Waveform abnormality determination device and waveform abnormality determination method

Abstract

To highly accurately determine whether there is abnormality in a signal waveform.SOLUTION: A determination device (1) for waveform abnormality comprises: a reference parameter setting unit (12) which performs, for each of a plurality of reference signal waveforms, the process of extracting, for each of a plurality of sections in the time axis direction of the signal waveform, a parameter characterizing the section, and the process of for setting a reference parameter for each section on the basis of the extracted parameter; an evaluation parameter extraction unit (13) which extracts, for each section in the signal waveform to be evaluated, a parameter characterizing the section; and a determination unit (14) which compares the parameter set by the reference parameter setting unit (12) with the parameter extracted by the evaluation parameter extraction unit (13) and thereby determining whether or not there is abnormality in the signal waveform being evaluated.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a waveform abnormality determination device that determines whether or not there is an abnormality in a signal waveform. [Background technology]

[0002] Conventionally, there are known techniques for determining abnormality in a signal waveform. For example, Patent Document 1 discloses a threshold waveform creation device used for determining the normality of a signal waveform. In this threshold waveform creation device, characteristic points are extracted from an observed waveform, and a statistical process is performed on the observed waveform based on the characteristic points to create a threshold waveform. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2015-212635 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology of Patent Document 1, a threshold waveform is created by setting upper and lower limits for the observed waveform, so if the observed waveform changes slightly later than the reference waveform, or if the observed waveform changes slightly earlier than the reference waveform, it may not be possible to determine that the waveform is abnormal.

[0005] An object of one aspect of the present invention is to provide a waveform abnormality determination device that can determine with high accuracy whether or not a signal waveform is abnormal. [Means for solving the problem]

[0006] In order to solve the above problems, a waveform abnormality determination device according to one aspect of the present invention includes a reference parameter setting unit that performs a process for extracting parameters characterizing each of multiple sections in a time axis direction of a signal waveform, for each of multiple reference signal waveforms, and sets reference parameters for each of the sections based on the extracted parameters; an evaluation parameter extraction unit that extracts parameters characterizing each of the sections in a signal waveform to be evaluated; and a determination unit that determines the presence or absence of an abnormality in the signal waveform to be evaluated by comparing the parameters set by the reference parameter setting unit with the parameters extracted by the evaluation parameter extraction unit.

[0007] In order to solve the above problems, a waveform abnormality determination method according to one embodiment of the present invention is a waveform abnormality determination method executed by one or more information processing devices, and includes a reference parameter setting step of performing a process for extracting parameters characterizing each of multiple sections in a time axis direction of a signal waveform for each of multiple reference signal waveforms, and setting reference parameters for each of the sections based on the extracted parameters, an evaluation parameter extraction step of extracting parameters characterizing each of the sections in a signal waveform to be evaluated, and a determination step of determining the presence or absence of an abnormality in the signal waveform to be evaluated by comparing the parameters set in the reference parameter setting step with the parameters extracted in the evaluation parameter extraction step.

[0008] The waveform abnormality judgment device according to each aspect of the present invention may be realized by a computer. In this case, the control program for the waveform abnormality judgment device, which causes a computer to operate as each part (software element) of the waveform abnormality judgment device, and the computer-readable recording medium on which it is recorded, also fall within the scope of the present invention. Effect of the Invention

[0009] According to one aspect of the present invention, the presence or absence of an abnormality in a signal waveform can be determined with high accuracy. [Brief description of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of a main part of a waveform abnormality determination device according to a first embodiment of the present invention. [Diagram 2] 4 is a flowchart showing an example of a waveform anomaly determination method performed by the waveform anomaly determination device. [Diagram 3] 13 is a flowchart showing an example of a process of a reference parameter setting step. [Figure 4] 11A and 11B are diagrams illustrating a method for setting a section for a reference signal waveform by a section setting section. [Diagram 5] 13 is a flowchart showing an example of a process of an evaluation parameter extraction step. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] An embodiment of the present invention will be described in detail below. Fig. 1 is a block diagram showing the configuration of the main parts of a waveform abnormality determination device 1 in this embodiment. The waveform abnormality determination device 1 is an information processing device that determines the presence or absence of an abnormality in a signal waveform output from an external device 100. The external device 100 is a device that outputs a signal waveform having a predetermined period in the time axis direction as an output value. As shown in Fig. 1, the waveform abnormality determination device 1 includes a control unit 10, a storage unit 20, and an output unit 30.

[0012] The control unit 10 controls each unit of the waveform abnormality determination device 1. The control unit 10 includes an analog / digital conversion unit 11, a reference parameter setting unit 12, an evaluation parameter extraction unit 13, and a determination unit 14.

[0013] The analog / digital conversion unit 11 converts an analog signal waveform output from the external device 100 into a digital signal waveform. Specifically, the analog / digital conversion unit 11 converts an analog signal (hereinafter referred to as a first analog signal) that is the source of a reference signal waveform used to set reference parameters in the reference parameter setting unit 12 into a digital signal waveform. The analog / digital conversion unit 11 outputs the digital signal waveform as a reference signal waveform generated by digitally converting the first analog signal to the reference parameter setting unit 12. Note that the reference signal waveform is a signal waveform that is output from the external device 100 and is known to be normal.

[0014] Furthermore, the analog / digital conversion unit 11 converts into a digital signal waveform an analog signal (hereinafter referred to as a second analog signal) that is the source of a signal waveform (hereinafter referred to as an evaluation target signal waveform) that is to be determined for the presence or absence of an abnormality in the evaluation parameter extraction unit 13. The analog / digital conversion unit 11 outputs to the evaluation parameter extraction unit 13 the digital signal waveform that is generated by digitally converting the second analog signal and serves as the evaluation target signal waveform.

[0015] The reference parameter setting unit 12 sets reference parameters used for determining the presence or absence of an abnormality in the evaluation target signal waveform in the determination unit 14. The reference parameter setting unit 12 includes a section setting unit 121, a parameter extraction unit 122, and a parameter setting unit 123.

[0016] The interval setting unit 121 sets a plurality of intervals in the time axis direction for the reference signal waveform output from the analog / digital conversion unit 11. For example, a case is assumed in which the reference signal waveform draws a curve and the signal value changes suddenly from a state in which the signal value increases or decreases. In this case, the interval setting unit 121 calculates the amount of increase or decrease in the signal value (first amount of change) between a sampling point of interest and the next sampling point in the time axis direction. The interval setting unit 121 also calculates the average amount of increase or decrease in the signal value between a plurality of sampling points within a predetermined time before the sampling point of interest (second amount of change). Then, when the first amount of change is greater than the second amount of change by a predetermined value or more, the interval setting unit 121 may set the sampling point of interest as the boundary of the interval.

[0017] As another example, assume that the signal value of the reference signal waveform changes suddenly from a state in which the signal value increases or decreases monotonically. In this case, the section setting unit 121 may set multiple sections for the signal waveform using, as boundaries, sampling points in the reference signal waveform where the difference between the signal value of a sampling point of interest and the signal value of the sampling point immediately preceding it in the time axis direction differs by a predetermined value or more. In the following description, a mode in which the section setting unit 121 sets multiple sections using, as boundaries, sampling points where the difference between the signal value of the sampling point immediately preceding it in the time axis direction differs from the signal value of the sampling point immediately following it in the time axis direction.

[0018] The parameter extraction unit 122 extracts parameters characterizing each of the multiple intervals set by the interval setting unit 121. In the waveform abnormality determination device 1, the start time of the interval is an example of a parameter characterizing the interval. Between, At the end of the section Between, Signals at each sampling point value, and at least one of the slope of the waveform in each section. The parameter extraction unit 122 performs a process of extracting the above parameters for each of the multiple reference signal waveforms. The parameter extraction unit 122 outputs the extracted parameters to the parameter setting unit 123.

[0019] The parameter setting unit 123 sets reference parameters for each section of the signal waveform based on the parameters extracted by the parameter extraction unit 122. The specific processing will be described later. The parameter setting unit 123 outputs the set reference parameters to the storage unit 20, and stores them in the storage unit 20.

[0020] The evaluation parameter extraction unit 13 extracts parameters used to determine the presence or absence of an abnormality in the evaluation target signal waveform. Specifically, the evaluation parameter extraction unit 13 extracts parameters characterizing each of the multiple intervals set by the interval setting unit 121 from the evaluation target signal waveform output from the analog / digital conversion unit 11. The parameters are the parameters extracted by the parameter extraction unit 122, i.e., the parameters at the start of the interval. Between, At the end of the section Between, Signals at each sampling point value, and at least one of the slope of the waveform in each section. Hereinafter, the parameters extracted by the evaluation parameter extraction unit 13 will be referred to as evaluation parameters. The evaluation parameter extraction unit 13 outputs the extracted evaluation parameters to the judgment unit 14.

[0021] The judgment unit 14 judges the presence or absence of an abnormality in the evaluation target signal waveform by comparing the reference parameters stored in the storage unit 20 set by the reference parameter setting unit 12 with the evaluation parameters extracted by the evaluation parameter extraction unit 13. The judgment result judged by the judgment unit 14 is transmitted to the output unit 30 and output to the outside by the output unit 30. The details of the processing by the judgment unit 14 will be described later.

[0022] Next, a method for determining the presence or absence of an abnormality in a signal waveform by the waveform abnormality determination device 1 (waveform abnormality determination method) will be described with reference to Fig. 2. Fig. 2 is a flowchart showing an example of the waveform abnormality determination method by the waveform abnormality determination device 1.

[0023] As shown in FIG. 2, the waveform anomaly determination method in this embodiment includes a reference parameter setting step S1 for determining reference parameters, an evaluation parameter extraction step S2 for extracting evaluation parameters, and a determination step S3 for determining whether or not there is an anomaly in the signal to be evaluated.

[0024] Fig. 3 is a flow chart showing an example of the process of the reference parameter setting step S1. As shown in Fig. 3, in the reference parameter setting step S1, first, the analog / digital converter 11 digitally converts an analog signal that is output from the external device 100 and that is known to be normal, to generate a reference signal waveform (step S11).

[0025] Next, the interval setting unit 121 sets a plurality of intervals for the signal waveform using, as boundaries, sampling points (hereinafter sometimes referred to as change points) in the reference signal waveform where the difference between the signal value of the immediately preceding sampling point in the time axis direction is different from the signal value of the immediately succeeding sampling point in the time axis direction (step S12). Fig. 4 is a diagram showing a method for setting intervals for the reference signal waveform by the interval setting unit 121. As shown in Fig. 4, the sampling points S n-1 and sampling point S n and the sampling point S n and sampling point S n+1 In this case, the interval setting unit 121 sets the sampling point S n is set as one of the boundaries that divide the reference signal waveform. In the example shown in FIG. 4, the sampling point (i.e., the change point) that is the boundary is S n , S n+5 , S n+15 , S n+23 Since there are four sections, the section setting section 121 sets the reference signal waveform to be divided into five sections, 1 to 5.

[0026] In addition, if the number of sections set by the section setting unit 121 is greater than expected due to reasons such as too much noise in the reference signal waveform, the section setting unit 121 may smooth out the reference signal waveform using a moving average and set the sections again, i.e., execute step S12 again.

[0027] Next, for each of the reference signal waveforms, the parameter extraction unit 122 extracts parameters characterizing the corresponding section for each of the sections set by the section setting unit 121 (step S13). Specifically, in the example shown in FIG. 4, the parameter extraction unit 122 extracts parameters characterizing the start and end times of each of sections 1 to 5, the signal duration for each sampling point, value, In addition, when the waveform in each of sections 1 to 5 is regarded as a straight line, at least one of the slopes of the straight line is extracted.

[0028] Next, the parameter setting unit 123 sets a reference parameter for each section in the signal waveform based on the parameter extracted by the parameter extraction unit 122. Here, as an example, a case where a lower limit value of the start time of a section as one of the reference parameters is set will be described. In this case, the parameter setting unit 123 first sets the start time of the section extracted from the first reference signal waveform as the set value of the lower limit value. Next, the parameter setting unit 123 judges whether the start time of the section extracted from the two reference signal waveforms is within the range of the set value set at this time (step S14). Specifically, when setting the lower limit value of the start time of a section as one of the reference parameters, the parameter setting unit 123 judges whether the start time of the section extracted from the second reference signal waveform is the same as or greater than the set value set at this time. If the start time of the section extracted from the second reference signal waveform is smaller than the set value of the lower limit value set at this time (NO in step S14), the set value of the start time is updated (step S15). Then, the process proceeds to step S16. On the other hand, if the start times of the sections extracted from the two reference signal waveforms are greater than or equal to the currently set value (YES in step S14), the process proceeds to step S16.

[0029] Next, as another example, a case where the slope of a straight line is set when the waveform in each section as one of the reference parameters is regarded as a straight line will be described. In this case, the parameter setting unit 123 first sets the smaller of the slopes of the straight lines when the waveforms in each section extracted from the first and second reference signal waveforms are regarded as straight lines as a minimum value, and sets the larger of the slopes as a maximum value. Next, the parameter setting unit 123 judges whether the slope of the straight line extracted from the three reference signal waveforms is within the range between the minimum and maximum set values ​​set at this time (step S14). If the slope of the straight line extracted from the third reference signal waveform is outside the range between the minimum and maximum set values ​​set at this time (NO in step S14), the slope of the straight line is used to update the minimum or maximum set value (step S15). Then, the process proceeds to step S16. On the other hand, if the slope of the straight line extracted from the three reference signal waveforms is within the range between the minimum and maximum set values ​​set at this time (YES in step S14), the process proceeds to step S16.

[0030] In step S16, parameter setting unit 123 determines whether or not the determination in step S14 has been performed for all parameters extracted in step S13. If the determination in step S14 has not been performed for all parameters (NO in step S16), parameter setting unit 123 performs steps S14 to S15 for undetermined parameters.

[0031] On the other hand, when step S14 has been performed for all parameters (YES in step S16), the reference parameter setting unit 12 judges whether or not the number of reference signal waveforms processed has reached a specified number. If the number of reference signal waveforms processed has not reached the specified number (NO in step S17), the processing of steps S11 to S16 is performed for another reference signal waveform. On the other hand, if the number of reference signal waveforms processed has reached the specified number (YES in step S17), the parameter setting unit 123 sets the set value at that time as the reference parameter for each parameter, and stores the set reference parameter in the storage unit 20 (step S18). This ends step S1 shown in FIG. 2.

[0032] Next, the evaluation parameter extraction unit 13 extracts parameters used to determine the presence or absence of an abnormality in the evaluation target signal waveform (evaluation parameter extraction step S2). FIG. 5 is a flowchart showing an example of the processing in the evaluation parameter extraction step S2. As shown in FIG. 5, in the evaluation parameter extraction step S2, first, the analog / digital conversion unit 11 digitally converts an analog signal output from the external device 100 to generate an evaluation target signal waveform (step S21). Next, the evaluation parameter extraction unit 13 sets a plurality of sections for the signal waveform, with change points among the sampling points in the evaluation target signal waveform as boundaries (step S22). Next, the evaluation parameter extraction unit 13 extracts an evaluation parameter for each of the set plurality of sections (step S23).

[0033] Next, the judgment unit 14 judges the presence or absence of an abnormality in the signal waveform to be evaluated by comparing the reference parameters stored in the storage unit 20 with the evaluation parameters extracted by the evaluation parameter extraction unit 13 (judgment step S3). Specifically, the presence or absence of an abnormality in the signal waveform to be evaluated is judged for each section as to whether all evaluation parameters in the signal waveform to be evaluated are the same as the reference parameters or are within the range of the reference parameters. Note that in the waveform abnormality judgment device according to one aspect of the present invention, the presence or absence of an abnormality in the signal waveform to be evaluated may be judged for each section as to whether a predetermined proportion of the evaluation parameters in the signal waveform to be evaluated are the same as the reference parameters or are within the range of the reference parameters.

[0034] For example, when the start time of a section as an evaluation parameter is smaller than the lower limit value or larger than the upper limit value of a reference parameter, the judgment unit 14 judges that the evaluation target signal waveform is abnormal. As another example, when at least one of the slopes of the waveform in each section as an evaluation parameter differs from the slope set as the reference parameter, the judgment unit 14 judges that the evaluation target signal waveform is abnormal.

[0035] In the waveform anomaly determination method described above, all processing is performed by the waveform anomaly determination device 1, but the above processing may be performed by a plurality of information processing devices.

[0036] As described above, the waveform anomaly determination device 1 compares the reference parameters and the evaluation parameters for each section of the signal waveform to be evaluated to determine whether or not there is an anomaly in the signal waveform to be evaluated. Therefore, when the upper and lower limits of the start time of the section and the upper and lower limits of the end time of the section are used as the parameters to be evaluated as in this embodiment, the signal waveform to be evaluated can be determined to be abnormal when the signal waveform to be evaluated changes slightly later than the reference signal waveform or when the signal waveform to be evaluated changes slightly earlier than the reference signal waveform. In other words, the presence or absence of an anomaly in the signal waveform can be determined with high accuracy.

[0037] Here, when determining whether or not there is an abnormality in a signal waveform using the upper and lower limit values ​​of each sampling point, as in Patent Document 1, if the change in the slope of the waveform is small, the abnormality in the signal waveform cannot be detected. In contrast, in this embodiment, the slope of the waveform in each section is used as the parameter to be evaluated. This makes it possible to detect an abnormality in the signal waveform even if the change in the slope of the waveform is small.

[0038] Furthermore, in the waveform abnormality determination device 1, in order to divide the signal waveform into a plurality of sections, a plurality of sections are set using as boundaries sampling points in the reference signal waveform where the difference between the signal value of the sampling point immediately preceding in the time axis direction is different from the difference between the signal value of the sampling point immediately following in the time axis direction. With this configuration, the boundaries of the sections can be relatively easily identified, making it possible to easily set the sections. Note that in the waveform abnormality determination device according to one aspect of the present invention, the signal waveform may be divided into a plurality of sections by a method other than the above.

[0039] In the waveform abnormality determination device 1, when the upper limit and the lower limit of the signal value for each sampling point are set as the reference parameters, the maximum value of each signal value of the reference signal waveform at the same sampling point is set as the upper limit, and the minimum value of each signal value of the reference signal waveform at the same sampling point is set as the lower limit. However, the waveform abnormality determination device of the present invention is not limited to this. In the waveform abnormality determination device of one aspect of the present invention, a value exceeding the maximum value of each signal value of the reference signal waveform at the same sampling point by a predetermined amount may be set as the upper limit, and a value below the minimum value of each signal value of the reference signal waveform at the same sampling point by a predetermined amount may be set as the lower limit. With this configuration, the range in which the evaluation target signal waveform is determined to be normal can be made wider than when the maximum and minimum values ​​of each signal value of the reference signal waveform at the same sampling point are set as the reference parameters. Therefore, when the evaluation target signal waveform changes slightly due to the external environment, the possibility of erroneously determining that a normal evaluation target signal waveform is abnormal due to the influence of the change can be reduced. When the signal value of the signal waveform changes significantly due to the external environment, the predetermined amount may be set to be larger than when there is no external influence. In addition, in the waveform abnormality determination device according to one aspect of the present invention, the predetermined amount in a section where the signal value rises or falls may be set to a value greater than the predetermined amount in a section where the signal value does not change.

[0040] In addition, in the waveform abnormality judgment device 1, when the upper and lower limit values ​​of the start time of a section are set as the reference parameters, the latest start time is set as the upper limit value and the earliest start time is set as the lower limit value for each corresponding section of the reference signal waveform, but the waveform abnormality judgment device of the present invention is not limited to this. In one aspect of the waveform abnormality judgment device of the present invention, the upper limit value may be set to a time a predetermined time later than the latest start time and the lower limit value may be set to a time a predetermined time earlier than the earliest start time for each corresponding section of the reference signal waveform. This makes it possible to reduce the possibility that, when the evaluation target signal waveform changes slightly late or slightly early due to the external environment, a normal evaluation target signal waveform is erroneously judged to be abnormal due to the influence of the change.

[0041] In addition, in the waveform abnormality judgment device 1, when the upper and lower limit values ​​of the end time of a section are set as the reference parameters, the latest end time is set as the upper limit value and the earliest end time is set as the lower limit value for each corresponding section of the reference signal waveform, but the waveform abnormality judgment device of the present invention is not limited to this. In one aspect of the waveform abnormality judgment device of the present invention, the upper limit value may be set to a time that is a predetermined time later than the latest end time for each corresponding section of the reference signal waveform, and the lower limit value may be set to a time that is a predetermined time earlier than the earliest end time for each corresponding section of the reference signal waveform. This makes it possible to reduce the possibility of erroneously judging a normal evaluation target signal waveform as abnormal due to the influence of the change when the evaluation target signal waveform changes slightly earlier or later due to the external environment.

[0042] In addition, in the waveform abnormality determination device according to one aspect of the present invention, when an upper limit value of the signal value for each sampling point is set as a reference parameter, a value obtained by adding a predetermined amount to a reference value (hereinafter referred to as a first reference value) determined within a range in which each signal value of the reference signal waveform at the same sampling point can be taken may be set as the upper limit value. The first reference value may be, for example, an average value of a median value and a maximum value of a signal value of the reference signal waveform at the same sampling point. This allows the upper limit value of the signal value for each sampling point as a reference parameter to be set to an appropriate value without being set as an outlier. Similarly, when a lower limit value of the signal value for each sampling point is set as a reference parameter, a value obtained by subtracting a predetermined amount from a reference value (hereinafter referred to as a second reference value) determined within a range in which each signal value of the reference signal waveform at the same sampling point can be taken may be set as the lower limit. The second reference value is a value smaller than the first reference value, and may be, for example, an average value of a median value and a minimum value of a signal value of the reference signal waveform at the same sampling point. This allows the lower limit value of the signal value for each sampling point as a reference parameter to be set to an appropriate value without being set as an outlier.

[0043] In addition, in the waveform abnormality determination device according to one aspect of the present invention, when an upper limit value of the start time of a section is set as a reference parameter, a time a predetermined time after a first reference time determined within a possible range of the start time of each corresponding section of the reference signal waveform may be set as the upper limit value. The first reference time may be, for example, an average value of a median and a maximum value of the start time of the corresponding section of the reference signal waveform. This allows the upper limit value of the start time of the section as a reference parameter to be set to an appropriate value without being set as an outlier. Similarly, when a lower limit value of the start time of a section may be set as a reference parameter, a time a predetermined time before a second reference time determined within a possible range of the start time of each corresponding section of the reference signal waveform and prior to the first reference time may be set as the lower limit value. The second reference time may be, for example, an average value of a median and a minimum value of the start time of the corresponding section of the reference signal waveform. This allows the lower limit value of the start time of the section as a reference parameter to be set to an appropriate value without being set as an outlier.

[0044] In addition, in the waveform abnormality determination device according to one aspect of the present invention, when an upper limit value of the end time of a section is set as a reference parameter, a time that is a predetermined time after a first reference time that is determined within a possible range of the end time of each corresponding section of the reference signal waveform may be set as the upper limit value. The first reference time may be, for example, an average value of a median and a maximum value of the end time of the corresponding section of the reference signal waveform. This allows the upper limit value of the end time of the section as a reference parameter to be set to an appropriate value without being set as an outlier. Similarly, when a lower limit value of the end time of a section may be set as a reference parameter, a time that is a predetermined time before a second reference time that is before the first reference time and that is determined within a possible range of the end time of each corresponding section of the reference signal waveform. The second reference time may be, for example, an average value of a median and a minimum value of the end time of the corresponding section of the reference signal waveform. This allows the lower limit value of the end time of the section as a reference parameter to be set to an appropriate value without being set as an outlier.

[0045] In addition, in the waveform abnormality determination device of one aspect of the present invention, when the reference parameter is set, the value after performing step S14 a specified number of times is set as the reference parameter, but the waveform abnormality determination device of the present invention is not limited to this. In the waveform abnormality determination device of one aspect of the present invention, the reference parameter may not be set while the degree of variation in the value of the extracted parameter exceeds a predetermined value, and when the degree of variation in the value of the extracted parameter is equal to or less than the predetermined value, a representative value of the extracted parameter may be set as the reference parameter. With the above configuration, the value of the reference parameter can be set to an appropriate value without being set as an outlier. In addition, in the waveform abnormality determination device of one aspect of the present invention, for example, when setting a lower limit value of the start time of a section as one of the reference parameters, if the set minimum value is not updated a predetermined number of times in succession in steps S14 and S15, the minimum value of the start time of the section set at that time may be set as the lower limit value. This can reduce the amount of processing required to set the reference parameter.

[0046] In addition, in the waveform abnormality determination device according to one embodiment of the present invention, the upper and lower limit values ​​of the start time of the section and the upper and lower limit values ​​of the end time of the section are used as the reference parameters, but the waveform abnormality determination device according to the present invention is not limited to this. In the waveform abnormality determination device according to one embodiment of the present invention, a specific time may be set as the reference parameter for the start time and the end time of the section, rather than a range. For example, in a case where it is desired to determine that there is an abnormality in the signal waveform when the start time and the end time of the section (i.e., the occurrence time of the sampling point that is the above-mentioned change point) of the waveform output from the external device 100 deviates even slightly from a predetermined time, it is possible to determine the presence or absence of an abnormality in the waveform signal with high accuracy.

[0047] In addition, in the waveform abnormality determination device of one embodiment of the present invention, the upper and lower limits of the start time of the section, the upper and lower limits of the end time of the section, the upper and lower limits of the signal value for each sampling point, and the slope of the waveform in each section are used as the reference parameters, but the waveform abnormality determination device of the present invention is not limited to this. In the waveform abnormality determination device of one embodiment of the present invention, the number of sampling points (hereinafter referred to as inflection points) in which the difference between the signal value of the immediately preceding sampling point in the time axis direction and the difference between the signal value of the immediately succeeding sampling point in the time axis direction are positive and negative may be added as the reference parameters. In addition, in the waveform abnormality determination device of one embodiment of the present invention, at least one of the start time of the section, the end time of the section, the upper and lower limits of the start time of the section, the upper and lower limits of the end time of the section, the upper and lower limits of the signal value for each sampling point, and the slope of the waveform in each section may be set as the reference parameters in accordance with the characteristics of the signal waveform output from the external device 100. In other words, the user can be allowed to select parameters that the user considers important for determining whether or not there is an abnormality in the signal waveform.

[0048] [Software implementation example] The functions of the waveform abnormality judgment device 1 (hereinafter referred to as the "device") can be realized by a program for causing a computer to function as the device, and a program for causing a computer to function as each control block of the device (particularly each part included in the control unit 10).

[0049] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program to realize each function described in the above embodiment.

[0050] The program may be non-transitory and may be recorded in one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be provided to the device via any wired or wireless transmission medium.

[0051] In addition, some or all of the functions of each of the control blocks can be realized by a logic circuit. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of each of the control blocks can be realized by, for example, a quantum computer.

[0052] Furthermore, each process described in the above embodiment may be executed by AI (Artificial Intelligence). In this case, the AI ​​may be operated by the control device or another device (for example, an edge computer or a cloud server).

[0053] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0054] 1 Waveform abnormality determination device 12 Reference parameter setting section 13 Evaluation parameter extraction unit 14 Judgment section

Claims

1. a reference parameter setting unit that performs a process of extracting parameters that characterize each of a plurality of sections in a time axis direction of a signal waveform for each of a plurality of reference signal waveforms, and sets reference parameters for each of the sections based on the extracted parameters; an evaluation parameter extraction unit that extracts, for each of the sections in an evaluation target signal waveform, a parameter that characterizes the section; a determination unit that determines the presence or absence of an abnormality in the evaluation target signal waveform by comparing the parameters set by the reference parameter setting unit with the parameters extracted by the evaluation parameter extraction unit, the reference parameter setting unit sets at least one of a start time of the section, an end time of the section, upper and lower limit values ​​of a signal value for each sampling point, an upper and lower limit values ​​of a start time of the section, an upper and lower limit values ​​of an end time of the section, and a slope of a waveform within the section as the reference parameter; When the reference parameter setting unit sets an upper limit value and a lower limit value of a start time of the section as the reference parameter, setting, as the upper limit value, a time that is a predetermined time after a first reference time that is determined within a range in which a start time of the corresponding section of each of the reference signal waveforms can take; A waveform abnormality determination device that sets as the lower limit a time that is a predetermined time before a second reference time that is earlier than the first reference time, the second reference time being determined within a possible range of start times of the corresponding sections of the reference signal waveform.

2. A reference parameter setting unit that performs a process of extracting parameters that characterize each of a plurality of sections in a time axis direction of a signal waveform for each of a plurality of reference signal waveforms, and sets reference parameters for each of the sections based on the extracted parameters; an evaluation parameter extraction unit that extracts, for each of the sections in an evaluation target signal waveform, parameters that characterize the section; a determination unit that determines the presence or absence of an abnormality in the evaluation target signal waveform by comparing the parameters set by the reference parameter setting unit with the parameters extracted by the evaluation parameter extraction unit, the reference parameter setting unit sets at least one of a start time of the section, an end time of the section, upper and lower limit values ​​of a signal value for each sampling point, an upper and lower limit values ​​of a start time of the section, an upper and lower limit values ​​of an end time of the section, and a slope of a waveform within the section as the reference parameter; When the reference parameter setting unit sets an upper limit value and a lower limit value of an end time of the section as the reference parameter, setting, as the upper limit value, a time that is a predetermined time after a first reference time that is determined within a range of possible end times of the corresponding sections of each of the reference signal waveforms; A waveform abnormality determination device that sets as the lower limit a time that is a predetermined time before a second reference time that is before the first reference time, the second reference time being determined within a possible range of end times of the corresponding sections of each of the reference signal waveforms.

3. 3. The waveform abnormality determination device according to claim 1, wherein the reference parameter setting unit sets the multiple sections using, as boundaries, sampling points in the reference signal waveform that have a difference between the signal value of a sampling point immediately preceding the sampling point in the time axis direction and a difference between the signal value of a sampling point immediately following the sampling point in the time axis direction.

4. When the reference parameter setting unit sets the upper limit value and the lower limit value of the signal value for each sampling point as the reference parameter, a first reference value, which is determined within a range in which each signal value of the reference signal waveform at the same sampling point can be taken, plus a predetermined amount is set as the upper limit value; 4. The waveform abnormality determination device according to claim 1, wherein the lower limit value is set to a value obtained by subtracting a predetermined amount from a second reference value that is smaller than the first reference value and is determined within a range in which each signal value of the reference signal waveform at the same sampling point can be taken.

5. The reference parameter setting unit The reference parameter is not set while the degree of variation in the extracted parameter value exceeds a predetermined value, 5. The waveform abnormality determination device according to claim 1, wherein when a degree of variation in the extracted parameter values ​​is equal to or less than the predetermined value, a representative value of the extracted parameter values ​​is set as the reference parameter.

6. A waveform anomaly determination method executed by one or more information processing devices, comprising: a reference parameter setting step of performing a process of extracting parameters characterizing each of a plurality of sections in a time axis direction of a signal waveform for each of a plurality of reference signal waveforms, and setting reference parameters for each of the sections based on the extracted parameters; an evaluation parameter extraction step of extracting, for each of the sections in an evaluation target signal waveform, parameters characterizing the section; a determination step of determining the presence or absence of an abnormality in the evaluation target signal waveform by comparing the parameters set in the reference parameter setting step with the parameters extracted in the evaluation parameter extraction step, In the reference parameter setting step, at least one of a start time of the section, an end time of the section, an upper limit value and a lower limit value of a signal value for each sampling point, an upper limit value and a lower limit value of a start time of the section, an upper limit value and a lower limit value of an end time of the section, and a slope of a waveform within the section is set as the reference parameter; In the case where an upper limit value and a lower limit value of a start time of the section are set as the reference parameters in the reference parameter setting step, setting, as the upper limit value, a time that is a predetermined time after a first reference time that is determined within a range in which a start time of the corresponding section of each of the reference signal waveforms can take; A waveform anomaly determination method, comprising: setting as the lower limit a time that is a predetermined time before a second reference time that is earlier than the first reference time and that is determined within a range of possible start times of the corresponding sections of the reference signal waveform.

7. A waveform anomaly determination method executed by one or more information processing devices, comprising: a reference parameter setting step of performing a process of extracting parameters characterizing each of a plurality of sections in a time axis direction of a signal waveform for each of a plurality of reference signal waveforms, and setting reference parameters for each of the sections based on the extracted parameters; an evaluation parameter extraction step of extracting, for each of the sections in an evaluation target signal waveform, parameters characterizing the section; a determination step of determining the presence or absence of an abnormality in the evaluation target signal waveform by comparing the parameters set in the reference parameter setting step with the parameters extracted in the evaluation parameter extraction step, In the reference parameter setting step, at least one of a start time of the section, an end time of the section, an upper limit value and a lower limit value of a signal value for each sampling point, an upper limit value and a lower limit value of a start time of the section, an upper limit value and a lower limit value of an end time of the section, and a slope of a waveform within the section is set as the reference parameter; In the case where an upper limit value and a lower limit value of an end time of the section are set as the reference parameters in the reference parameter setting step, setting, as the upper limit value, a time that is a predetermined time after a first reference time that is determined within a range of possible end times of the corresponding sections of each of the reference signal waveforms; A waveform anomaly determination method, comprising: setting as the lower limit a time that is a predetermined time before a second reference time that is before the first reference time and is determined within a range of possible end times of the corresponding sections of each of the reference signal waveforms.

Images