Computer, life prediction method, and life prediction program

Abstract

To easily predict the remaining life of an electronic component.SOLUTION: In a computer having at least one processor and at least one memory resource, the at least one processor executes the steps of: acquiring the waveform of a power source current of an electronic system having an electronic component; specifying a waveform change showing a change in a waveform from an initial waveform of the power source current when the parameter of the electronic component is at an initial value; estimating an amount of change from a specified waveform change on the basis of a model learning a relationship between the amount of change from the initial value of the parameter and the waveform change; and predicting the remaining life of the electronic component on the basis of the estimated amount of change.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a computer, a life prediction method, and a life prediction program. [Background technology]

[0002] As the trend of reducing environmental load increases, there is a demand for technology that reuses electronic components used inside electronic devices without discarding them. One such technology is a technology that estimates the remaining life of electronic components in the middle of use. With this technology, the value of electronic components in the recycling market can be determined according to the estimated remaining life, and electronic components can be distributed in the recycling market at an appropriate price. For example, in Patent Document 1, the internal temperature of electronic components such as capacitors is defined as the stress applied to the electronic components, and the remaining life of the electronic components is estimated based on the stress. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7090832 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology of Patent Document 1 requires that a monitor circuit for acquiring stress be provided for each electronic component.Since an extremely large number of electronic components are mounted on one electronic board, it is not realistic to provide a monitor circuit for each electronic component and estimate their remaining lifespan, as in Patent Document 1.

[0005] The present invention has been made in view of the above circumstances, and has an object to easily predict the remaining life of an electronic component. [Means for solving the problem]

[0006] In order to solve the above problem, a computer according to one embodiment of the present invention is a computer having one or more processors and one or more memory resources, wherein the one or more processors execute the steps of acquiring a waveform of a power supply current of an electronic system including an electronic component, identifying a waveform change indicating a change in the waveform from an initial waveform of the power supply current when a parameter of the electronic component is at an initial value, estimating an amount of change from the identified waveform change based on a model that has learned the relationship between an amount of change of the parameter from the initial value and the waveform change, and predicting a remaining life of the electronic component based on the estimated amount of change. Effect of the Invention

[0007] According to the present invention, the remaining life of an electronic component can be predicted simply and easily.

[0008] Problems, configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a schematic diagram showing an example of a system configuration of a life prediction system according to the present embodiment. [Diagram 2] FIG. 2 is a schematic diagram showing an example of the hardware configuration of each of the computer and the electronic system according to this embodiment. [Figure 3A] FIG. 3A is an example of a circuit diagram of an electronic circuit. [Figure 3B] FIG. 3B is a schematic diagram showing an example of degradation simulation parameter information corresponding to the electronic circuit of FIG. 3A. [Figure 4] FIG. 4 is a schematic diagram showing an example of a simulation waveform and a nominal waveform. [Diagram 5] FIG. 5 is a schematic diagram of an example of a part deterioration model during learning. [Figure 6] FIG. 6 is a schematic diagram of an example of a part deterioration model for predicting deterioration. [Figure 7A] FIG. 7A is a schematic diagram showing an example of a life prediction model. [Figure 7B] FIG. 7B is a schematic diagram showing an example data structure of remaining life information. [Figure 8] FIG. 8 is a flowchart showing an example of a process performed by a computer when generating a part deterioration model. [Figure 9] FIG. 9 is a flowchart showing an example of a process performed by an electronic system when predicting the electronic life of an electronic component in an actual electronic circuit. [Figure 10] FIG. 10 is a flow chart showing an example of a process performed by a computer when predicting the electronic life of an electronic component in an actual electronic circuit. [Figure 11] FIG. 11 is a diagram showing an example of the configuration of an electronic system according to another embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In all the drawings for describing the embodiment, the same members are generally given the same reference numerals, and the repeated description thereof will be omitted as appropriate. In the following embodiment, the components (including element steps, etc.) are not necessarily essential, unless otherwise specified or considered to be obviously essential in principle. In addition, when "consisting of A", "consisting of A", "having A", or "including A" is used, it is understood that other elements are not excluded, except when it is specifically specified that only the element is included. Similarly, in the following embodiment, when referring to the shape, positional relationship, etc. of the components, etc., it includes those that are substantially similar to or similar to the shape, etc., except when it is specifically specified or considered to be obviously not essential in principle.

[0011] <Present embodiment> 1 is a schematic diagram showing an example of a system configuration of a life prediction system according to this embodiment. The life prediction system is a system for predicting the life of an electronic component, and includes a computer 1 and an electronic system 3.

[0012] The calculator 1 is a computer that predicts a life span and presents the predicted life span results to a user via a GUI (Graphical User Interface) or the like. The electronic system 3 is a system that includes electronic components that are the subject of life span prediction. The calculator 1 and the electronic system 3 are connected to each other via a network 2 such as the Internet or a LAN (Local Area Network).

[0013] FIG. 2 is a schematic diagram showing an example of the hardware configuration of each of the computer 1 and the electronic system 3 according to this embodiment.

[0014] The electronic system 3 is a system including a power supply circuit 31 , an electronic circuit 32 , and a control circuit 33 .

[0015] The power supply circuit 31 supplies a power supply current I in For example, the power supply circuit 31 includes a power supply filter that cuts noise and a circuit that controls the output voltage and output current.

[0016] The electronic circuit 32 is a circuit including an electronic component to be predicted for its lifespan, and has a power supply current I in As an example, the electronic circuit 32 performs processing according to its circuit configuration on the input signal S in The result of the processing is the output signal S out Output.

[0017] The control circuit 33 is a circuit including a processor such as a CPU (Central Processing Unit) for controlling each circuit of the electronic system 3. For example, the control circuit 33 may include a power supply current I in The waveform of the power supply current I is notified to Calculator 1. A monitor circuit such as an ammeter is installed later, and the monitor circuit measures the power supply current I in The waveform of the signal may be measured and notified to Calculator 1.

[0018] In order to generate, transmit, receive data, and perform various other processes, the computer 1 reads a processing program stored in a memory resource, and the processor executes processing according to the processing program. Note that the computer 1 may be, for example, a personal computer, a tablet terminal (computer), a smartphone, a server computer, a blade server, a cloud server, or a system including at least one of these computers. In other words, the computer 1 also includes a system including, for example, a cloud server and a computer for display (for example, a tablet terminal or a smartphone). Another example of the computer 1 is a controller that controls or manages some kind of device including a processor and memory resources.

[0019] 2, the computer 1 has one or more processors 10, one or more UI (User Interface) devices 11, one or more NI (Network Interface) devices 12, and one or more memory resources 13. The computer 1 may include other components. The processor 10, the UI device 11, the NI device 12, and the memory resource 13 are connected to each other via a bus 28.

[0020] The processor 10 is a calculation device that reads a life prediction program 14 stored in a memory resource 13 and executes each process of the life prediction method according to this embodiment. Examples of the processor 10 include a microprocessor, a CPU, a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a quantum processor, or other semiconductor devices capable of calculation.

[0021] The UI device 11 is an input device for inputting instructions from a user (which may be an operator) to the calculator 1, and an output device for outputting information generated by the calculator 1. Examples of the input device include a keyboard, a touch panel, a pointing device such as a mouse, and a voice input device such as a microphone. Examples of the output device include a display, a printer, and a voice synthesizer. Unless otherwise specified below, it is assumed that input and output of information between the calculator 1 and the user is performed via the UI device 11. The UI device 11 may be only an input device, or only an output device.

[0022] The NI device 12 is a communication device that performs information communication with an external device. The NI device 12 performs information communication with an external device such as an electronic system 3 via a network 2. Note that, unless otherwise specified below, information communication between the computer 1 (or the processor 10) and an external device is assumed to be performed via the NI device 12.

[0023] The memory resource 13 is, for example, a non-volatile memory and / or a volatile memory. Examples of the volatile memory are a RAM (Random Access Memory) and a ROM (Read Only Memory). Examples of the non-volatile memory may be a rewritable storage medium such as a flash memory, a hard disk, or an SSD (Solid State Drive), or may be a USB (Universal Serial Bus) memory, a memory card, or a hard disk. In addition, RAM such as MRAM (Magnetoresistive RAM), PRAM (Phase change RAM), and ReRAM (Resistive RAM) may be regarded as a non-volatile memory. The processor 10 may provide a service of distributing the life prediction program 14 stored in the memory resource 13 to other computers.

[0024] The memory resource 13 stores a life prediction program 14, circuit information 15, input signal information 16, parts list information 17, nominal waveform 18, deterioration simulation parameter information 19, simulation waveform 20, part deterioration model 21, simulation waveform change 22, actual waveform change 23, parameter change information 24, operating time information 25, life prediction model 26, and remaining life information 27.

[0025] The life prediction program 14 is a program for causing the computer 1 to execute the life prediction method according to this embodiment.

[0026] The circuit information 15 is information indicating the electronic components included in the electronic circuit 32 and the connection relationships between the electronic components, and is stored in advance in the memory resource 13 by the user. The electronic components are, for example, resistors, capacitors, coils, etc. The circuit information 15 also includes parameters of these electronic components. When the electronic component is a resistor, the parameter is the resistance value. When the electronic component is a capacitor, the parameter is the capacitance value, and when the electronic component is a coil, the parameter is the inductance.

[0027] The input signal information 16 is an input signal S in The information indicates the waveform of the input signal S. in The waveform of the input signal S may be any waveform, but in this example, an impulse waveform is stored in advance in the input signal information 16. The processor 10 inputs the input signal S indicated by the input signal information 16 to a circuit simulator that simulates the electronic circuit 32. in The circuit simulator used in this embodiment is, for example, LTSpice made by Analog Devices.

[0028] The parts list information 17 is information that lists the electronic components included in the electronic circuit 32, and is stored in advance by the user in the memory resource 13. For example, the parts list information 17 is information that associates symbols that uniquely identify electronic components, such as R1 and C1, the types of electronic components, such as resistors and capacitors, the manufacturers of the electronic components, the series of the electronic components, and the initial values ​​of the parameters of the electronic components.

[0029] The nominal waveform 18 is an example of an initial waveform, and is a power supply current I when the electronic components of the electronic circuit 32 are not degraded and the parameters of the electronic components are set to their initial values ​​at the time of shipment from the factory. in When each electronic component deteriorates and its parameters change from the initial value, the power supply current I in The waveform of the signal also changes. Using this, the processor 10 estimates the lifespan of each electronic component, as described below.

[0030] The nominal waveform 18 may be acquired by the processor 10 from the electronic system 3 and stored in the memory resource 13. The processor 10 may also set the parameters of each electronic component in a circuit simulator to initial values ​​and calculate the power supply current I in This waveform may be stored in the memory resource 13 as a nominal waveform 18.

[0031] The deterioration simulation parameter information 19 is information including parameters for simulating deterioration of electronic components. The deterioration simulation parameter information 19 will be described with reference to Figs. 3A and 3B.

[0032] Fig. 3A is an example of a circuit diagram of an electronic circuit 32. Fig. 3B is a schematic diagram showing an example of degradation simulation parameter information 19 corresponding to the electronic circuit 32 of Fig. 3A.

[0033] The electronic circuit 32 of FIG. in The output signal S with high frequency components removed from out A Sallen key type low-pass filter that outputs a power supply current I inThe electronic circuit 32 also has resistors R1 to R5 and capacitors C1 and C2 as electronic components.

[0034] As shown in FIG. 3B, the degradation simulation parameter information 19 is information that associates electronic components with the amount of change in the parameters. Here, the amount of change from the initial value of the parameter is expressed as a percentage. A range is set for the amount of change in the parameter. In this example, the lower limit of the range of the amount of change in each electronic component is "-5%" and the upper limit is "5%". The upper and lower limits may be different for each electronic component. In this example, the amount of change is changed in increments of 1%, but the increment size is not limited to this and may be smaller or larger than 1%.

[0035] The processor 10 generates degradation simulation parameter information 19 based on the parts list information 17, and stores the degradation simulation parameter information 19 in the memory resource 13. For example, the processor 10 determines the amount of change in parameters for each electronic component within a range and increment preset by the user, and generates the degradation simulation parameter information 19.

[0036] 2 again. Simulation waveform 20 is a power supply current I obtained as a simulation result of the circuit simulator when processor 10 sets the amount of change in the parameters of each electronic component in the circuit simulator to the value in degradation simulation parameter information 19. in This is the waveform.

[0037] 4 is a schematic diagram showing an example of the simulation waveform 20 and the above-mentioned nominal waveform 18. In the example of FIG. 4, the processor 10 inputs an input signal S that changes periodically with a period T to an electronic circuit 32 in a circuit simulator. inis supplied, a nominal waveform 18 and a simulation waveform 20 are obtained. The processor 10 calculates the difference between the waveforms 18, 20 as a simulation waveform change 22. The simulation waveform change 22 is time series data in which the difference between the waveforms 18, 20 is associated with time. The simulation waveform change 22 is not limited to this, and may be time series data in which the difference is normalized, such as the absolute value of the difference between the waveforms 18, 20. Furthermore, the frequency components of the waveforms 18, 20 may be extracted by FFT (Fast Fourier Transform) or the like, and the difference between the frequency components of the waveforms 18, 20 may be taken as the simulation waveform change 22.

[0038] Referring again to Fig. 2, the component degradation model 21 is a model such as a neural network that learns the relationship between the amount of change in the parameters of the electronic component and the simulation waveform change 22 by machine learning or the like.

[0039] Fig. 5 is a schematic diagram of an example of part degradation model 21 during learning. As shown in Fig. 5, part degradation model 21 is a model that has learned the relationship between simulation waveform change 22 and parameter change amount so as to output a correct value of the parameter change amount when simulation waveform change 22 is input. The number of input layers of part degradation model 21 is the number of simulation waveform changes used for learning. Also, the number of output layers of part degradation model 21 is the number of electronic components.

[0040] In the example of Fig. 5, the processor 10 performs a circuit simulation by varying only the parameter (capacitance) of the capacitor C1 among the multiple electronic components of the electronic circuit 32 of Fig. 3A by a variation (-5%) selected from the degradation simulation parameter information. The processor 10 uses the variation of the parameter used in the circuit simulation as teacher data, and uses the simulation waveform variation 22 obtained by the circuit simulation as learning data for the component degradation model 21.

[0041] In addition, instead of changing the parameter of only one electronic component in this manner, the processor 10 may change the parameters of multiple electronic components by the amount of change in the deterioration simulation parameter information 19 and use each amount of change as training data.

[0042] Here, an example is shown in which the simulation waveform change 22 in one period T is used as the learning data, but the simulation waveform change 22 over a plurality of periods T may be used as the learning data.

[0043] Furthermore, the processor 10 may use multiple simulation waveform changes 22 for multiple periods T as learning data. The magnitude of the noise components contained in the N simulation waveform changes 22 is N times the magnitude of the noise components contained in one simulation waveform change 22. -1 / 2 Therefore, by using a plurality of simulation waveform changes 22 as learning data, the learning accuracy is improved.

[0044] FIG. 6 is a schematic diagram of an example of a part degradation model 21 when predicting degradation. The input of the part degradation model 21 when predicting degradation is an actual waveform change 23 of the electronic system 3. The actual waveform change 23 is a function of the nominal waveform 18 and the power supply current I in The actual waveform change 23 is not limited to this, and may be time series data in which the difference is normalized, such as the absolute value of the difference between the waveforms. Furthermore, the power supply current I in Alternatively, the frequency components of the waveform and the nominal waveform 18 may be extracted by FFT or the like, and the difference between these frequency components may be taken as the actual waveform change 23.

[0045] When an actual waveform change 23 is input, the component deterioration model 21 outputs, for each electronic component, the amount of change in the parameter estimated from the actual waveform change 23. The input actual waveform change 23 may be for one cycle T, or the actual waveform change 23 over a plurality of cycles T may be input to the component deterioration model 21.

[0046] 2 again. The parameter change information 24 is information indicating the amount of change in the parameter for each electronic component estimated by the component deterioration model 21. For example, the processor 10 inputs the actual waveform change 23 to the component deterioration model 21, and stores in the memory resource 13 as the parameter change information 24 the amount of change in the parameter for each electronic component output by the component deterioration model 21 in response to the input.

[0047] The operating time information 25 is information indicating the cumulative operating time of the electronic circuit 32. For example, in The accumulated time during which the control circuit 33 receives the accumulated time information is the operating time. The accumulated time is monitored by the control circuit 33. The processor 10 obtains the accumulated time information from the control circuit 33 and stores it in the memory resource 13.

[0048] The life prediction model 26 is a model for predicting the remaining life of each electronic component based on the parameter change information 24, and is stored in the memory resource 13 in advance by the user.

[0049] 7A is a schematic diagram showing an example of the life prediction model 26. For example, the life prediction model 26 is information that associates the type, manufacturer, series, and remaining life of an electronic component. The remaining life is calculated by functions f1, f2, f3, ... defined for each electronic component. The arguments of each function f1, f2, f3, ... are the change amount of a parameter such as the resistance change amount ΔR or the capacitance change amount ΔC, and the operating time Tu. Since the length of the remaining life differs depending on the type, manufacturer, and series of the electronic component, the form of each function f1, f2, f3, ... also generally differs.

[0050] The processor 10 identifies a function of remaining life associated with the type, manufacturer, and series of an electronic component by referring to the parts list information 17. The processor 10 then calculates the remaining life TL returned by the function for each electronic component by providing the parameter change amount and the operating time to the function. By calculating the remaining life TL based on the function in this manner, there is no need to perform a complex simulation to calculate the remaining life TL, and the processor 10 can easily calculate the remaining life TL.

[0051] 2 again, the remaining life information 27 is information indicating the remaining life calculated by the processor 10 for each electronic component based on the life prediction model 26.

[0052] Fig. 7B is a schematic diagram showing an example data structure of the remaining life information 27. In this example, each electronic component included in the electronic circuit 32 in Fig. 3A is associated with its remaining life and stored in the remaining life information 27.

[0053] Next, the process performed by the calculator 1 according to this embodiment will be described.

[0054] FIG. 8 is a flowchart showing an example of a process performed by the calculator 1 when generating the part deterioration model 21.

[0055] First, the processor 10 sets the parameters of each electronic component in the circuit simulator to an initial value, and executes a simulation in the circuit simulator (step S1). For example, the processor 10 generates a simulated circuit of the electronic circuit 32 by connecting each electronic component in the circuit simulator according to the circuit information 15. Then, the processor 10 generates a simulated circuit of the electronic circuit 32 by inputting an input signal S indicated by the input signal information 16. in By inputting this to the simulation circuit, the power supply current I in The time variation of is simulated.

[0056] Next, the processor 10 calculates the power supply current I in The time variation of is obtained as a nominal waveform 18 and stored in the memory resource 13 (step S2).

[0057] Next, the processor 10 generates the degradation simulation parameter information 19 and stores it in the memory resource 13 (step S3). For example, the processor 10 determines the amount of change in the parameter for each electronic component present in the parts list information 17 within the range and interval width preset by the user, and stores the amount of change in the degradation simulation parameter information 19.

[0058] Next, the processor 10 judges whether the simulation is completed in a state in which each electronic component of the simulation circuit of the electronic circuit 32 is deteriorated (step S4). For example, the processor 10 judges that the simulation is completed (YES) if the simulation is executed by applying the changes in all parameters in the deterioration simulation parameter information 19, and judges that the simulation is not completed (NO) if not.

[0059] If it is determined that the simulation is not yet completed (NO), the process proceeds to step S5. In step S5, the processor 10 identifies the amount of change that has not yet been applied to the simulation in the degradation simulation parameter information 19, and applies the amount of change to the associated electronic component, thereby executing a simulation of the electronic component in a degraded state. In the simulation, similar to step S1, the processor 10 generates a simulated circuit of the electronic circuit 32 by connecting the electronic components in the circuit simulator according to the circuit information 15. Then, the processor 10 generates the input signal S indicated by the input signal information 16. in By inputting this to the simulation circuit, the power supply current I in The time variation of is simulated.

[0060] Next, the processor 10 calculates the power supply current I obtained by the simulation in step S5. in The time variation of is obtained as a simulation waveform 20 and stored in the memory resource 13 (step S6).

[0061] Next, the processor 10 identifies a waveform change of the simulation waveform 20 from the nominal waveform 18, and stores it in the memory resource 13 as a simulation waveform change 22 (step S7). As an example, the processor 10 identifies the difference between the waveforms 18, 20 as the simulation waveform change 22, and stores it in the memory resource 13. Then, the process returns to step S4.

[0062] In this example, step S7 is executed until the simulation is completed for each of a plurality of amounts of change within the range of the amount of change of the parameter defined by the deterioration simulation parameter information 19. Therefore, the simulation waveform change 22 corresponding to each of the plurality of different amounts of change is obtained, and the learning accuracy of the part deterioration model 21 using the simulation waveform change 22 as learning data can be improved.

[0063] If the answer in step S4 is YES, the process proceeds to step S8. In step S8, the processor 10 generates a part deterioration model 21 by machine learning. The learning data in the machine learning are each simulation waveform change 22. Moreover, the teacher data is the amount of change in the parameters used in the simulation that obtained the simulation waveform change 22.

[0064] In step S5, the input signal S changes with a period T. in may be input to the simulation circuit, and in step S6, a plurality of simulation waveform changes 22 may be obtained for each of a plurality of periods T. By using these simulation waveform changes 22 as learning data, the learning accuracy of the part deterioration model 21 can be improved as described above.

[0065] This completes the basic process for generating the part deterioration model 21. According to the above process, the power supply current I in Instead of using the waveform changes in the actual electronic system 3 as learning data, a simulation waveform change 22 based on a simulation is used as learning data to generate a part deterioration model 21. This eliminates the need to take the time and effort required for acquiring learning data from the actual electronic system 3, and allows the part deterioration model 21 to be generated easily.

[0066] Next, a description will be given of a process for predicting the remaining life of electronic components in the actual electronic circuit 32. First, a description will be given of the process performed by the electronic system 3.

[0067] FIG. 9 is a flowchart showing an example of a process performed by the electronic system 3 when predicting the electronic lifespan of electronic components in the actual electronic circuit 32.

[0068] First, the control circuit 33 starts the power supply circuit 31 in response to a press of a power button (not shown) of the electronic system 3, and supplies a power supply current I in is supplied (step S11).

[0069] Next, the control circuit 33 starts measuring the cumulative operating time of the electronic circuit 32 (step S12).

[0070] Next, the control circuit 33 judges whether it is time to judge whether the electronic components of the electronic circuit 32 have deteriorated (step S13). The timing is, for example, the timing when a power button (not shown) of the electronic system 3 is pressed, or the timing when a predetermined time has elapsed since the power button was pressed. If the judgment here is NO, step S13 is repeated.

[0071] On the other hand, if the answer to step S13 is YES, the process proceeds to step S14. In step S14, the control circuit 33 supplies the electronic circuit 32 with an input signal S in Input signal S in An example of the waveform is an impulse waveform.

[0072] Next, the control circuit 33 receives the input signal S in The power supply current I in The waveform is notified to the processor 10 (step S15).

[0073] Next, the control circuit 33 controls the power supply current I in The electronic system 3 then calculates the cumulative operating time of the electronic circuit 32 at the time when the waveform of the waveform was notified, and notifies the processor 10 of the operating time information 25 indicating the operating time. After that, the process returns to step S13. This completes the basic processing performed by the electronic system 3.

[0074] Next, a description will be given of the processing performed by Calculator 1. Fig. 10 is a flow chart showing an example of the processing performed by Calculator 1 when predicting the electronic life of electronic components in actual electronic circuit 32.

[0075] First, the processor 10 receives a power supply current I in The waveform of is acquired (step S21).

[0076] Next, the processor 10 calculates the power supply current I from the nominal waveform 18. in The processor 10 then identifies the waveform change of the power supply current I in The difference between the waveform and the nominal waveform 18 is identified as the actual waveform change 23.

[0077] Next, the processor 10 estimates the amount of change from the initial value of the parameter for each electronic component of the electronic circuit 32 by inputting the actual waveform change 23 to the component deterioration model 21 (step S23). The processor 10 also generates parameter change information 24 that associates the estimated amount of change with each electronic component, and stores it in the memory resource 13.

[0078] Next, the processor 10 acquires the operating time information 25 from the electronic system 3 (step S24).

[0079] Next, the processor 10 predicts the remaining life of each electronic component of the electronic circuit 32 based on the life prediction model 26 (step S25). As an example, the processor 10 predicts the remaining life TL for each electronic component by providing the parameter change amount indicated by the parameter change information 24 and the operation time indicated by the operation time information 25 as arguments of functions f1, f2, f3, ... of the life prediction model 26. Then, the processor generates remaining life information 27 that associates the predicted remaining life TL with the electronic component, and stores the remaining life information 27 in the memory resource 13.

[0080] Next, the processor 10 presents the predicted remaining life of each electronic component to the user (step S26). For example, the processor 10 presents the remaining life to the user by displaying a GUI that visualizes the remaining life information 27 on the UI device 11. This allows the user to determine that a component with a long remaining life is a reusable electronic component. Furthermore, by setting a price for the electronic component according to its remaining life, the electronic component can be distributed in the recycling market. This completes the basic processing performed by the calculator 1.

[0081] According to the above-described embodiment, the power supply current I in The amount of change from the initial value of the parameter of each electronic component is estimated by inputting actual waveform change 23, which is the difference between the waveform of and nominal waveform 18, into component deterioration model 21, and the remaining life of each electronic component is estimated based on the amount of change. Therefore, there is no need to provide a monitor circuit for estimating the remaining life in each electronic component, and the remaining life can be predicted easily.

[0082] <Other embodiments> 11 is a diagram showing an example of the configuration of an electronic system 3 according to another embodiment. In this example, a power supply circuit 31 of the electronic system 3 includes power supply filters 42 and 44 and a power conversion circuit 43.

[0083] The power supply filter 42 is connected to an external power supply 41 that supplies a power supply current of, for example, 100 V AC, and is a low-pass filter that removes high-frequency noise contained in the power supply current.

[0084] The power conversion circuit 43 is a conversion circuit that converts the power of the external power source 41 into power suitable for the electronic circuit 32 .

[0085] The power supply filter 44 is a low-pass filter that removes high-frequency noise from the power supply current output from the power conversion circuit 43 .

[0086] According to this configuration, the current output from the power supply filter 44 is the power supply current I in The power supply current Iin If this current is further supplied to another filter circuit, the change in frequency characteristic caused by the deterioration of the electronic components will be reduced by the filter circuit. in By doing so, the power supply current I in This makes it possible to predict the remaining life of electronic components with high accuracy.

[0087] Similarly, if the power supply circuit 31 includes a power supply protection circuit, the frequency characteristics of the power supply current will change due to the power supply protection circuit. Therefore, in this case as well, the current output from the power supply protection circuit at the final stage of the power supply circuit 31 will be referred to as the power supply current I in It is preferable to set the above.

[0088] The effects described in this specification are merely examples and are not limiting, and other effects may also be present.

[0089] The present invention is not limited to the above-described embodiments, and various modifications are included. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the components described. In addition, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. In addition, it is possible to add, delete, or replace a part of the configuration of each embodiment with another configuration.

[0090] In addition, each of the above configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them as an integrated circuit, for example. In addition, each of the above configurations, functions, etc. may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as a program, a judgment table, and a file that realizes each function can be placed in a memory, a storage device such as an HDD or SSD, or a recording medium such as an IC (Integrated Circuit) card, an SD (Secure Digital) card, or a DVD (Digital Versatile Disc). In addition, the control lines and information lines are shown as those considered necessary for explanation, and not all control lines and information lines are necessarily shown in the product. In reality, it may be considered that almost all configurations are connected to each other.

[0091] The computer 1 may be realized by having a user (operator) execute some or all of the functions and processes realized by the life prediction program 14.

[0092] There may be cases where the calculator 1 does not have the UI device 11 and instead leaves some of the output processing to the user and some of the input processing from the user to a processor system (called an external processor system) such as a smartphone or tablet terminal outside the system. In such cases, the calculator 1 (or the processor 10, the life prediction program 14) may perform the following to execute the processing described above and other parts of the program.

[0093] *As an alternative to the output to the user using the UI device 11 described above, data required for output to the user is transmitted to an external processor system via the NI device 12. Examples of the data in question include the data to be output itself, and data for generating output data in another processor system, but it may also be a program describing the process of performing user output in the external processor system, or Web data.

[0094] *Instead of receiving an input or operation from a user using the UI device 11 described above, data indicating a user input or operation is received from an external processor system via the NI device 12. From another perspective, the meaning of outputting data to a user may include not only the computer 1 itself outputting the data, but also having another entity other than the computer 1 output the data (using the computer 1 to do so). Also, the meaning of receiving an input or operation from a user may include not only direct output or reception to a user by the UI device 11 of the computer 1, but also indirect reception by the computer 1. [Explanation of symbols]

[0095] 1...computer, 2...network, 3...electronic system, 10...processor, 11...UI device, 12...NI device, 13...memory resource, 14...life prediction program, 15...circuit information, 16...input signal information, 17...parts list information, 18...nominal waveform, 19...deterioration simulation parameter information, 20...simulation waveform, 21...part deterioration model, 22...simulation waveform change, 23...actual waveform change, 24...parameter change information, 25...operation time information, 26...life prediction model, 27...remaining life information, 28...bus, 31...power supply circuit, 32...electronic circuit, 33...control circuit, 41...external power supply, 42...power supply filter, 43...power conversion circuit, 44...power supply filter.

Claims

1. A computer having one or more processors and one or more memory resources, The one or more processors: obtaining a waveform of a power supply current of an electronic system comprising an electronic component; identifying a waveform change indicative of a change in the waveform from an initial waveform of the power supply current when a parameter of the electronic component is at an initial value; estimating the amount of change from the identified waveform change based on a model that has learned a relationship between the amount of change from the initial value of the parameter and the waveform change; predicting a remaining life of the electronic component based on the estimated amount of change; A computer that runs

2. 2. The computer of claim 1, The one or more processors: acquiring a simulation waveform of the power supply current when the parameter is changed by the change amount in a circuit simulator that simulates the electronic system; calculating a simulation waveform change indicative of a change in the simulation waveform from the initial waveform; generating the model by learning the relationship between the amount of change and the simulation waveform change through machine learning; A computer that runs

3. 3. The computer of claim 2, The one or more processors: In the step of acquiring the simulation waveform, a periodically changing input signal is input to the electronic system in the circuit simulator to acquire the simulation waveform; In the step of generating the model, the simulation waveform change for each of a plurality of periods of the input signal is used as learning data to generate the model. calculator.

4. 3. The computer of claim 2, The one or more processors: determining a range of the amount of change of the parameter for each of the electronic components included in the electronic system; In the step of generating the model, the model is generated using each of the plurality of change amounts within the range as training data. calculator.

5. 2. The computer of claim 1, The electronic system comprises: a power supply circuit including either a filter circuit or a power supply protection circuit, and outputting the power supply current; an electronic circuit including the electronic component and driven by the power supply current output from the power supply circuit, The one or more processors acquire a waveform of the power supply current output from the power supply circuit in the step of acquiring the waveform of the power supply current. calculator.

6. 2. The computer of claim 1, The one or more processors: In the step of predicting the remaining life, the remaining life is estimated based on a function that calculates the remaining life from the amount of change. calculator.

7. A lifespan prediction method executed by a computer having one or more processors and one or more memory resources, comprising: obtaining a waveform of a power supply current of an electronic system comprising an electronic component; identifying a waveform change indicative of a change in the waveform from an initial waveform of the power supply current when a parameter of the electronic component is at an initial value; estimating the amount of change from the identified waveform change based on a model that has learned a relationship between the amount of change from the initial value of the parameter and the waveform change; predicting a remaining life of the electronic component based on the estimated amount of change; A life prediction method comprising:

8. The life prediction method according to claim 7, acquiring a simulation waveform of the power supply current when the parameter is changed by the change amount in a circuit simulator that simulates the electronic system; calculating a simulation waveform change indicative of a change in the simulation waveform from the initial waveform; generating the model by learning the relationship between the amount of change and the simulation waveform change through machine learning; The life prediction method further comprises:

9. 9. A life prediction method according to claim 8, comprising: In the step of acquiring the simulation waveform, a periodically changing input signal is input to the electronic system in the circuit simulator to acquire the simulation waveform; In the step of generating the model, the simulation waveform change for each of a plurality of periods of the input signal is used as learning data to generate the model. Life expectancy prediction methods.

10. 9. A life prediction method according to claim 8, comprising: determining a range of the amount of change of the parameter for each of the electronic components included in the electronic system; In the step of generating the model, the model is generated using each of the plurality of change amounts within the range as training data. Life expectancy prediction methods.

11. The life prediction method according to claim 7, The electronic system comprises: a power supply circuit including either a filter circuit or a power supply protection circuit, and outputting the power supply current; an electronic circuit including the electronic component and driven by the power supply current output from the power supply circuit, In the step of acquiring the waveform of the power supply current, a waveform of the power supply current output from the power supply circuit is acquired. Life expectancy prediction methods.

12. The life prediction method according to claim 7, In the step of predicting the remaining life, the remaining life is estimated based on a function that calculates the remaining life from the amount of change. Life expectancy prediction methods.

13. A program for causing a computer to execute the life prediction method according to any one of claims 7 to 12.

Images