WO2011048661A1 - 建設機械の診断システム及び診断方法 - Google Patents
建設機械の診断システム及び診断方法 Download PDFInfo
- Publication number
- WO2011048661A1 WO2011048661A1 PCT/JP2009/068038 JP2009068038W WO2011048661A1 WO 2011048661 A1 WO2011048661 A1 WO 2011048661A1 JP 2009068038 W JP2009068038 W JP 2009068038W WO 2011048661 A1 WO2011048661 A1 WO 2011048661A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- diagnostic
- data
- diagnosis
- knowledge
- acquired
- Prior art date
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02F—DREDGING; SOIL-SHIFTING
- E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
- E02F9/20—Drives; Control devices
- E02F9/2025—Particular purposes of control systems not otherwise provided for
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02F—DREDGING; SOIL-SHIFTING
- E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
- E02F9/26—Indicating devices
- E02F9/267—Diagnosing or detecting failure of vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Definitions
- the present invention relates to a system and method for diagnosing the state of a construction machine, and more specifically, a user who has little knowledge of procedures and methods for diagnosing a state performs effective diagnosis according to data to be diagnosed.
- System and diagnostic method for construction machines capable of
- Patent Document 1 A technology that can easily obtain knowledge about past defects by storing the characteristics of products designed in the past and the number of defects that occurred in those products in a database and searching the database at the time of design are known (see, for example, Patent Document 1).
- Patent Document 2 there is known a technique of accumulating combinations of data analysis purpose and analysis method in a database and presenting an analysis method according to an analysis purpose input from a user at the time of data analysis (see, for example, Patent Document 2).
- the technology for storing and presenting the combination of the product characteristics and the number of failures in the past to the user is a technology for supporting the design time, and can not be applied to the diagnosis of the condition of the construction machine. Also, in the technology that presents an analysis method based on the analysis purpose of data, if there are multiple analysis methods that correspond to the analysis purpose, the user must select an appropriate analysis method. In some cases, there is a problem in that a non-optimized analysis method is selected, and the time required to obtain the correct analysis result increases.
- An object of the present invention is to provide a diagnostic system for a construction machine which enables a user having little knowledge about procedures and methods for diagnosing a construction machine to execute diagnosis suitable for data characteristics of a device to be diagnosed in a short time. And providing a diagnostic method.
- the present invention acquires a data characteristic of input diagnostic data when the diagnosis is performed by the diagnostic device, and a diagnostic knowledge storage device which is considered to be effective for the characteristic. Obtain a diagnosis from the diagnostic device
- the diagnostic device acquires diagnostic data from the diagnostic data storage device, and includes the number of parameters included in the data, the type of sensor of each parameter, the characteristics of the parameters, etc. from the information included in the diagnostic data Data characteristics are extracted, diagnostic methods considered to be effective for diagnostic purposes and data characteristics are obtained from the diagnostic knowledge storage device, and presented to the user along with the effectiveness calculated from the number of cases matching the data characteristics and the number of cases. . Then, the user selects a diagnostic method based on the degree of effectiveness and makes a diagnosis.
- a combination of data characteristics of diagnostic data as a target of diagnosis and a diagnostic method effective for diagnosis of the data is stored in a diagnostic knowledge storage device as diagnostic knowledge.
- FIG. 1 is a block diagram of a construction machine diagnostic system to which an embodiment of the present invention is applied.
- a diagnostic device 10 In the diagnostic system of the present embodiment, as illustrated in FIG. 1, a diagnostic device 10, a diagnostic knowledge storage device 20, and a diagnostic data storage device 30 are mutually connected.
- the diagnostic device 10 inputs data and information from the outside, and outputs an input / output unit 101 that outputs a result, a diagnostic data acquisition unit 102 that acquires diagnostic data from the diagnostic data storage device 30, and diagnosis from the acquired diagnostic data
- a diagnostic knowledge input having a function of a data characteristic acquisition unit 103 for acquiring characteristics of data and a diagnostic knowledge acquisition unit 104A for acquiring from the diagnostic knowledge storage device 20 a diagnostic method adapted to the data characteristics acquired by the data characteristic acquisition unit An output unit 104; and a diagnosis unit 105 for performing diagnosis using the diagnosis data acquired by the diagnosis data acquisition unit 102 and the diagnosis method acquired by the diagnosis knowledge input / output unit 104 (diagnosis knowledge acquisition unit 104A).
- the input / output unit 101 is a display device 101A for displaying various screens related to diagnosis such as a diagnosis initial screen (FIG. 12), a screen after diagnosis knowledge search (FIG. 12), a diagnosis result screen (FIG. 13), a keyboard and a mouse And other input devices.
- the diagnostic unit 105 diagnoses the combination of the characteristic of the diagnostic data and the used diagnostic method as new diagnostic knowledge from the diagnostic knowledge input / output unit 104 when the used diagnostic method included in the diagnostic knowledge is effective after the execution of the diagnosis. It further has a function of storing in the knowledge storage device 20.
- the diagnostic device 10 includes an effectiveness calculation unit 106 that calculates the effectiveness of the diagnostic method acquired by the diagnostic knowledge input / output unit 104 (diagnosis knowledge acquisition unit 104A), and diagnostic knowledge stored in the diagnostic knowledge storage device 20. Collecting diagnostic knowledge including each element of the common diagnostic method (described later) from among the items, common diagnosis among components of data characteristics included in the collected diagnostic knowledge and combination of the diagnostic method elements with new diagnosis It further includes a diagnostic knowledge generation unit 107 which is generated as knowledge and stored in the diagnostic knowledge storage device 20.
- the diagnostic knowledge storage device 20 includes a data transmission / reception unit 201 that transmits / receives data to / from the diagnostic device 10, and a diagnostic knowledge storage unit 202 that stores the diagnostic knowledge including the data characteristics and the diagnostic method.
- the diagnostic data storage device 30 includes a data transmission / reception unit 301 that transmits / receives data to / from the diagnostic device 10, and a diagnostic data storage unit 302 that stores diagnostic data such as operation data of the device and sensor information.
- FIG. 2 is a diagram illustrating the hardware configuration of the diagnostic device 10.
- the diagnostic device 10 includes a communication device 11, an input / output device 12, a storage device 13, a CPU 14, a memory 15, and a reading device 16, which are connected by an internal communication line 18 such as a bus. .
- the input / output device 12 corresponds to the input / output unit 101 of FIG. 1 and includes an input device such as a display device, a keyboard, and a mouse as described above.
- the configuration shown in FIG. 2 is the same as in the diagnostic knowledge storage device 20 and the diagnostic data storage device 30.
- each program stored in the storage device of each of the devices 10, 20, and 30 is loaded into the memory and executed by the CPU to execute on each of the devices 10, 20, and 30 configuring the diagnostic system. It is executed by each processing unit embodied. Also, each program may be stored in advance in a storage device, or may be introduced as needed via another storage medium or communication medium (network or carrier wave propagating through the network).
- FIG. 3 is a diagram showing a diagnostic flow executed among the diagnostic device 10, the diagnostic data storage device 30, and the diagnostic knowledge storage device 20.
- the diagnostic device 10 displays a diagnostic initial screen on the display device 101A of the input / output unit 101 (step S301 (hereinafter simply referred to as S301. The same applies to the following)).
- the diagnosis initial screen is a screen having the items shown in FIG. 12, and the details will be described later.
- the user inputs a diagnostic purpose into the input / output unit 101 of the diagnostic device 10 using the diagnostic initial screen (S302).
- the purpose of diagnosis is information for specifying what type of state diagnosis is to be performed, and what type of viewpoint of what type of part of which type of diagnosis is to be performed, for example, loader type It is a state diagnosis of a hydraulic shovel, a heat balance diagnosis of an engine of a hydraulic shovel, a pressure diagnosis of a pump, and the like.
- the user inputs diagnostic data information to the input / output unit 101 of the diagnostic device 10 using the diagnostic initial screen (S303).
- Diagnostic data information is information that identifies diagnostic data to be diagnosed, and indicates, for example, information such as date, acquisition location, installation location, machine number, and the like.
- the diagnostic data information (A301) is transmitted to the diagnostic data storage device 30. This transmission is performed, for example, by pressing the search button on the diagnosis initial screen.
- the diagnostic data storage device 30 acquires target diagnostic data from the diagnostic data storage unit 302 based on the received diagnostic data information (S304).
- the diagnostic data is data having a structure shown in FIG. 5, and the details will be described later.
- the acquired diagnostic data (A 302) is transmitted to the diagnostic data acquisition unit 102 of the diagnostic device 10.
- the data characteristic acquisition unit 103 of the diagnostic device 10 acquires the data characteristic of the diagnostic data from the diagnostic data acquired by the diagnostic data acquisition unit 102 (S305).
- the data characteristic is data having the structure shown in FIG. 7, and the details will be described later.
- the diagnostic knowledge input / output unit 104 transmits the diagnostic purpose input by the input / output unit 101 and the data characteristic (A 303) acquired by the data characteristic acquisition unit 103 to the diagnostic knowledge storage device 20.
- the diagnostic knowledge storage device 20 acquires a diagnostic method that matches the characteristics of the data among the diagnostic methods that the diagnostic purpose received from the diagnostic knowledge storage unit 202 matches (S306).
- the diagnostic knowledge storage unit 202 stores diagnostic knowledge by a combination of data characteristics, a diagnostic method, and the number of cases. The details of the structure of diagnostic knowledge will be described later with reference to FIG.
- the diagnostic methods to which the characteristics of the data conform include not only those in which the input data characteristics and the data characteristics of the diagnostic knowledge completely match, but also those in which they partially match.
- the diagnostic method is data having a structure shown in FIG. 8, and the details will be described later. Furthermore, not only one but a plurality of diagnostic techniques may be applied.
- the diagnostic knowledge storage unit 202 transmits the acquired diagnostic method and the number of cases (A304) of the diagnostic method to the diagnostic knowledge input / output unit 104 (diagnostic knowledge acquisition unit 104A) of the diagnostic device 10.
- the effectiveness calculation unit 106 of the diagnostic device 10 calculates the effectiveness of the diagnostic method acquired by the diagnostic knowledge acquisition unit 104A (S307).
- the degree of effectiveness is the data characteristic input from the diagnostic knowledge input / output unit 104 to the diagnostic knowledge storage device 20 in order to acquire from the diagnostic knowledge storage device 20 the diagnostic knowledge that matches the data characteristics acquired by the data characteristic acquisition unit 103.
- the ratio is calculated from the product of the ratio of the number of elements of the data to the number of elements of the data characteristics included in the diagnostic knowledge that matches the data characteristics and the number of cases included in the matched diagnostic knowledge.
- the diagnostic device 10 displays a screen after diagnostic knowledge search on the display device 101A of the input / output unit 101, and displays the diagnostic method and the effectiveness of the diagnostic method to the user (S308).
- the screen after the diagnostic knowledge search is a screen having the items shown in FIG. 12, and the details will be described later.
- the diagnostic method is composed of a plurality of steps (diagnostic method elements), and in that case, in S308, it is preferable to display the diagnostic method and the effectiveness for each diagnostic method element.
- diagnosis method selection is not necessarily performed by the user, and one having the highest effectiveness may be automatically selected to perform diagnosis.
- the diagnosis unit 105 of the diagnosis apparatus 10 carries out diagnosis in accordance with the selection result of the user (S310).
- the start of the execution of this diagnosis is instructed, for example, by pressing the diagnostic button on the screen after the diagnostic knowledge search.
- the diagnosis unit 105 displays a diagnosis result screen on the display device 101A of the input / output unit 101, and displays the diagnosis result to the user (S311).
- the diagnosis result screen is a screen having the items shown in FIG. 13 and the details will be described later.
- it is determined whether or not the valid button on the diagnosis result screen is pressed (S312). If the valid button has not been pressed, the process ends (S313).
- the diagnostic unit 105 When the valid button is pressed, the diagnostic unit 105 causes the diagnostic knowledge storage device 20 via the diagnostic knowledge input / output unit 104 to use the combination of the characteristics of the diagnostic data and the diagnostic method used as the new diagnostic knowledge (A 305). Send.
- the user determines whether the diagnosis result is valid. In addition, the number of cases in this case is one and diagnostic knowledge is generated.
- the diagnostic knowledge storage device 20 stores the received diagnostic knowledge (S314), and transmits a response (A306) to the diagnostic device 10.
- FIG. 4 is a flow diagram describing an optimization procedure performed by the diagnostic knowledge generation unit 107 of the diagnostic device 10 in order to improve the utilization efficiency of the diagnostic knowledge stored in the diagnostic knowledge storage device 20.
- the diagnostic knowledge generation unit 107 of the diagnostic device 10 transmits a diagnostic method element list acquisition command (A401) to the diagnostic knowledge storage device 20, and requests acquisition of the diagnostic method element list.
- the diagnostic method is often composed of a plurality of procedures (diagnostic method elements), and the plurality of steps (diagnostic method elements) in the diagnostic method are respectively specific plural Contains specific elements.
- the diagnostic method element acquired as the diagnostic method element list means a plurality of specific elements included in the plurality of steps (diagnostic method elements).
- the diagnostic method element to be acquired is, for example, FFT (Fast Fourier Transform), selection of a maximum value, or the like.
- the diagnostic knowledge storage device 20 searches the diagnostic knowledge storage unit 202, and acquires a diagnostic method element list (S401).
- the acquired diagnostic method element list (A402) is transmitted to the diagnostic knowledge generation unit 107 of the diagnostic device 10.
- the diagnostic knowledge generation unit 107 selects a diagnostic method element from the received diagnostic method element list, and transmits the selected diagnostic method element (A403 1 ) to the diagnostic knowledge storage device 20. (S402 1 ).
- the selection of the diagnostic method element is performed by the diagnostic knowledge generation unit 107 in the order determined in advance with respect to the specific element included in each diagnostic method element for each diagnostic method element as a process of the diagnostic method.
- the diagnostic knowledge storage device 20 acquires data characteristics corresponding to the received diagnostic method element from the diagnostic knowledge storage unit 202 (S403 1 ).
- the acquired data characteristic group (A404 1 ) is transmitted to the diagnostic knowledge generation unit 107 of the diagnostic device 10.
- the diagnostic knowledge generation unit 107 extracts and classifies the characteristic having the common element in the received data characteristic group (S404 1 ).
- the number of cases is calculated using the number included for each classified characteristic (S405 1 ). The classification method of this characteristic and the calculation method of the number of cases are described in detail in FIG.
- the classified data characteristic, the diagnostic method element, and the number of cases (A405 1 ) are transmitted to the diagnostic knowledge storage device 20.
- the diagnostic knowledge storage device 20 stores the received combination of the classification data characteristic, the diagnostic method element, and the number of cases in the diagnostic knowledge storage unit 202 as new diagnostic knowledge (S406 1 ).
- a response (A406 1 ) indicating the storage result is transmitted to the diagnostic knowledge generation unit 107 of the diagnostic device 10.
- the diagnostic procedures element there are a plurality by repeated to the procedure described above (A402 1 ⁇ A406 1) the number of diagnostic procedures elements, can achieve optimization of the diagnostic knowledge storage device 20 is there.
- the above flow may be performed before S304 in FIG. 3, may be performed after S308, or may be performed periodically at certain intervals. Also, it may be implemented in the diagnostic knowledge storage device 20 or may be implemented with devices other than the diagnostic device 10.
- processes such as authentication processing, signature verification processing, data encryption processing, etc. are particularly described between the diagnostic device 10 and the diagnostic data storage device 30, and between the diagnostic device 10 and the diagnostic knowledge storage device 20. Although not, they may be processed to make them more secure.
- FIG. 5 is a diagram showing the details of the structure of the diagnostic data (A302) acquired in S303 of FIG. 5, the diagnostic data is indicated by a symbol A501.
- the diagnostic data (A501) includes a target device (A502) indicating the type and name of a device to be diagnosed, a data acquisition date and time (A503) indicating a date and time when the data was acquired, and a data acquisition location indicating a place where the data is acquired (A 504), the number of observation parameters (A 505) indicating the number of parameter sensors observed in the target device, the parameter name (A 506 1 ) indicating the names of observation parameters, and the parameter sensor indicating the type of sensor of observation parameters the type (A507 1), composed of parameter data string indicating the actually observed data (A508 1).
- the diagnostic data need not include all of the above-described components, and may include at least one component. Also, the order of the elements of the diagnostic data is not limited to this.
- FIG. 6 is a diagram showing the structure of diagnostic knowledge stored in the diagnostic knowledge storage unit 202 of FIG.
- Diagnostic knowledge includes a data characteristic (A602) acquired from diagnostic data, a diagnostic method (A603) capable of effectively diagnosing the diagnostic data, and a case including a combination of the data characteristic and the diagnostic method. It consists of the number of cases (A 604) indicating the number.
- the detailed structure of the data characteristics and the diagnostic procedure will be described in the following FIGS. 7 and 8. The method of calculating the number of cases is described in FIG.
- the order of the elements of diagnostic knowledge is not limited to this, as long as it includes at least the above components.
- FIG. 7 is a diagram showing in detail the data characteristic (A 602) of FIG. 6 and the structure of the data characteristic acquired in S304 of FIG. In FIG. 7, the data characteristic is indicated by a symbol A701.
- the data characteristic (A 701) includes a target device (A 702) indicating the type and name of a device to be diagnosed, a data acquisition date and time (A 703) indicating a date and time when data was acquired, and a data acquisition location indicating a place where data is acquired.
- A704 the number of observation parameters (A705) indicating the number of parameters observed in the target device (or the number of sensors for which the parameters are measured), and parameter characteristics (A706 1 ) indicating the characteristics of the observation parameters , parameters characteristic parameter name (a 707 1) indicating the name of the parameter, the sensor type (a 708 1) indicating the type of sensor that generated the parameters, the amount of data of the parameter (A709 1) and the number of the operation mode parameters ( a 710 1) and the data acquisition frequency indicating how often a parameter is acquired (a 711 1) , The average value of the parameters (A712 1), the variance of parameters (A713 1), the maximum value of the parameter and (A714 1), the minimum value of the parameter with (A 715 1), the change trend of the parameters (A716 1) Configured When there are a plurality of observation parameters, a plurality of the above configurations (A707 1 to A716 1 ) are included according to the number of parameters.
- the number of operation modes is calculated from the number of times of discrete change by analyzing a data string of parameters. For example, when the value becomes 0 at time t and the value becomes 100 at time t + 1, it is assumed that the operation mode has changed, and the number of operation modes is increased by one. With this calculation method, all of the data strings are confirmed, and the number of operation modes is calculated.
- the threshold value for detecting the change in the operation mode is slightly different depending on the type of data, it is a standard that the amount of change per unit time of the normalized data string is 10 or more.
- a method of normalization a method using maximum value, minimum value, a method using average, and a variance can be considered, but it is not limited to these methods.
- the change tendency means the tendency of the parameter to change with time, for example, the tendency of monotonous increase or monotonous decrease, and the spread of the dispersion value at each data point causes the monotonous decrease or monotonous increase or normal distribution
- the tendency close to is extracted and described as the change tendency.
- the data characteristic does not have to include all of the above-described components, as long as it includes at least one of the above-described components. Also, the order of elements of data characteristics is not limited to this.
- FIG. 8 is a diagram showing in detail the structure of the diagnostic method (A 603) of FIG. 6 and acquired in S305 of FIG. In FIG. 8, the diagnostic method is indicated by reference numeral A801.
- the diagnostic method (A801) includes a diagnostic purpose (A802) indicating the purpose of performing a diagnosis, data extraction (A803) indicating a list of parameters used for diagnosis, and a preprocess (A804) indicating pre-processing for each parameter. And a diagnosis (A 807) indicating a method of state diagnosis, and a result display (A 810) indicating a display method of a diagnosis result.
- the pre-processing (A 805) includes pre-processing target parameters (A 805) indicating combinations of parameters to be pre-processed and a pre-processing method (A 806) implemented for the combinations.
- diagnosis (A 807) includes diagnostic methods (A 808) indicating threshold determination, clustering, correlation analysis, etc., and diagnostic setting values (such as threshold values used at diagnosis, and setting values such as the number of clusters and weights) A 809) is included.
- a result output method (A 811) indicating a method (text, line graph, bar graph, etc.) for outputting a diagnosis result, and attention should be paid to identifying states among the output results.
- the diagnostic method does not have to include all of the above-described components, as long as it includes at least one element. Also, the order of the elements of the diagnostic procedure is not limited to this.
- FIG. 9 is a diagram illustrating a construction machine used to explain a specific diagnosis case.
- the crawler pressure is a driving pressure of a cylinder provided to adjust the tension of the crawler.
- FIG. 10 is a flow of deriving a diagnostic method from input data in order to diagnose the state of the construction machine shown in FIG. 9, and is a diagram showing an example of the processing procedure of S301 to S305 in FIG.
- input data (A1001) to be diagnosed is input to the data characteristic acquisition unit 103.
- the data characteristic (A1002) of the input data is extracted.
- the device to be diagnosed (A1003), the crawler pressure per unit time (A1004), and the engine speed per unit time (A1005) are extracted as data characteristics required for the search of diagnostic knowledge.
- the diagnostic purpose (A1005) and the acquired data characteristic (A1002) are input to the diagnostic knowledge storage unit 202.
- the diagnostic knowledge storage unit 202 extracts a diagnostic method that matches the input diagnostic purpose (A1006) and data characteristic (A1002). Specifically, first, a device to be diagnosed is identified (S1001). If the device to be diagnosed is a hydraulic shovel, reference is made to the average value of crawler pressure per unit time (S1002).
- the crawler pressure per unit time is 1.0 bar or more, it is judged that it is a loader characteristic (A1002), and the diagnostic method (A1011) which was effective to the characteristic is extracted.
- the crawler pressure per unit time is less than 1.0 bar, it is determined that the backhoe characteristic (A1003) is obtained, and the diagnostic method (A1012) that has been effective in those characteristics is extracted.
- the device to be diagnosed is a dump, the average value per unit time of the engine speed of the input data is referred to (S1003).
- the engine speed per unit time is 1500 rpm or more, it is determined that the characteristic (A1004) of the dump traveling on the slope is extracted, and the diagnostic method (A1013) that is effective for the characteristic is extracted .
- the engine speed per unit time is less than 1500 rpm, it is determined that the characteristic (A1005) of a dump traveling on a flat ground is extracted, and a diagnostic method (A1014) that has been effective for that characteristic is extracted.
- the diagnostic method (A1011) extracted in the case of the loader extracts arm cylinder pressure data in data extraction (A1015), acquires the maximum value as pretreatment (A1016), and diagnoses the arm cylinder pressure at 4.0 bar or more Threshold determination (A1017), a line graph is used as a result output method, and points that exceed the threshold are noted (A1018).
- the diagnostic method (A1012) extracted in the case of backhoe extracts arm cylinder pressure data in data extraction (A1019), acquires the maximum value as preprocessing (A1020), and diagnoses the arm cylinder pressure at 3.
- the threshold value is 6 bar or more (A1021), and a line graph is used as a result output method to focus on points exceeding the threshold value (A1022).
- the threshold value of the arm cylinder pressure is a larger value than that of the backhoe type hydraulic shovel.
- the diagnostic method (A1013) extracted in the case of dumping traveling on a slope extracts the coolant temperature in data extraction (A1023), acquires the maximum value as a pretreatment (A1024), and diagnoses the coolant temperature It is determined whether the threshold value is 70 degrees or more (A1025), and a line graph is used as a result output method to pay attention to the point exceeding the threshold value (A1026).
- the diagnostic method (A1014) extracted in the case of dumping traveling on a flat ground extracts the coolant temperature in data extraction (A1027), acquires the maximum value as a pretreatment (A1028), and diagnoses the coolant temperature It is determined whether or not the angle is not less than 60 degrees (A1029), and a line graph is used as a result output method to pay attention to the point exceeding the threshold (A1030).
- the engine rotational speed inevitably increases in order to travel on a slope, and the coolant temperature tends to increase with an increase in the amount of heat generation from the engine.
- the value is higher than a dump truck traveling on a flat ground.
- each diagnostic method extracted as described above is output to the display device 101A, displayed on a screen after diagnostic knowledge search, and used for diagnosis.
- the state diagnosis with higher accuracy than the conventional state diagnosis can be performed by appropriately switching the diagnosis method according to the use environment and the characteristics of the construction machine. It becomes possible.
- FIG. 10 is a case where there is one effective diagnostic method extracted based on each characteristic, when there are a plurality of effective diagnostic methods, a plurality of diagnostic methods are extracted. You may In this case, as described above, the effectiveness of the diagnostic method is calculated, and the number of displayed items is limited by, for example, displaying the top 5 effectiveness.
- the example in FIG. 10 is for extracting a diagnostic method including a set of diagnostic method elements of data extraction, preprocessing, diagnosis, and result display, but the diagnostic knowledge generated by the diagnostic knowledge generation unit 107 is When stored in the diagnostic knowledge storage device 20, each diagnostic method element may be extracted individually for each diagnostic method element (FIG. 12).
- the device to be diagnosed is a model unit such as a hydraulic shovel, dump, etc.
- the diagnostic purpose is the condition diagnosis of the object device in the model unit.
- Diagnosis of a specific part (for example, engine, pump etc.) of a model (for example, loader type hydraulic shovel) or diagnosis focusing on a specific viewpoint of a specific part (for example, heat balance diagnosis of engine, pressure diagnosis of pump etc. ) May be.
- FIG. 11 is a diagram showing a specific example of the method of acquiring classification characteristics and the method of calculating the number of cases, which are performed in S404 and S405 of FIG.
- an FFT which is one of preprocessing
- the FFT (A1101) of the preprocessing method is input to the diagnostic knowledge storage unit 202 as a search key (S1101: corresponding to S402 in FIG. 4).
- the diagnostic knowledge storage unit 202 searches for data characteristics related to the FFT (S1102: corresponding to S403 in FIG. 4).
- S1102 data characteristics related to the FFT
- S1103 data characteristics related to the FFT
- the characteristics of the vibration sensor (A 1103 1) as the classification characteristic of the first one is extracted, the characteristic has been extracted as a sound sensor (A 1003 2) as the classification characteristic of the second.
- the number of data characteristics having the extracted classification characteristics is calculated as the number of cases (A1104 1 , A1104 2 ) (corresponding to S405 in FIG. 4).
- the number of cases 2 is calculated for the classification characteristic of the vibration sensor, and the number of cases 3 is calculated for the classification characteristic of the sound sensor.
- the extracted classification characteristic (A1103 1, A1103 2) and diagnostic procedures element (A 1101) and the number of cases (A1104 1, A1104 2) in combination to generate a new diagnostic knowledge (A1105 1, A1105 2) S1104 : Corresponds to S406 in FIG. 4).
- the data characteristic which is not a numerical value was mentioned as an example and explained, in the case of a numerical value, it is possible to classify, considering that it is a common characteristic, even when the values themselves do not match. For example, if there is a valid diagnostic method element for data with a maximum value of 50 and a maximum value of 60, if the maximum value is 50 to 60, the classification characteristic is determined as valid. Generate By realizing such a flow, it is possible to extract data characteristics that can effectively utilize each diagnostic method element, and it is possible to increase the applicability of diagnostic knowledge.
- FIG. 12 shows a screen image displayed when the user performs a diagnosis using the diagnostic device 10.
- the diagnosis initial screen (A1201) is the screen displayed in S301 of FIG. 3, and a form (A1202) for inputting a diagnostic purpose, a form (A1203) for inputting information of data to be diagnosed, and a form According to the information, diagnostic data is acquired from the diagnostic data storage device 30, and the diagnostic knowledge search button (A1204) is used to search the diagnostic knowledge storage unit 202 for diagnostic knowledge that is considered to be effective for the acquired diagnostic data.
- the components of the diagnosis initial screen are not limited to this, and the number of forms or buttons may be any number as long as the functions of the components can be realized.
- the diagnostic knowledge search screen (A1205) is the screen displayed in S308 of FIG. 3, and in addition to the components of the diagnostic initial screen (A1201), data extraction (A1206), pre-processing (A1206) A1210), diagnosis (A1214), result display (A1218), and diagnosis button (A1222) for performing diagnosis according to the set diagnosis information.
- the data extraction (A1206) is performed by the data extraction method (A1207) indicating the data to be extracted matching the diagnostic purpose and the data characteristics in the diagnosis object data, the effectiveness (A1208), and the diagnosis knowledge storage unit 202 It consists of a user input form (A1209) used when there is no diagnostic method corresponding to the purpose or data characteristic, or when analysis is performed without using diagnostic knowledge.
- the preprocessing (A1210) is a preprocessing method (A1211) indicating preprocessing that is considered to be effective for the data extracted by the data extraction, the effectiveness (A1212), and the diagnostic knowledge storage unit 202.
- the user input form (A1213) is used when there is no diagnostic method that corresponds to the data characteristics, or when analysis is performed without using diagnostic knowledge.
- diagnosis is a diagnostic method (A1215) that indicates a diagnostic method that matches the diagnostic purpose and data characteristics using the data obtained by performing the pre-processing on the data extracted by the data extraction, and its effective And a user input form (A1217) used when analysis is performed without using the diagnostic knowledge corresponding to the data characteristic in the diagnostic knowledge storage unit 202 or without using the diagnostic knowledge. .
- the result display (A1218) is a result display method (A1219) for displaying the result of performing the diagnosis using the data obtained by performing the pre-processing on the data extracted by the data extraction, and the effectiveness (A1219) A1220) and a user input form (A1221) used when the diagnostic knowledge storage unit 202 does not have a diagnostic method corresponding to the data characteristic, or when analysis is performed without using diagnostic knowledge.
- the diagnostic knowledge storage unit 202 does not have a diagnostic method corresponding to the data characteristic, or when analysis is performed without using diagnostic knowledge.
- a plurality of diagnostic methods that correspond to each item a plurality of combinations of diagnostic methods and effectiveness are displayed, and can be freely selected by the user. However, displaying a large number of diagnostic methods at the same time may cause confusion to the user.
- the top five cases of valid diagnostic methods are displayed in a pull-down menu to limit the number of displayed items.
- the combination of diagnostic methods to which the diagnostic method belongs is color-coded and displayed according to the item (for example, diagnostic method) selected by the user, and the user can easily distinguish the set of diagnostic methods from those highly effective. You may do so.
- the components of the diagnostic knowledge search screen are not limited to this, and the number of forms and buttons may be any number as long as the functions of the components can be realized.
- FIG. 13 shows a screen image displayed after the user performs a diagnosis using the diagnostic device 10.
- the diagnosis result screen (A1301) is a screen displayed in S311 of FIG. 3 and includes a portion (A1302) for displaying a diagnosis result such as a graph and a valid button (A1303) to be pressed when the diagnosis result is valid.
- a diagnosis result such as a graph
- a valid button A1303 to be pressed when the diagnosis result is valid.
- the components of the diagnostic result screen are not limited to this, and the number of forms or buttons may be any number as long as the functions of the components can be realized.
- the diagnostic device 10 when the diagnostic device 10, the diagnostic knowledge storage device 20, and the diagnostic data storage device 30 are connected to each other by a network or the like, or when diagnosis of an apparatus that is not a construction machine is performed.
- Diagnostic device 11 communication device 12: input / output device 13: storage device 14: CPU 15: Memory 16: Reading device 17: Storage medium 18: Internal signal line 20: Diagnostic knowledge storage device 30: Diagnostic data storage device 101: Input / output unit 102: Diagnostic data acquisition unit 103: Data characteristic acquisition unit 104: Diagnostic knowledge input Output unit 105: Diagnosis unit 201: Data transmission / reception unit 202: Diagnosis knowledge storage unit 301: Data transmission / reception unit 302: Diagnosis data storage unit A301: Diagnosis data information A 302: Diagnosis data A 303: Diagnosis purpose, data characteristics A 304: Diagnosis method, case Number A 305: Diagnostic knowledge A 306: Response A 401: Diagnostic method element list acquisition command A 402: Diagnostic method element list A 403 1 to A 403 N : Diagnostic method element A 404 1 to A 404 N : Data characteristic group A 405 1 to A 405 N : Classification data characteristic, Diagnostic method element, number of cases A406 1 to A
Abstract
Description
11:通信装置
12:入出力装置
13:記憶装置
14:CPU
15:メモリ
16:読取装置
17:記憶媒体
18:内部信号線
20:診断知識保管装置
30:診断データ保管装置
101:入出力部
102:診断データ取得部
103:データ特性取得部
104:診断知識入出力部
105:診断部
201:データ送受信部
202:診断知識保管部
301:データ送受信部
302:診断データ保管部
A301:診断データ情報
A302:診断データ
A303:診断目的、データ特性
A304:診断手法、事例数
A305:診断知識
A306:レスポンス
A401:診断手法要素一覧取得コマンド
A402:診断手法要素一覧
A4031~A403N:診断手法要素
A4041~A404N:データ特性群
A4051~A405N:分類データ特性、診断手法要素、事例数
A4061~A406N:レスポンス
A501:診断データ
A502:対象機器
A503:データ取得日時
A504:データ取得場所
A505:観測パラメータ数
A5061~A506N:パラメータ名称
A5071~A507N:パラメータセンサ種類
A5081~A508N:パラメータデータ列
A601:診断知識
A602:データ特性
A603:診断手法
A604:事例数
A701:データ特性
A702:対象機器
A703:データ取得日時
A704:データ取得場所
A705:観測パラメータ数
A7061~A706N:パラメータ特性
A7071~A707N:パラメータ名称
A7081~A708N:センサ種類
A7091~A709N:データ量
A7101~A710N:運転モード数
A7111~A711N:データ取得頻度
A7121~A712N:平均値
A7131~A713N:分散値
A7141~A714N:最大値
A7151~A715N:最小値
A7161~A716N:変化傾向
A801:診断手法
A802:診断目的
A803:データ抽出
A804:前処理
A805:前処理対象パラメータ
A806:前処理方法
A807:診断
A808:診断方法
A809:診断設定値
A810:結果表示
A811:結果出力方法
A812:結果注目点
A901:バックホウ
A902:バックホウのクローラ圧の時間変化
A903:ローダ
A904:ローダのクローラ圧の時間変化
A905:平地を走行するダンプ
A906:平地を走行するダンプのエンジン回転数の時間変化
A907:斜面を走行するダンプ
A908:斜面を走行するダンプのエンジン回転数の時間変化
A1001:入力データ
A1002:データ特性
A1003、診断対象機器
A1004:単位時間あたりのクローラ圧
A1005:単位時間あたりのエンジン回転数
A1006:診断目的
A1007:ローダ特性
A1008:バックホウ特性
A1009:ダンプ(斜面)特性
A1010:ダンプ(平地)特性
A1011:診断手法
A1012:診断手法
A1013:診断手法
A1014:診断手法
A1015:データ抽出
A1016:前処理
A1017:診断
A1018:結果表示
A1019:データ抽出
A1020:前処理
A1021:診断
A1022:結果表示
A1023:データ抽出
A1024:前処理
A1025:診断
A1026:結果表示
A1027:データ抽出
A1028:前処理
A1029:診断
A1030:結果表示
A1101:診断手法要素
A1102:検索結果
A11031~A11032:分類特性
A11041~A11042:事例数
A11051~A11052:新たな診断知識
A1201:診断初期画面
A1202:診断目的
A1203:診断データ情報入力フォーム
A1204:診断知識検索ボタン
A1205:診断知識検索後画面
A1206:データ抽出に関する診断情報
A1207:データ抽出方法
A1208:有効度
A1209:ユーザ入力フォーム
A1210:前処理に関する診断情報
A1211:前処理方法
A1212:有効度
A1213:ユーザ入力フォーム
A1214:診断に関する診断情報
A1215:診断方法
A1216:有効度
A1217:ユーザ入力フォーム
A1218:結果表示に関する診断情報
A1219:結果表示方法
A1220:有効度
A1221:ユーザ入力フォーム
A1222:診断ボタン
A1301:診断結果画面
A1302:診断結果
A1303:有効ボタン
Claims (23)
- 建設機械の状態を診断する診断システムであって、
建設機械を診断する診断装置(10)と、診断に使用する診断手法を含む診断知識を保管する診断知識保管装置(20)と、診断に使用する診断データを保管する診断データ保管装置(30)とを有し、
前記診断装置は、
外部とのデータ入出力を行う入出力部(101)と、
前記入出力部に入力されたデータに基づいて、前記診断データ保管装置から該当する診断データを取得する診断データ取得部(102)と、
前記診断データ取得部で取得した診断データからその診断データのデータ特性を取得するデータ特性取得部(103)と、
前記データ特性取得部で取得したデータ特性と適合する診断手法を前記診断知識保管装置から取得する診断知識取得部(104A)と、
前記診断データ取得部で取得した前記診断データと前記診断知識取得部で取得した前記診断手法を用いて診断を行う診断部(105)とを備えことを特徴とする診断システム。 - 請求項1に記載の診断システムであって、
前記診断知識保管装置(20)に保管されている診断知識は、事前に取得した診断データのデータ特性と、その診断データの診断に有効であった前記診断手法とを含み、
前記診断知識取得部(104A)は、少なくとも、前記データ特性取得部(102)で取得したデータ特性と適合するデータ特性が属する診断知識の診断手法を取得し、
前記診断部(105)は、前記診断データ取得部で取得した前記診断データに対して、前記診断知識取得部で取得した前記診断手法を用いて診断を行うことを特徴とする診断システム。 - 請求項2に記載の診断システムであって、
前記診断知識に含まれる前記診断データのデータ特性は、診断対象機器の名称や種類を示す対象機器と、前記診断データを取得した日時を示すデータ取得日時と、前記診断データを取得した場所を示すデータ取得場所と、前記対象機器で観測しているパラメータの数を示す観測パラメータ数と、観測パラメータが持つ特性を示すパラメータ特性の少なくとも1つを含むことを特徴とする診断システム。 - 請求項3に記載の診断システムであって、
前記パラメータ特性は、前記パラメータの名称を示すパラメータ名称と、前記パラメータを生成したセンサの種類を示すセンサ種類と、前記パラメータのデータ量と、前記パラメータが短時間で大きく変動した回数を示す運転モード数と、前記パラメータが取得された頻度を示すデータ取得頻度と、前記パラメータの平均値と、前記パラメータの分散値と、前記パラメータの最大値と、前記パラメータの最小値と、前記パラメータの変化の傾向を示す変化傾向の少なくとも1つを含むことを特徴とする診断システム。 - 請求項1~4のいずれか1項に記載の診断システムであって、
前記診断手法は、前記診断データを診断する目的を示す診断目的と、前記診断データのパラメータの中で診断に使用するパラメータを示すデータ抽出方法と、診断に使用するパラメータに対して診断の前に実施する前処理を示す前処理方法と、診断を行う方式やアルゴリズムを示す診断方法と、該診断を実施した結果の出力方法を示す結果出力方法の少なくとも1つを含むことを特徴とする診断システム。 - 請求項1~5のいずれか1項に記載の診断システムであって、
前記診断装置(10)は、前記診断知識取得部(104A)で取得した前記診断手法の有効度を算出する有効度算出部(106)を更に備え、
前記診断部(105)は、前記有効度算出部で算出した診断手法の有効度にしたがって前記診断知識取得部で取得した前記診断手法のうちの最適のものを選択して診断を実施することを特徴とする診断システム。 - 請求項6に記載の診断システムであって、
前記診断知識は、前記データ特性と前記診断手法の組合せが有効である事例の数を示す事例数を更に含み、
前記診断知識取得部(104A)は、前記診断手法に加えて前記事例数を取得し、
前記有効度算出部(106)は、前記有効度を、前記データ特性取得部(103)で取得したデータ特性と適合する診断手法を前記診断知識保管装置(20)から取得するために前記診断知識保管装置(20)に入力したデータ特性の要素数と、該入力したデータ特性と一致した診断知識に含まれるデータ特性の要素数との比と、前記診断知識に含まれる前記事例数との積から算出することを特徴とする診断システム。 - 請求項1~7のいずれか1項に記載の診断システムであって、
前記診断部(105)は、診断実施後に使用した診断手法が有効であった場合に、そのときの診断データの特性と使用した診断手法の組み合わせを新たな診断知識として前記診断知識保管装置(20)に格納することを特徴とする診断システム。 - 請求項1~8のいずれか1項に記載の診断システムであって、
前記診断装置(10)は、前記診断知識保管装置(20)に保管している診断知識の中から共通する診断手法要素が含まれる診断知識を収集し、収集された診断知識に含まれるデータ特性の構成要素間の共通点と前記診断手法要素の組合せを新たな診断知識として生成し、前記診断知識保管装置に格納する診断知識生成部(107)を更に備えることを特徴とする診断システム。 - 請求項9に記載の診断システムであって、
前記診断知識生成部(107)は、前記新たな診断知識を生成する際に、共通するデータ特性の構成要素を含む診断知識の個数を事例数として前記新たな診断知識に付与することを特徴とする診断システム。 - 請求項1~10のいずれか1項に記載の診断システムであって、
前記入出力部(101)は少なくとも診断初期画面(A1202)を表示する表示装置(101A)を有し、前記診断初期画面は、診断目的及び診断対象データの情報を入力するフォーム(A1202,A1203)と、診断知識の検索の開始を指示する検索ボタン(A1204)を含むことを特徴とする診断システム。 - 請求項1~11のいずれか1項に記載の診断システムであって、
前記入出力部(101)は少なくとも診断知識検索後画面(A1205)を表示する表示装置(101A)を有し、前記診断知識検索後画面は、前記診断知識取得部(104A)が取得した診断手法(A1207,A1211,A1215,A1219)と、その診断手法の有効度(A1208,A1212,A1216,A1220)と、診断の開始を指示する診断ボタン(A1222)を含み、かつ前記診断手法を診断する手順に従って表示することを特徴とする診断システム。 - 請求項1~10のいずれか1項に記載の診断システムであって、
前記入出力部(101)は、少なくとも診断初期画面(A1202)と診断知識検索後画面(A1205)を表示する表示装置(101A)を有し、
前記診断初期画面は、診断目的及び診断対象データの情報を入力するフォーム(A1202,A1203)と、診断知識の検索の開始を指示する検索ボタン(A1204)を含み、
前記診断データ取得部(102)は、前記診断初期画面の検索ボタンが操作されると、前記診断初期画面のフォームに入力された診断目的と診断対象データの情報に基づいて、前記診断データ保管装置(30)から診断データを取得し、
前記診断知識検索後画面は、前記診断知識取得部(104A)が取得した診断手法(A1207,A1211,A1215,A1219)と、その診断手法の有効度(A1208,A1212,A1216,A1220)と、診断の開始を指示する診断ボタン(A1222)を含み、
前記診断部(105)は、前記診断知識検索後画面に表示された診断手法のうちの任意のものが選択され、前記診断知識検索後画面の診断ボタンが操作されると、その選択した診断手法に基づいて、前記診断データ取得部(102)で取得した前記診断データの診断を行うことを特徴とする診断システム。 - 建設機械の状態を診断する診断方法であって、
入出力部(101)より入力されたデータに基づいて、診断に使用する診断手法を含む診断知識を保管した診断データ保管装置(30)から該当する診断データを取得する第1手順(S304)と、
前記第1手順で取得した診断データからその診断データのデータ特性を取得する第2手順(S305)と、
前記第2手順で取得したデータ特性と適合する診断手法を、診断に使用する診断手法を含む診断知識を保管した診断知識保管装置(20)から取得する第3手順(S306)と、
前記第1手順で取得した前記診断データと前記第3手順で取得した前記診断手法を用いて診断を行う第4手順(S310)とを有することを特徴とする診断方法。 - 請求項14に記載の診断方法であって、
前記診断知識保管装置(20)に保管された診断知識は、事前に取得した診断データのデータ特性と、その診断データの診断に有効であった前記診断手法とを含み、
前記第3手順(S306)は、少なくとも、前記第2手順(S305)で取得したデータ特性と適合するデータ特性が属する診断知識の診断手法を取得し、
前記第4手順(S310)は、前記第1手順(S304)で取得した前記診断データに対して、前記第3手順(S306)で取得した前記診断手法を用いて診断を行うことを特徴とする診断方法。 - 請求項15に記載の診断方法であって、
前記診断知識に含まれる前記診断データのデータ特性は、診断対象機器の名称や種類を示す対象機器と、前記診断データを取得した日時を示すデータ取得日時と、前記診断データを取得した場所を示すデータ取得場所と、前記対象機器で観測しているパラメータの数を示す観測パラメータ数と、観測パラメータが持つ特性を示すパラメータ特性の少なくとも1つを含むことを特徴とする診断方法。 - 請求項16に記載の診断方法であって、
前記パラメータ特性は、前記パラメータの名称を示すパラメータ名称と、前記パラメータを生成したセンサの種類を示すセンサ種類と、前記パラメータのデータ量と、前記パラメータが短時間で大きく変動した回数を示す運転モード数と、前記パラメータが取得された頻度を示すデータ取得頻度と、前記パラメータの平均値と、前記パラメータの分散値と、前記パラメータの最大値と、前記パラメータの最小値と、前記パラメータの変化の傾向を示す変化傾向の少なくとも1つを含むことを特徴とする診断方法。 - 請求項14~17のいずれか1項に記載の診断方法であって、
前記診断手法は、前記診断データを診断する目的を示す診断目的と、前記診断データのパラメータの中で診断に使用するパラメータを示すデータ抽出方法と、診断に使用するパラメータに対して診断の前に実施する前処理を示す前処理方法と、診断を行う方式やアルゴリズムを示す診断方法と、該診断を実施した結果の出力方法を示す結果出力方法の少なくとも1つを含むことを特徴とする診断方法。 - 請求項14~18のいずれか1項に記載の診断方法であって、
前記第3手順(S306)で取得した前記診断手法の有効度を算出する第5手順(S307)を更に有し、
前記第4手順(S310)は、前記第5手順で算出した診断手法の有効度にしたがって前記第3手順で取得した前記診断手法のうちの最適のものを選択して診断を実施することを特徴とする診断方法。 - 請求項19に記載の診断方法であって、
前記診断知識は、前記データ特性と前記診断手法の組合せが有効である事例の数を示す事例数を更に含み、
前記第3手順(S306)は、前記診断手法に加えて前記事例数を取得し、
前記第5手順(S307)は、前記有効度を、前記第2手順(S305)で取得したデータ特性と適合する診断手法を前記診断知識保管装置(20)から取得するために前記診断知識保管装置(20)に入力したデータ特性の要素数と、該入力したデータ特性と一致した診断知識に含まれるデータ特性の要素数との比と、前記診断知識に含まれる前記事例数との積から算出することを特徴とする診断方法。 - 請求項14~20のいずれか1項に記載の診断方法であって、
前記第4手順(S310)で診断実施後に使用した診断手法が有効であった場合に、そのときの診断データの特性と使用した診断手法の組み合わせを新たな診断知識として前記診断知識保管装置(20)に格納する第6手順(S312,S314)を更に有することを特徴とする診断方法。 - 請求項14~21のいずれか1項に記載の診断方法であって、
前記診断知識保管装置(20)に保管している診断知識の中から共通する診断手法要素が含まれる診断知識を収集し、収集された診断知識に含まれるデータ特性の構成要素間の共通点と前記診断手法要素の組合せを新たな診断知識として生成し、前記診断知識保管装置に格納する第7手順(S401~S406)を更に有することを特徴とする診断方法。 - 請求項22に記載の診断方法であって、
前記第7手順(S401~S406)は、前記新たな診断知識を生成する際に、共通するデータ特性の構成要素を含む診断知識の個数を事例数として前記新たな診断知識に付与することを特徴とする診断方法。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP09850559.7A EP2492660A4 (en) | 2009-10-19 | 2009-10-19 | Diagnosis system and diagnosis method of construction machine |
CN200980161988.7A CN102575973B (zh) | 2009-10-19 | 2009-10-19 | 工程机械的诊断系统及诊断方法 |
US13/502,896 US9057174B2 (en) | 2009-10-19 | 2009-10-19 | Diagnosis system and diagnosis method for construction machine |
JP2011537044A JP5296219B2 (ja) | 2009-10-19 | 2009-10-19 | 建設機械の診断システム及び診断方法 |
AU2009354283A AU2009354283B2 (en) | 2009-10-19 | 2009-10-19 | Diagnosis system and diagnosis method of construction machine |
PCT/JP2009/068038 WO2011048661A1 (ja) | 2009-10-19 | 2009-10-19 | 建設機械の診断システム及び診断方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2009/068038 WO2011048661A1 (ja) | 2009-10-19 | 2009-10-19 | 建設機械の診断システム及び診断方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011048661A1 true WO2011048661A1 (ja) | 2011-04-28 |
Family
ID=43899912
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2009/068038 WO2011048661A1 (ja) | 2009-10-19 | 2009-10-19 | 建設機械の診断システム及び診断方法 |
Country Status (6)
Country | Link |
---|---|
US (1) | US9057174B2 (ja) |
EP (1) | EP2492660A4 (ja) |
JP (1) | JP5296219B2 (ja) |
CN (1) | CN102575973B (ja) |
AU (1) | AU2009354283B2 (ja) |
WO (1) | WO2011048661A1 (ja) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20160058536A (ko) * | 2014-11-17 | 2016-05-25 | 두산인프라코어 주식회사 | 시야성 가상 검증 방법 |
JP6567229B1 (ja) * | 2018-03-30 | 2019-08-28 | 三菱電機株式会社 | 学習処理装置、データ分析装置、分析手法選択方法、及び分析手法選択プログラム |
JP2019195377A (ja) * | 2018-05-07 | 2019-11-14 | オムロン株式会社 | データ処理装置、モニタリングシステム、覚醒システム、データ処理方法、及びデータ処理プログラム |
JP2021067614A (ja) * | 2019-10-25 | 2021-04-30 | 日立建機株式会社 | 故障診断装置及び故障診断方法 |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9569327B2 (en) * | 2012-10-03 | 2017-02-14 | Xerox Corporation | System and method for labeling alert messages from devices for automated management |
DE102013212505A1 (de) * | 2013-06-27 | 2014-12-31 | Robert Bosch Gmbh | Werkstatt-Diagnosesystem |
CA3007973C (en) * | 2015-12-08 | 2020-11-03 | Sight Machine, Inc. | System and method for monitoring manufacturing |
CN106193144A (zh) * | 2016-07-01 | 2016-12-07 | 蔡雄 | 一种具备道路检测功能的装载车 |
GB201709406D0 (en) | 2017-06-13 | 2017-07-26 | Euro-Cletique S A | Compounds for treating TNBC |
US11180904B2 (en) | 2018-04-18 | 2021-11-23 | Deere & Company | Excavator control for load delivery |
US11222202B2 (en) | 2019-01-14 | 2022-01-11 | Deere & Company | Targeted testing and machine-learning systems for detecting and identifying machine behavior |
CN112924205B (zh) * | 2021-01-27 | 2023-10-13 | 上海三一重机股份有限公司 | 作业机械故障诊断方法、装置、作业机械和电子设备 |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0526782A (ja) * | 1991-07-23 | 1993-02-02 | Toyo Umpanki Co Ltd | 電気−機械系装置の診断装置 |
JPH07271589A (ja) * | 1994-03-29 | 1995-10-20 | Fuji Heavy Ind Ltd | 故障診断装置 |
JPH08164827A (ja) * | 1994-12-13 | 1996-06-25 | Nissan Motor Co Ltd | 車両故障診断装置 |
JPH10232874A (ja) | 1997-02-19 | 1998-09-02 | Hitachi Ltd | 情報処理ノウハウ共有方法 |
JPH10275168A (ja) | 1997-03-31 | 1998-10-13 | Hitachi Ltd | 設計支援方法および設計支援システム |
JP2001202125A (ja) * | 2000-01-20 | 2001-07-27 | Snap On Tools Corp | 装置作動状態のダイナミック診断システム |
JP2001317403A (ja) * | 2000-05-01 | 2001-11-16 | Toyota Motor Corp | 異常診断システム及び異常診断データ記憶方法 |
JP2002342508A (ja) * | 2001-05-17 | 2002-11-29 | Nec Fielding Ltd | 自動車の故障検出と修理依頼システムおよび方法 |
JP2003178148A (ja) * | 2001-12-12 | 2003-06-27 | Komatsu Ltd | 機械の保守点検システム、その保守点検方法およびその保守点検プログラム |
JP2004299473A (ja) * | 2003-03-28 | 2004-10-28 | Mazda Motor Corp | 遠隔故障診断システム及びその制御方法、並びに車両 |
JP2008001233A (ja) * | 2006-06-22 | 2008-01-10 | Mazda Motor Corp | 遠隔故障診断システム |
JP2009146059A (ja) * | 2007-12-12 | 2009-07-02 | Autonetworks Technologies Ltd | 診断項目の設定方法、故障診断装置、プログラム及び記録媒体 |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08189846A (ja) * | 1995-01-11 | 1996-07-23 | Yokogawa Electric Corp | プラント診断システム |
JPH08221117A (ja) * | 1995-02-09 | 1996-08-30 | Mitsubishi Electric Corp | 異常診断支援用解析装置 |
US7444216B2 (en) * | 2005-01-14 | 2008-10-28 | Mobile Productivity, Inc. | User interface for display of task specific information |
US7882394B2 (en) * | 2005-07-11 | 2011-02-01 | Brooks Automation, Inc. | Intelligent condition-monitoring and fault diagnostic system for predictive maintenance |
KR101044740B1 (ko) * | 2006-01-12 | 2011-06-28 | 히다치 겡키 가부시키 가이샤 | 건설기계의 점검 이력 정보 관리시스템 |
CN101438251A (zh) * | 2006-05-07 | 2009-05-20 | 应用材料股份有限公司 | 调适多变量错误检测 |
US8423226B2 (en) * | 2006-06-14 | 2013-04-16 | Service Solutions U.S. Llc | Dynamic decision sequencing method and apparatus for optimizing a diagnostic test plan |
JP2008097363A (ja) * | 2006-10-12 | 2008-04-24 | Okuma Corp | 異常診断方法及びその装置 |
KR20090049492A (ko) | 2007-11-13 | 2009-05-18 | 유빅테크주식회사 | 차량 고장진단기기 |
CA2613491C (en) * | 2007-12-04 | 2015-03-24 | Clark Equipment Company | Power machine diagnostic system and method |
US8185290B2 (en) * | 2008-03-07 | 2012-05-22 | Caterpillar Inc. | Data acquisition system indexed by cycle segmentation |
-
2009
- 2009-10-19 AU AU2009354283A patent/AU2009354283B2/en active Active
- 2009-10-19 EP EP09850559.7A patent/EP2492660A4/en not_active Withdrawn
- 2009-10-19 US US13/502,896 patent/US9057174B2/en active Active
- 2009-10-19 CN CN200980161988.7A patent/CN102575973B/zh active Active
- 2009-10-19 WO PCT/JP2009/068038 patent/WO2011048661A1/ja active Application Filing
- 2009-10-19 JP JP2011537044A patent/JP5296219B2/ja not_active Expired - Fee Related
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0526782A (ja) * | 1991-07-23 | 1993-02-02 | Toyo Umpanki Co Ltd | 電気−機械系装置の診断装置 |
JPH07271589A (ja) * | 1994-03-29 | 1995-10-20 | Fuji Heavy Ind Ltd | 故障診断装置 |
JPH08164827A (ja) * | 1994-12-13 | 1996-06-25 | Nissan Motor Co Ltd | 車両故障診断装置 |
JPH10232874A (ja) | 1997-02-19 | 1998-09-02 | Hitachi Ltd | 情報処理ノウハウ共有方法 |
JPH10275168A (ja) | 1997-03-31 | 1998-10-13 | Hitachi Ltd | 設計支援方法および設計支援システム |
JP2001202125A (ja) * | 2000-01-20 | 2001-07-27 | Snap On Tools Corp | 装置作動状態のダイナミック診断システム |
JP2001317403A (ja) * | 2000-05-01 | 2001-11-16 | Toyota Motor Corp | 異常診断システム及び異常診断データ記憶方法 |
JP2002342508A (ja) * | 2001-05-17 | 2002-11-29 | Nec Fielding Ltd | 自動車の故障検出と修理依頼システムおよび方法 |
JP2003178148A (ja) * | 2001-12-12 | 2003-06-27 | Komatsu Ltd | 機械の保守点検システム、その保守点検方法およびその保守点検プログラム |
JP2004299473A (ja) * | 2003-03-28 | 2004-10-28 | Mazda Motor Corp | 遠隔故障診断システム及びその制御方法、並びに車両 |
JP2008001233A (ja) * | 2006-06-22 | 2008-01-10 | Mazda Motor Corp | 遠隔故障診断システム |
JP2009146059A (ja) * | 2007-12-12 | 2009-07-02 | Autonetworks Technologies Ltd | 診断項目の設定方法、故障診断装置、プログラム及び記録媒体 |
Non-Patent Citations (1)
Title |
---|
See also references of EP2492660A4 |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20160058536A (ko) * | 2014-11-17 | 2016-05-25 | 두산인프라코어 주식회사 | 시야성 가상 검증 방법 |
KR102324425B1 (ko) * | 2014-11-17 | 2021-11-11 | 현대두산인프라코어 주식회사 | 시야성 가상 검증 방법 |
JP6567229B1 (ja) * | 2018-03-30 | 2019-08-28 | 三菱電機株式会社 | 学習処理装置、データ分析装置、分析手法選択方法、及び分析手法選択プログラム |
WO2019187012A1 (ja) * | 2018-03-30 | 2019-10-03 | 三菱電機株式会社 | 学習処理装置、データ分析装置、分析手法選択方法、及び分析手法選択プログラム |
US11042786B2 (en) | 2018-03-30 | 2021-06-22 | Mitsubishi Electric Corporation | Learning processing device, data analysis device, analytical procedure selection method, and recording medium |
JP2019195377A (ja) * | 2018-05-07 | 2019-11-14 | オムロン株式会社 | データ処理装置、モニタリングシステム、覚醒システム、データ処理方法、及びデータ処理プログラム |
JP7099037B2 (ja) | 2018-05-07 | 2022-07-12 | オムロン株式会社 | データ処理装置、モニタリングシステム、覚醒システム、データ処理方法、及びデータ処理プログラム |
JP2021067614A (ja) * | 2019-10-25 | 2021-04-30 | 日立建機株式会社 | 故障診断装置及び故障診断方法 |
JP7217216B2 (ja) | 2019-10-25 | 2023-02-02 | 日立建機株式会社 | 故障診断装置及び故障診断方法 |
Also Published As
Publication number | Publication date |
---|---|
US9057174B2 (en) | 2015-06-16 |
US20120209570A1 (en) | 2012-08-16 |
CN102575973B (zh) | 2015-06-24 |
AU2009354283A1 (en) | 2012-04-19 |
CN102575973A (zh) | 2012-07-11 |
EP2492660A1 (en) | 2012-08-29 |
AU2009354283B2 (en) | 2013-05-30 |
EP2492660A4 (en) | 2017-02-01 |
JPWO2011048661A1 (ja) | 2013-03-07 |
JP5296219B2 (ja) | 2013-09-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2011048661A1 (ja) | 建設機械の診断システム及び診断方法 | |
EP3106949B1 (en) | Monitoring system and monitoring method | |
CN102844721B (zh) | 故障原因诊断系统及其方法 | |
JP6039696B2 (ja) | ショベルの異常判定方法、管理装置、及びショベル | |
US10496466B2 (en) | Preprocessor of abnormality sign diagnosing device and processing method of the same | |
JP6112488B2 (ja) | ショベル、ショベル管理装置、及びショベル管理方法 | |
KR20130065621A (ko) | 주기적 구동계의 이상 검지 장치, 주기적 구동계를 갖는 처리 장치, 주기적 구동계의 이상 검지 방법 및 컴퓨터 프로그램 | |
CN106575117A (zh) | 作业机械的油特性的诊断系统 | |
US20160098637A1 (en) | Automated Data Analytics for Work Machines | |
CN105275043A (zh) | 挖土机支援装置 | |
CN106662504A (zh) | 旋转机械异常检测装置及其方法以及旋转机 | |
US11222202B2 (en) | Targeted testing and machine-learning systems for detecting and identifying machine behavior | |
US10677765B2 (en) | Structural health monitoring of cyclically loaded structures | |
EP4310620A2 (en) | Hybrid ensemble approach for iot predictive modelling | |
CN102763047B (zh) | 用于诊断压缩机的方法和系统 | |
JP5963579B2 (ja) | ショベルの管理装置及びショベルの異常検出方法 | |
CN109839900A (zh) | 数值控制装置 | |
JP2019096014A (ja) | 判定装置,判定プログラム,判定方法 | |
AU2021202999A1 (en) | Fault detection technique for a bearing | |
JPH10134034A (ja) | 時系列データの識別方法およびその識別装置 | |
WO2016117453A1 (ja) | 異常診断分析装置 | |
JP6917805B2 (ja) | データフィルタリング装置および方法 | |
Tsai et al. | A study of function-based diagnosis strategy and testability analysis for a system | |
JP5810877B2 (ja) | 異常診断システム及び異常診断方法 | |
US20200143004A1 (en) | Visualization of machine structure damage from machine sensor data using machine learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 200980161988.7 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 09850559 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2011537044 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2009354283 Country of ref document: AU |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2009850559 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2009354283 Country of ref document: AU Date of ref document: 20091019 Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13502896 Country of ref document: US |