Equipment condition evaluation system and equipment condition evaluation method

Abstract

To provide a device state evaluating technique that can evaluate a presence or absence of an abnormality in a device from actual measurement data of an appliance, even if the device includes the appliance which has not experienced the abnormality in the past.SOLUTION: A device state evaluating system 1 comprises: an analysis unit 10 that performs a calculation by reflecting a parameter in an equation formulated based on a physical model; a physical quantity measuring unit 12 that acquires a physical quantity actually measured by each appliance 21 as measurement data; a setting unit 16 that sets reference information for determining a state of the device 20; and a state determining unit 15 that determines the state of the device 20 based on reference information when the measurement data is reflected in the parameter of the physical model and the measurement data is analyzed.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Embodiments of the present invention relate to apparatus state evaluation technology.

Background Art

[0002] Conventionally, there has been a technique for determining the presence or absence of an abnormality or estimating the cause of an electric motor from measurement data detected by a sensor. For example, there is a technique for determining the presence or absence of an abnormality by comparing measurement data with a preset threshold value.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] When setting an appropriate threshold value, data related to past abnormalities is utilized. For example, when determining the presence or absence of abnormal signs or the cause at the time of an abnormality, abnormal data acquired when the abnormality occurs is required. However, since it is difficult to acquire abnormal data for equipment with few abnormal occurrence cases, it is difficult to determine an abnormality from measurement data. For example, for important equipment such as large plants that lead to long-term stoppages or safety-critical equipment such as nuclear power plants, regular disassembly inspections are performed before an abnormality occurs, and repairs or replacements are made. Therefore, the number of abnormal occurrence cases is extremely small. In addition, various abnormal modes may occur for one piece of equipment, and data is required for all such abnormal modes.

[0005] For electric motors, techniques are sometimes used to monitor vibrations and determine signs of abnormality from changes in level and frequency characteristics. However, the determination of whether or not there are signs of abnormality is made by inspectors based on their experience, and the validity of the judgment is questionable. Furthermore, changes in vibration depend on the frequency characteristics of the equipment or the installation conditions of the sensors. Therefore, diagnosis based solely on predetermined data makes it difficult to determine whether or not there is an abnormality or to estimate its cause.

[0006] Embodiments of the present invention have been made in consideration of these circumstances, and even in devices that include equipment that has never experienced any abnormalities in the past, Physical models From the actual measurement data of the equipment Based on the parameters of the device to be acquired The objective is to provide a device condition evaluation technology that can evaluate whether or not there are any abnormalities in the device. [Means for solving the problem]

[0007] The apparatus state evaluation system according to an embodiment of the present invention includes at least No experience of abnormalities A model building unit constructs a physical model that reproduces the operation of a device composed of multiple devices, including a rotating electric machine, and reproduces the state of the devices that occurs in relation to the operation; an analysis unit performs calculations by reflecting parameters in equations formulated based on the physical model; and the actual measurements taken by each of the devices. Present or past A physical quantity measurement unit that acquires physical quantities as actual measurement data, Based on the calculation results of the aforementioned analysis unit A setting unit that sets reference information for determining the state of the device, and a setting unit that reflects the measured data in the parameters of the physical model, In the aforementioned analysis unit When the aforementioned measured data is analyzed The parameters of the device obtained are associated with the parameters of the device. The system includes a state determination unit that determines the state of the device based on the aforementioned reference information. [Effects of the Invention]

[0008] Embodiments of the present invention provide a device condition evaluation technology that enables the evaluation of whether or not a device is abnormal based on actual measurement data of the equipment, even if the device includes equipment that has never experienced any abnormalities in the past. [Brief explanation of the drawing]

[0009] [Figure 1] Block diagram showing the system configuration of the device state evaluation system. [Figure 2] Configuration diagram showing the device state evaluation system connected to the device. [Figure 3] Explanatory diagram showing a mode of converting a physical quantity acquired from a sensor into analysis data. [Figure 4] Explanatory diagram showing the first example of poor coupling installation. [Figure 5] Explanatory diagram showing the second example of poor coupling installation. [Figure 6] Explanatory diagram showing a mode of learning based on parameters, calculation results, and anomaly labels. [Figure 7] Explanatory diagram showing an example of setting an anomaly label. [Figure 8] Graph showing the relationship between fatigue and time. [Figure 9] Graph showing the relationship between stress amplitude and number of fracture repetitions. [Figure 10] Flowchart showing the device state evaluation method. [Figure 11] Explanatory diagram showing a modification example of setting a threshold value.

Mode for Carrying Out the Invention

[0010] Hereinafter, embodiments of the device state evaluation system and the device state evaluation method will be described in detail with reference to the drawings.

[0011] Reference numeral 1 in FIG. 1 is the device state evaluation system of the present embodiment. This device state evaluation system 1 supports the maintenance activities of the device 20 by optimizing the determination of the presence or absence of an abnormality in the predetermined device 20 (FIG. 2), estimation of the cause of the abnormality, and the like. In particular, the device state evaluation system 1 is used to evaluate the state of the device 20 from the measured data for a device 20 that has no abnormal experience in the past. Note that the state of the device 20 includes at least any one of the presence or absence of an abnormality, the presence or absence of an abnormal sign, an abnormal event, a cause of the abnormality, a degree of the abnormality, and a type of the abnormality.

[0012] The device state evaluation system 1 of this embodiment is composed of a computer that has hardware resources such as a CPU, ROM, RAM, and HDD, and information processing by software is realized using the hardware resources by the CPU executing various programs. Further, the device state evaluation method of this embodiment is realized by causing a computer to execute various programs.

[0013] First, the system configuration of the device state evaluation system 1 will be described with reference to the block diagram shown in FIG. 1.

[0014] The device state evaluation system 1 includes a plurality of sensors 2 and an analysis computer 3. The analysis computer 3 includes an input unit 4, an output unit 5, a communication unit 6, a storage unit 7, and a main control unit 8.

[0015] Predetermined information is input to the input unit 4 according to the operation of a user who uses the analysis computer 3. The input unit 4 includes an input device such as a mouse or a keyboard. That is, predetermined information is input to the input unit 4 according to the operation of these input devices.

[0016] The output unit 5 outputs predetermined information. The device state evaluation system 1 of this embodiment includes a device that displays an image such as a display that outputs an analysis result. That is, the output unit 5 controls the image displayed on the display. Note that the display may be separate from or integrated with the computer main body.

[0017] Note that the device state evaluation system 1 of this embodiment may control an image displayed on a display included in another computer connected via a network. In that case, the output unit 5 included in the other computer may control the output of the analysis result of this embodiment.

[0018] In this embodiment, a display is given as an example of a device for displaying images, but other embodiments are also possible. For example, images may be displayed using a head-mounted display or a projector. Furthermore, a printer that prints information on paper may be used instead of a display. In other words, the objects controlled by the output unit 5 may include a head-mounted display, a projector, or a printer.

[0019] The communication unit 6 communicates with other computers via a communication line such as the Internet. In this embodiment, the device status evaluation system 1 and other computers are connected to each other via the Internet, but other configurations are also possible. For example, the device status evaluation system 1 and other computers may be connected to each other via a LAN (Local Area Network), WAN (Wide Area Network), or mobile communication network.

[0020] The memory unit 7 stores various information necessary for evaluating the status of the device 20. This memory unit 7 also includes a predetermined database. This database is a collection of information organized for retrieval or storage, and stored in memory, an HDD, or the cloud.

[0021] The main control unit 8 comprises a model building unit 9, an analysis unit 10, a learning unit 11, a physical quantity measurement unit 12, a measured data processing unit 13, a parameter identification unit 14, a state determination unit 15, a setting unit 16, a remaining life evaluation unit 17, and an inspection estimation unit 18. These are realized by the CPU executing a program stored in memory or on the HDD.

[0022] Furthermore, each component of the analysis computer 3 does not necessarily have to be located on a single computer. For example, one analysis computer 3 may be implemented using multiple computers connected to each other via a network. For example, the learning unit 11 may be located on a computer separate from the analysis computer 3.

[0023] As shown in Figure 2, the device 20 to be diagnosed in this embodiment is exemplified as one installed in a nuclear power plant or the like. The device 20 is composed of multiple pieces of equipment 21. For example, the device 20 is composed of a control panel 21A, an electric motor 21B, a rotating body 21C, and a group of load-side equipment 21D.

[0024] Here, the control panel 21A corresponds to the component (control unit) related to controlling the behavior of the electric motor 21B. For example, the control panel 21A controls the rotational speed or torque of the electric motor 21B.

[0025] Furthermore, the rotating body 21C is a component that transmits the energy output from the electric motor 21B to the load-side equipment group 21D.

[0026] The load-side equipment group 21D corresponds to the components that consume the energy transmitted from the rotating body 21C. The load-side equipment group 21D may consist of, for example, a pump, a fan, gears, etc.

[0027] Here, an electric motor 21B is given as an example of the rotating electric machine in this embodiment. In other words, the device 20 is composed of multiple devices 21, each including at least a rotating electric machine. Note that the rotating electric machine may also be a generator. This embodiment can be applied whether the rotating electric machine is an electric motor 21B or a generator.

[0028] For example, suppose there is a predetermined frequency parameter related to a rotating electric machine. This frequency can be either the frequency of the power output from the rotating electric machine or the frequency of the power supplied to the rotating electric machine. If the rotating electric machine is an electric motor 21B, this frequency will be the frequency of the AC power supplied to the electric motor 21B from an external source. If the rotating electric machine is a generator, this frequency will be the frequency of the AC power output from the generator to the outside.

[0029] Each sensor 2 of the device condition evaluation system 1 is installed on the device 20. The sensor 2 detects at least one of the following physical quantities: vibration, current, voltage, magnetic flux, temperature, pressure, rotational torque, and load. In this way, physical quantities can be obtained by the sensor 2 regardless of the type of equipment 21.

[0030] For example, sensors 2 are provided on the control panel 21A, the electric motor 21B, the rotating body 21C, and the load-side equipment group 21D. Predetermined information acquired by these sensors 2 is input to the analysis computer 3. The sensors 2 may not only be pre-installed on the device 20, but may also be installed each time an inspection is performed. Furthermore, the installation locations of already installed sensors 2 may be changed.

[0031] These sensors 2 detect physical quantities that change according to the state of the device 20. Specific examples of physical quantities include current and voltage in the control panel 21A and motor 21B, temperature of motor 21B, vibration of motor 21B and rotating body 21C, magnetic flux of motor 21B, load, and torque.

[0032] In this embodiment, the model building unit 9 (Figure 1) constructs a physical model that reproduces the operation of the device 20 and the state of the equipment 21 that occurs in relation to the operation. A physical model is a virtual model that can simulate physical quantities related to the device 20. By using a physical model, it is possible to simulate not only the equipment 21 in normal operation but also the equipment 21 in abnormal operation.

[0033] The physical model reproduces the behavior of the device 20 through a combination of parameters. For example, the physical model includes at least one of the following: a dynamic model, a control model, an electrical model, a magnetic model, a thermal model, a fluid model, a material properties model, and a structural model.

[0034] Here, the dynamic model represents the behavior of the dynamic system with respect to at least one of the rotational and translational motions of each component 21, such as the electric motor 21B, the rotating body 21C, and the load-side equipment group 21D. The control model is for a control panel 21A, which acts as a control unit constituting at least one component 21, to control the behavior of the entire apparatus 20. The electrical model represents the behavior of the electrical system of the apparatus 20. The magnetic model represents the behavior of the magnetic system of the apparatus 20. The thermal model represents the thermal behavior of the apparatus 20. The fluid model represents the behavior of at least one of the flow rate and pressure of the fluid flowing through piping connected to a pump constituting at least one component 21. The material properties model represents the material properties of each component 21. The structural model contains information on at least one of the dimensions and shape of each component 21. In this way, the behavior of the apparatus 20 can be precisely reproduced according to various models.

[0035] In other words, the physical model is a model and formulation of the structure or function of the device 20. And a set of equations corresponding to these is formulated.

[0036] Furthermore, the physical model includes an anomaly model that shows abnormalities in each component 21 that make up the device 20. For example, as shown in Figures 4 and 5, consider a coupling as a rotating body 21C. Eccentricity e from the center of rotation caused by improper installation of the coupling. c or the angle d c The effect of this has been formulated as a model. Furthermore, the eccentric e c or the angle d c Parameters are defined that represent the degree of abnormality, such as its size.

[0037] Furthermore, some models may use mathematical models that associate inputs and outputs. This allows for the incorporation and analysis of the functions of equipment for which design information is unavailable. The data required to construct the mathematical model may be actual equipment data, or data obtained in advance through element testing. Alternatively, the results of separate analyses may be used.

[0038] Furthermore, abnormalities in the rotating body 21C include bearing misalignment, fracture of the rotor bar or short-circuit ring of the motor 21B, protrusion of the rotor bar, protrusion of coils in the stator or slots, bending or cracking of the rotating body 21C, missing parts, residual imbalance, short circuit or burnout of the stator windings, power supply voltage imbalance, inverter erroneous waveform, and defects in the rolling bearings (inner ring, outer ring, rolling elements). Parameters are defined for each of these abnormalities.

[0039] The analysis unit 10 (Figure 1) performs calculations by reflecting parameters in equations (a group of equations) formulated based on a physical model. These calculations include structural analysis using methods such as the Finite Element Method (FEM).

[0040] Here, the physical quantity measurement unit 12 (Figure 1) acquires the physical quantities actually measured by each device 21 as measured data. This physical quantity measurement unit 12 acquires the physical quantities detected by the sensor 2 (Figure 1) as time-series data. For example, as shown in Figure 3, the physical quantity measurement unit 12 acquires time-series data from each device 21 that includes physical quantities such as current, magnetic flux, acceleration, angular velocity, torque, displacement, and pressure as measured data.

[0041] In this embodiment, the physical quantity measuring unit 12 is shown as an example of acquiring physical quantities in real time using the sensor 2 while the device 20 is in operation, but other embodiments are also possible. For example, the sensor 2 may be attached to the equipment 21 for periodic inspection to acquire and record physical quantities, and the physical quantity measuring unit 12 may acquire this record at a later date.

[0042] In other words, the physical quantity measuring unit 12 acquires as actual measurement data at least one of the physical quantities detected by each sensor 2 and the physical quantities included in the test data or inspection data obtained when the equipment 21 was previously tested or inspected. In this way, it is possible to determine whether or not there is an abnormality in the device 20 based on at least one of the current physical quantities and past physical quantities.

[0043] Furthermore, the test data or inspection data also includes information indicating whether or not the device 21 has malfunctioned. In other words, the physical quantities in this embodiment include information indicating whether or not the device 21 has malfunctioned in the past. The physical quantities also include information indicating the date, time, location, and condition of any past malfunctions.

[0044] Furthermore, it is preferable for the physical quantity measurement unit 12 to acquire data from multiple types of physical quantities. For example, since vibration is affected by the support structure characteristics of the equipment 21 or the installation conditions of the sensor 2, it is difficult to determine whether the change in physical quantity is due to an abnormality based on vibration data alone. In such cases, a comprehensive judgment can be made based on physical quantities such as electric current in addition to vibration.

[0045] Furthermore, the measurement data processing unit 13 (Figure 1) converts the measurement data acquired by the physical quantity measurement unit 12 into analytical data in a format corresponding to the calculations performed by the analysis unit 10. Here, the calculations performed by the analysis unit 10 include calculations to output the data in the same format as the analytical data output from the measurement data processing unit 13.

[0046] For example, as shown in Figure 3, when the measured data processing unit 13 outputs vibration spectral data, the corresponding calculation result of the analysis unit 10 is similarly subjected to a Fast Fourier Transform (FFT) to output vibration spectral data. Here, the time-series data as measured data is converted into data for analysis. In this way, the measured data is converted into a format optimized for calculation, allowing the analysis unit 10 to perform calculations at high speed.

[0047] The measured data processing unit 13 converts measured data such as vibration, current, voltage, and magnetic flux acquired by the physical quantity measurement unit 12 into spectral data using a Fourier transform. The measured data processing unit 13 also performs filtering as needed. Furthermore, for time-series data such as temperature and pressure, the measured data processing unit 13 performs processing to convert the data into maximum, minimum, average, RMS, overall, etc., as needed. These processes enable the extraction of characteristic features from the measured data and the removal of unwanted noise. It can also process errors and variability arising from measurements. For example, it processes measurement errors or statistical errors of measuring instruments.

[0048] The parameter identification unit 14 (Figure 1) identifies the measured parameters, which are the parameters required when the calculation result of the analysis unit 10 reproduces the measured data, based on the training data (teaching data) learned by the learning unit 11. For example, the parameter identification unit 14 identifies the measured parameters, which are the parameters required when the calculation result of the analysis unit 10 reproduces the measured data, based on a learned model. In this embodiment, analysis data converted from measured data is used. In other words, the parameters are identified based on the training data learned by the learning unit 11 so that the calculation result of the analysis unit 10 reproduces the analysis data. To put it another way, the analysis unit 10 performs analysis using a physical model so that the analysis data derived as a result of the reproduction matches the measured data.

[0049] For example, if the operation of device 20 in an abnormal state is reproduced using a physical model, the parameters at that time of abnormality can be obtained. In this way, the parameters at the time of abnormality can be used to determine whether or not the actual device 20 is abnormal.

[0050] Furthermore, the parameter identification unit 14 infers the optimal combination of parameters that allows the physical model of the device 20 to reproduce the analytical data output from the measured data processing unit 13, and outputs these as measured parameters. At this time, estimation is performed taking into account errors and variability.

[0051] Furthermore, the analysis unit 10 performs calculations reflecting the parameters identified by the parameter identification unit 14. For example, the analysis unit 10 obtains calculation results related to the time changes of the load acting on each of the components 21 that make up the apparatus 20 or the position of the rotating body 21C. It also evaluates the numerical errors that occur in the calculations.

[0052] In this embodiment, the device state evaluation system 1, in the parameter identification unit 14, uses, for example, a trained model generated by a neural network to determine the measured parameters that reproduce the analysis data output from the measured data processing unit 13.

[0053] The parameters of this embodiment include, for example, those relating to the dimensions and shape of the electric motor 21B, the number of coil turns, or the number of slots, in the case of the electric motor 21B. The parameters also include the characteristics of the components, such as electrical resistance. Furthermore, the parameters include the operating conditions of the device 20 or the surrounding environment. These parameters may be obtained based on the specifications of each component 21 constituting the device 20, or they may be obtained through actual testing or simulation.

[0054] The learning unit 11 (Figure 1) learns each parameter corresponding to the calculation results of the analysis unit 10 as training data. For example, the learning unit 11 inputs the parameters corresponding to the calculation results of the analysis unit 10 as training data into the learning model and performs machine learning. The learning unit 11 inputs each parameter and the calculation results corresponding to these parameters as training data into the learning model when calculations corresponding to combinations of multiple parameters have been performed in advance by the analysis unit 10. In this way, the accuracy of learning can be improved.

[0055] For example, if the analysis unit 10 determines that the device 20 is abnormal, the parameters are associated with an abnormality label. The learning unit 11 inputs these parameters as training data into the learning model. Specifically, the analysis unit 10 may perform calculations corresponding to combinations of multiple parameters in advance, and the result may be determined to indicate an abnormality in the device 20. In this case, the learning unit 11 associates each parameter with the abnormality label corresponding to the calculation result for these parameters as training data and performs machine learning. In this way, an abnormality label is set based on the result of determining that the device 20 is abnormal, so the abnormality of the device 20 can be appropriately evaluated.

[0056] As shown in Figure 6, the learning unit 11 generates a learning model by machine learning, using the results pre-calculated in the analysis unit 10 under various parameter conditions as training data. For example, a learning model generated by machine learning using a neural network may be used. Here, the learning unit 11 creates the learning model using the parameters and calculation results used in the analysis unit 10's calculations as training data.

[0057] The device status evaluation system 1 of this embodiment includes a computer equipped with a machine learning algorithm. In other words, it includes a computer equipped with artificial intelligence (AI) that performs machine learning. For example, this device status evaluation system 1 may consist of one computer equipped with a neural network, or it may consist of multiple computers equipped with neural networks.

[0058] Furthermore, the device status evaluation system 1 may include a deep learning unit that extracts a specific pattern from multiple patterns based on deep learning.

[0059] The computer-based analysis in this embodiment can utilize analytical techniques based on artificial intelligence learning. For example, it can use learning models generated by machine learning using neural networks, learning models generated by other machine learning methods, deep learning algorithms, and mathematical algorithms such as regression analysis. Furthermore, forms of machine learning include clustering and deep learning.

[0060] Here, a neural network is a mathematical model that represents the characteristics of brain function through computer simulation. For example, it shows a model in which artificial neurons (nodes) that form a network through synaptic connections change the strength of their synaptic connections through learning and acquire problem-solving abilities. Furthermore, neural networks acquire problem-solving abilities through deep learning.

[0061] For example, a neural network may have multiple layers, each consisting of several units. By pre-training a multi-layer neural network with training data, it is possible to automatically extract features from patterns of changes in the state of a circuit or system. Furthermore, the number of hidden layers, units, learning rate, number of training iterations, and activation function of a multi-layer neural network can be set arbitrarily via the user interface.

[0062] Furthermore, a deep reinforcement learning approach may be used in the neural network, in which a reward function is set for each information item to be learned, and the information item with the highest value is extracted based on the reward function.

[0063] For example, a Convolutional Neural Network (CNN), which has a proven track record in image recognition, is used. In this CNN, the intermediate layers consist of convolutional layers and pooling layers. The convolutional layer obtains a feature map by filtering nearby nodes in the previous layer. The pooling layer further reduces the feature map output from the convolutional layer to create a new feature map. At this time, by obtaining the maximum value of pixels included in the region of interest in the feature map, slight shifts in the position of the feature quantities can be absorbed.

[0064] Convolutional layers extract local features from an image, and pooling layers combine these local features. These processes reduce the image size while preserving the features of the input image. In other words, convolutional neural networks (CNNs) can significantly compress (abstract) the amount of information contained in an image. Then, using the abstracted image stored in the neural network, it can recognize and classify input images.

[0065] Furthermore, there are various machine learning techniques, including autoencoders, LSTM (Long Short-Term Memory), SDF (Signed Distance Function), GAN (Generative Adversarial Network), and RNN (Recurrent Neural Network). These techniques may also be applied to the machine learning in this embodiment.

[0066] The setting unit 16 sets reference information for determining the status of the device 20. The reference information in this embodiment is set based on the calculation results of the analysis unit 10 and includes an abnormality label indicating at least one of the following: whether or not there is an abnormality in the device 20, whether or not there are signs of an abnormality, the event of the abnormality, the cause of the abnormality, the degree of the abnormality, and the type of abnormality.

[0067] For example, the setting unit 16 sets an abnormality label to determine whether or not there is an abnormality in the device 20. By performing machine learning using this abnormality label, the learning model can determine whether or not the calculation result of the analysis unit 10 indicates an abnormal state in the device 20, based on the analysis result corresponding to a combination of multiple parameters.

[0068] The setting unit 16 sets an abnormality label based on the combination of parameters used when the device 20 is determined to be abnormal, and the calculation results of the analysis unit 10. In this way, abnormalities in the device 20 can be appropriately evaluated.

[0069] The criteria for judgment include whether the results of calculations performed by the analysis unit 10 on predetermined parameters satisfy the requirements of the apparatus 20, which is composed of multiple devices 21, such as functional requirements, material properties, and legal restrictions.

[0070] Functional requirements include, for example, rotational speed, torque, flow rate, pressure, drive speed, response, temperature, voltage, and current. Material properties include, for example, fatigue life, thermal cycle life, plastic deformation, and load to fracture. Legal restrictions include, for example, noise levels, chemical emission levels, and temperature.

[0071] The setting unit 16 of this embodiment sets an abnormality label (reference information) based on whether the device 20 meets at least one of the following conditions: required function, material properties, or legal requirements. In this way, when determining whether a device 20 equipped with equipment 21 that has never experienced any abnormalities in the past has an abnormality, it becomes possible to set a rational evaluation criterion rather than a criterion based on the inspector's experience.

[0072] Furthermore, abnormality labels may be set not only for the calculation results of the analysis unit 10, but also for the parameters of the physical model. In this way, abnormalities in the device 20 can be determined from the parameters identified by the parameter identification unit 14.

[0073] Sensing, simulation, parameter identification, and material properties all involve variations and errors. Therefore, anomaly labels are set considering statistical distributions. Furthermore, anomaly labels may be set with a tolerance in the required conditions. This allows for evaluation of the signs of an anomaly immediately before it occurs, enabling repair or replacement of the equipment 21.

[0074] The remaining life evaluation unit 17 (Figure 1) calculates the remaining life of each device 21 based on the calculation results of the analysis unit 10 when the parameters identified by the parameter identification unit 14 from the measured data are reflected in the physical model. In this way, the remaining life can be evaluated for combinations of multiple parameters.

[0075] Furthermore, the remaining life evaluation unit 17 evaluates the remaining life based on the results obtained by the analysis unit 10, which determine at least one of the load, stress, voltage, current, and temperature associated with each piece of equipment 21, when the measured parameters identified by the parameter identification unit 14 are reflected in the physical model. In this way, the remaining life can be evaluated while taking into account the load or stress applied to the piece of equipment 21.

[0076] For example, the remaining life evaluation unit 17 calculates the time changes in load and stress of each component 21 that makes up the device 20, and determines the remaining life from the life evaluation formula and material properties. In this embodiment, it is also possible to determine the remaining life not only from load and stress, but also from the deterioration of insulating material due to the time change of voltage or current, and the deterioration of material due to thermal cycling (time change of temperature).

[0077] As a method for determining the abnormality label, for example, as shown in Figure 7, assume that vibration due to centrifugal force occurs due to misalignment of the bearing of the equipment 21 or unbalance of the rotating body 21C. Here, there is a basic rated life L10 when a radial load P acts on the rolling bearing supporting the rotating body 21C. This radial load P is added to a combination of multiple parameters based on a physical model. The radial load P is then calculated by the analysis unit 10. For example, the basic rated life L10 of the rolling bearing is calculated using the following remaining life evaluation formula.

[0078] L10 = (C / P) p

[0079] Here, C is the basic dynamic load rating, representing the dynamic load capacity of the rolling bearing. For example, it refers to a constant load that gives the basic rated life L10 of 1 million rotations. Also, p is an index that varies depending on the type of rolling bearing. For example, in the case of a ball bearing, p=3. In the case of a roller bearing, p=10 / 3.

[0080] Based on the calculation results of the radial load P, an abnormality label is set for the parameter combination and calculation result that cause the rolling bearing's lifespan to fall below the required operating period. At this time, information regarding the abnormality event and its cause may be associated with the abnormality label. In this case, the abnormality event can be set as an abnormality of the bearing in question. The cause of the abnormality can be set from the parameter combination. This allows for the rapid estimation of the location and cause of an abnormality when it occurs.

[0081] As shown in Figure 7, for example, the cause of an anomaly can be selected based on the relative magnitudes of the parameters. Alternatively, the analysis unit 10 may perform sensitivity analysis or the like in advance to calculate the correlation between the cause of the anomaly and the parameters. In this way, the accuracy of estimating the cause when an anomaly occurs can be improved.

[0082] Furthermore, when the rotating body 21C is connected to the electric motor 21B, the physical quantities acquired by the sensor 2 may be physical quantities other than vibration, such as the winding current and leakage flux of the electric motor 21B, or they may be a combination of several of these. In this way, it becomes possible to set abnormality labels for devices 20 where the vibration-detecting sensor 2 cannot be installed, or for events that cannot be judged by vibration. In addition, appropriate physical quantities or parameters for determining abnormalities may be selected in advance through sensitivity analysis or the like.

[0083] Furthermore, the remaining life evaluation unit 17 may evaluate the remaining life of any device 20 by, for example, using a Minor's rule (modified Minor's rule) determined from material properties for the fluctuating stress obtained by the analysis unit 10. In this case, the stress frequency distribution of the actual operating stress can be determined using methods such as the rainflow method.

[0084] The method for evaluating remaining life using Minor's rule will be explained with reference to the graphs in Figures 8 and 9. Note that the solid line graph G1 in Figure 9 represents the fatigue limit curve (material properties). The dashed line graph G2 in Figure 9 represents the case where the fatigue limit curve is extended using the modified Minor's rule.

[0085] Here, Ni is the number of cycles at which fracture occurs in the SN curve of the material in question due to a cyclic stress σi with a constant stress amplitude. For example, suppose a given object is subjected to k cyclic stresses σi (i=1 to k) with different amplitudes, each repeated ni (i=1 to k) times. In this case, the accumulated fatigue damage D in this object is given by the following equation. Here, the lifespan is defined as when D reaches 1.

[0086]

number

[0087] The stress frequency distribution can be calculated in the analysis unit 10 based on the physical model. Here, if it is determined that the time until fatigue damage D reaches 1 does not meet the required operating period, an abnormality label may be set.

[0088] Furthermore, if the load results calculated by the analysis unit 10 result in material property conditions, such as fracture or plastic deformation, an abnormality label may be set for the physical quantity or parameter at that time.

[0089] Furthermore, in this embodiment, the remaining lifespan is determined not only from load and stress, but also from the deterioration of the insulating material due to changes in voltage or current over time, and the deterioration of the material due to thermal cycling. Based on this determination, an abnormality label may be set.

[0090] Furthermore, an abnormality label may be set based on the functional requirements of the device 20 (Figure 2). For example, suppose a predetermined rotational speed is required for the electric motor 21B in the design. If the calculation result of the analysis unit 10 does not achieve the required rotational speed, an abnormality label may be set for the physical quantity or parameter at that time.

[0091] Furthermore, abnormality labels may be set based on requirements imposed by legal constraints. For example, if an acoustic analysis is performed on the motor 21B and it exceeds the noise level stipulated by law, an abnormality label may be set for the physical quantity or parameter at that time.

[0092] The example described above illustrates how to set an abnormality label when there is no data regarding an abnormality in the device 20. On the other hand, if there is data regarding an abnormality in the device 20, the abnormality label may be set using this data. In other words, if there is data that was previously determined to be abnormal, and this data is reproduced in the calculation results of the analysis unit 10, an abnormality label may be set for the physical quantity and parameter at that time.

[0093] Furthermore, while the above example illustrates a method for setting abnormality labels for the mechanical behavior of device 20, abnormality labels may also be set for other systems. For example, physical quantities that can be set include temperature, current, voltage, magnetic flux (density), sound, flow rate, and pressure. Abnormality labels may also be set for parameters related to these.

[0094] In this embodiment, the state determination unit 15 (Figure 1) determines the state of the device 20 based on reference information when the measured data is reflected in the parameters of the physical model and the measured data is analyzed. For example, when the measured parameters identified by the parameter identification unit 14 are analyzed, the state determination unit 15 determines the state of the device 20 based on a learned model that has been trained using training data to which abnormality labels are associated. In this way, the learned model can be trained to recognize the parameters of the device 20 that have abnormalities. Then, the device 20 can be appropriately evaluated using this trained learned model.

[0095] Furthermore, the setting unit 16 sets an abnormality label based on a comparison between the remaining lifespan calculated by the remaining lifespan evaluation unit 17 and the pre-planned operating period. In this way, it is possible to evaluate whether or not an abnormality will occur in the device 20 during the pre-planned operating period. For example, the presence or absence of an abnormality can be evaluated by comparing the remaining lifespan of each piece of equipment 21 with the planned operating time.

[0096] Furthermore, the status determination unit 15 determines whether or not there is an abnormality in the device 20 by comparing the measured parameters identified by the parameter identification unit 14 with an arbitrarily set tolerance range for the parameters. In this way, the determination process for whether or not there is an abnormality in the device 20 can be easily performed using an arbitrarily set tolerance range for the parameters.

[0097] Furthermore, the status determination unit 15 determines whether or not there is an abnormality in the device 20 by comparing the actual measurement data acquired by the physical quantity measurement unit 12 with an arbitrarily set data tolerance range. In this way, the process of determining whether or not there is an abnormality in the device 20 can be easily performed using an arbitrarily set data tolerance range.

[0098] For example, the state determination unit 15 determines whether there is an abnormality by comparing the actual measurement data acquired by the physical quantity measurement unit 12 with the allowable range for the data. The state determination unit 15 also determines whether there is an abnormality by comparing the analysis data output from the data processing unit with the allowable range.

[0099] The tolerance ranges for parameters and data used for determination in the state determination unit 15 are pre-set. These tolerance ranges may also be arbitrarily set by the user in advance. Furthermore, all of these tolerance ranges may be the same for the device 20, or they may differ for each individual device 20.

[0100] Furthermore, these tolerances may be set based on actual measurement data, specifications regarding the behavior of the device 20, actual test results, simulation results, or a combination of these.

[0101] The state determination unit 15 (Figure 1) identifies the degree and cause of the abnormality when it determines that the device 20 is abnormal. In this way, the degree and cause of the abnormality can be identified based on measured data. Furthermore, the degree of the abnormality can be evaluated from the combination of measured parameters and the magnitude of their values.

[0102] The inspection estimation unit 18 (Figure 1), when the condition determination unit 15 determines that the device 20 is normal, estimates the progression of the abnormality from the combination and magnitude of the measured parameters, and estimates the next inspection location and inspection timing from the remaining lifespan of the equipment 21 calculated by the remaining lifespan evaluation unit 17. In this way, the inspection location and inspection timing can be automatically presented to the user.

[0103] The main control unit 8 controls the output unit 5 to output the evaluation results of the device status evaluation system 1. For example, the main control unit 8 outputs the results derived by the status determination unit 15 and the inspection estimation unit 18.

[0104] Next, the device status evaluation method (process) performed by the device status evaluation system 1 of this embodiment will be explained using the flowchart in Figure 10. Refer to the aforementioned drawings as appropriate. The following steps are at least some of the processes included in the device status evaluation method, and other steps may also be included in the device status evaluation method.

[0105] First, in step S1, the model building unit 9 constructs a physical model that reproduces the operation of a device 20, which is composed of multiple pieces of equipment 21, including at least a rotating electric machine, and reproduces the state of the equipment 21 that occurs in relation to the operation.

[0106] In the next step S2, the analysis unit 10 performs calculations by reflecting the parameters in the equations formulated based on the physical model.

[0107] In the next step, S3, the setting unit 16 sets reference information for determining the state of the device 20. Here, the setting unit 16 sets abnormality labels as reference information and processes the association of the abnormality labels with the respective training data.

[0108] In the next step, S4, the learning unit 11 inputs the anomaly labels set in the setting unit 16, the calculation results of the analysis unit 10, and their corresponding parameters as training data into the learning model. Machine learning is then performed.

[0109] In the next step S5, the physical quantity measurement unit 12 acquires the physical quantities actually measured by each device 21 as actual measurement data.

[0110] In the next step S6, the measured data processing unit 13 converts the measured data acquired by the physical quantity measurement unit 12 into analytical data in a format corresponding to the calculations performed by the analysis unit 10. This analytical data is reflected in the parameters of the physical model, and the analysis unit 10 performs analysis of the measured data.

[0111] In the next step S7, the parameter identification unit 14 identifies the measured parameters, which are the parameters used when the calculation result of the analysis unit 10 reproduces the analysis data (measured data), based on the training data learned by the learning unit 11.

[0112] In the next step S8, the state determination unit 15 determines the state of the device 20 based on a learned model that has been trained using training data to which abnormality labels as reference information are associated. For example, the state determination unit 15 determines whether or not there is an abnormality in the device 20 at the present time based on each measured parameter identified by the parameter identification unit 14. If there is no abnormality (NO in step S8), the process proceeds to step S9. On the other hand, if there is an abnormality (YES in step S8), the process proceeds to step S11.

[0113] In step S9, which proceeds if the result in step S8 is NO, the remaining life evaluation unit 17 calculates the remaining life of each device 21 based on the calculation results of the analysis unit 10, which reflect the parameters identified by the parameter identification unit 14 in the analysis data (measured data).

[0114] In the next step S10, the inspection estimation unit 18 estimates the progression of the abnormality from the combination and magnitude of the measured parameters, and estimates the next inspection location and inspection timing from the remaining life of the equipment 21 calculated by the remaining life evaluation unit 17. The main control unit 8 outputs the evaluation results of the equipment condition evaluation system 1 by controlling the output unit 5. Then the equipment condition evaluation method is completed.

[0115] In step S11, which proceeds if the answer in step S8 is YES, the status determination unit 15 determines that the device 20 is abnormal and identifies the degree and cause of the abnormality. The main control unit 8 controls the output unit 5 to output the evaluation result of the device status evaluation system 1. The device status evaluation method is then terminated.

[0116] Next, a modified example will be described using Figure 11. Referencing the aforementioned drawings as appropriate, components identical to those shown in the previously described embodiments are denoted by the same reference numerals, and redundant descriptions are omitted. The configuration applied in this modified example may also be applied to the previously described embodiments, or it may be combined with the configuration of the previously described embodiments as appropriate.

[0117] The reference information for the modified version includes a predetermined threshold. This threshold is set based on the data tolerance range, which indicates the acceptable range of the measured data. The data tolerance range itself may also be treated as reference information. Furthermore, in the modified version, the state of the device 20 is evaluated without the use of a learning model.

[0118] The modified configuration unit 16 (Figure 1) sets an acceptable threshold for the measured data as a method for determining whether or not there is an abnormality in the device 20. The modified state determination unit 15 (Figure 1) determines the state of the device 20 based on the threshold when the measured data is analyzed. In this way, the evaluation criteria become clear through the setting of the threshold, allowing for an appropriate evaluation of the state of the device 20. Furthermore, even when parameter identification is not possible, it becomes possible to determine the presence or absence of an abnormality by considering all possible abnormal events. For example, if the measured data obtained from sensor 2 is small and the accuracy of parameter identification is poor, the presence or absence of an abnormality can be determined from the measured data.

[0119] Furthermore, when the reference information is within the acceptable range for data, the state determination unit 15 determines the state of the device 20 by comparing the measured data with the acceptable range for data. In this way, the evaluation criteria become clear by setting the acceptable range for data, and the state of the device 20 can be appropriately evaluated.

[0120] Furthermore, the threshold values ​​or data tolerance ranges set in the setting unit 16 may be arbitrarily set by the user in advance. Also, all threshold values ​​or data tolerance ranges may be the same for all devices 20, or they may be different for each individual device 20.

[0121] For example, as shown in Figure 11, the analysis unit 10 (Figure 1) pre-calculates the bearing life for multiple parameters. If the result is shorter than the required operating period, a threshold value indicating the acceptable range of vibration is set for at least one vibration location. In this case, the threshold value for vibration may be applied to the amplitude of the vibration, or to the spectrum for each frequency of the FFT.

[0122] The setting unit 16 calculates thresholds indicating the permissible range of vibration based on various requirements. Then, among the thresholds calculated for the target physical quantity or parameter, the threshold with the smallest permissible range is set as the threshold used to determine signs of abnormality. In this way, even when the parameter cannot be identified, it is possible to determine the presence or absence of an abnormality by considering all possible abnormal events.

[0123] Figure 11 shows an example where vibration is used as measured data, but other measured data may be used, or these measured data may be combined. Furthermore, the measured data may also include, for example, current, voltage, magnetic flux, temperature, etc.

[0124] Although the flowchart of the above-described embodiment illustrates a configuration in which each step is executed in series, the order of each step is not necessarily fixed, and the order of some steps may be reversed. Also, some steps may be executed in parallel with other steps.

[0125] The device status evaluation system 1 of the above-described embodiment comprises a control device with highly integrated processors such as an FPGA (Field Programmable Gate Array), GPU (Graphics Processing Unit), CPU (Central Processing Unit), and dedicated chips; storage devices such as ROM (Read Only Memory) and RAM (Random Access Memory); external storage devices such as HDD (Hard Disk Drive) and SSD (Solid State Drive); a display device such as a display; input devices such as a mouse and keyboard; and a communication interface. This device status evaluation system 1 can be implemented with a hardware configuration using a normal computer.

[0126] The program executed by this device status evaluation system 1 is provided pre-installed in ROM or similar media. Alternatively, this program may be provided as an installable or executable file stored on a computer-readable non-temporary storage medium such as a CD-ROM, CD-R, memory card, DVD, or flexible disk (FD).

[0127] Furthermore, the program executed by this device status evaluation system 1 may be stored on a computer connected to a network such as the Internet and provided for download via the network. Alternatively, this device status evaluation system 1 can be configured by combining separate modules, each independently performing its respective function, which are interconnected via a network or dedicated line.

[0128] According to the embodiments described above, by including a state determination unit 15 that determines the state of the device 20 based on reference information when the measured data is reflected in the parameters of the physical model and the measured data is analyzed, it is possible to evaluate whether or not there is an abnormality in the device 20 from the measured data of the equipment 21, even if the device 20 includes equipment 21 that has never experienced any abnormalities in the past.

[0129] While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be carried out in a variety of other forms, and various omissions, substitutions, modifications, and combinations are possible without departing from the spirit of the invention. These embodiments or their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0130] 1...Device condition evaluation system, 2...Sensor, 3...Analysis computer, 4...Input unit, 5...Output unit, 6...Communication unit, 7...Storage unit, 8...Main control unit, 9...Model construction unit, 10...Analysis unit, 11...Learning unit, 12...Physical quantity measurement unit, 13...Measurement data processing unit, 14...Parameter identification unit, 15...Condition determination unit, 16...Setting unit, 17...Remaining life evaluation unit, 18...Inspection estimation unit, 20...Device, 21...Equipment, 21A...Control panel, 21B...Electric motor, 21C...Rotating body, 21D...Load-side equipment group.

Claims

1. A model building unit constructs a physical model that reproduces the operation of a device consisting of multiple pieces of equipment, including a rotating electric machine that has never experienced any abnormalities, and reproduces the state of the equipment that occurs in relation to the said operation. An analysis unit that performs calculations by reflecting parameters in the equations formulated based on the aforementioned physical model, A physical quantity measuring unit that acquires current or past physical quantities actually measured by each of the aforementioned devices as actual measurement data, A setting unit that sets reference information for determining the state of the device based on the calculation results of the analysis unit, A state determination unit determines the state of the device based on the reference information associated with the device's parameters, which is acquired when the measurement data is analyzed by the analysis unit, and the measurement data is reflected in the parameters of the physical model. Equipped with, Equipment status evaluation system.

2. A learning unit that inputs the calculation results of the analysis unit and the parameters corresponding to the calculation results as training data into a learning model to perform machine learning, A parameter identification unit identifies the measured parameters, which are the parameters when the calculation result of the analysis unit reproduces the measured data, based on the training data of the learning model. Equipped with, The aforementioned reference information includes an abnormality label indicating at least one of the following: whether or not there is an abnormality in the device, whether or not there are signs of an abnormality, the event of the abnormality, the cause of the abnormality, the degree of the abnormality, and the type of abnormality. The state determination unit determines the state of the device when the measured parameters identified by the parameter identification unit are analyzed, using the learning model that has been trained with the training data to which the abnormality labels are associated. The device status evaluation system according to claim 1.

3. The learning unit inputs the parameters and the corresponding calculation results from calculations performed in advance by the analysis unit for multiple combinations of the parameters, as training data into the learning model. The device status evaluation system according to claim 2.

4. The aforementioned reference information includes a predetermined threshold, The state determination unit determines the state of the device based on the threshold when the measured data is analyzed. The device status evaluation system according to claim 1.

5. The aforementioned reference information includes a data tolerance range indicating the tolerance range of the measured data, The state determination unit determines the state of the device by comparing the measured data with the allowable range for the data. The device status evaluation system according to claim 1.

6. The reference information includes a parameter tolerance range indicating the tolerance range of the measured parameter, The state determination unit determines the state of the device by comparing the measured parameter with the allowable range for the parameter. The device status evaluation system according to claim 2.

7. The system includes a remaining life evaluation unit that calculates the remaining life of each of the devices based on the calculation results obtained when the parameters identified by the parameter identification unit are reflected in the physical model. The device status evaluation system according to claim 2.

8. The setting unit sets the abnormality label based on a comparison between the remaining life calculated by the remaining life evaluation unit and a predetermined operating period. The device status evaluation system according to claim 7.

9. The remaining life evaluation unit evaluates the remaining life based on the results obtained by the analysis unit when the measured parameters identified by the parameter identification unit are reflected in the physical model, and at least one of the load, stress, voltage, current, and temperature related to each of the devices is determined. The apparatus state evaluation system according to claim 7 or claim 8.

10. The setting unit sets the reference information based on whether it satisfies at least one of the following conditions: the required function of the device, the material properties, or the legal requirements. The device status evaluation system according to claim 1 or claim 2.

11. The system includes a measurement data processing unit that converts the measurement data acquired by the physical quantity measurement unit into analytical data in a format corresponding to the calculations performed by the analysis unit. The device status evaluation system according to claim 1 or claim 2.

12. The aforementioned physical model, A dynamic model representing the behavior of the dynamic system with respect to at least one of the rotational motion and translational motion of each of the aforementioned devices, A control model for controlling the behavior of the entire apparatus, comprising at least one control unit constituting the device, An electrical model representing the behavior of the electrical system of the aforementioned device, A magnetic model representing the behavior of the magnetic system of the aforementioned device, A thermal model representing the thermal behavior of the aforementioned device, A fluid model representing the behavior of at least one of the flow rate and pressure of a fluid flowing through piping connected to a pump constituting at least one of the devices, A physical property model representing the material properties of each of the aforementioned devices, A structural model having information on at least one of the dimensions and shape of each of the aforementioned devices, Includes at least one of the following: The behavior of the device is reproduced by the combination of the aforementioned parameters. The device status evaluation system according to claim 1 or claim 2.

13. The model building unit constructs a physical model that reproduces the operation of a device consisting of multiple pieces of equipment, including a rotating electric machine that has never experienced any abnormalities, and reproduces the state of the equipment that occurs in relation to said operation. The analysis unit performs calculations by reflecting parameters in the equations formulated based on the physical model, The physical quantity measurement unit acquires current or past physical quantities actually measured by each of the aforementioned instruments as actual measurement data. The setting unit performs the step of setting reference information for determining the state of the device based on the calculation results of the analysis unit, The measured data is reflected in the parameters of the physical model, and the state determination unit determines the state of the device based on the reference information associated with the device's parameters, which is acquired when the analysis unit analyzes the measured data. including, A method for evaluating the condition of the device.

Images