a (Step S214).
Further, the processor 41 calculates the third function for estimating changes in the values obtained by subtracting the standard deviation of the normal distribution from the parameter values at a plurality of time points over time for each part of the ball screw shaft 51a (Step S215).
In addition, a method for calculating the first to third functions is the same as that in Embodiment 1.
Then, the processor 41 calculates the failure time and failure probability of the ball screw 51 for each part of the ball screw shaft 51a using the first function (Step S216). Similarly, the processor 41 calculates the failure time and failure probability of the ball screw 51 for each part of the ball screw shaft 51a using the second function (Step S217). In addition, the processor 41 calculates the failure time and failure probability of the ball screw 51 for each part of the ball screw shaft 51a using the third function (Step S218).
Further, a method for calculating the failure time and the failure probability using the first to third functions is the same as that in Embodiment 1.
Then, the processor 41 displays, for example, the measured value graph 45a and the estimated value graphs 45b, 45c, and 45d on the display unit 45 (Step S219) and ends the process.
According to the injection molding machine 1 of Embodiment 2, it is possible to accumulate the acceleration data indicating the state of the ball screw 51 of the injection molding machine 1 and to calculate the failure time and failure probability of the ball screw 51 for each part of the ball screw shaft 51a.
An injection molding machine 1 according to Embodiment 3 differs from the injection molding machine according to Embodiment 1 in that the failure time and failure probability of the ball screw shaft 51a are calculated by machine learning. Since the other configurations of the injection molding machine 1 are the same as those of the injection molding machine 1 according to Embodiment 1, the same portions are denoted by the same reference numerals, and a detailed description thereof will be omitted.
The processor 41 reads the learning model 42b and the computer program 42a from the storage unit 42 and executes them.
The learning model 42b is a neural network that outputs a failure probability in a case where a peak value of vibration acceleration and the elapsed time, which is the operating time of the ball screw 51, are input. The learning model 42b includes an input layer, a hidden layer, and an output layer. The input layer has a plurality of nodes to which the peak value of the vibration acceleration and the elapsed time are input. The hidden layer includes a plurality of middle layers each having a plurality of nodes, and the nodes of the middle layer on the input side are connected to the nodes of the input layer. The output layer has nodes that output failure probabilities. Each node of the output layer is connected to the node of the middle layer on the output side.
The learning model 42b can be generated by performing machine learning using training data including the peak value of the vibration acceleration, the elapsed time, and the failure probability. For example, the learning processing unit 41a of the processor 41 performs machine learning on the learning model 42b by optimizing weighting coefficients of the learning model 42b with an error backpropagation, an error gradient descent method, or the like using training data.
In addition, the learning model 42b may be configured such that the output layer includes nodes corresponding to a plurality of elapsed times and the failure probabilities are output from the nodes corresponding to each elapsed time in a case where when the peak value of the vibration acceleration is input.
The processor 41 can input the peak value of the vibration acceleration detected at the current time and any elapsed time to the learning model 42b to calculate the failure probability of the ball screw 51. The processor 41 may display the measured value graph 45a and the estimated value graphs 45b, 45c, and 45d on the display unit 45 in the same manner as in Embodiment 1, using the relationship between the elapsed time and the failure probability calculated using the learning model 42b.
According to the injection molding machine 1 of Embodiment 3, as in Embodiment 1, it is possible to calculate the failure time and failure probability of the ball screw 51 and to display the measured value graph 45a and the estimated value graphs 45b, 45c, and 45d on the display unit 45.
In addition, in Embodiment 3, the learning model 42b using the neural network has been described. However, a configuration may be adopted in which the failure time and the failure probability are estimated using other known machine learning models such as a support vector machine (SVM) and a Bayesian network.
| Number | Date | Country | Kind |
|---|---|---|---|
| 2021-151214 | Sep 2021 | JP | national |
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/JP2022/022706 | 6/6/2022 | WO |
