Equipment management device, equipment management method, and program

Abstract

We provide equipment management devices, equipment management methods, and programs. [Solution] The equipment management device may include an acquisition unit that acquires the measurement data history of a specific target equipment measured by a specific sensor. The equipment management device may also include a determination unit that determines the maintenance quality level for a specific target equipment based on the measurement data history of each target equipment measured by each sensor, which has been collected in advance, the maintenance quality level for each target equipment, and the measurement data history of the specific target equipment.

Description

Technical Field

[0001] The present invention relates to a facility management device, a facility management method, and a program.

Background Art

[0002] Patent Document 1 discloses a data analysis system that realizes analysis using data including confidential data held by each organization without releasing it outside the organization. Patent Document 2 discloses a management server that instructs each information processing device selected to generate information related to a request for information purchase from a user terminal to provide or process information, and determines a reward for the administrator of each selected information processing device. Patent Document 3 discloses that for each storage server, storage fees and retrieval fees are determined according to the usage frequency. [Prior Art Documents] [Patent Documents] [Patent Document 1] Japanese Patent Application Laid-Open No. 2021-089679 [Patent Document 2] Japanese Patent Application Laid-Open No. 2020-67829 [Patent Document 3] Japanese Patent Application Laid-Open No. 2022-153420

Summary of the Invention

[0003] The facility management device according to one aspect of the present invention may include an acquisition unit that acquires a measurement data history of a specific measurement target facility measured by a specific sensor. The facility management device may include a determination unit that determines a maintenance quality level for the specific measurement target facility based on the measurement data history of each measurement target facility measured by each sensor collected in advance, each maintenance quality level for each measurement target facility, and the measurement data history of the specific measurement target facility.

[0004] In the facility management device, the acquisition unit may further acquire additional information related to the specific sensor. The determination unit may further determine the maintenance quality level for the specific measurement target facility based on the additional information related to each sensor collected in advance and the additional information related to the specific sensor.

[0005] In any of the equipment management devices, the acquisition unit may further acquire the operating period of the specific equipment to be measured. The determination unit may further determine the maintenance quality level for the specific equipment to be measured based on the previously collected operating periods of each piece of equipment to be measured and the operating period of the specific equipment to be measured.

[0006] Any of the equipment management devices may further include a display unit that, based on the maintenance quality level of the specific equipment to be measured and the respective maintenance quality levels for each of the equipment to be measured, presents recommended thresholds that serve as criteria for determining whether an abnormality is likely to occur in the specific equipment to be measured, based on measurement data measured by the specific sensor.

[0007] In any of the aforementioned equipment management devices, if the display unit finds that the maintenance quality level of a particular piece of equipment is lower than the average value of the maintenance quality levels of each of the aforementioned pieces of equipment to be measured, it may display a threshold lower than the current threshold for the particular piece of equipment to be measured as a recommended threshold.

[0008] In any of the equipment management devices, the acquisition unit may further acquire additional information related to the specific sensor. The determination unit may determine the predicted operating period of the specific sensor based on the measurement data history of each sensor, the operating period of each sensor identified based on the measurement data history of each sensor, the additional information of each sensor collected in advance, the measurement data history of the specific sensor, and the additional information of the specific sensor.

[0009] Any of the equipment management devices may include an abnormal period identification unit that identifies an abnormal period based on the history of measurement data from each sensor, from a first time when each piece of equipment under measurement entered an abnormal state and a second time when each piece of equipment under measurement returned from the abnormal state to a normal state. The equipment management device may also include a maintenance content request unit that requests maintenance content to each piece of equipment under measurement performed between the first and second time points. The acquisition unit may acquire the maintenance content entered in response to the request. The determination unit may determine recommended maintenance content for a specific piece of equipment under measurement based on the history of measurement data from each sensor, additional information related to each sensor, maintenance content for each piece of equipment under measurement, the history of measurement data for a specific piece of equipment under measurement, and additional information related to a specific sensor. The equipment management device may further include a presentation unit that presents recommended maintenance content for the specific piece of equipment under measurement.

[0010] In any of the aforementioned equipment management devices, the additional information may include at least one of the following: identification information of the equipment to be measured, a method of mounting the sensor, information on the location where the sensor is installed, setting information indicating the settings of the sensor, and environmental information of the location where the sensor is installed.

[0011] In any of the equipment management devices, the acquisition unit may further acquire additional information related to the specific sensor and the target operating period of the specific sensor. The additional information may include the sensor's setting information and at least one of the sensor's installation location information and environmental information of the sensor's setting location. The determination unit may determine the settings of the specific sensor so that the operating period of the specific sensor satisfies the target operating period, based on the measurement data history of each sensor, the operating period of each sensor identified based on the measurement data history of each sensor, the additional information of each sensor, the measurement data history of the specific sensor, at least one of the specific sensor's setting location information and environmental information of the setting location, and the target operating period of the specific sensor.

[0012] In any of the aforementioned equipment management devices, the determination unit may determine the maintenance quality level of a specific piece of equipment to be measured as an output when the measurement data history of that specific piece of equipment to be measured is input, using a learning model that has been learned with the measurement data history as input and each maintenance quality level as output.

[0013] In any of the aforementioned equipment management devices, the determination unit may use a learning model, which has been learned by inputting the measurement data history and outputting the maintenance quality levels of each organization that manages each of the aforementioned measurement target equipment, to determine the maintenance quality level of a specific organization that manages a specific measurement target equipment, when the measurement data history of that specific measurement target equipment is input, as the maintenance quality level for that specific measurement target equipment.

[0014] In any of the aforementioned equipment management devices, each of the measurement target equipment may be managed by each organization. The determination unit may determine the maintenance quality level for the specific measurement target equipment managed by the specific organization based on the measurement data history of each measurement target equipment measured by the sensors provided on each measurement target equipment of each organization, which have been collected in advance, and the maintenance quality level for each measurement target equipment, as well as the measurement data history measured by the specific sensor provided on the specific measurement target equipment of the specific organization. The equipment management device may further include a presentation unit that presents information showing the maintenance quality level of a comparison target based on the maintenance quality level of each organization and the maintenance quality level of the specific measurement target equipment managed by the specific organization.

[0015] In any of the aforementioned equipment management devices, the maintenance quality level to be compared may be the average value of the maintenance quality levels of each of the aforementioned organizations.

[0016] A facility management method according to one aspect of the present invention may include a step in which an acquisition unit acquires the measurement data history of a specific target facility measured by a specific sensor. The facility management method may also include a step in which a determination unit determines the maintenance quality level for a specific target facility based on the measurement data history of each target facility measured by each sensor, which has been collected in advance, the maintenance quality level for each target facility, and the measurement data history of the specific target facility.

[0017] A program according to one aspect of the present invention, when executed by a computer, may function as an acquisition unit that acquires the measurement data history of a specific target equipment measured by a specific sensor, and a determination unit that determines the maintenance quality level for the specific target equipment based on the measurement data history of each target equipment measured by each sensor, which has been collected in advance, the maintenance quality level for each target equipment, and the measurement data history of the specific target equipment.

[0018] It should be noted that the above summary of the invention does not enumerate all of its features. Furthermore, subcombinations of these features may also constitute an invention. [Brief explanation of the drawing]

[0019] [Figure 1] This figure shows an example of the system configuration of the equipment management system according to this embodiment. [Figure 2] This figure shows an example of a functional block for an equipment management system. [Figure 3] This figure shows an example of measurement data history. [Figure 4] This flowchart shows an example of a procedure for indicating the maintenance quality level of specific equipment. [Figure 5] This flowchart shows an example of a procedure for suggesting recommended thresholds for predictive maintenance detection based on the maintenance quality level. [Figure 6] This flowchart shows an example of a procedure for presenting the predicted operating time of a specific sensor. [Figure 7]It is a flowchart showing an example of a procedure for presenting recommended maintenance contents to be performed when an abnormality occurs in a specific facility. [Figure 8] It is a flowchart showing an example of a procedure for presenting recommended setting information according to the target operation period of a specific sensor. [Figure 9] It is a diagram showing an example of a hardware configuration.

Best Mode for Carrying Out the Invention

[0020] Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential for the solution means of the invention.

[0021] FIG. 1 is a diagram showing an example of the system configuration of the facility management system 10 according to the present embodiment. The facility management system 10 includes sensors 20-1, 20-2,..., 20-n (hereinafter sometimes collectively referred to as "sensor 20") installed in facilities 50-1, 50-2,..., 50-n (hereinafter sometimes collectively referred to as "facility 50"), imaging devices 30-1, 30-2,..., 30-n (hereinafter sometimes collectively referred to as "imaging device 30"), relay devices 40-1, 40-2,..., 40-n (hereinafter sometimes collectively referred to as "relay device 40"), and terminals 60-1, 60-2,..., 60-n (hereinafter sometimes collectively referred to as "terminal 60"). Here, n is a positive integer.

[0022] Equipment 50 is managed by an organization. The organization may be a company, a government agency, another organization, or a department belonging to one of these. Equipment 50 is an example of equipment to be measured. Equipment 50 comprises one or more devices that manufacture products from raw materials. Equipment 50 may be a plant or a composite device that combines multiple pieces of equipment. The plant may be an industrial plant such as a chemical or bio-plant, a plant that manages and controls the wellhead or surrounding area of ​​a gas or oil field, a plant that manages and controls power generation such as hydroelectric, thermal, or nuclear power, a plant that manages and controls environmental power generation such as solar or wind power, a plant that manages and controls water and sewage or a dam, etc.

[0023] Each of the multiple sensors 20 is installed at multiple locations on one or more devices of the equipment 50. Each of the multiple sensors 20 is installed at a location in one or more devices of the equipment 50 where an anomaly can be detected by measuring the physical quantity measured by the sensor 20. The sensor 20 may be installed, for example, in the piping of the devices of the equipment 50. The sensor 20 measures various physical quantities in the equipment 50 in a time series.

[0024] Sensor 20 may be, for example, a sensor installed in the OT (Operational Technology) domain (e.g., a process control (measurement) sensor) or an IoT (Internet of Things) sensor. Sensor 20 may be an industrial sensor connected to or integrated with one or more field devices installed in the plant.

[0025] Sensing data from such a sensor 20, or data obtained by signal processing of sensing data, is referred to as measurement data. Measurement data may include, for example, pressure, vibration (displacement, velocity, or acceleration), temperature, and sound pressure, or at least one of these. Measurement data may also include physical quantities that can be detected by human senses (sight, hearing, smell, taste, touch), or physical quantities that cannot be detected by human senses, such as flow rate, humidity, acceleration, angular velocity, gas concentration, odor, image, light, sound, magnetism, or radiation dose.

[0026] The imaging device 30 captures images of the equipment or sensors 20 provided by the facility 50. The imaging device 30 may capture images showing the status of the equipment. The imaging device 30 may capture images showing the installation status of the sensors 20.

[0027] The relay device 40 communicates with the sensor 20, the imaging device 30, and the facility management device 100 wirelessly or via wired connection. The relay device 40 collects time-series measurement data from the multiple sensors 20. The relay device 40 periodically transmits the collected time-series measurement data to the facility management device 100 as a measurement data history. The relay device 40 may collect multiple image data captured by the multiple imaging devices 30. The relay device 40 may periodically transmit the collected multiple image data to the facility management device 100.

[0028] Terminal 60 communicates with sensor 20 and equipment management device 100. Terminal 60 may be a mobile device such as a smartphone or tablet computer, or a personal computer. Equipment management device 100 manages the measurement data history for each piece of equipment 50 of each organization, which is collected via multiple relay devices 40.

[0029] In the equipment management system 10 configured in this way, the equipment management device 100 determines the maintenance quality level for a specific piece of equipment 50 based on the measurement data history collected from each sensor 20 of multiple organizations, the maintenance quality level for each piece of equipment 50 determined based on the measurement data history, and the measurement data history measured by a specific sensor 50x installed on that piece of equipment 50x. For example, if the determined maintenance quality level for a specific piece of equipment 50x is low, the settings of a specific device or a specific sensor 50x installed on that piece of equipment 50x can be updated to increase the maintenance quality level, thereby enabling more stable operation of the specific piece of equipment 50.

[0030] Figure 2 shows an example of a functional block of the facility management device 100. The facility management device 100 may be a computer having a central processing unit (CPU) and memory. The computer may be a personal computer, tablet computer, smartphone, workstation, server computer, or general-purpose computer, or it may be a computer system in which multiple computers are connected. Such a computer system is also a computer in a broad sense. The computer may be a dedicated computer designed for facility management, or it may be dedicated hardware realized by dedicated circuits. The computer may also be implemented in a virtual computer environment. When a computer is used, the facility management device 100 is realized by executing a program on the computer.

[0031] The equipment management device 100 comprises a control unit 110, a storage unit 120, and a communication unit 130. The control unit 110 may be composed of a microprocessor such as a CPU or MPU, a microcontroller such as an MCU, etc. The storage unit 120 may be a non-temporary computer-readable medium and may include at least one of SRAM, DRAM, EPROM, EEPROM, and flash memory such as a USB memory. The communication unit 130 is a communication interface for communicating with the relay device 40 wirelessly or via a wired connection.

[0032] The control unit 110 includes an acquisition unit 111, a determination unit 112, an abnormal period identification unit 113, a maintenance content request unit 114, an operation period identification unit 115, a presentation unit 116, and a learning model generation unit 117. A microprocessor such as a CPU or MPU, or a microcontroller such as an MCU may function as the acquisition unit 111, the determination unit 112, the abnormal period identification unit 113, the maintenance content request unit 114, the operation period identification unit 115, the presentation unit 116, and the learning model generation unit 117.

[0033] The acquisition unit 111 acquires the measurement data history of a specific piece of equipment 50x measured by at least one specific sensor 20x and stores it in the storage unit 120. The determination unit 112 determines the maintenance quality level for a specific piece of equipment 50x based on the measurement data history of each piece of equipment 50 measured by each sensor 20, which has been collected in advance and stored in the storage unit 120, the maintenance quality level for each piece of equipment 50, and the measurement data history of the specific piece of equipment 50x.

[0034] The determination unit 112 may use the learning model generated by the learning model generation unit 117 to determine the maintenance quality level for a specific piece of equipment 50x based on the measurement data history of that piece of equipment 50x.

[0035] The learning model generation unit 117 takes the measurement data history of each sensor 20 of each piece of equipment 50 as input and generates a learned model with the maintenance quality level of each piece of equipment 50 as output. The determination unit 112 may use the learned model generated by the learning model generation unit 117 to determine the maintenance quality level of a specific piece of equipment 50x as output when the measurement data history of that specific piece of equipment 50x is taken as input.

[0036] The learning model generation unit 117 may generate a learning model by performing machine learning according to a supervised learning algorithm, using the measurement data history of each sensor 20 of each piece of equipment 50 as explanatory variables and the maintenance quality level of each piece of equipment 50 as the objective variable. The algorithm may be any type of algorithm, such as a neural network, support vector machine, multiple regression analysis, or decision tree.

[0037] The learning model generation unit 117 may generate a learning model of maintenance quality levels by inputting the measurement data history from each sensor 20 of each piece of equipment 50 and outputting the maintenance quality levels of each organization that manages each piece of equipment 50. The learning model generation unit 117 may generate a learning model of maintenance quality levels by performing machine learning according to a supervised learning algorithm, using the measurement data history from each sensor 20 of each piece of equipment 50 as explanatory variables and the maintenance quality levels of each organization that manages each piece of equipment 50 as the objective variable.

[0038] The display unit 116 may display maintenance quality level information indicating the maintenance quality level for each organization. By referring to such maintenance quality level information, the relative maintenance quality level of each organization can be grasped. If the maintenance quality level is low, there is a possibility that the risk of equipment failure is high. Therefore, by reviewing the settings of each device in the equipment 50 or reviewing the settings of the sensor 20, the sensor 20 can detect signs of equipment abnormality at an early stage, thereby reducing the risk of equipment failure and preventing a decrease in the operating rate of the equipment 50.

[0039] Furthermore, a high maintenance quality level means that equipment 50 is properly maintained and that malfunctions in equipment 50 are infrequent. Therefore, equipment 50 with a high maintenance quality level is less prone to malfunctions such as production line shutdowns, and thus signifies high organizational reliability. Thus, the value of each organization can be judged from the perspective of maintenance quality level, which is objectively determined from measurement data history. This organizational value can be used, for example, as the basis for calculating insurance premiums related to various types of compensation for the organization.

[0040] Figure 3 shows an example of the measurement data history. Periods in which physical quantities such as pressure, temperature, vibration (displacement, velocity, or acceleration), and sound pressure, as shown in the measurement data, are greater than or equal to the first threshold th1 and less than the second threshold th2, for example, are precursory periods in which there are signs that an abnormality may occur in the equipment 50 in the near future. Periods in which the physical quantities are greater than or equal to the second threshold th2 are abnormal periods in which an abnormality has occurred in the equipment 50. Periods in which the physical quantities are less than the first threshold th are normal periods in which the equipment 50 is operating normally.

[0041] The learning model generation unit 117 may accept each maintenance quality level for each piece of equipment 50 specified by the user as training data. The maintenance quality level may be defined in multiple stages. For example, the maintenance quality level may be defined in 3 stages, 5 stages, or 10 stages. The maintenance quality level may be defined according to predetermined conditions based on the frequency of abnormalities of the equipment 50, the length of the abnormal period, the length of the normal period, etc. The maintenance quality level may be higher the lower the frequency of abnormalities of the equipment 50. The maintenance quality level may be higher the longer the period of normal operation. The maintenance quality level may be higher the shorter the abnormal period. The maintenance quality level may be high if the frequency of reaching the warning period is high but the frequency of reaching the abnormal period is low. The maintenance quality level may be higher the longer the normal period.

[0042] The learning model generation unit 117 may further utilize additional information related to the sensor 20 as explanatory variables. The additional information may include at least one of the following: identification information of the equipment 50, the mounting method of the sensor 20, information on the installation location of the sensor 20, and environmental information of the installation location of the sensor 20. The additional information may include an image showing the installation status of the sensor 20 captured by the imaging device 30. The identification information of the equipment 50 may include at least one of the identification information of the device provided by the equipment 50 and the identification information of the parts provided by the device. The identification information of the device may include the manufacturer's name or the model number. The identification information of the parts provided by the device may include the manufacturer's name and the model number. The mounting method of the sensor 20 includes methods of attaching it to pipes etc. using a mounting bracket and belt, and methods of attaching it to pipes etc. using a magnet provided on the sensor 20. The environmental information of the sensor 20's location may include at least one of the temperature, humidity, and atmospheric pressure around the installation location of the sensor 20.

[0043] The learning model generation unit 117 may group (cluster) the measurement data history based on the additional information, and generate a learning model for the maintenance quality level based on the grouped measurement data history and the maintenance quality level.

[0044] The acquisition unit 111 may acquire additional information along with the measurement data history of a specific sensor 20x. The determination unit 112 may determine the maintenance quality level for a specific piece of equipment 50x based on the additional information about each sensor 20 that has been collected in advance, and the additional information about the specific sensor 20. The measurement data history referenced when determining the maintenance quality level for a specific piece of equipment 50x may be data measured by one or more sensors 20x. A specific sensor 20x is a general term for one or more sensors 20x.

[0045] The learning model generation unit 117 may further use the operating period, which indicates the elapsed time since each piece of equipment 50 started operation, as an explanatory variable. When the operating period is short, the probability of an abnormality occurring in the equipment 50 is lower than when the operating period is long. Therefore, the shorter the operating period, the lower the maintenance quality level may be. Thus, the operating period of the equipment 50 may be used as one of the parameters for determining the maintenance quality level. Note that the maintenance quality level may be high during the trial operation period after each piece of equipment 50 starts operation. After the trial operation period, the shorter the operating period, the lower the maintenance quality level may be.

[0046] The learning model generation unit 117 may generate a learning model of maintenance quality levels by performing machine learning according to a supervised learning algorithm, using the measurement data history from each sensor 20 of each piece of equipment 50 and the operating period of each piece of equipment 50 as explanatory variables, and the maintenance quality level of each piece of equipment 50 as the objective variable. The learning model generation unit 117 may generate a learning model of maintenance quality levels by performing machine learning according to a supervised learning algorithm, using the measurement data history from each sensor 20 of each piece of equipment 50, additional information of each sensor 20, and the operating period of each piece of equipment 50 as explanatory variables, and the maintenance quality level of each piece of equipment 50 as the objective variable.

[0047] The acquisition unit 111 may further acquire the operating period of a specific piece of equipment 50x. The determination unit 112 may determine the maintenance quality level for a specific piece of equipment 50x based on the previously collected operating periods of each piece of equipment 50 and the operating period of the specific piece of equipment 50x. The determination unit 112 may use a maintenance quality level learning model to determine the maintenance quality level for a specific piece of equipment 50x as an output when the measurement data history of the specific piece of equipment 50x and the operating period of the specific piece of equipment 50x are input. The determination unit 112 may use a maintenance quality level learning model to determine the maintenance quality level for a specific piece of equipment 50x as an output when the measurement data history of the specific piece of equipment 50x, additional information of a specific sensor 20x, and the operating period of the specific piece of equipment 50x are input.

[0048] The operating period identification unit 115 identifies the operating period of each sensor 20 based on the measurement data history of each sensor 20. The operating period of a sensor 20 may be the period from the time when the sensor 20 first measures a physical quantity to the time when the sensor 20 last measures a physical quantity, and may be the lifespan of the sensor 20. If the sensor 20 operates on battery power, the operating period of the sensor 20 may be the period from when the power of the sensor 20 is turned on and measurement of the physical quantity begins until the battery charge level decreases and the sensor 20 can no longer measure the physical quantity. Alternatively, the operating period of the sensor 20 may be the period from when the power of the sensor 20 is turned on until the sensor 20 fails.

[0049] The determination unit 112 may determine the predicted operating period of a specific sensor 20x based on the measurement data history of each sensor 20, the operating period of each sensor 20, and the measurement data history of a specific sensor 20x. The learning model generation unit 117 may generate a learning model of the operating period by performing machine learning according to a supervised learning algorithm, using the measurement data history of each sensor 20 of each piece of equipment 50 as explanatory variables and the operating period of each sensor 20 as the objective variable. The determination unit 112 may use the learning model of the operating period to determine the predicted operating period of a specific sensor 20 for the measurement data history of that specific sensor 20x.

[0050] The determination unit 112 may determine the predicted operating period of a specific sensor 20x based on the measurement data history of each sensor 20, the operating period of each sensor 20, additional information of each sensor 20, the measurement data history of a specific sensor 20x, and the additional information of a specific sensor 20x. The additional information of each sensor 20 may include the setting information of each sensor 20, and at least one of the installation location information of each sensor 20 and environmental information of the setting location of each sensor 20. The setting details include, for example, the sensing period of the sensor 20, the measurement data transmission period, and at least one of the amount of measurement data to be transmitted.

[0051] The learning model generation unit 117 may generate a learning model for the operating period by performing machine learning according to a supervised learning algorithm, using the measurement data history of each sensor 20 and the additional information of each sensor 20 as explanatory variables, and the operating period of each sensor 20 as the objective variable. The determination unit 112 may use the learning model for the operating period to determine the predicted operating period of a specific sensor 20x based on the measurement data history and additional information of a specific sensor 20x.

[0052] The predicted operating period of a particular sensor 20x is determined from the operating periods of other sensors 20 used in a similar environment with similar settings. By determining whether the predicted operating period of the particular sensor 20x meets the desired operating period, it is possible to determine whether the settings of the particular sensor 20x are appropriate.

[0053] The display unit 116 displays the predicted operating period of a specific sensor 20x. The display unit 116 may display the predicted operating period of a specific sensor 20x to the terminal 60x of a specific piece of equipment 50x. This allows, for example, the manager of the specific piece of equipment 50x to adjust the sensor 20x to extend its predicted operating period if the predicted operating period is shorter than the desired operating period, by increasing the sensing cycle or transmission cycle of the specific sensor 20x or decreasing the amount of transmitted data. This extends the lifespan of the characteristic sensor 20x.

[0054] The determination unit 112 may determine the settings of a specific sensor 20 so that its operating period satisfies the target operating period, based on the measurement data history of each sensor 20, the operating period of each sensor 20, at least one of the installation location information and environmental information of the installation location of each sensor 20, the settings of each sensor 20, the measurement data history of a specific sensor 20x, at least one of the installation location information and environmental information of the installation location of the specific sensor 20, and the target operating period of the specific sensor 20.

[0055] The learning model generation unit 117 may generate a learning model of the settings by performing machine learning according to a supervised learning algorithm, using the measurement data history of each sensor 20, at least one of the installation location information and environmental information of the installation location of each sensor 20, and the operating period of each sensor 20 as explanatory variables, and the settings of each sensor 20 as the objective variable. The determination unit 112 may use the learning model of the settings to determine the measurement data history of a specific sensor 20x, at least one of the installation location information and environmental information of the installation location of a specific sensor 20x, and the settings of a specific sensor 20x for a target operating period of the specific sensor 20x.

[0056] The abnormal period identification unit 113 identifies the abnormal period based on the history of measurement data from each sensor 20, using a first time t1 when each piece of equipment 50 entered an abnormal state and a second time t2 when each piece of equipment 50 returned from the abnormal state to a normal state.

[0057] The maintenance request unit 114 requests the person in charge of each piece of equipment 50 for the maintenance performed on each piece of equipment 50 from the first time t1 to the second time t2. The maintenance details include the abnormal state of the equipment 50 and the work performed by the maintenance person when the equipment 50 was returned from the abnormal state to the normal state. The acquisition unit 111 acquires the maintenance details entered in response to the request and stores them in the storage unit 120.

[0058] The determination unit 112 determines recommended maintenance for a specific piece of equipment 50x based on the measurement data history of each sensor 20, additional information of each sensor 20, maintenance details of each piece of equipment 50, the measurement data history of a specific piece of equipment 50x, and additional information of a specific sensor 20x. The presentation unit 116 presents the recommended maintenance for the specific piece of equipment 50x. The presentation unit 116 may, for example, present the maintenance details to the terminal 60x of the specific piece of equipment 50x.

[0059] The decision unit 112 may determine recommended maintenance for a specific piece of equipment 50x that meets a target maintenance quality level, based on the measurement data history of each sensor 20, additional information of each sensor 20, the maintenance quality level of each piece of equipment 50, the maintenance content of each piece of equipment 50, the measurement data history of a specific piece of equipment 50x, and the additional information of a specific sensor 20x. The learning model generation unit 117 may generate a learning model of maintenance content by performing machine learning according to a supervised learning algorithm, using the measurement data history of each sensor 20, the additional information of each sensor 20, and the maintenance quality level of each piece of equipment 50 as explanatory variables and the maintenance content of each piece of equipment 50 as the objective variable. The decision unit 112 may use the learning model of maintenance content to determine recommended maintenance content for a specific piece of equipment 50x as an output when the measurement data history of a specific piece of equipment 50x, the additional information of a specific sensor 20x, and the target maintenance quality level are input. The maintenance content includes the work performed during periodic inspections and the work performed to confirm whether each device installed in the equipment 50 is operating normally and whether there are any signs of abnormality. Maintenance details include the timing of periodic inspections.

[0060] The acquisition unit 111 may acquire additional information, including setting information indicating the settings of a specific sensor 20x, in addition to the measurement data history of the specific sensor 20x. The determination unit 112 may determine the maintenance quality level for a specific piece of equipment 50x based on the previously collected setting information of each sensor 20 and the setting information of the specific sensor 20x. The setting information may include at least one of the sensing cycle of the sensor 20, the transmission cycle of the measurement data, and the amount of measurement data, as described above. The learning model generation unit 117 may generate a learning model of the maintenance quality level by performing machine learning according to a supervised learning algorithm, using the measurement data history of each sensor 20 and the additional information including the setting information of each sensor 20 as explanatory variables, and the maintenance quality level of each piece of equipment 50 as the objective variable. The determination unit 112 may use the learning model of the maintenance quality level to determine the maintenance quality level for a specific piece of equipment 50x as the output when the measurement data history of the specific piece of equipment 50x and the additional information including the setting information of the specific sensor 20x are input.

[0061] The presentation unit 116 presents a recommended threshold that serves as a criterion for detecting signs of abnormality in a specific piece of equipment 50x based on measurement data measured by a specific sensor 20x, based on the maintenance quality level of the specific piece of equipment 50x and the maintenance quality levels of each piece of equipment 50 other than the specific piece of equipment 50x. If the maintenance quality level of the specific piece of equipment 50x is lower than the average value of the maintenance quality levels of each piece of equipment 50, the presentation unit 116 may present a threshold lower than the current threshold for the specific piece of equipment 50x as the recommended threshold level. By aligning the threshold that serves as the criterion for detecting signs of abnormality with the threshold set for the piece of equipment 50 with a high maintenance quality level, signs of abnormality in the piece of equipment 50 can be detected early, and failure of the piece of equipment 50 can be prevented more reliably.

[0062] The display unit 116 may display comparative information on maintenance quality levels, showing the maintenance quality level of a comparison target based on the maintenance quality level of each organization, and the maintenance quality level of a specific organization. The maintenance quality level of the comparison target may be the average value of the maintenance quality levels of each organization. The display unit 116 may display the comparative information on maintenance quality levels to the terminal 60x of a specific organization. By comparing the maintenance quality level of the equipment 50x of a specific organization with the maintenance quality levels of other organizations, a relative evaluation of the maintenance quality level of the equipment 50x of a specific organization can be performed.

[0063] The presentation unit 116 may present recommended settings for a specific sensor 20x based on the maintenance quality level of a specific piece of equipment 50x and the maintenance quality levels of each piece of equipment 50 other than the specific piece of equipment 50x. If the maintenance quality level of a specific piece of equipment 50x is lower than the average of the maintenance quality levels of each piece of equipment 50, the presentation unit 116 may present the terminal 60x of the specific piece of equipment 50x with recommended settings for the specific sensor 20x, such as shortening the sensing cycle or transmission cycle of the specific sensor 20x or increasing the amount of transmitted data compared to the current setting.

[0064] Figure 4 is a flowchart illustrating an example of a procedure for indicating the maintenance quality level of specific equipment.

[0065] The acquisition unit 111 acquires the measurement data history from a specific sensor 20x installed on a specific piece of equipment 50x via a relay device 40x of the specific piece of equipment 50x (S100). The determination unit 112 uses a maintenance quality level learning model to determine the maintenance quality level for the specific piece of equipment 50x as an output when the measurement data history of the specific piece of equipment 50x is input (S102). The presentation unit 116 presents the determined maintenance quality level for the specific piece of equipment 50x to the terminal 60x of the specific piece of equipment 50x, etc. (S104).

[0066] Using a learned model that uses measurement history data of other equipment 50 as explanatory variables and the maintenance quality level of other equipment 50 as the dependent variable, the relative maintenance quality level of a specific piece of equipment 50 can be determined. For example, by reviewing the maintenance procedures for equipment 50x and the settings of the sensor 20 according to the maintenance quality level, the failure rate of equipment 50x can be reduced.

[0067] Figure 5 is a flowchart illustrating an example of a procedure for suggesting recommended thresholds for predictive maintenance detection based on the maintenance quality level.

[0068] The acquisition unit 111 acquires the measurement data history from a specific sensor 20x installed on a specific piece of equipment 50x, additional information about the specific sensor 20x, and the operating period of the specific piece of equipment 50x via a relay device 40x of the specific piece of equipment 50x (S200). The determination unit 112 uses a maintenance quality level learning model to determine the maintenance quality level for the specific piece of equipment 50x as an output when the measurement data history of the specific piece of equipment 50x, additional information about the specific sensor 20x, and the operating period of the specific piece of equipment 50x are input (S202).

[0069] Next, the determination unit 112 compares the average maintenance quality level of equipment 50 whose operating period falls within the same time range with the maintenance quality level of the specific equipment 50x (S204). If the maintenance quality level of the specific equipment 50x is equal to or greater than the average maintenance quality level, the presentation unit 116 presents the determined maintenance quality level for the specific equipment 50x to the terminal 60x of the specific equipment 50x (S206).

[0070] On the other hand, if the maintenance quality level of a particular piece of equipment 50x is lower than the average maintenance quality level, the presentation unit 116 presents the maintenance quality level of the particular piece of equipment 50x along with a threshold lower than the current threshold for the particular piece of equipment 50x as a recommended threshold for determining the detection of anomalies (S208). The recommended threshold level may be, for example, the average threshold for determining the detection of anomalies based on the measurement data of each sensor 20 set for each piece of equipment 50 whose operating period is included in the same period range.

[0071] When the operating period is short, the probability of equipment 50 failing is low, and the maintenance quality level can be relatively low. On the other hand, when the operating period is long, the probability of equipment 50 failing is high, and a higher maintenance quality level is preferable. Thus, the appropriate maintenance quality level differs depending on the operating period of equipment 50. Therefore, by determining the appropriate maintenance quality level considering the operating period of equipment 50, it is possible to appropriately set the recommended threshold that serves as the criterion for detecting signs of anomalies. For example, when the operating period is short, the operating period of sensor 20 can be extended by increasing the sensing cycle or the transmission cycle of measurement data of sensor 20, or by decreasing the amount of measurement data transmitted.

[0072] Figure 6 is a flowchart showing an example of a procedure for presenting the predicted operating time of a specific sensor 20x.

[0073] The acquisition unit 111 acquires measurement history data and additional information of the specific sensor 20x from the sensor 20x of the specific equipment 50 (S300). The determination unit 112 uses a learning model of the operating period to determine the predicted operating period of the specific sensor 20x based on the measurement data history and additional information of the specific sensor 20x (S302). The presentation unit 116 presents the determined predicted operating period of the specific sensor 20x to the terminal 60x of the specific equipment 50x, etc. (S304).

[0074] This allows the predicted operating period of a particular sensor 20x to be determined based on the operating periods of other sensors 20 used in a similar environment with the same settings. Depending on the predicted operating period, the operating period of the characteristic sensor 20x can be adjusted by adjusting at least one of the sensing period, the measurement data transmission period, and the amount of measurement data transmitted.

[0075] Figure 7 is a flowchart illustrating an example of a procedure for recommending maintenance to be performed when a malfunction occurs in a specific piece of equipment 50x.

[0076] When the acquisition unit 111 detects that an abnormality has occurred in a specific piece of equipment 50x (S400), it acquires the measurement data history from the sensor 20x of the specific piece of equipment 50x and additional information of the specific sensor 20x (S402). The decision unit 112 uses a maintenance content learning model to determine the recommended maintenance content for the specific piece of equipment 50x as an output when the measurement data history and additional information of the specific sensor 20x of the specific piece of equipment 50x are input (S404). The presentation unit 116 presents the maintenance content to the terminal 60x of the specific piece of equipment 50x (S406).

[0077] If a malfunction occurs in a specific piece of equipment 50x, recommended maintenance procedures for that specific piece of equipment 50x can be suggested based on maintenance records collected in advance from other pieces of equipment 50x that have experienced malfunctions.

[0078] Figure 8 is a flowchart illustrating an example of the procedure for presenting recommended setting information according to the target operating period of a specific sensor 20x.

[0079] The acquisition unit 111 acquires the measurement data history from the sensor 20x of a specific piece of equipment 50x, additional information about the specific sensor 20x, and the target operating period of the specific sensor 20x (S500). The additional information about the specific sensor 20x may include at least one of the installation location information and environmental information of the installation location. Next, the determination unit 112 uses a learning model of the settings to determine the settings of the specific sensor 20x for the target operating period of the characteristic sensor 20x as an output when the measurement data history of the specific sensor 20x, the additional information about the specific sensor 20x, and the target operating period of the specific sensor 20x are input (S502). The presentation unit 116 presents the settings of the specific sensor 20x for the target operating period of the characteristic sensor 20x to the terminal 60x of the piece of equipment 50x (S504).

[0080] This allows the settings of a specific sensor 20x to be appropriately configured to meet the target operating period of that sensor 20x, based on the installation location information and environmental information of the installation location.

[0081] Figure 9 shows an example of a computer 1200 that may embody an aspect of this embodiment in whole or in part. A program installed on the computer 1200 can cause the computer 1200 to function as an operation associated with an apparatus according to an embodiment of the present invention, or as one or more "parts" of said apparatus. Alternatively, the program can cause the computer 1200 to execute said operation or said one or more "parts". The program can cause the computer 1200 to execute a process or a stage of said process according to an embodiment of the present invention. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute a particular operation associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0082] The computer 1200 according to this embodiment includes a CPU 1212 and RAM 1214, which are interconnected by a host controller 1210. The computer 1200 also includes a communication interface 1222 and input / output units, which are connected to the host controller 1210 via an input / output controller 1220. The computer 1200 also includes a ROM 1230. The CPU 1212 operates according to programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit.

[0083] The communication interface 1222 communicates with other electronic devices via a network. A hard disk drive may store programs and data used by the CPU 1212 in the computer 1200. The ROM 1230 stores boot programs and / or programs that depend on the computer 1200's hardware, such as a boot program executed by the computer 1200 upon activation. Programs are provided via computer-readable storage media such as a CR-ROM, USB memory, or IC card, or via a network. Programs are installed in RAM 1214, which is also an example of computer-readable storage media, or in ROM 1230, and executed by the CPU 1212. The information processing described within these programs is read by the computer 1200, resulting in coordination between the programs and the various types of hardware resources described above. An apparatus or method may be configured to implement information operations or processing in accordance with the use of the computer 1200.

[0084] For example, when communication is performed between a computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into RAM 1214 and, based on the processing described in the communication program, instruct the communication interface 1222 to perform communication processing. Under the control of the CPU 1212, the communication interface 1222 reads the transmission data stored in the transmission buffer area provided in RAM 1214 or a storage medium such as a USB memory, sends the read transmission data to the network, or writes the received data received from the network to a receive buffer area or the like provided on the storage medium.

[0085] Furthermore, the CPU 1212 may read all or necessary parts of a file or database stored on an external storage medium such as a USB memory stick into the RAM 1214, and perform various types of processing on the data in the RAM 1214. The CPU 1212 may then write the processed data back to the external storage medium.

[0086] Various types of information, such as various types of programs, data, tables, and databases, may be stored in the storage medium and subjected to information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to the RAM 1214. The CPU 1212 may also retrieve information in files, databases, etc., within the storage medium. For example, if multiple entries are stored in the storage medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 1212 may search among the multiple entries for an entry that matches the condition for which the attribute value of the first attribute is specified, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0087] The programs or software modules described above may be stored on or near computer 1200 in a computer-readable storage medium. Alternatively, a storage medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to computer 1200 via the network.

[0088] Computer-readable media may include any tangible device capable of storing instructions that can be executed by a suitable device. As a result, computer-readable media having instructions stored therein will comprise a product containing instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable media may include floppy disks (registered trademark), diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM (registered trademark)), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital versatile disk (DVD), Blu-ray (RTM) disk, memory stick, integrated circuit card, etc.

[0089] Computer-readable instructions may include either source code or object code written in any combination of one or more programming languages. Source code or object code may include conventional procedural programming languages. These conventional procedural programming languages ​​may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or object-oriented programming languages ​​such as Smalltalk®, Java®, C++, etc., and the "C" programming language or similar programming languages. Computer-readable instructions may be provided locally or via a wide area network (WAN), such as a local area network (LAN) or the internet, to the processor or programmable circuit of a general-purpose computer, a special-purpose computer, or other programmable data processing device. The processor or programmable circuit may execute computer-readable instructions to create means for performing operations specified in a flowchart or block diagram. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0090] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0091] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before," "prior to," etc., and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," "next," etc. for convenience, it does not mean that it is essential to perform the operations in that order. [Explanation of Symbols]

[0092] 10. Equipment Management System 20 sensors 30 Imaging device 40 Relay device 50 Equipment 60 devices 100 Equipment management equipment 110 Control Unit 111 Acquisition Department 112 Decision Section 113 Abnormal Period Identification Section 114 Maintenance content request section 115 Operating period specification section 116 Presentation section 117 Learning Model Generation Unit 120 Storage section 130 Communications Department 1200 Computers 1210 Host Controller 1212 CPU 1214 RAM 1220 Input / Output Controller 1222 Communication Interface 1230 ROM

Claims

1. An acquisition unit that acquires the measurement data history of a specific equipment to be measured, measured by a specific sensor, A determination unit determines the maintenance quality level for a specific piece of equipment based on the measurement data history of each piece of equipment measured by each sensor collected in advance, the maintenance quality level for each piece of equipment, and the measurement data history of the specific piece of equipment. A facility management device equipped with the following features.

2. The acquisition unit further acquires additional information related to the specific sensor, The equipment management device according to claim 1, wherein the determination unit determines the maintenance quality level for the specific equipment to be measured based on additional information about each of the sensors collected in advance and additional information about the specific sensor.

3. The acquisition unit further acquires the operating period of the specific equipment to be measured, The equipment management device according to claim 1, wherein the determination unit determines the maintenance quality level for the specific equipment to be measured based on the operating period of each equipment to be measured, which has been collected in advance, and the operating period of the specific equipment to be measured.

4. The equipment management device according to claim 1, further comprising a display unit that displays recommended thresholds that serve as criteria for determining abnormality in the specific equipment to be measured, based on measurement data measured by the specific sensor, based on the maintenance quality level of the specific equipment to be measured and the respective maintenance quality levels for each of the equipment to be measured.

5. The equipment management device according to claim 4, wherein the display unit, when the maintenance quality level of a particular piece of equipment to be measured is lower than the average value of the maintenance quality levels of each piece of equipment to be measured, displays a threshold lower than the current threshold for the particular piece of equipment to be measured as a recommended threshold.

6. The acquisition unit further acquires additional information related to the specific sensor, The equipment management device according to claim 1, wherein the determination unit determines the predicted operating period of a specific sensor based on the measurement data history of each sensor, the operating period of each sensor identified based on the measurement data history of each sensor, additional information of each sensor collected in advance, the measurement data history of the specific sensor, and the additional information of the specific sensor.

7. An abnormal period identification unit identifies the abnormal period based on the history of measurement data from each of the aforementioned sensors, from a first time when each of the measurement target equipment entered an abnormal state and a second time when each of the measurement target equipment returned from the abnormal state to a normal state. The system includes a maintenance content request unit that requests the maintenance content performed on each of the measurement target equipment from the first time to the second time, The acquisition unit acquires the maintenance details entered in response to the request, The determination unit determines recommended maintenance for the specific equipment to be measured based on the measurement data history of each sensor, additional information related to each sensor, maintenance details for each equipment to be measured, the measurement data history of the specific equipment to be measured, and additional information related to the specific sensor. The aforementioned equipment management device is The equipment management device according to claim 2, further comprising a display unit that displays recommended maintenance procedures for the aforementioned specific equipment to be measured.

8. The equipment management device according to any one of claims 2, 6, and 7, wherein the additional information includes at least one of the following: identification information of the equipment to be measured, a method of mounting the sensor, information on the location where the sensor is installed, setting information indicating the settings of the sensor, and environmental information of the location where the sensor is installed.

9. The acquisition unit further acquires additional information related to the specific sensor and the target operating period of the specific sensor. The additional information includes the sensor setting information and at least one of the sensor installation location information and the environmental information of the sensor setting location. The equipment management device according to claim 1, wherein the determination unit determines the setting content of the specific sensor so that the operating period of the specific sensor satisfies the target operating period, based on the measurement data history of each sensor, the operating period of each sensor identified based on the measurement data history of each sensor, the additional information of each sensor, the measurement data history of the specific sensor, at least one of the setting location information and environmental information of the setting location of the specific sensor, and the target operating period of the specific sensor.

10. The equipment management device according to claim 1, wherein the determination unit determines the maintenance quality level of a specific piece of equipment to be measured as an output when the measurement data history of that specific piece of equipment to be measured is input, using a learning model that has been learned with the measurement data history as input and each maintenance quality level as output.

11. The equipment management device according to claim 1, wherein the determination unit uses a learning model that has been learned with the measurement data history as input and the maintenance quality levels of each organization that manages each of the equipment to be measured as output to determine the maintenance quality level of a specific organization that manages a specific equipment to be measured when the measurement data history of the specific equipment to be measured is input as the maintenance quality level for the specific equipment to be measured.

12. Each of the aforementioned measurement target facilities is managed by the respective organization. The determination unit determines the maintenance quality level for the specific target equipment managed by the specific organization, based on the measurement data history of each target equipment measured by the sensors installed on each target equipment of each organization, which have been collected in advance, and the maintenance quality level for each target equipment, and the measurement data history measured by the specific sensor installed on the specific target equipment of the specific organization. The aforementioned equipment management device is The equipment management device according to claim 1, further comprising a display unit that displays information indicating the maintenance quality level of a comparison target based on the maintenance quality level of each of the aforementioned organizations, and the maintenance quality level of the specific equipment to be measured that is managed by the specific organization.

13. The equipment management device according to claim 12, wherein the maintenance quality level of the comparison target is the average value of the maintenance quality levels of each organization.

14. The acquisition unit acquires the measurement data history of a specific equipment to be measured, measured by a specific sensor. The determination unit determines the maintenance quality level for a specific piece of equipment based on the measurement data history of each piece of equipment to be measured measured by each sensor collected in advance, the maintenance quality level for each piece of equipment to be measured, and the measurement data history of the specific piece of equipment to be measured. A facility management method that includes the following features.

15. When executed by a computer, An acquisition unit that acquires the measurement data history of a specific equipment to be measured, measured by a specific sensor, A determination unit determines the maintenance quality level for a specific piece of equipment based on the measurement data history of each piece of equipment measured by each sensor collected in advance, the maintenance quality level for each piece of equipment, and the measurement data history of the specific piece of equipment. A program to make the aforementioned computer function.

Images