Apparatus, method, and program

Abstract

To provide a device, a method, and a program for detecting a sign of failure in state of an object which is at least one portion of own vessel.SOLUTION: A device is provided including: an index value acquirement unit for successively acquiring a state index value indicating quality of state of an object which is at least one portion of own vessel; a frequency acquirement unit for acquiring at least one of frequency for rocking of own vessel and frequency of waves imparting external force to own vessel; a filtering unit for eliminating noise of frequency component acquired by the index value acquirement unit from transition in the state index value acquired by the index value acquirement unit; and a detection unit for detecting a sign of failure in state of the object based on the transition of the state index value with noise eliminated by the filtering unit.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an apparatus, a method, and a program.

Background Art

[0002] Patent Documents 1 to 4 describe "a functional diagnosis method for diagnosing the soundness of onboard equipment of a ship, which steers the ship according to a predetermined sequence during operation of the ship, compares the expected change in the operation of the onboard equipment with the change in the operation accompanying the steering of the onboard equipment, and diagnoses the soundness of the onboard equipment." (Claim 1 of Patent Document 1) etc. [Prior Art Documents] [Patent Documents] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2002-326598 [Patent Document 2] Japanese Unexamined Patent Application Publication No. 2021-189803 [Patent Document 3] Japanese Unexamined Patent Application Publication No. 2020-158074 [Patent Document 4] Japanese Unexamined Patent Application Publication No. 2010-89550

Summary of the Invention

[0003] In a first aspect of the present invention, there is provided an apparatus including: an index value acquisition unit that sequentially acquires a state index value indicating whether the state of a target, which is at least a part of the own ship, is good or bad; a frequency acquisition unit that acquires at least one of the frequency of the sway of the own ship or the frequency of a wave applying an external force to the own ship; a filtering unit that removes noise of a frequency component acquired by the index value acquisition unit from the transition of the state index value acquired by the index value acquisition unit; and a detection unit that detects a sign that the state of the target becomes bad based on the transition of the state index value from which noise has been removed by the filtering unit.

[0004] In the apparatus according to the first aspect, the detection unit may detect the sign by comparing a moving average of the state index value with a preset threshold value.

[0005] In the apparatus of the first embodiment, the detection unit may detect the warning sign by comparing the variance of the state index value over the most recent period with the reference variance.

[0006] In any of the above-described devices, a measurement data acquisition unit is further provided to acquire at least one type of measurement data indicating the state of the target, and the index value acquisition unit may acquire a state index value from the measurement data acquired by the measurement data acquisition unit.

[0007] In the above-described apparatus, the index value acquisition unit may acquire a state index value corresponding to the measurement data acquired by the measurement data acquisition unit, using a model that outputs a state index value in response to the input of measurement data.

[0008] A second embodiment of the present invention provides a method comprising: an index value acquisition step of sequentially acquiring a state index value indicating the quality of the state of an object which is at least a part of the vessel; a frequency acquisition step of acquiring at least one of the frequency of the vessel's motion or the frequency of waves applying an external force to the vessel; a filtering step of removing noise from the frequency components acquired in the index value acquisition step from the transition of the state index value acquired in the index value acquisition step; and a detection step of detecting signs that the state of the object will deteriorate based on the transition of the state index value from which the noise has been removed in the filtering step.

[0009] In a third aspect of the present invention, a program is provided that causes a computer to function as an index value acquisition unit that sequentially acquires a state index value indicating whether the state of an object that is at least a part of the ship is good or bad; a frequency acquisition unit that acquires at least one of the frequency of the ship's oscillation or the frequency of waves that apply an external force to the ship; a filtering unit that removes noise from the frequency components acquired by the index value acquisition unit from the transition of the state index value acquired by the index value acquisition unit; and a detection unit that detects signs of the object's state deteriorating based on the transition of the state index value from which the noise has been removed by the filtering unit.

[0010] It should be noted that the above summary of the invention does not enumerate all the necessary features of the present invention. Furthermore, subcombinations of these features may also constitute an invention. [Brief explanation of the drawing]

[0011] [Figure 1] System 1 according to an embodiment is shown. [Figure 2] The function of the filtering unit 25 is shown. [Figure 3] This demonstrates the operation of device 2. [Figure 4] Examples of a computer 2200 in which multiple aspects of the present invention may be embodied in whole or in part are shown. [Modes for carrying out the invention]

[0012] The present invention will be described below through embodiments, but these embodiments are not intended to limit the scope of the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0013] <1. System 1> Figure 1 shows System 1 according to this embodiment. System 1 is installed on a ship (also referred to as the ship itself) and detects signs that the condition of the target 10 on the ship is deteriorating. System 1 may include one or more first sensors 11, one or more second sensors 12, and a device 2.

[0014] Here, the vessel may be any of the following: a passenger ship, a cargo ship (for example, an LNG tanker or container ship), a fishing vessel (for example, a whaling ship or trawler), a workboat (for example, a tugboat), or a warship.

[0015] The object 10 on the ship may be at least a part of the ship, the whole ship, or a part of the ship. For example, the object 10 may be equipment such as a valve, pump, fan, engine, or generator that controls at least one physical quantity, such as the ship's speed.

[0016] <1.1. First Sensor 11> Each first sensor 11 measures the state of the object 10. Each first sensor 11 may measure at least one physical quantity such as pressure, temperature, velocity, or flow rate. Each first sensor 11 may also measure the operating status of the object 10. If multiple first sensors 11 are provided in the system 1, each first sensor 11 may be of a different type, or at least two or more of the first sensors 11 may be of the same type. In this embodiment, as an example, each first sensor 11 is described as being provided on the object 10, but they may also be provided outside the object 10. Each first sensor 11 may supply measurement data to the device 2.

[0017] <1.2. Second Sensor 12> Each second sensor 12 measures the frequency of the ship's motion or the frequency of waves applying an external force to the ship. For example, the second sensor 12 may have an acceleration sensor to measure the ship's motion and calculate the frequency from the progression of the ship's motion. The second sensor 12 may have a wave height meter to measure the wave height around the ship and calculate the wave frequency from the progression of the wave height. The second sensor 12 may have a pressure sensor to measure the water pressure on the outer surface of the ship (for example, the side of the ship) and calculate the wave frequency from the progression of the water pressure. In this embodiment, the second sensor 12 is described as being different from the first sensor 11 as an example, but it may be the same sensor as the first sensor 11. Each second sensor 12 may supply the measured frequency to the device 2.

[0018] <1.3.Device 2> The device 2 comprises a measurement data acquisition unit 21, an index value acquisition unit 22, a model 23, a frequency acquisition unit 24, a filtering unit 25, a detection unit 26, and a display unit 27.

[0019] <1.3.1. Measurement Data Acquisition Unit 21> The measurement data acquisition unit 21 acquires at least one type of measurement data indicating the state of the target 10. The measurement data acquisition unit 21 may sequentially acquire measurement data from each first sensor 11. The measurement data acquisition unit 21 may supply the acquired measurement data to the index value acquisition unit 22.

[0020] <1.3.2. Index value acquisition unit 22> The index value acquisition unit 22 sequentially acquires state index values indicating whether the state of the target 10 is good or bad. The index value acquisition unit 22 may acquire state index values from the measurement data acquired by the measurement data acquisition unit 21. For example, the index value acquisition unit 22 may use the model 23 described later to acquire state index values corresponding to the measurement data acquired by the measurement data acquisition unit 21. In this embodiment, as an example, the index value acquisition unit 22 may acquire state index values from the model 23 in response to supplying the measurement data to the model 23. The index value acquisition unit 22 may supply the acquired state index values to the filtering unit 25.

[0021] <1.3.3. Model 23> The model 23 outputs a state index value indicating whether the state of the target 10 is good or bad in response to the input of measurement data. The model 23 may output a state index value to the index value acquisition unit 22 in response to the supply of measurement data from the index value acquisition unit 22.

[0022] The model 23 may output a state index value (also referred to as a health index) that is not binarized into a value indicating that the state of the target 10 is good and a value indicating that it is bad. For example, the model 23 may be one learned using two values, a value indicating that the state of the target 10 is good and a value indicating that the state of the target 10 is bad, and may output a state index value before binarization by comparison with a threshold value. In this embodiment, as an example, the model 23 may output a positive value as the state index value when the state of the target 10 is good (or close to good), and may output a negative value as the state index value when the state of the target 10 is bad (or close to bad).

[0023] Model 23 may be, for example, a support vector machine, but it may also be a pre-trained model using other algorithms such as logistic regression, decision trees, or neural networks. Model 23 may be trained using measurement data labeled to indicate that the state of object 10 is good, and measurement data labeled to indicate that the state of object 10 is poor. The measurement data used for training may be measured in advance by the first sensor 11 when the state of object 10 is good or poor, or it may be generated using a simulator of object 10.

[0024] <1.3.4. Frequency Acquisition Unit 24> The frequency acquisition unit 24 acquires at least one of the frequencies of the ship's motion or the frequencies of the waves applying external force to the ship. The frequency acquisition unit 24 may acquire frequencies sequentially from each of the second sensors 12. The frequency acquisition unit 24 may supply data indicating each acquired frequency to the filtering unit 25.

[0025] <1.3.5. Filtering Section 25> The filtering unit 25 removes noise from the frequency components acquired by the frequency acquisition unit 24 from the state index value transitions acquired by the index value acquisition unit 22. This removes noise caused by the ship's movement and waves from the state index value transitions. The filtering unit 25 may supply the noise-free state index value transitions to the detection unit 26.

[0026] <1.3.6. Detection Unit 26> The detection unit detects signs of a deterioration in the state of the target 10 based on the changes in the state index value from which noise has been removed by the filtering unit 25. For example, the detection unit 26 may detect signs by comparing the variance of the state index value over the most recent period with the reference variance. In this embodiment, as an example, the detection unit 26 may detect that there are signs when the variance over the most recent reference period becomes larger than the reference variance. The reference period and reference variance may be set arbitrarily. The detection unit 26 may supply the detection result of the signs to the display unit 27.

[0027] <1.3.7.Display section 27> The display unit 27 displays various information. For example, the display unit 27 may display the results of the detection of anomalies by the detection unit 26.

[0028] According to the device 2 described above, noise from at least one of the frequency components of either the ship's oscillation frequency or the wave frequency that applies external force to the ship is removed from the trend of the state index value, and signs of a poor state in the target 10 are detected. Therefore, even if noise from at least one of the ship's oscillation or waves is included in the trend of the state index value, signs of a poor state can be detected with high accuracy.

[0029] Furthermore, since a state index value is obtained from at least one type of measurement data indicating the state of the target 10, it is possible to obtain a state index value corresponding to the state of the target 10.

[0030] Furthermore, since a state index value corresponding to the measurement data is obtained using Model 23, which outputs a state index value in response to input measurement data, the state index value can be obtained by supplying the measurement data to Model 23.

[0031] Furthermore, since the variance of the state index value over the most recent period is compared with the baseline variance to detect warning signs, it is possible to detect warning signs in response to fluctuations and variability in the state index value.

[0032] <2. Filtering section 25> Figure 2 shows the function of the filtering unit 25. In the figure, the waveforms on the left and right show the changes in state index values ​​before and after input to the filtering unit 25, for each frequency component. As shown in this figure, the filtering unit 25 may be a bandstop filter (also called a band-rejection filter), and may attenuate and remove the components of each frequency band acquired by the frequency acquisition unit 24 (the frequency components of the waveform in the middle of the figure) from among the frequency components included in the changes in state index values.

[0033] <3.Operation> Figure 3 shows the operation of device 2. Device 2 assists in monitoring the target 10 through the processing in steps S11 to S23. This operation may start when device 2 is activated.

[0034] In step S11, the measurement data acquisition unit 21 acquires at least one type of measurement data indicating the state of the target 10. The measurement data acquisition unit 21 may acquire measurement data from each of the first sensors 11.

[0035] In step S13, the index value acquisition unit 22 supplies the acquired measurement data to the model 23. As a result, the model 23 outputs a state index value corresponding to the measurement data. In this embodiment, as an example, the model 23 may output an un-binarized state index value. Furthermore, the model 23 may output a state index value corresponding to measurement data measured at a single point in time, or it may output a state index value corresponding to time-series measurement data measured at multiple points in time.

[0036] In step S15, the index value acquisition unit 22 acquires a state index value indicating whether the state of the target 10 is good or bad. As a result, the state index value is acquired sequentially by repeating the process in step S15. In this embodiment, as an example, the index value acquisition unit 22 may acquire the state index value from the model 23.

[0037] In step S17, the frequency acquisition unit 24 acquires at least one of the frequencies of the ship's motion or the frequencies of the waves applying external force to the ship. The frequency acquisition unit 24 may acquire at least one frequency from each of the second sensors 12. Note that the processing in step S17 may be performed before step S11 or between steps S11 to S15.

[0038] In step S19, the filtering unit 25 removes noise from the frequency components acquired by the frequency acquisition unit 24 from the transition of the state index value acquired by the index value acquisition unit 22. The filtering unit 25 may also remove noise from the components of each frequency acquired by the processing of one or more steps S17 from the transition of the state index value acquired by the processing of one or more steps S15.

[0039] In step S21, the detection unit 26 detects signs of the target 10 becoming unhealthy based on the changes in the state index values ​​from which noise has been removed by the processing in step S19. For example, the detection unit 26 may detect signs by comparing the variance of the state index values ​​over the most recent period with the reference variance.

[0040] In step S23, the display unit 27 displays the result of detecting a precursor. The display unit 27 may further display the denoised state index value output from the filtering unit 25. The display unit 27 may further display at least one measurement data acquired by the measurement data acquisition unit 21. Once the processing in step S23 is completed, the process may proceed to step S11 described above.

[0041] <4. Variation> In the above embodiment, the device 2 was described as comprising a measurement data acquisition unit 21, a model 23, and a display unit 27, but it may be omitted from the device. If the device 2 does not include a measurement data acquisition unit 21, the index value acquisition unit 22 may acquire the state index value from outside the device 2. If the device 2 does not include a model 23, the index value acquisition unit 22 may acquire the state index value by supplying measurement data to a model 23 stored in an external storage device. If the device 2 does not include a display unit 27, the detection unit 26 may output the detection result to an external display device or alarm device. The alarm device may emit an alarm sound when an indication of a malfunction is detected.

[0042] Furthermore, although the filtering unit 25 was described as removing the components of each frequency acquired by the frequency acquisition unit 24 from the state index value transition, it is also possible to remove only some of the frequency components acquired by the frequency acquisition unit 24. For example, the frequency acquisition unit 24 may acquire the number of second sensors 12 that measured a frequency along with the frequency measured by the second sensor 12, and the filtering unit 25 may select a reference number of frequencies from among the multiple measured frequencies for which the number of second sensors 12 that measured is large, and remove its components from the state index value transition. In this case, noise components that have a large influence on the fluctuation of the state index value can be efficiently removed.

[0043] Furthermore, although the indicator value acquisition unit 22 was described as acquiring a state indicator value for a single target 10 on the vessel, it may also acquire state indicator values ​​for multiple targets 10. In this case, the filtering unit 25 may remove noise of common frequency components from the trend of the state indicator values ​​for each target 10, and the detection unit 26 may detect signs of poor condition for each target 10.

[0044] Furthermore, although the detection unit 26 was described as detecting an early warning by comparing the variance of the state index value over the most recent period with the reference variance, it may also detect an early warning by comparing the moving average of the state index value with a preset threshold. The moving average of the state index value may be the moving average of the state index values ​​output from the model 23 within the reference period, and for example, it may be the moving average of the state index values ​​output within the most recent reference period. The reference period (also called the time window) for calculating the moving average may be set to any length (for example, 10 minutes). When an early warning is detected by comparing the moving average of the state index value with a threshold, it is possible to prevent the detection of an early warning from becoming unstable as the state index value fluctuates around the threshold. Here, the threshold may be set based on the boundary value between the state index value indicating that the target 10 is in a good state and the state index value indicating that the target 10 is in a bad state. For example, if the state index value indicating that object 10 is in a good state is positive, the state index value indicating that object 10 is in a poor state is negative, and the boundary value is zero, then the threshold may be a positive value obtained by adding a reference margin to zero.

[0045] Furthermore, various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where a block may represent (1) a stage in a process in which an operation is performed or (2) a section of a device having the role of performing an operation. Specific stages and sections may be implemented by dedicated circuits, programmable circuits supplied with computer-readable instructions stored on a computer-readable medium, and / or processors supplied with computer-readable instructions stored on a computer-readable medium. Dedicated circuits may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuits may include reconfigurable hardware circuits, including logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logic operations, flip-flops, registers, memory elements such as field-programmable gate arrays (FPGAs), programmable logic arrays (PLAs), etc.

[0046] Computer-readable media may include any tangible device capable of storing instructions to be executed by a suitable device, and 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, 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), 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.

[0047] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and traditional procedural programming languages ​​such as the C programming language or similar programming languages.

[0048] 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 a processor or programmable circuit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, and these instructions may be executed 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, and the like.

[0049] Figure 4 shows an example of a computer 2200 in which multiple aspects of the present invention may be embodied in whole or in part. A program installed on the computer 2200 can cause the computer 2200 to function as an operation or one or more sections of an apparatus according to an embodiment of the present invention, or to execute such operation or one or more sections, and / or to cause the computer 2200 to execute a process or a stage of such process according to an embodiment of the present invention. Such a program may be executed by the CPU 2212 to cause the computer 2200 to perform a particular operation associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0050] The computer 2200 according to this embodiment includes a CPU 2212, RAM 2214, a graphics controller 2216, and a display device 2218, which are interconnected by a host controller 2210. The computer 2200 also includes input / output units such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the host controller 2210 via an input / output controller 2220. The computer also includes legacy input / output units such as a ROM 2230 and a keyboard 2242, which are connected to the input / output controller 2220 via an input / output chip 2240.

[0051] The CPU 2212 operates according to programs stored in the ROM 2230 and RAM 2214, thereby controlling each unit. The graphics controller 2216 retrieves image data generated by the CPU 2212 from a frame buffer provided in RAM 2214 or from itself, and displays the image data on the display device 2218.

[0052] The communication interface 2222 communicates with other electronic devices via a network. The hard disk drive 2224 stores programs and data used by the CPU 2212 in the computer 2200. The DVD-ROM drive 2226 reads programs or data from the DVD-ROM 2201 and provides them to the hard disk drive 2224 via the RAM 2214. The IC card drive reads programs and data from the IC card and / or writes programs and data to the IC card.

[0053] The ROM 2230 stores boot programs and / or programs that depend on the computer 2200's hardware, which are executed by the computer 2200 when activated. The input / output chip 2240 may also connect various input / output units to the input / output controller 2220 via parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0054] The program is provided on a computer-readable medium such as a DVD-ROM 2201 or an IC card. The program is read from the computer-readable medium and installed on a hard disk drive 2224, RAM 2214, or ROM 2230, which are also examples of computer-readable medium, and executed by the CPU 2212. The information processing described within these programs is read by the computer 2200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the manipulation or processing of information in accordance with the use of the computer 2200.

[0055] For example, when communication is performed between a computer 2200 and an external device, the CPU 2212 may execute a communication program loaded into RAM 2214 and, based on the processing described in the communication program, instruct the communication interface 2222 to perform communication processing. Under the control of the CPU 2212, the communication interface 2222 reads transmission data stored in a transmission buffer processing area provided in a recording medium such as RAM 2214, a hard disk drive 2224, a DVD-ROM 2201, or an IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer processing area provided on the recording medium.

[0056] Furthermore, the CPU 2212 may read all or necessary parts of files or databases stored on external storage media such as the hard disk drive 2224, DVD-ROM drive 2226 (DVD-ROM 2201), or IC card into the RAM 2214, and perform various types of processing on the data in the RAM 2214. The CPU 2212 then writes the processed data back to the external storage media.

[0057] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 2212 may perform various types of processing on the data read from RAM 2214, 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 RAM 2214. The CPU 2212 may also retrieve information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 2212 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.

[0058] The programs or software modules described above may be stored on or near computer 2200 on a computer-readable medium. Alternatively, recording media such as hard disks or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as computer-readable media, thereby providing programs to computer 2200 via the network.

[0059] 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.

[0060] 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]

[0061] 1 System 2 equipment 10 Target 11. First Sensor 12. Second Sensor 21 Measurement data acquisition unit 22. Indicator Value Acquisition Section 23 Models 24 Frequency acquisition unit 25 Filtering section 26 Detection unit 27 Display section 2200 Computers 2201 DVD-ROM 2210 Host Controller 2212 CPU 2214 RAM 2216 Graphics Controller 2218 Display Devices 2220 Input / Output Controller 2222 Communication Interface 2224 Hard Disk Drive 2226 DVD-ROM drive 2230 ROM 2240 Input / Output Chip 2242 keyboard

Claims

1. An index value acquisition unit that sequentially acquires a condition index value indicating the goodness or badness of the condition of at least a part of the vessel, A frequency acquisition unit that acquires at least one of the frequency of the ship's motion or the frequency of the waves applying an external force to the ship, Based on the transition of the state index value acquired by the index value acquisition unit, a noise removal filtering unit for the frequency component acquired by the frequency acquisition unit is used, A detection unit detects signs that the target state will deteriorate based on the changes in the state index value from which noise has been removed by the filtering unit, Equipped with, The frequency acquisition unit acquires multiple frequencies using multiple sensors, each of which measures frequency. The filtering unit is a device that removes noise from the frequency components of only a reference number of frequencies among the multiple frequencies, where the number of measured sensors is large.

2. The apparatus according to claim 1, wherein the detection unit detects the warning sign by comparing the moving average of the state index value with a preset threshold.

3. The apparatus according to claim 1, wherein the detection unit detects the warning sign by comparing the variance of the state index value over the most recent period with the reference variance.

4. The system further includes a measurement data acquisition unit that acquires at least one type of measurement data indicating the state of the target, The apparatus according to any one of claims 1 to 3, wherein the index value acquisition unit acquires a state index value from the measurement data acquired by the measurement data acquisition unit.

5. The apparatus according to claim 4, wherein the index value acquisition unit acquires a state index value corresponding to the measurement data acquired by the measurement data acquisition unit, using a model that outputs a state index value in response to the input of measurement data.

6. An index value acquisition stage in which a condition index value indicating the goodness or badness of the condition of at least a part of the vessel is successively acquired, A frequency acquisition step in which at least one of the frequency of the ship's motion or the frequency of the wave applying an external force to the ship is obtained, A filtering step is performed to remove noise from the frequency components obtained in the frequency acquisition step, based on the changes in the state index values ​​obtained in the index value acquisition step. A detection step in which, based on the changes in the state index value from which noise has been removed by the filtering step, a precursor to a deterioration in the state of the target is detected, Equipped with, In the frequency acquisition stage, multiple frequencies are acquired using multiple sensors, each measuring a frequency. In the filtering stage, the noise of the frequency component is removed only for a reference number of frequencies among the multiple frequencies, where the number of measured sensors is large.

7. Computers, An index value acquisition unit that sequentially acquires a condition index value indicating the goodness or badness of the condition of at least a part of the vessel, A frequency acquisition unit that acquires at least one of the frequency of the ship's motion or the frequency of the waves applying an external force to the ship, Based on the transition of the state index value acquired by the index value acquisition unit, a noise removal filtering unit for the frequency component acquired by the frequency acquisition unit is used, A detection unit detects signs of the target being in a bad state based on the trend of the state index value from which noise has been removed by the filtering unit. To make it function as, The frequency acquisition unit acquires multiple frequencies using multiple sensors, each of which measures frequency. The filtering unit is a program that removes noise from the frequency components of only the reference number of frequencies among the multiple frequencies that have been measured by a large number of sensors.

Images