JP2020149382A - Abnormality detection device, abnormality detection method, and program - Google Patents

Abstract

To easily determine an abnormality of an electronic device.SOLUTION: An abnormality detection device includes a heat generation component, an environment sensor, a first calculation part 30B, and a determination part 30C. The heat generation component is a component which is provided in an electronic device and which is driven by an electric power whereby the heat generation amount changes. The environment sensor detects the environment of the heat generation component. A plurality of environment sensors are arranged at mutually different positions. The first calculation part 30B calculates a first estimated value indicating the heat generation amount of the heat generation component in accordance with respective first detection values of the plurality of environment sensors. When the first estimated value is equal to or greater than a first threshold value, the detection part 30C determines that the heat generation component is abnormal.SELECTED DRAWING: Figure 2

Description

Embodiments of the present invention relate to anomaly detection devices, anomaly detection methods, and programs.

Conventionally, there is known a technique for determining an abnormality such as a cooling abnormality of a heat generating component in an electronic device. For example, there is disclosed a technique for determining a decrease in cooling performance for a heat-generating component by using a usage rate indicating how much the processing time of a heat-generating component such as a processor is occupied.

However, even if the usage rate of heat-generating components such as a processor is the same, the amount of heat generated differs depending on the software. Further, it is not easy in terms of cost to measure and grasp the heat generation state of the heat generating component by measuring the current value and the voltage value of the heat generating component. In addition, it has been difficult to individually measure the current value or the voltage value flowing through each of a plurality of components mounted on an electronic device for each component. Therefore, in the prior art, it has been difficult to easily determine an abnormality in an electronic device.

Japanese Unexamined Patent Publication No. 2014-52689 JP-A-2017-54498 Japanese Unexamined Patent Publication No. 2016-51213

The present invention has been made in view of the above, and an object of the present invention is to provide an abnormality detection device, an abnormality detection method, and a program capable of easily determining an abnormality in an electronic device.

The abnormality detection device of the embodiment includes a heat-generating component that is provided in an electronic device and is driven by electric power to change the amount of heat generated, a plurality of environmental sensors that detect the environment of the heat-generating component, and a plurality of environmental sensors having different arrangement positions. A first calculation unit that calculates a first estimated value indicating the amount of heat generated by the heat-generating component according to the first detected value of each of the environmental sensors, and the first estimated value is equal to or higher than the first threshold value. In the case of, a determination unit for determining that the heat generating component is abnormal is provided.

Schematic diagram of the abnormality detection device. Block diagram of information processing device. The schematic diagram of the calculation of the first estimated value. A flowchart showing the flow of information processing. The figure which shows the relationship between the usage rate and the calorific value. The figure which shows the measurement result of the 1st estimated value and the actual calorific value. Block diagram of information processing device. The schematic diagram of the calculation of the third estimated value. A flowchart showing the flow of information processing. A block diagram showing a hardware configuration example of the control unit.

The details of the present embodiment will be described below with reference to the accompanying drawings.

FIG. 1 is a schematic view showing an example of the abnormality detection device 1.

The abnormality detection device 1 includes an electronic device 10 and an information processing device 20. The electronic device 10 and the information processing device 20 are connected so as to be able to exchange data or signals.

The electronic device 10 is a device including one or more components 14 and driven by the supplied electric power. The electronic device 10 is applied to, for example, various devices in which one or a plurality of electronic components are mounted in one rack. Specifically, the electronic device 10 is applied to various electronic devices such as a digital broadcasting transmitter, a data relay device, a computer, and a server.

The electronic device 10 includes a housing 12 that houses various parts 14 and the like.

The housing 12 is a main body portion of the electronic device 10, and is an exterior that houses various parts and devices. In the present embodiment, the case where the housing 12 is a box-shaped member having a hollow inside will be described as an example.

A part of the housing 12 is provided with an intake port 13A for taking in the air outside the housing 12 into the inside of the housing 12. Further, a part of the housing 12 is provided with an exhaust port 13B for discharging the air inside the housing 12 to the outside of the housing 12.

One or more components 14 and a plurality of sensors 16 are arranged in the housing 12. In the present embodiment, a mode in which a plurality of sensors 16 and a plurality of sensors 16 are arranged in the housing 12 will be described as an example.

The component 14 is at least one of an electronic component and a member having various functions.

The electronic component is, for example, a component 14 that is driven according to the supplied electric power and the amount of heat generated by the drive changes. "Drive" includes both electrical drive and mechanical drive. The electrical drive includes, for example, processing by a processor such as a CPU (Central Processing Unit). Mechanical drive includes, for example, drive of a motor.

The electronic components are, for example, a heat generating component 14A, a blower 14C, and the like.

The heat generating component 14A is provided in the electronic device 10 and is driven according to the supplied electric power to change the amount of heat generated. Specifically, the heat generating component 14A shows a non-linear relationship between the heat generation amount of the heat generating component 14A and the power consumption of the electronic device 10. That is, the heat generating component 14A is a component 14 whose calorific value of the heat generating component 14A cannot be derived from the power consumption of the electronic device 10 by using a linear function.

The heat generating component 14A is, for example, a processor such as a CPU and a GPU (Graphics Processing Unit). The heat-generating component 24 may be a component that generates heat by being driven according to the supplied electric power and the amount of heat generated changes, and is not limited to the CPU and GPU. For example, the heat generating component 14A may be a motor, an electronic circuit, or the like.

In the present embodiment, a mode in which a plurality of heat generating parts 14A (heat generating parts 14A1, heat generating parts 14A2, heat generating parts 14A3) are provided in the housing 12 will be described as an example. The number of heat generating parts 14A provided in the housing 12 is not limited to three, and may be one, two, or four or more.

When the blower 14C is driven according to the supplied electric power, the drive portion (for example, a rotary drive motor or the like) generates heat, and the amount of heat generated changes according to the drive. That is, it can be said that the blower 14C is an example of the heat generating component 14A.

In the present embodiment, the blower 14C is provided at the intake port 13A side end of the housing 12. The blower 14C is arranged at a position where the wind F can be sent from the intake port 13A into the housing 12. A filter 17 is provided on the upstream side of the blower 14C in the direction in which the wind F flows. Therefore, by driving the blower 14C, the air outside the housing 12 is sent into the housing 12 through the filter 17, and the wind F is sent into the housing 12. The heat generated inside the housing 12 is removed by the wind F sent into the housing 12.

The blower 14C may be referred to as, for example, a fan or blower.

The blower 14C may be arranged at a position where the air inside the housing 12 can be discharged to the outside of the housing 12. That is, the blower 14C may be arranged at the end of the housing 12 on the exhaust port 13B side. Further, even if the blower 14C is arranged at both a position where the wind F can be sent into the housing 12 and a position where the air inside the housing 12 can be discharged to the outside of the housing 12. Good.

The member having various functions, which is an example of the component 14, may be a member that is not driven. The member having various functions is, for example, a member having a cooling function. The member having a cooling function is, for example, a member made of a metal material having high thermal conductivity. Specifically, the member having a cooling function is a heat sink 14B, a heat radiating component, and the like.

The heat generating component 14A arranged in the housing 12 is cooled by a member having a cooling function such as a heat sink 14B and the wind F sent by the blower 14C.

In the present embodiment, as shown in FIG. 1, one or a plurality of heat generating components 14A are arranged on the respective substrates 18 of the substrate 18A and the substrate 18B in the housing 12.

The board 18 is an example of an electronic circuit board, and may be referred to as a motherboard or a main board.

In the present embodiment, the heat generating component 14A1 and the heat generating component 14A2 are arranged as the heat generating component 14A on the substrate 18A. Further, the heat sink 14B is arranged on the heat generating component 14A1 or the substrate 18A. The heat sink 14B functions as a heat radiating member that dissipates heat generated by the heat generating component 14A.

Further, a heat generating component 14A3 is arranged on the substrate 18B.

The electronic device 10 may have a configuration in which another substrate 18 is further arranged in the housing 12. Further, the electronic device 10 may be configured to further include a plurality of heat generating parts 14A and other parts 14 in the housing 12.

A plurality of sensors 16 (sensors 16a to 16h) are arranged in the housing 12. These plurality of sensors 16 are arranged at different positions from each other.

The sensor 16 is a sensor capable of measuring a fluctuating physical quantity in the housing 12. For example, the sensor 16 detects physical quantities such as temperature, humidity, pressure, flow rate, acceleration, current, voltage, rotation speed, and outputs the detection result as a detection value. The physical quantity and the detected value are represented by numerical values indicating, for example, temperature, humidity, pressure, flow rate, acceleration, current, voltage, rotation speed, and the like. In the following, the detected value of the sensor 16 may be referred to as a detected value X.

The sensor 16 is, for example, a temperature sensor, a humidity sensor, a pressure sensor, a flow sensor for wind F, a current sensor, a voltage sensor, a rotation speed sensor for detecting the rotation speed of the blower 14C, and an acceleration sensor for detecting the rotation acceleration of the blower 14C. , And so on.

It is assumed that the electronic device 10 is not provided with the sensor 16 capable of detecting the current, voltage, and usage rate (operating rate, load rate) of each of the heat generating components 14A.

The sensor 16 may be arranged at a position in the housing 12 where various physical quantities can be measured.

In the present embodiment, the sensors 16a to 16c and the sensors 16e to 16h will be described on the assumption that they are temperature sensors that detect the temperature. The sensor 16a is arranged at a position where the temperature of the heat generating component 14A1 can be detected. Specifically, the sensor 16a is contact-arranged with the heat generating component 14A1.

The sensor 16b is arranged on the substrate 18A and is arranged at a position where the heat generating component 14A1 and the heat generating component 14A2 are not in contact with each other. The sensor 16g is arranged in contact with the heat generating component 14A2. The sensor 16h is installed on the substrate 18A and is arranged at a position not in contact with the heat generating component 14A1 and the heat generating component 14A2. The sensor 16c, the sensor 16e, and the sensor 16f are arranged in a non-contact manner with respect to the component 14 in the housing 12, and are arranged at different positions from each other.

The sensor 16d is a sensor 16 that detects the rotation speed of the blower 14C. The sensor 16c may be capable of measuring a phenomenon related to driving the blower 14C. Therefore, the sensor 16c may be a sensor that detects a physical quantity such as a physical quantity (current value, voltage value) supplied to the blower 14C.

The information processing device 20 is a device that determines an abnormality in the electronic device 10. The information processing device 20 and each of the plurality of sensors 16 provided in the housing 12 are connected so as to be able to exchange data or signals. The information processing device 20 may be further connected to various electronic devices other than the sensor 16 mounted on the housing 12 so that data or signals can be exchanged. For example, the information processing device 20 may be connected to the sensor 16, at least one of the plurality of components 14, and the blower 14C so as to exchange data or signals.

Next, an example of the functional configuration of the information processing device 20 will be described.

FIG. 2 is a block diagram showing an example of the functional configuration of the information processing device 20. For the sake of explanation, FIG. 2 shows the information processing device 20 and the sensor 16 for exchanging data or signals with the information processing device 20 in the electronic device 10.

The information processing device 20 and the plurality of sensors 16 are connected so as to exchange data or signals. As described above, the information processing device 20 is connected to both the plurality of sensors 16 and various electronic devices other than the sensors 16 mounted on the housing 12 so as to be able to exchange data or signals. You may.

The information processing device 20 includes a control unit 30, a storage unit 32, and an output unit 34. The control unit 30, the storage unit 32, and the output unit 34 are connected so as to exchange data or signals.

The storage unit 32 stores various types of data. The storage unit 32 is, for example, a storage medium such as a known HDD (hard disk drive).

The output unit 34 outputs various information. In this embodiment, the output unit 34 outputs error information. Details of the error information will be described later.

The output unit 34 includes at least one of a display function for displaying various information, a sound output function for outputting sound, and a communication function for communicating data with an external device. The external device is a device provided outside the abnormality detection device 1. The information processing device 20 and the external device may be able to communicate with each other via a network or the like. For example, the output unit 34 is configured by combining at least one of a known display device, a known speaker, and a known communication device.

Next, the control unit 30 will be described.

The control unit 30 includes an acquisition unit 30A, a first calculation unit 30B, a determination unit 30C, and an output control unit 30D.

The acquisition unit 30A, the first calculation unit 30B, the determination unit 30C, and the output control unit 30D are realized by, for example, one or more processors. For example, each of the above parts may be realized by causing a processor such as a CPU to execute a program, that is, by software. Each of the above parts may be realized by a processor such as a dedicated IC, that is, hardware. Each of the above parts may be realized by using software and hardware in combination. When a plurality of processors are used, each processor may realize one of each part, or may realize two or more of each part.

The acquisition unit 30A acquires the detection value X of the sensor 16. In the present embodiment, the acquisition unit 30A acquires the first detection value Xa of the environment sensor 16A as the detection value X of the sensor 16.

Here, in the present embodiment, the information processing device 20 determines an abnormality of the specific heat generating component 14A provided in the electronic device 10. The heat generating component 14A to be determined for abnormality may be determined in advance. Further, the heat generating component 14A to be determined for abnormality may be changed by inputting an instruction by the user or the like.

In the present embodiment, a mode for determining an abnormality of the heat generating component 14A1 among the plurality of heat generating components 14A will be described as an example. Further, a case where the heat generating component 14A1 is a processor such as a CPU or GPU will be described as an example.

At the time of abnormality determination of the heat generating component 14A1 by the control unit 30, the acquisition unit 30A uses a plurality of sensors 16 for detecting the environment of the heat generating component 14A1 to be abnormally determined among the plurality of sensors 16 provided in the electronic device 10. Used as sensor 16A.

The environment sensor 16A is at least a part of the plurality of sensors 16 provided in the electronic device 10, and is arranged at different positions in the housing 12.

The environment sensor 16A is a sensor that detects the environment of the heat generating component 14A1. The "environment" detected by the environment sensor 16A does not include the current value of the heat generating component 14A1 to be determined for abnormality, the voltage value of the heat generating component 14A1, and the usage rate of the heat generating component 14A1. That is, the environment sensor 16A is a sensor that detects an environment other than the current value of the heat generating component 14A1, the voltage value of the heat generating component 14A1, and the usage rate of the heat generating component 14A1.

Specifically, the environmental sensor 16A is a sensor 16 that detects the temperature of the heat generating component 14A1 to be determined for abnormality. That is, the environment sensor 16A is a temperature sensor. The environmental sensor 16A may be arranged at a position where the detected temperature changes according to the fluctuation of the heat generation amount of the heat generating component 14A1. Therefore, the environmental sensor 16A may be in contact with the heat generating component 14A1 to be determined for abnormality, or may be non-contact.

In the configuration shown in FIG. 1, when the abnormality determination target is the heat generating component 14A1, the environmental sensor 16A for detecting the temperature of the heat generating component 14A1 is, for example, a sensor 16a, a sensor 16b, a sensor 16c, a sensor 16g, and a sensor 16h. is there.

The "environment" detected by the environment sensor 16A may include an environment that directly or indirectly affects the environment of the heat generating component 14A1 to be determined for abnormality. Specifically, the environmental sensor 16A may include a sensor 16 that detects a fluctuating physical quantity of a component 14 other than the heat generating component 14A1 to be determined for abnormality. As described above, the physical quantity includes temperature, humidity, pressure, flow rate, acceleration, current, voltage, rotation speed, and the like.

That is, the environment sensor 16A is a sensor 16 that can detect the fluctuating physical quantity of the component 14 other than the heat generating component 14A1 to be determined for abnormality, which is arranged in the housing 12, and is the heat generating component 14A1 to be determined for abnormality. A sensor 16 capable of detecting the physical quantity that may affect the detection result of the calorific value may be included.

In this case, the environment sensor 16A may include, for example, a sensor 16d that detects the rotation speed or the electric energy of the blower 14C.

That is, the environment sensor 16A is the first of at least one of the fluctuating physical quantity of the component 14 other than the heat generating component 14A1 to be determined for abnormality and the temperature of the heat generating component 14A1 to be determined for abnormality, which are arranged in the housing 12. The detected value Xa of is detected.

In the present embodiment, a case where the heat generating component 14A1 is an abnormality determination target and the environmental sensors 16A for detecting the environment of the heat generating component 14A1 are the sensors 16a to 16d, the sensor 16g, and the sensor 16h will be described as an example. To do.

Therefore, in the present embodiment, the acquisition unit 30A receives from each of the sensor 16a to 16d, the sensor 16g, and the sensor 16h, which are the environmental sensors 16A, among the detection values X received from each of the plurality of sensors 16. The detected value X is acquired as the first detected value Xa.

The first calculation unit 30B calculates a first estimated value Ia indicating the amount of heat generated by the heat generating component 14A1 to be determined for abnormality according to the first detected value Xa of each of the plurality of environmental sensors 16A.

FIG. 3 is a schematic diagram of the calculation of the first estimated value Ia. As shown in FIG. 3, the first calculation unit 30B uses a plurality of first detection values Xa (first detection values Xa to first detection value Xn) to indicate the amount of heat generated by the heat generating component 14A1. The first estimated value Ia is calculated.

The first estimated value Ia is an estimated value of the amount of heat generated by the heat generating component 14A1. The amount of heat generated is the amount of energy per unit (the amount of heat generated) and is expressed in units such as W and W / kg. Since the calorific value may be a dimensionless quantity or a value representing a qualitative change from the standard, it may be expressed without a unit.

The first calculation unit 30B derives in advance the correlation between the plurality of first detected values Xa and the first estimated value Ia indicating the amount of heat generated by the heat generating component 14A1. The correlation between the plurality of first detected values Xa and the first estimated value Ia is expressed by, for example, the following equation (1).

Ia = p0 + p1 · Xa1 + p2 · Xa2 + ... + pn · Xan equation (1)

In the formula (1), Xa represents the first detected value Xa. The numerical values (1 to n) adjacent to each of Xa are identifiers of the environmental sensor 16A. p0 to pn indicate a coefficient. Ia indicates a first estimated value Ia of the amount of heat generated by the heat generating component 14A1 to be determined for abnormality.

The first calculation unit 30B determines the correlation between the plurality of first detected values Xa and the first estimated value Ia for each of the components 14 (heat generating components 14A1 in the present embodiment) to be determined for abnormality. It may be derived in advance. Specifically, for example, the first calculation unit 30B may derive in advance the values of the counts p0 to Pn of the above formula (1) for each component 14 to be determined for abnormality. This correlation may be derived by experiment, simulation, machine learning, or the like. For machine learning, known machine learning methods such as a convolutional neural network (CNN), hierarchical Bayes modeling, DNN (Deep Natural Network), and data assimilation technology such as a particle filter may be used.

Equation (1) is given as an example of a function showing a correlation for calculating the first estimated value Ia of the heat generating component 14A1 to be determined for abnormality. However, the correlation equation for calculating the first estimated value Ia may be either a one-dimensional polynomial or a multidimensional polynomial. Further, the correlation equation for calculating the first estimated value Ia may be an equation with strong non-linearity.

Then, the first calculation unit 30B substitutes each of the plurality of first detection values Xa into the function indicating the correlation derived in advance (for example, the above equation (1)), thereby generating heat as an abnormality determination target. The first estimated value Ia indicating the calorific value of the component 14A1 may be calculated.

It is preferable that the first calculation unit 30B calculates the first estimated value Ia according to three or more first detected values Xa. That is, in the case of the equation (1), it is preferable to calculate the first estimated value Ia by using the above equation (1) including a term for substituting at least three or more first detected values Xa.

The determination unit 30C determines whether or not the first estimated value Ia, which is calculated by the first calculation unit 30B and indicates the amount of heat generated by the heat generating component 14A1 to be determined for abnormality, is equal to or greater than the first threshold value. The first threshold value may be a threshold value for determining that the heat generating component 14A1 to be abnormally determined is abnormal. The determination unit 30C may set a first threshold value in advance for each heat generating component 14A (component 14) to be determined for abnormality. The first threshold value may be appropriately changed according to a change instruction by the user or the like.

For example, the determination unit 30C may preset a threshold value of the amount of heat generated for determining the abnormality of the cooling function of the electronic device 10 with respect to the heat generating component 14A1 as the first threshold value.

When the determination unit 30C determines that the first estimated value Ia is equal to or greater than the first threshold value, the determination unit 30C determines that the heat generating component 14A1 is abnormal. The fact that the heat-generating component 14A1 is abnormal means at least one of a heat-generating abnormality of the heat-generating component 14A1 itself and an abnormality of at least a part of the cooling function of the heat-generating component 14A1.

The output control unit 30D outputs error information to the output unit 34.

The error information includes information indicating that an abnormality has occurred in the amount of heat generated by the heat generating component 14A1 to be determined for abnormality, which is determined by the determination unit 30C. The error information may further include maintenance information indicating the maintenance work procedure of the heat generating component 14A1 to be determined for abnormality, precaution items during maintenance work, contact information for maintenance work service, and the like. In this case, the heat generating component 14A1 to be determined for abnormality and the maintenance information may be stored in the storage unit 32 in advance in association with each other. Then, the output control unit 30D may output the error information including the maintenance information to the output unit 34 by reading the maintenance information corresponding to the heat generating component 14A1 to be determined as abnormal.

The output unit 34 outputs error information. When the output unit 34 has a display function, the output unit 34 displays error information. When the output unit 34 has a sound output function, the output unit 34 displays a sound indicating error information.

Therefore, error information can be easily provided to the user. By checking the output error information, the user can grasp the abnormality of the heat generating component 14A1 to be determined for abnormality indicated in the error information, and maintain the electronic device 10 according to the maintenance information indicated in the error information. You can work. That is, the information processing device 20 can appropriately provide the user with information necessary for the maintenance work of the electronic device 10.

In addition, by performing maintenance work based on error information, it is possible to reduce the frequency of occurrence of abnormalities in the electronic device 10, and reduce labor costs for maintenance workers and replacement costs for unnecessary parts 14. be able to.

On the other hand, when the output unit 34 has a communication function, the output unit 34 transmits error information to an external device via a network or the like.

The external device that has received the error information uses the error information to remotely monitor the electronic device 10 that is the source of the error information, process the error information, analyze the error information, and use the error information as another external device. Various processes such as transfer to may be executed. For example, the external device can analyze the usage environment and usage method of the electronic device 10 by analyzing the installation environment of the electronic device 10 and the error information in combination. Therefore, the information processing apparatus 20 can provide information that can be used for improving the design criteria of the electronic device 10 by outputting the error information. In addition, the information processing device 20 can provide information that can be used for improving the usage environment of the electronic device 10 and optimizing the usage method.

Further, the external device to which the error information is transmitted or another device to which the error information is transferred from the external device may be a server device of a service provider in charge of maintenance work. In this case, the information processing device 20 can improve the efficiency of maintenance work.

Next, the flow of information processing executed by the information processing apparatus 20 will be described.

FIG. 4 is a flowchart showing an example of the flow of information processing executed by the information processing apparatus 20. The order of each of the plurality of steps can be changed as appropriate, and is not limited to the example of FIG. In addition, at least a part of the plurality of steps may be executed in parallel.

In FIG. 4, the heat generating component 14A to be determined for abnormality will be described as being predetermined.

First, the acquisition unit 30A acquires the first detection value Xa from each of the plurality of environment sensors 16A that detect the environment of the heat generating component 14A1 to be determined for abnormality (step S100).

The first calculation unit 30B calculates a first estimated value Ia indicating the amount of heat generated by the heat generating component 14A1 to be determined for abnormality according to the plurality of first detected values Xa acquired in step S100 (step S102). ..

The determination unit 30C determines whether or not the first estimated value Ia, which indicates the amount of heat generated by the heat generating component 14A1, calculated in step S102, is equal to or greater than the first threshold value (step S104). When it is determined that the first estimated value Ia is less than the first threshold value (step S104: No), this routine ends. On the other hand, if it is determined that the first estimated value Ia is equal to or higher than the first threshold value (step S104: Yes), the process proceeds to step S106.

In step S106, the output control unit 30D outputs error information to the output unit 34 (step S106). The output control unit 30D outputs error information including information indicating that an abnormality has occurred in the heat generation amount of the heat generation component 14A1 to be determined as an abnormality to the output unit 34. Then, this routine is terminated.

As described above, the abnormality detection device 1 of the present embodiment includes a heat generating component 14A, an environment sensor 16A, a first calculation unit 30B, and a determination unit 30C. The heat generating component 14A is a component 14 provided in the electronic device 10 and driven by electric power to change the amount of heat generated. The environment sensor 16A detects the environment of the heat generating component 14A. The plurality of environmental sensors 16A are arranged at different positions from each other. The first calculation unit 30B calculates a first estimated value Ia indicating the amount of heat generated by the heat generating component 14A according to the first detected value Xa of each of the plurality of environmental sensors 16A. When the first estimated value Ia is equal to or greater than the first threshold value, the determination unit 30C determines that the heat generating component 14A is abnormal.

Here, the amount of heat generated by the heat generating component 14A such as the processor changes with time. Conventionally, even if the usage rate of the heat generating component 14A such as a processor is the same value, the amount of heat generated differs depending on the software. That is, the correlation between the usage rate and the calorific value is not strong.

FIG. 5 is a diagram showing the relationship between the usage rate of a CPU, which is an example of the heat generating component 14A, and the amount of heat generated by the CPU. FIG. 5 shows the result of experimentally investigating the relationship between the usage rate and the amount of heat generated by the heat generating component 14A1 which is a CPU. Multiple types of software were used in the experiment. The calorific value was measured using a dedicated sensor. As shown in FIG. 5, it can be seen that the derived heat generation amount varies even if the CPU usage rate has substantially the same value. Therefore, the amount of heat generated from the usage rate of the heat generating component 14A by the processor varies.

Further, it is not easy in terms of cost to measure and grasp the heat generation state of the heat generation component 14A by measuring the current value and the voltage value of the heat generation component 14A.

The power consumption, current value, and supply voltage of the entire electronic device 10 provided with the heat generating component 14A can be measured by the sensor 16 that detects the current or voltage. However, it has been difficult to individually measure the current value or the voltage value flowing through each of the plurality of components 14 mounted on the electronic device 10 for each component 14.

Further, in the electronic device 10 equipped with a plurality of heat generating components 14A whose calorific value changes with time, it is difficult to derive the calorific value of each of the plurality of heat generating components 14A from the power consumption of the electronic device 10. This is because, while the unknown number is 2 or more, only one function for deriving the calorific value of each of the plurality of heat generating components 14A can be established.

Therefore, conventionally, it has been difficult to easily determine an abnormality in the electronic device 10.

On the other hand, in the abnormality detection device 1 of the present embodiment, the first one showing the heat generation amount of the heat generation component 14A estimated according to the plurality of first detection values Xa of the environment sensor 16A that detects the environment of the heat generation component 14A. The estimated value Ia is used to determine whether or not the heat generating component 14A is abnormal.

As described above, in the abnormality detection device 1 of the present embodiment, the abnormality of the heat generating component 14A is determined by using only the first detection value Xa that can be acquired while the electronic device 10 is being driven. Therefore, in the abnormality detection device 1 of the present embodiment, the heat generating component 14A does not suspend the driving of the electronic device 10 or impose a load that hinders the processing by the program being executed by the electronic device 10. Abnormality can be determined.

Therefore, the abnormality detection device 1 of the present embodiment can easily determine the abnormality of the electronic device 10.

Further, the heat generating component 14A is, for example, a processor such as a CPU or GPU. Therefore, in addition to the above effects, the abnormality detection device 1 of the present embodiment can easily determine an abnormality of the heat generating component 14A which is a processor such as a CPU or GPU.

FIG. 6 shows the measurement results of the first estimated value Ia indicating the heat generation amount of the CPU, which is an example of the heat generation component 14A1, derived by the information processing device 20 of the present embodiment, and the actual heat generation amount of the CPU. It is a figure which shows. As shown in FIG. 6, the first estimated value Ia and the calorific value showed a linear relationship.

Therefore, the abnormality detection device 1 of the present embodiment can easily estimate the heat generation amount of the heat generating component 14A1 by using the first detection value Xa used for estimating the first estimated value Ia, and can accurately estimate the heat generation amount. It can be said that the abnormality of the heat generating component 14A1 can be determined.

(Second Embodiment)
In the present embodiment, a mode of determining an abnormality in a specific region in the housing 12 will be described using the first estimated value Ia and other estimated values. The specific area will be described later.

FIG. 7 is a block diagram showing an example of the functional configuration of the information processing device 21 of the present embodiment. As shown in FIG. 1, the abnormality detection device 1A of the present embodiment is different from the abnormality detection device 1 of the first embodiment except that the information processing device 21 is provided instead of the information processing device 20. The same is true.

The information processing device 21 and the plurality of sensors 16 are connected so as to exchange data or signals. As in the above embodiment, the information processing device 21 can exchange data or signals with both the plurality of sensors 16 and various electronic devices other than the sensors 16 mounted on the housing 12. It may be connected.

The information processing device 21 includes a control unit 31, a storage unit 32, and an output unit 34. The control unit 31, the storage unit 32, and the output unit 34 are connected so as to be able to exchange data or signals. The storage unit 32 and the output unit 34 are the same as those in the first embodiment.

The control unit 31 includes an acquisition unit 30A, a first calculation unit 30B, a second calculation unit 31E, a third calculation unit 31F, a determination unit 31C, and an output control unit 31D. The acquisition unit 30A and the first calculation unit 30B are the same as those in the first embodiment.

The acquisition unit 30A, the first calculation unit 30B, the second calculation unit 31E, the third calculation unit 31F, the determination unit 31C, and the output control unit 31D are realized by, for example, one or more processors. For example, each of the above parts may be realized by causing a processor such as a CPU to execute a program, that is, by software. Each of the above parts may be realized by a processor such as a dedicated IC, that is, hardware. Each of the above parts may be realized by using software and hardware in combination. When a plurality of processors are used, each processor may realize one of each part, or may realize two or more of each part.

The acquisition unit 30A acquires a plurality of first detected values Xa as in the first embodiment. The first detected value Xa is the same as that of the first embodiment. The first calculation unit 30B calculates the first estimated value Ia from the plurality of first detected values Xa.

FIG. 8 is a schematic diagram of the calculation of the second estimated value Ic. The second estimated value Ic will be described later. As shown in FIG. 8, the first calculation unit 30B calculates a first estimated value Ia indicating the amount of heat generated by the heat generating component 14A to be determined for abnormality according to the plurality of first detected values Xa. The first calculation unit 30B calculates the first estimated value Ia in the same manner as in the first embodiment.

In the present embodiment, among the plurality of heat-generating components 14A mounted on the electronic device 10, the first estimated value of the heat-generating amount of the heat-generating component 14A, which is a factor affecting an abnormality in a specific region of the electronic device 10. Calculate Ia. In the present embodiment, the case where the abnormality in the specific region is the abnormality in the temperature in the specific region will be described as an example. However, the abnormality in a specific region is not limited to the temperature abnormality. For example, the abnormality in a specific region may be an abnormality such as humidity or pressure.

That is, in the present embodiment, the heat generating component 14A to be determined for abnormality is the heat generating component 14A which is a factor affecting the temperature abnormality in the specific region of the electronic device 10.

As the specific area of the electronic device 10, a specific area in the housing 12 may be defined in advance. However, it is preferable that the specific region is an region in the housing 12 of the electronic device 10 that cannot be directly measured by the sensor 16. That is, it is preferable that the specific area is an area in the housing 12 where the sensor 16 is not installed.

The information indicating the heat-generating component 14A, which is a factor that affects the abnormality in the specific area, may be stored in the storage unit 32 in advance for each identification information in the specific area. Then, at the time of calculating the first estimated value Ia, the first calculation unit 30B may read the information indicating the heat generating component 14A corresponding to the identification information of the specific region of the abnormality determination target from the storage unit 32. Then, the first calculation unit 30B may calculate the first estimated value Ia of the read heat generating component 14A by using the first detected value Xa.

Further, in the present embodiment, the case where the number of heat generating parts 14A to be determined for abnormality is a plurality is described. Therefore, the first calculation unit 30B calculates the first estimated value Ia of the calorific value of each of the plurality of heat generating parts 14A arranged at different positions by using the plurality of first detected values Xa. To do. That is, the first calculation unit 30B calculates a plurality of first estimated values Ia from the plurality of first detected values Xa. It is assumed that the number of the first detected value Xa and the number of the first estimated value Ia are the same number. This is because we need as many functions as there are unknowns.

In the first calculation unit 30B, the first estimated value Ia (first estimated value Ia1 to 1) of the calorific value of each of the plurality of first detected values Xa and the plurality of heat generating parts 14A to be abnormally determined is determined. The correlation with the estimated value Ian) of 1 is derived in advance. For example, the first calculation unit 30B derives in advance an equation showing the correlation between the first estimated value Ia and the first detected value Xa represented by the above equation (1) for each heat generating component 14A. Therefore, in the correlation represented by the equation (1), at least one value of the coefficient (p0 to pn) represented by the equation (1) is different from each other for each corresponding heat generating component 14A.

Note that the first calculation unit 30B may derive this correlation in advance by experiment, simulation, machine learning, or the like, as in the first embodiment. For machine learning, known machine learning methods such as CNN, Bayesian modeling, DNN, and data assimilation techniques such as particle filters may be used.

Further, it is preferable that the first calculation unit 30B calculates the first estimated value Ia according to three or more first detected values Xa. Further, it is assumed that the type of the first detected value Xa and the number of the first detected values Xa used for calculating the first estimated value Ia of the heat generation amount of each of the plurality of heat generating parts 14A are the same. ..

The second calculation unit 31E is a factor that affects the abnormality in the specific region of the abnormality determination target according to the plurality of first detection values Xa, and evaluates the evaluation value Ib of the factor other than the heat generating component 14A. calculate.

Factors that affect the abnormality in the specific area to be determined for abnormality, and the factors other than the heat generating component 14A, include, for example, the temperature outside the housing 12, the contact state of the heat sink 14B, and the clogging of the filter 17. Factors other than the heat generating component 14A, such as insufficient rotation of the blower 14C, a closed state of the intake port 13A, and a closed state of the exhaust port 13B.

The evaluation value Ib shows a higher value as the influence on the temperature abnormality of the specific region to be determined for abnormality is greater. In the present embodiment, the second calculation unit 31E calculates a plurality of evaluation values Ib (evaluation values Ib1 to evaluation value Ibn) having different factors from each other. That is, the second calculation unit 31E calculates a plurality of evaluation values Ib from the plurality of first detection values Xa. It is assumed that the number of the first detected values Xa and the number of the evaluation values Ib are the same. This is because we need as many functions as there are unknowns.

The second calculation unit 31E derives the correlation between the plurality of first detected values Xa and the evaluation value Ib in advance. For example, this correlation is expressed by the following equation (2).

Ib = q0 + q1 · Xa1 + q2 · Xa2 + ... + qn · Xan equation (2)

In the formula (2), Xa represents the first detected value Xa. The numerical values (1 to n) adjacent to each of Xa are identifiers of the environmental sensor 16A. q0 to qn indicate a coefficient. n represents an integer of 2 or more. Ib indicates the evaluation value Ib of the factor.

The second calculation unit 31E may derive the correlation between the evaluation value Ib of the factor and the plurality of first detection values Xa in advance for each factor. Specifically, for example, the second calculation unit 31E may derive in advance the values of the counts q0 to qn in the above formula (2). This correlation may be derived by experiment, simulation, machine learning, or the like. For machine learning, known machine learning methods such as CNN, Bayesian modeling, DNN, and data assimilation techniques such as particle filters may be used. In the above, the equation (2) is given as an example of the function showing the correlation for calculating from the first detected value Xa. However, the correlation equation for calculating the evaluation value Ib from the first detected value Xa may be either a one-dimensional polynomial or a multidimensional polynomial. Further, the correlation equation for calculating the evaluation value Ib from the first detected value Xa may be an equation with strong non-linearity.

Then, the second calculation unit 31E substitutes each of the plurality of first detected values Xa into the function (for example, the above equation (2)) showing the correlation for each factor derived in advance, so that each factor In addition, the evaluation value Ib of the factor may be calculated.

The second calculation unit 31E uses a plurality of first detected values Xa by using a trained model showing the correlation represented by the above equation (2) in addition to the function showing the correlation derived in advance. Therefore, the evaluation value Ib may be calculated for each factor.

The third calculation unit 31F calculates the second estimated value Ic of the temperature in the specific region based on the first estimated value Ia and the evaluation value Ib of the factor.

The third calculation unit 31F derives in advance the correlation between the plurality of first estimated values Ia and the plurality of evaluated values Ib and the second estimated value Ic. For example, this correlation is expressed by the following equation (3).

Ic = r0 + r1, Ia1 + r2, Ia2 + ... + rn, Ian + s1, Ib1 + s2, Ib2 + ... + sn, Ibn equation (3)

In formula (3), Ia represents the first estimated value Ia. The numerical values (1 to n) adjacent to each of Ia are identifiers of the heat generating component 14A. Ib indicates the evaluation value Ib of the factor. The numerical values (1 to n) adjacent to each of the Ibs are identifiers of the factors. rn0 to rn and s1 to sn represent coefficients. n represents an integer of 2 or more. Ic indicates a second estimate Ic of the temperature in a particular region.

The third calculation unit 31F may derive in advance the correlation between the plurality of first estimated values Ia and the plurality of evaluated values Ib and the second estimated value Ic. Specifically, for example, the third calculation unit 31F may derive in advance the values of the counts r0 to rn and s1 to sn in the above formula (3). This correlation may be derived by experiment, simulation, machine learning, or the like. For machine learning, known machine learning methods such as CNN, Bayesian modeling, DNN, and data assimilation techniques such as particle filters may be used. In the above, the equation (3) is given as an example of the function showing the correlation between the plurality of first estimated values Ia and the plurality of evaluated values Ib and the second estimated value Ic. However, the equation of this correlation may be either a one-dimensional polynomial or a multidimensional polynomial. Further, the equation of this correlation may be an equation having strong non-linearity.

Then, the third calculation unit 31F substitutes each of the plurality of first estimated values Ia and the plurality of evaluation values Ib into the function showing this correlation (for example, the above equation (3)), so that the third calculation unit 31F The estimated value Ic of 2 may be calculated.

In addition to the function showing the correlation, the third calculation unit 31F uses a plurality of first estimated values Ia and a plurality of first estimated values Ia using a learned model showing the correlation represented by the above equation (3). The second estimated value Ic may be calculated from the evaluation value Ib of.

The third calculation unit 31F may calculate a second estimated value Ic of each temperature in specific regions different from each other. That is, the third calculation unit 31F may calculate the second estimated value Ic of each temperature of the plurality of specific regions from the plurality of first estimated values Ia and the plurality of evaluation values Ib (FIG. 8). ). In FIG. 8, Ic indicates a second estimated value Ic, and the numerical value to the right of Ic is an identifier of a specific region. In this way, the third calculation unit 31F may calculate a plurality of second estimated values Ic.

Next, the determination unit 31C and the output control unit 31D will be described.

Similar to the determination unit 30C of the first embodiment, the determination unit 31C determines whether or not the first estimated value Ia of the heat generation amount of the heat generation component 14A1 to be abnormally determined is equal to or greater than the first threshold value. To do. When the determination unit 30C determines that the first estimated value Ia is equal to or greater than the first threshold value, the determination unit 30C determines that the heat generating component 14A1 is abnormal. Then, the output control unit 31D outputs the error information to the output unit 34. In this case, the error information includes information indicating that an abnormality has occurred in the amount of heat generated by the heat generating component 14A1 to be determined for abnormality, which is determined by the determination unit 31C.

In the present embodiment, the determination unit 31C further determines whether or not the evaluation value Ib of the factor other than the heat generating component 14A is equal to or higher than the third threshold value. The third threshold value may be a threshold value for determining that the factor represented by the evaluation value Ib is abnormal. The determination unit 31C may set a third threshold value in advance for each factor. Specifically, the determination unit 31C determines that each of the factors other than the heat generating component 14A, such as the contact state of the heat sink 14B, the clogging of the filter 17, and the insufficient rotation of the blower 14C, is abnormal. The threshold value of 3 may be set in advance. The third threshold value may be appropriately changed according to a change instruction by the user or the like.

Further, in the present embodiment, the determination unit 31C determines that the specific region is abnormal when the second estimated value Ic is equal to or greater than the second threshold value. That is, when the second estimated value Ic is equal to or greater than the second threshold value, the determination unit 31C determines that an abnormality has occurred in the specific region.

For the second threshold value, a threshold value for determining the occurrence of an abnormality may be set in advance for each specific region. Further, the second threshold value may be appropriately changed according to a change instruction by the user or the like.

As described above, the specific region is preferably a region in the housing 12 of the electronic device 10 that cannot be directly measured by the sensor 16. That is, it is preferable that the specific area is an area in the housing 12 where the sensor 16 is not installed. Therefore, the determination unit 31C can easily determine whether or not an abnormality has occurred in a specific area, which is an area in which the sensor 16 is not installed.

Next, the flow of information processing executed by the information processing device 21 will be described.

FIG. 9 is a flowchart showing an example of the flow of information processing executed by the information processing apparatus 21 of the present embodiment. The order of each of the plurality of steps can be changed as appropriate, and is not limited to the example of FIG. In addition, at least a part of the plurality of steps may be executed in parallel.

Note that FIG. 9 describes a mode in which the second estimated value Ic of each of the plurality of specific regions is calculated as an example.

First, the acquisition unit 30A acquires a plurality of first detected values Xa (step S200).

Next, the first calculation unit 30B calculates the first estimated value Ia of the heat generation amount of the heat generation component 14A to be determined for abnormality according to the plurality of first detection values Xa acquired in step S200 (step). S202). Here, it is assumed that the first estimated value Ia of the calorific value of each of the plurality of heat generating parts 14A different from each other is calculated.

Next, the determination unit 31C and the output control unit 31D repeatedly execute the processes of steps S204 and S206 for each of the plurality of first estimated values Ia calculated in step S202.

Specifically, the determination unit 31C determines whether or not the first estimated value Ia is equal to or greater than the first threshold value (step S204). When the first estimated value Ia is equal to or greater than the first threshold value (step S204: Yes), the determination unit 31C has error information indicating that the heat generating component 14A of the first estimated value Ia used for the determination is abnormal. Is output to the output unit 34 (step S204). Then, this iterative process ends. If a negative determination is made in step S204 (step S204: No), this iterative process ends. If an affirmative decision is made in step S204 (step S204: Yes), this routine may be terminated after the error information is output in step S206.

Next, the second calculation unit 31E is a factor that affects the abnormality in the specific region of the abnormality determination target according to the plurality of first detection values Xa acquired in step S200, and is other than the heat generating component 14A. The evaluation value Ib of the factor is calculated (step S208). Here, it is assumed that the evaluation value Ib of each of the plurality of factors different from each other is calculated.

Next, the determination unit 31C and the output control unit 31D repeatedly execute the processes of steps S210 and S212 for each of the plurality of evaluation values Ib calculated in step S208.

Specifically, the determination unit 31C determines whether or not the evaluation value Ib is equal to or greater than the third threshold value (step S210). When the evaluation value Ib is equal to or higher than the third threshold value (step S220: Yes), the determination unit 31C outputs error information indicating that the factor of the evaluation value Ib used for the determination is abnormal to the output unit 34. (Step S212). Then, this iterative process ends. If a negative determination is made in step S210 (step S210: No), this iterative process ends. If an affirmative decision is made in step S210 (step S210: Yes), this routine may be terminated after the error information is output in step S212.

Next, the third calculation unit 31F uses the plurality of first estimated values Ia calculated in step S202 and the plurality of evaluation values Ib calculated in step S208 to obtain the second estimated value Ic. Calculate (step S214). Here, it is assumed that the second estimated value Ic of each temperature of a plurality of specific regions different from each other is calculated.

Next, the determination unit 31C and the output control unit 31D repeatedly execute the processes of steps S216 and S218 for each of the plurality of second estimated values Ic calculated in step S214.

Specifically, the determination unit 31C determines whether or not the second estimated value Ic is equal to or greater than the second threshold value (step S216). When the second estimated value Ic is equal to or greater than the second threshold value (step S216: Yes), the determination unit 31C has error information indicating that the specific region indicating the second estimated value Ic used for the determination is abnormal. Is output to the output unit 34 (step S218). Then, this iterative process ends. If a negative determination is made in step S216 (step S216: No), this iterative process ends.

As described above, the first calculation unit 30B of the abnormality detection device 1A of the present embodiment is a factor that affects the abnormality in the specific region of the electronic device 10 according to the plurality of first detection values Xa. The first estimated value Ia of the calorific value of the heat generating component 14A is calculated. The second calculation unit 31E determines the evaluation value Ib of the factor other than the heat generating component 14A, which is a factor that affects the abnormality in the specific region according to the first detection value Xa of each of the plurality of environmental sensors 16A. calculate. The third calculation unit 31F calculates the second estimated value Ic of the temperature in the specific region based on the first estimated value Ia and the evaluation value Ib. When the second estimated value Ic is equal to or greater than the second threshold value, the determination unit 31C determines that the specific region is abnormal.

Therefore, in the abnormality detection device 1A of the present embodiment, even if the specific region is a region that cannot be directly measured by the sensor 16, the first estimated value Ia and the first estimated value IaB are used. By calculating the second estimated value Ic of the temperature in the specific region, it is possible to determine the abnormality in the specific region.

Therefore, the abnormality detection device 1A of the present embodiment can accurately and easily determine an abnormality in a specific region in the electronic device 10 in addition to the effect of the above embodiment.

Further, in the abnormality detection device 1A of the present embodiment, even when the sensor 16 is not arranged in the specific area of the abnormality identification target, the abnormality in the specific area can be determined, so that the electronic device 10 can be determined. It is possible to reduce the amount of the sensor 16 mounted on the sensor 16.

Further, in the abnormality detection device 1A of the present embodiment, the output control unit 31D causes an error by determining an abnormality using each of the first estimated value Ia, the evaluation value Ib, and the second estimated value Ic. Output information. The error information includes information indicating that an abnormality has occurred in the heat generation amount of the heat generating component 14A1 to be determined as an abnormality, information indicating that an abnormality has occurred in a factor other than the heat generating component 14A, and an abnormality in a specific area. Includes at least one piece of information indicating that is occurring.

Therefore, the abnormality detection device 1A of the present embodiment includes replacement of the component 14, maintenance of the component 14, analysis of the component 14 in which an error is likely to occur, life of the component 14, and optimization of the component 14 constituting the electronic device 10. Information that can be used for analysis such as designing the electronic device 10 and elucidating the cause at the time of failure can be provided as error information.

In the first embodiment and the second embodiment, an example in which the electronic device 10 and the information processing device 20 are configured as separate bodies is shown as an example (see FIG. 1). However, the electronic device 10 and the information processing device 20 may be integrally configured. That is, the electronic device 10 may be configured to include the information processing device 20. In this case, for example, the information processing device 20 may be arranged in the housing 12 of the electronic device 10.

-Hardware configuration-
Next, the hardware configuration of the control unit 30 of the first embodiment and the second embodiment of the hoai embodiment and the modified example will be described.

FIG. 10 is a block diagram showing a hardware configuration example of the control unit 30 and the control unit 31 of the above-described embodiment and modification.

The control unit 30 and the control unit 31 of the above-described embodiment and modification include a control device such as a CPU (Central Processing Unit) 51 and a storage device such as a ROM (Read Only Memory) 52 or a RAM (Random Access Memory) 53. A communication I / F 54 that connects to a network for communication and a bus 61 that connects each unit are provided.

The programs executed by the control unit 30 and the control unit 31 of the above-described embodiment and modification are provided by being incorporated in the ROM 52 or the like in advance.

The program executed by the control unit 30 and the control unit 31 of the above-described embodiment and modification is a CD-ROM (Computer Disk Read Only Memory), a flexible disk (FD) in an installable format or an executable format file. , CD-R (Compact Disk Recordable), DVD (Digital Versaille Disk), or the like, which may be recorded on a computer-readable recording medium and provided as a computer program product.

Further, the program executed by the control unit 30 and the control unit 31 of the above-described embodiment and modification is stored on a computer connected to a network such as the Internet, and is provided by being downloaded via the network. You may. Further, the program executed by the control unit 30 and the control unit 31 of the above-described embodiment and modification may be configured to be provided or distributed via a network such as the Internet.

The program executed by the control unit 30 and the control unit 31 of the embodiment and the modification can cause the computer to function as each unit of the control unit 30 and the control unit 31 of the embodiment and the modification. The computer can read a program from a computer-readable storage medium onto the main storage device and execute the program.

Although some embodiments and modifications of the present invention have been described, these embodiments and modifications are presented as examples and are not intended to limit the scope of the invention. These novel embodiments and modifications can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

1, 1A Anomaly detection device 10 Electronic device 14 Parts 14A, 14A1, 14A2, 14A3 Heat generation parts 16A Environmental sensor 20, 21 Information processing device 30B First calculation unit 30C, 31C Judgment unit 30D, 31D Output control unit 31E Second Calculation unit 31F Third calculation unit

Claims (9)

Heat-generating parts that are installed in electronic devices and are driven by electric power to change the amount of heat generated.
A plurality of environmental sensors having different arrangement positions and detecting the environment of the heat generating component,
A first calculation unit that calculates a first estimated value indicating the amount of heat generated by the heat-generating component according to the first detection value of each of the plurality of environmental sensors.
When the first estimated value is equal to or greater than the first threshold value, a determination unit for determining that the heat generating component is abnormal, and a determination unit.
Anomaly detection device. The abnormality detection device according to claim 1, wherein the amount of heat generated by the heat-generating component and the power consumption of the electronic device show a non-linear relationship. The environment sensor detects the environment other than the current value of the heat generating component, the voltage value of the heat generating component, and the usage rate of the heat generating component.
The abnormality detection device according to claim 1 or 2. The environmental sensor is
The first detected value of at least one of a fluctuating physical quantity of a component other than the heat generating component and a temperature of the heat generating component provided in the electronic device is detected.
The abnormality detection device according to any one of claims 1 to 3. The abnormality detection device according to any one of claims 1 to 4, wherein the heat generating component is a processor. The first calculation part is
The first estimated value of the calorific value of the heat generating component, which is a factor affecting the abnormality in the specific region of the electronic device, is calculated according to the plurality of first detected values.
The abnormality detection device is
A second calculation unit that calculates the evaluation value of the factor other than the heat generating component, which is a factor affecting the abnormality in the specific region, according to the first detection value of each of the plurality of environmental sensors. Prepare,
A third calculation unit that calculates a second estimate of the temperature of the specific region based on the first estimate and the evaluation value.
With
The determination unit
When the second estimated value is equal to or greater than the second threshold value, it is determined that the specific region is abnormal.
The abnormality detection device according to any one of claims 1 to 5. The first calculation unit is
The first estimated value is calculated according to three or more of the first detected values.
The abnormality detection device according to any one of claims 1 to 6. Anomaly detection method executed by a computer
The heat generation amount of the heat generation component is determined according to the first detection value of each of a plurality of environment sensors having different arrangement positions, which detect the environment of the heat generation component provided in the electronic device and driven by electric power to change the heat generation amount. Steps to calculate the first estimate shown and
When the first estimated value is equal to or greater than the first threshold value, the step of determining that the heat generating component is abnormal, and
Anomaly detection method including. The amount of heat generated by the heat-generating component is determined according to the first detection value of each of a plurality of environmental sensors having different arrangement positions, which detect the environment of the heat-generating component provided in the electronic device and driven by electric power to change the amount of heat generated. Steps to calculate the first estimate shown and
When the first estimated value is equal to or greater than the first threshold value, the step of determining that the heat generating component is abnormal, and
A program that lets your computer run.

Images