TW201830223A - Time series data processing apparatus and processing method for smoothing processing - Google Patents
Time series data processing apparatus and processing method for smoothing processing Download PDFInfo
- Publication number
- TW201830223A TW201830223A TW107100790A TW107100790A TW201830223A TW 201830223 A TW201830223 A TW 201830223A TW 107100790 A TW107100790 A TW 107100790A TW 107100790 A TW107100790 A TW 107100790A TW 201830223 A TW201830223 A TW 201830223A
- Authority
- TW
- Taiwan
- Prior art keywords
- time
- series data
- processing
- data
- smoothing
- Prior art date
Links
- 238000009499 grossing Methods 0.000 title claims abstract description 163
- 238000012545 processing Methods 0.000 title claims abstract description 151
- 238000003672 processing method Methods 0.000 title claims abstract description 91
- 238000013500 data storage Methods 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims description 110
- 230000008569 process Effects 0.000 claims description 91
- 230000008859 change Effects 0.000 claims description 24
- 238000012544 monitoring process Methods 0.000 claims description 17
- 238000010586 diagram Methods 0.000 description 29
- 230000006870 function Effects 0.000 description 24
- 238000001914 filtration Methods 0.000 description 20
- 239000000284 extract Substances 0.000 description 7
- 238000001514 detection method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 230000000052 comparative effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Recording Measured Values (AREA)
- Indication And Recording Devices For Special Purposes And Tariff Metering Devices (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
Description
本發明係關於一種對從監視物件等採集到的時間序列資料進行平滑化處理的時間序列資料處理裝置及處理方法。 The present invention relates to a time-series data processing device and method for smoothing time-series data collected from surveillance objects and the like.
在多回路的調溫器等當中，為了執行其操作及資料獲取，存在並用具備觸控面板式HMI(Human Machine Interface)的設備的情況。例如在圖25的例子中，在能夠從4回路的調溫器的本體部100分離的顯示部101上設置有帶觸控面板功能的顯示器102。 In a multi-loop thermostat or the like, in order to perform operations and data acquisition thereof, there are cases where a device having a touch panel HMI (Human Machine Interface) is used in combination. For example, in the example of FIG. 25, a display 102 with a touch panel function is provided on the display portion 101 that can be separated from the main body portion 100 of the 4-circuit thermostat.
近年來，存在運用資料分析技術來創造新的價值的需求。對於調溫器等測量控制設備，也對從測量控制設備獲得的時間序列資料運用有多種多樣的資料分析技術。例如，專利文獻1中提出有一種用於對任意資料通用地運用而獲得判斷指標的資料處理方法。專利文獻1所公開的技術如下：獲取監視物件生產設備的時間運轉率、性能運轉率、產品良率這3個指標的時間序列資料，將這3個指標的時間序列資料合成而生成作為綜合指標的設備綜合效率的時間序列資料，檢測設備綜合效率的值中出現有意義的變化的點作為生產設備的狀態的變化點。 In recent years, there has been a need to use data analysis techniques to create new value. For measurement and control equipment such as thermostats, various data analysis techniques are also applied to the time series data obtained from the measurement and control equipment. For example, Patent Document 1 proposes a data processing method for universally using arbitrary data to obtain a judgment index. The technique disclosed in Patent Document 1 is as follows: acquiring time series data of three indexes of time operation rate, performance operation rate, and product yield rate of production equipment for monitoring objects, and synthesizing time series data of these three indexes as a comprehensive index Time series data of the comprehensive efficiency of the equipment, and the point where a meaningful change occurs in the value of the comprehensive efficiency of the detection equipment is used as the change point of the state of the production equipment.
在專利文獻1所公開的技術中，為了計算時刻t下的生產設備的運轉實際狀況(時間運轉率、性能運轉率、產品良率)和設備綜合效率，要使用時刻t的最近的規定期間p內的資料(時刻t-p到時刻t的資料)。此處，p的值任意， 但是，若減小p的值，則時間序列資料中雜訊增多，因此有變化點的誤檢測增加之虞，若增大p的值，則時間序列資料平滑化的程度變得過強，從而有變化點檢測的靈敏度變差之虞。因而，在專利文獻1所公開的技術中，是根據誤檢測與靈敏度的平衡而將規定期間p設定為適當的值。 In the technique disclosed in Patent Document 1, in order to calculate the actual operating conditions (time operating rate, performance operating rate, product yield) and overall equipment efficiency of the production equipment at time t, the most recent predetermined period p at time t is used. Within the data (data from time tp to time t). Here, the value of p is arbitrary, but if the value of p is decreased, the noise in the time series data will increase, so there may be an increase in false detection of change points. If the value of p is increased, the time series data will be smoothed. The degree becomes too strong, and there is a possibility that the sensitivity of the change point detection becomes worse. Therefore, in the technique disclosed in Patent Document 1, the predetermined period p is set to an appropriate value based on the balance between erroneous detection and sensitivity.
如此，在對時間序列資料進行平滑化處理時，為了恰當地決定平滑化處理的參數，需要基於專業知識的試錯，從而存在需要對於操作人員而言較為繁雜的作業這一問題。需要這種試錯的狀況不僅是決定參數時是必要的，在決定通過何種處理方法來進行平滑化處理時也是必要的。 In this way, when smoothing the time series data, in order to properly determine the parameters of the smoothing process, trial and error based on professional knowledge is required, and there is a problem that a complicated operation for the operator is required. The situation where such trial and error is required is not only necessary when deciding parameters, but also when deciding which processing method to perform smoothing processing.
〔專利文獻1〕日本專利特開2015-152933號公報 [Patent Document 1] Japanese Patent Laid-Open No. 2015-152933
本發明是為了解決上述問題而成，其目的在於提供一種能夠降低用以決定平滑化處理的處理方法和參數的試錯的繁雜性的時間序列資料處理裝置及處理方法。 The present invention has been made to solve the above-mentioned problems, and an object thereof is to provide a time-series data processing device and a processing method capable of reducing the complexity of trial and error for processing methods and parameters for smoothing processing.
本發明的時間序列資料處理裝置的特徵在於具備：資料存儲部，其構成為存儲處理物件的時間序列資料；處理方法存儲部，其構成為預先存儲針對所述時間序列資料的平滑化處理的一種至多種處理方法；顯示部，其構成為顯示資訊；輸入部，其構成為接收操作人員的操作；資料顯示控制部，其構成為使所述時間序列資料的波形顯示在所述顯示部上；參考軌跡輸出部，其根據操作人員對所述輸入部的操作來輸出表示平滑化處理後的時間序列資料的理想軌跡的參考軌跡資料；以及處理探索執行部，其構成為一邊逐次變更所述平滑化處理的處理方法以及所述平滑化處理的參數中的至少一方，一邊對所述資料存儲部中存儲的時間序列資料執行平滑化處理，並探索對該時間序列資 料實施平滑化處理所得的結果與所述參考軌跡資料最符合的所述處理方法及所述參數中的至少一方。 The time-series data processing device of the present invention is characterized by including: a data storage unit configured to store time-series data of a processing object; and a processing method storage unit configured to store a smoothing process for the time-series data in advance. To a variety of processing methods; a display section configured to display information; an input section configured to receive an operator's operation; a data display control section configured to display a waveform of the time series data on the display section; The reference trajectory output unit outputs reference trajectory data representing an ideal trajectory of the time-series data after smoothing processing according to the operation of the input unit by the operator; and a processing exploration execution unit configured to sequentially change the smoothing while At least one of the processing method of the smoothing process and the parameters of the smoothing process, while performing a smoothing process on the time series data stored in the data storage unit, and exploring a result obtained by performing a smoothing process on the time series data The processing method and the most consistent with the reference trajectory data At least one of the parameters.
此外，本發明的時間序列資料處理裝置的一構成例的特徵在於，還具備探索結果顯示控制部，所述探索結果顯示控制部構成為使通過所述探索而確定後的處理方法及參數顯示 A configuration example of the time-series data processing device according to the present invention further includes a search result display control unit configured to display a processing method and a parameter display after the search is determined.
此外，本發明的時間序列資料處理裝置的一構成例的特徵在於，還具備區域分割處理部，所述區域分割處理部構成為以預先規定的次序分割所述資料存儲部中存儲的時間序列資料的時間區域，所述處理探索執行部針對分割後的每一時間區域而執行所述平滑化處理，並針對所述每一時間區域而探索所述處理方法及所述參數中的至少一方。此外，本發明的時間序列資料處理裝置的一構成例的特徵在於，所述區域分割處理部均等地分割所述時間序列資料的時間區域。此外，本發明的時間序列資料處理裝置的一構成例的特徵在於，還具備資料獲取部，所述資料獲取部構成為從監視物件的裝置採集處理物件的時間序列資料並存儲至所述資料存儲部，所述區域分割處理部針對所述監視物件的裝置的狀態的每一切換而分割所述時間序列資料的時間區域。此外，本發明的時間序列資料處理裝置的一構成例的特徵在於，還具備探索結果顯示控制部，所述探索結果顯示控制部構成為針對分割後的每一時間區域而使通過所述探索而確定後的處理方法及參數顯示在所述顯示部上。 In addition, a configuration example of the time-series data processing device according to the present invention is characterized by further including a region division processing unit configured to divide the time-series data stored in the data storage unit in a predetermined order. Time zone, the processing search execution unit executes the smoothing process for each time zone after division, and searches for at least one of the processing method and the parameter for each time zone. A configuration example of the time-series data processing device according to the present invention is characterized in that the region division processing unit equally divides time regions of the time-series data. In addition, a configuration example of the time-series data processing device of the present invention is characterized by further including a data acquisition unit configured to collect time-series data of a processing object from a device monitoring the object and store the time-series data of the processing object in the data storage. The region division processing unit divides a time region of the time series data for each switching of the state of the device of the monitoring object. In addition, a configuration example of the time-series data processing device according to the present invention is characterized by further including a search result display control unit configured to perform the search through the search for each of the divided time regions. The determined processing method and parameters are displayed on the display section.
此外，本發明的時間序列資料處理裝置的一構成例的特徵在於，所述處理方法為基於中值濾波(median filter)的處理方法和基於低通濾波的處理方法中的至少一方，所述參數為所述中值濾波的資料數以及所述低通濾波的時間常數中的至少一方。此外，本發明的時間序列資料處理裝置的一構成例的特徵在於，還具備平滑化處理結果顯示控制部，所述平滑化處理結果顯示控制部構成為使所述資料存儲部中存儲的時間序列資料的波形和通過所述探索而 確定後的平滑化處理後的時間序列資料的波形重疊地顯示在所述顯示部上。此外，本發明的時間序列資料處理裝置的一構成例的特徵在於，所述顯示部和所述輸入部為帶觸控面板功能的顯示元件，所述參考軌跡輸出部接收根據操作人員對所述帶觸控面板功能的顯示元件的畫面的操作而從所述帶觸控面板功能的顯示元件輸出的位置座標信號，將該位置座標信號表示的畫面上的各點轉換為與所述資料存儲部中存儲的時間序列資料相同的坐標系上的點，由此生成由轉換後的各點匯集而成的所述參考軌跡資料。 A configuration example of the time-series data processing device of the present invention is characterized in that the processing method is at least one of a processing method based on a median filter and a processing method based on a low-pass filter, and the parameter is Is at least one of the number of data of the median filtering and the time constant of the low-pass filtering. In addition, a configuration example of the time-series data processing device of the present invention is characterized by further including a smoothing processing result display control unit configured to cause the time series stored in the data storage unit to be stored. The waveform of the data and the waveform of the time-series data after the smoothing process determined after the search are superimposed are displayed on the display unit. In addition, a configuration example of the time-series data processing device according to the present invention is characterized in that the display section and the input section are display elements with a touch panel function, and the reference trajectory output section receives the operator's The position coordinate signal output from the display element with a touch panel function is operated on the screen of the display element with a touch panel function, and each point on the screen indicated by the position coordinate signal is converted to the data storage unit. The points on the same coordinate system of the time series data stored in the reference data are generated from the reference trajectory data collected from the converted points.
此外，本發明的時間序列資料處理方法的特徵在於包含：第1步驟，使資料存儲部中存儲的處理物件的時間序列資料的波形顯示在顯示部上；第2步驟，根據操作人員對輸入部的操作而生成表示平滑化處理後的時間序列資料的理想軌跡的參考軌跡資料；以及第3步驟，參考預先存儲針對所述時間序列資料的平滑化處理的一種至多種處理方法的處理方法存儲部，一邊逐次變更所述平滑化處理的處理方法以及所述平滑化處理的參數中的至少一方，一邊對所述資料存儲部中存儲的時間序列資料執行平滑化處理，並探索對該時間序列資料實施平滑化處理所得的結果與所述參考軌跡資料最符合的所述處理方法及所述參數中的至少一方。 In addition, the time-series data processing method of the present invention is characterized by including: a first step of displaying the waveform of the time-series data of the processing object stored in the data storage section on the display section; and the second step, according to the input section of the operator Operation to generate reference trajectory data representing an ideal trajectory of the time-series data after the smoothing process; and a third step, referring to a processing method storage unit that previously stores one or more processing methods for smoothing the time-series data. , While sequentially changing at least one of the processing method of smoothing processing and the parameters of the smoothing processing, perform smoothing processing on time series data stored in the data storage unit, and explore the time series data At least one of the processing method and the parameter that is best matched with the reference trajectory data as a result of the smoothing processing.
根據本發明，使處理物件的時間序列資料的波形顯示在顯示部上，根據操作人員對輸入部的操作而生成表示平滑化處理後的時間序列資料的理想軌跡的參考軌跡資料，一邊逐次變更平滑化處理的處理方法以及平滑化處理的參數中的至少一方，一邊對時間序列資料執行平滑化處理，並探索對該時間序列資料實施平滑化處理所得的結果與參考軌跡資料最符合的處理方法及參數中的至少一方，由此，能夠根據操作人員所輸入的軌跡而恰當地決定平滑化處理的處理方法及參數中的至少一方，因此，能夠降低用以決定處理方法和參 數的試錯的繁雜性。 According to the present invention, the waveform of the time-series data of the processing object is displayed on the display unit, and the reference trajectory data indicating the ideal trajectory of the time-series data after the smoothing process is generated according to the operation of the input unit by the operator, and the smoothing is changed one by one. At least one of the processing method of the smoothing process and the parameters of the smoothing process, while performing the smoothing process on the time series data, and exploring the processing method in which the results obtained by performing the smoothing process on the time series data are most consistent with the reference trajectory data and At least one of the parameters can appropriately determine at least one of the processing method and the parameters of the smoothing processing based on the trajectory input by the operator, and therefore, the complexity of trial and error for determining the processing method and the parameters can be reduced. Sex.
此外，在本發明中，以預先規定的次序分割處理物件的時間序列資料的時間區域，針對分割後的每一時間區域執行平滑化處理，而針對每一時間區域而探索處理方法及參數中的至少一方，由此，能夠根據時間序列資料的特性的變化、操作人員所輸入的軌跡的變化而恰當地決定平滑化處理的處理方法及參數中的至少一方。 In addition, in the present invention, the time region of the time series data of the processing object is divided in a predetermined order, the smoothing process is performed for each time region after the division, and the processing methods and parameters in each time region are explored. At least one of them can appropriately determine at least one of the processing method and parameters of the smoothing process based on changes in the characteristics of the time-series data and changes in the trajectory input by the operator.
此外，在本發明中，針對監視物件的裝置的狀態的每一切換而分割時間序列資料的時間區域，由此，能夠提高使平滑化處理適應時間序列資料的特性變化的概率。 In addition, in the present invention, the time region of the time series data is divided for each switching of the state of the device of the monitoring object, so that the probability of adapting the smoothing process to a change in the characteristics of the time series data can be increased.
1‧‧‧資料獲取部 1‧‧‧Data Acquisition Department
2‧‧‧資料存儲部 2‧‧‧Data Storage Department
3‧‧‧處理方法存儲部 3‧‧‧Processing method storage
4‧‧‧帶觸控面板功能的顯示元件 4‧‧‧ Display element with touch panel function
5‧‧‧資料顯示控制部 5‧‧‧Data Display Control Department
6‧‧‧參考軌跡輸出部 6‧‧‧Reference track output section
7、7a‧‧‧處理探索執行部 7, 7a ‧ ‧ ‧ Processing Exploration Executive
8、8a‧‧‧探索結果顯示控制部 8, 8a‧‧‧ Exploration result display control unit
9‧‧‧平滑化處理結果顯示控制部 9‧‧‧ Smoothing processing result display control unit
10‧‧‧區域分割處理部 10‧‧‧ Regional Division Processing Department
圖1為表示從監視物件採集到的時間序列資料的1例的圖。 FIG. 1 is a diagram showing an example of time-series data collected from a monitoring object.
圖2為表示對圖1的時間序列資料實施基於一階遲滯後低通濾波的平滑化處理的結果的圖。 FIG. 2 is a diagram showing a result of performing smoothing processing based on first-order lag low-pass filtering on the time-series data of FIG. 1.
圖3為表示對圖1的時間序列資料實施基於一階遲滯後低通濾波的平滑化處理的另一結果的圖。 FIG. 3 is a diagram showing another result of performing smoothing processing based on first-order lag low-pass filtering on the time-series data of FIG. 1.
圖4為表示對圖1的時間序列資料實施基於中值濾波的平滑化處理的結果的圖。 FIG. 4 is a diagram showing a result of performing a smoothing process by a median filter on the time-series data of FIG. 1.
圖5為表示對圖1的時間序列資料實施基於中值濾波的平滑化處理的另一結果的圖。 FIG. 5 is a diagram showing another result of performing a smoothing process based on a median filter on the time-series data of FIG. 1.
圖6為表示本發明的第1實施例的時間序列資料處理裝置的構成的方塊圖。 FIG. 6 is a block diagram showing a configuration of a time-series data processing device according to the first embodiment of the present invention.
圖7為說明本發明的第1實施例的時間序列資料處理裝置的工作流程圖。 FIG. 7 is a flowchart illustrating the operation of the time-series data processing device according to the first embodiment of the present invention.
圖8為表示本發明的第1實施例中操作人員輸入平滑化處理後的時間序列資 料的理想軌跡的例子的圖。 Fig. 8 is a diagram showing an example of an ideal trajectory of the time-series data input by the operator after smoothing processing in the first embodiment of the present invention.
圖9為表示本發明的第1實施例中操作人員輸入平滑化處理後的時間序列資料的理想軌跡的另一例的圖。 FIG. 9 is a diagram showing another example of the ideal trajectory of the time-series data input by the operator after the smoothing process in the first embodiment of the present invention.
圖10為表示本發明的第1實施例的時間序列資料處理裝置的平滑化處理結果顯示控制部的顯示例的圖。 10 is a diagram showing a display example of a smoothing processing result display control unit of the time-series data processing device according to the first embodiment of the present invention.
圖11為表示本發明的第1實施例的時間序列資料處理裝置的平滑化處理結果顯示控制部的另一顯示例的圖。 11 is a diagram showing another display example of the smoothing processing result display control unit of the time-series data processing device according to the first embodiment of the present invention.
圖12為表示本發明的第1實施例的時間序列資料處理裝置的平滑化處理結果顯示控制部的另一顯示例的圖。 FIG. 12 is a diagram showing another display example of the smoothing processing result display control unit of the time-series data processing device according to the first embodiment of the present invention.
圖13為表示本發明的第1實施例的時間序列資料處理裝置的平滑化處理結果顯示控20制部的另一顯示例的圖。 13 is a diagram showing another display example of the smoothing processing result display control unit of the time-series data processing device according to the first embodiment of the present invention.
圖14為表示基於圖8所示的軌跡的參考軌跡資料的差分值和圖2所示的以往的平滑化處理的時間序列資料的差分值的圖。 FIG. 14 is a diagram showing a difference value of reference trajectory data based on the trajectory shown in FIG. 8 and a difference value of time series data of a conventional smoothing process shown in FIG. 2.
圖15為表示基於圖9所示的軌跡的參考軌跡資料的差分值和圖3所示的以往的平滑化處理的時間序列資料的差分值的圖。 FIG. 15 is a diagram showing a difference value of reference trajectory data based on the trajectory shown in FIG. 9 and a difference value of time series data of a conventional smoothing process shown in FIG. 3.
圖16為表示基於圖8所示的軌跡的參考軌跡資料的差分值和本發明的第1實施例的平滑化處理的時間序列資料的差分值的圖。 FIG. 16 is a diagram showing a difference value of a reference trajectory data based on the trajectory shown in FIG. 8 and a difference value of time series data of a smoothing process according to the first embodiment of the present invention.
圖17為表示基於圖9所示的軌跡的參考軌跡資料的差分值和本發明的第1實施例的平滑化處理的時間序列資料的差分值的圖。 FIG. 17 is a diagram showing a difference value of reference trajectory data based on the trajectory shown in FIG. 9 and a difference value of time-series data of a smoothing process according to the first embodiment of the present invention.
圖18為表示本發明的第2實施例的時間序列資料處理裝置的構成的方塊圖。 18 is a block diagram showing a configuration of a time-series data processing device according to a second embodiment of the present invention.
圖19為說明本發明的第2實施例的時間序列資料處理裝置的工作流程圖。 FIG. 19 is a flowchart illustrating the operation of the time-series data processing device according to the second embodiment of the present invention.
圖20為表示從監視物件採集到的時間序列資料的另一例的圖。 FIG. 20 is a diagram showing another example of time-series data collected from a monitoring object.
圖21為表示本發明的第2實施例中操作人員輸入平滑化處理後的時間序列 資料的理想軌跡的例子的圖。 Fig. 21 is a diagram showing an example of an ideal trajectory of the time-series data after the smoothing process is input by the operator in the second embodiment of the present invention.
圖22為表示本發明的第2實施例中操作人員輸入平滑化處理後的時間序列資料的理想軌跡的另一例的圖。 FIG. 22 is a diagram showing another example of an ideal trajectory of the time-series data after the smoothing process is input by the operator in the second embodiment of the present invention.
圖23為表示本發明的第2實施例中操作人員輸入平滑化處理後的時間序列資料的理想軌跡的另一例的圖。 FIG. 23 is a diagram showing another example of the ideal trajectory of the time-series data input by the operator after the smoothing process in the second embodiment of the present invention.
圖24為表示本發明的第2實施例的時間序列資料處理裝置的平滑化處理結果顯示控制部的顯示例的圖。 24 is a diagram showing a display example of a smoothing processing result display control unit of a time-series data processing device according to a second embodiment of the present invention.
圖25為多回路調溫器的外觀圖。 Fig. 25 is an external view of a multi-loop thermostat.
[發明的原理1] [Principle of Invention 1]
作為針對時間序列資料的分析處理的代表例之一，有去除雜訊成分的平滑化處理。在該平滑化處理中，與前文所述的專利文獻1的規定期間相當的參數值(關注的資料數或資料時間)的決定也較為重要。平滑化處理的目的之一是時間序列資料的採集源的測量物件或控制物件的本質的特性掌握，此外是特性變化的監視。並且，對於物件的監視較為熟練的操作人員大多能夠憑直覺掌握如何對平滑化前的時間序列資料進行平滑化將便於物件的監視。 As one of the representative examples of analysis processing of time series data, there is a smoothing processing for removing noise components. In this smoothing process, the determination of parameter values (the number of data to be focused or the time of data) corresponding to the predetermined period of Patent Document 1 described above is also important. One of the purposes of the smoothing process is to grasp the essential characteristics of the measurement object or control object of the collection source of the time-series data, and also to monitor the change of characteristics. In addition, most skilled operators who monitor objects can intuitively grasp how to smooth the time-series data before smoothing, which will facilitate the monitoring of objects.
因此，發明者想到了如下方法：在帶觸控面板功能的顯示器上顯示平滑化處理前的時間序列資料，使操作人員通過觸控面板的描畫操作等來輸入平滑化處理後的時間序列資料的軌跡圖像，由此獲得用以自動決定平滑化處理的處理方法和參數的參考軌跡。根據該方法，能夠自動決定與對監視較為熟練的操作人員的直覺相匹配的處理方法和參數的值，因此能夠降低試錯的繁雜性。 Therefore, the inventor thought of a method of displaying the time-series data before the smoothing process on a display with a touch panel function, so that an operator can input the time-series data after the smoothing process through a drawing operation of the touch panel, and the like. The trajectory image, thereby obtaining a reference trajectory for automatically determining the processing method and parameters of the smoothing process. According to this method, it is possible to automatically determine a processing method and a value of a parameter that match the intuition of an operator skilled in monitoring, so that the complexity of trial and error can be reduced.
[發明的原理2] [Principle of Invention 2]
在操作人員輸入平滑化處理後的時間序列資料的理想軌跡圖像時，未必會對時間序列資料的全部區域都一律以相同平滑化感覺進行軌跡的輸入操作。時間序列資料本身也未必在全部區域內都一律是相同特性。因而，針對時間序列資料的全部區域而獲得同樣的處理方法和參數的值是不合理的。另一方面，認為操作人員的平滑化感覺、時間序列資料的特性也難以發生頻繁地變化是較為妥當的。 When the operator inputs the ideal trajectory image of the time-series data after the smoothing process, the entire area of the time-series data may not always be input with the same smoothing sensation. The time series data itself may not always have the same characteristics in all regions. Therefore, it is not reasonable to obtain the same processing method and parameter values for all regions of the time series data. On the other hand, it is considered appropriate that the smooth feeling of the operator and the characteristics of the time-series data are unlikely to change frequently.
因而，較佳簡單地以2分割、4分割、8分割的方式對時間序列資料全部區域進行劃分，在各區域內分別進行自動決定處理。結果，雖然也有可能在多個區域內成為相同處理方法、相同參數值，但暫且進行分割是上策。此外，對於區域分割，不僅簡單地進行等分割，也能夠考慮如下方法，即，從MES(Manufacturing Execution System，製造執行系統)等獲取監視物件的裝置的狀態資訊(模式資訊等)，針對狀態的每一切換(模式不同的每面一區域)而進行自動分割。在該情況下，能夠期待與時間序列資料的特性變化一致的概率變高。 Therefore, it is preferable to simply divide the entire area of the time series data into 2 divisions, 4 divisions, and 8 divisions, and perform automatic decision processing in each region. As a result, although it is possible to have the same processing method and the same parameter value in a plurality of regions, it is best to perform division for the time being. In addition, for the area division, not only simple equal division, but also a method can be considered, that is, the MES (Manufacturing Execution System, manufacturing execution system) and other devices to obtain the status information (mode information, etc.) of the monitoring object, Automatic segmentation is performed for each switch (one area per side with different modes). In this case, it is expected that the probability of matching the change in characteristics of the time-series data will be high.
[第1實施例] [First embodiment]
下面，參考圖式，對本發明的實施例進行說明。本實施例是對應於上述發明的原理1的例子。 Hereinafter, embodiments of the present invention will be described with reference to the drawings. This embodiment is an example corresponding to principle 1 of the above-mentioned invention.
[用以驗證本實施例的效果的比較例] [Comparative example to verify the effect of this embodiment]
首先，對用以驗證本實施例的效果的比較例進行說明。圖1的例子表示以0.1秒週期從監視物件採集到的時間序列資料D1(溫度資料)。在該例中，時間序列資料D1中重登有測量雜訊、1秒週期左右的高頻變動、以及12秒週期左右的低頻變動。在本實施例中，設想對於操作人員而言相對不繁雜的作業，對限定於單一種類的平滑化處理加以運用的情況進行說明。若是單一種類的平滑化處理，則應進行試錯的參數數能夠精簡為1個，因此，例如能以從較小的數值起逐次少量增大這樣的簡單的作業的形式實施。 First, a comparative example for verifying the effect of this embodiment will be described. The example in FIG. 1 shows time-series data D1 (temperature data) collected from a monitoring object at a period of 0.1 second. In this example, the time series data D1 is re-registered with measurement noise, high-frequency fluctuations around a 1-second period, and low-frequency fluctuations around a 12-second period. In the present embodiment, it is assumed that a relatively uncomplicated task for the operator is applied to a case where a smoothing process limited to a single type is applied. In the case of a single type of smoothing process, the number of parameters to be trial-and-error can be reduced to one. Therefore, for example, it can be implemented in the form of a simple operation of gradually increasing the number from a small value.
再者，本發明的時間序列資料是在規定的每一採樣週期採集的離散型資料，但圖1中是以連續波形來表現時間序列資料。對於後面的圖，也同樣地以連續波形來表現時間序列資料和對時間序列資料進行平滑化處理之後的資料。 In addition, the time series data of the present invention is discrete data collected at a predetermined sampling period, but the time series data is represented by a continuous waveform in FIG. 1. In the following figures, the time series data and the data obtained by smoothing the time series data are similarly represented by continuous waveforms.
圖2的D2表示為提取圖1的時間序列資料D1的高頻變動而對時間序列資料D1實施基於一階遲滯後低通濾波的平滑化處理的結果。在圖2的例子中，將一階遲滯後低通濾波的時間常數設定為0.13秒。圖3D3表示為提取時間序列資料D1的低頻變動而對時間序列資料D1實施基於另一一階遲滯後低通濾波的平滑化處理的結果。在圖3的例子中，將一階遲滯後低通濾波的時間常數設定為1.8秒。 D2 in FIG. 2 shows a result of performing a smoothing process based on a first-order lag low-pass filter on the time-series data D1 to extract high-frequency fluctuations of the time-series data D1 in FIG. 1. In the example of FIG. 2, the time constant of the low-pass filtering of the first-order lag is set to 0.13 seconds. FIG. 3D3 shows the result of performing smoothing processing based on another first-order lag low-pass filter on the time series data D1 in order to extract the low-frequency variation of the time series data D1. In the example of FIG. 3, the time constant of the low-pass filtering of the first-order lag is set to 1.8 seconds.
圖4的D4表示為提取時間序列資料DI的高頻變動而對時間序列資料D1實施基於中值濾波的平滑化處理的結果。在圖4的例子中，將針對包含處理物件的關注資料和其附10近的資料的共計3個資料的中值濾波的結果作為關注資料的平滑化處理結果。圖5的D5表示為提取時間序列資料D1的低頻變動而對時間序列資料D1實施基於另一中值濾波的平滑化處理的結果。在圖5的例子中，將針對包含處理物件的關注資料和其附近的資料的共計11個資料的中值濾波的結果作為關注資料的平滑化處理結果。 D4 in FIG. 4 shows a result of performing a smoothing process based on a median filter on the time-series data D1 in order to extract high-frequency fluctuations of the time-series data DI. In the example of FIG. 4, a result of median filtering of a total of three data including the attention data of the processing object and data near it is used as the smoothing processing result of the attention data. D5 in FIG. 5 shows a result of performing a smoothing process based on another median filter on the time series data D1 in order to extract the low-frequency variation of the time series data D1. In the example of FIG. 5, a result of median filtering on a total of 11 pieces of data including the attention data of the processing object and the data in the vicinity is used as the smoothing processing result of the attention data.
在基於低通濾波的平滑化處理中，與原時間序列資料D1相對應的處理後的資料D2、D3的振幅的衰減和相位的偏移較為顯眼。另一方面，在基於中值濾波的平滑化處理中，相對於原時間序列資料D1的變化而言，處理後的資料4、D5不跟隨並頻繁地產生同一值連續的部位。如此，圖2~圖5所示的結果可以說在物件的本質的特性掌握或者特性變化的監視這一目的上還有改善的餘地。 In the smoothing processing based on the low-pass filtering, the attenuation and phase shift of the processed data D2 and D3 corresponding to the original time series data D1 are more prominent. On the other hand, in the smoothing process based on the median filter, compared with the change of the original time series data D1, the processed data 4, D5 do not follow and frequently produce parts with the same continuous value. In this way, it can be said that the results shown in FIG. 2 to FIG. 5 have room for improvement for the purpose of grasping the essential characteristics of the object or monitoring the changes in characteristics.
圖6為表示本實施例的時間序列資料處理裝置的構成的方塊圖。 時間序列資料處理裝置具備：資料獲取部1，其從監視物件採集時間序列資料，資料存儲部2，其存儲採集到的時間序列資料；處理方法存儲部3，其預先存儲針對時間序列資料的平滑化處理的一種至多種處理方法(運算次序)；帶觸控面板功能的顯示元件4，其是向操作人員傳達資訊的顯示部，同時也是接收來自操作人員的操作的輸入部；資料顯示控制部5，其使資料存儲部2中存儲的時間序列資料的波形顯示在帶觸控面板功能的顯示元件4上；參考軌跡輸出部6，其根據操作人員的操作而輸出表示平滑化處理後的時間序列資料的理想軌跡的參考軌跡資料；處理探索執行部7，其一邊逐次變更平滑化處理的處理方法以及平滑化處理的參數中的至少一方，一邊對資料存儲部2中存儲的時間序列資料執行平滑化處理，並探索30對該時間序列資料實施平滑處理所得的結果與參考軌跡資料最符合的處理方法及參數中的至少一方；探索結果顯示控制部8，其顯示探索結果；以及平滑化處理結果顯示控制9，其顯示平滑化處理結果。 FIG. 6 is a block diagram showing a configuration of a time-series data processing apparatus according to the present embodiment. The time-series data processing device includes: a data acquisition unit 1 that collects time-series data from a monitored object, a data storage unit 2 that stores the collected time-series data, and a processing method storage unit 3 that previously stores smoothing for time-series data. One or more processing methods (calculation order) of the processing process; the display element 4 with a touch panel function is a display unit that conveys information to the operator, and also an input unit that receives operations from the operator; a data display control unit 5, which causes the waveform of the time-series data stored in the data storage unit 2 to be displayed on the display element 4 with a touch panel function; with reference to the trajectory output unit 6, which outputs the time after smoothing processing according to the operation of the operator Reference trajectory data of the ideal trajectory of the sequence data; the processing exploration execution unit 7 executes the time series data stored in the data storage unit 2 while sequentially changing at least one of the smoothing processing method and the smoothing parameters. Smoothing, and explore 30 results obtained by smoothing the time series data Processing method, and parameter and the reference trajectory of the best information for at least one of; the search result display control unit 8, which displays the search result; and a smoothing processing result display control 9, which shows the results of the smoothing process.
接著，參考圖7，對本實施例的時間序列資料處理裝置的動作進行說明。資料獲取部51從監視物件採集時間序列資料(例如溫度資料)(圖7步驟S100)。資料獲取部1所採集到的時間序列資料存儲至資料存儲部2(圖7步驟S101)。接著，資料顯示控制部5使資料存儲部2中存儲的時間序列資料的波形顯示在帶觸控面板功能的顯示元件4上(圖7步驟S102)。 Next, an operation of the time-series data processing device according to this embodiment will be described with reference to FIG. 7. The data acquisition unit 51 collects time-series data (for example, temperature data) from the monitoring object (step S100 in FIG. 7). The time-series data collected by the data acquisition unit 1 is stored in the data storage unit 2 (step S101 in FIG. 7). Next, the data display control unit 5 causes the waveform of the time-series data stored in the data storage unit 2 to be displayed on the display element 4 with a touch panel function (step S102 in FIG. 7).
操作人員查看在帶觸控面板功能的顯示元件4上所顯示的時間序列資料的波形，輸入平滑化處理後的時間序列資料的理想軌跡(波形)。作為輸入方法，在帶觸控面板功能的顯示元件4的畫面上劃動手指或書寫工具等來描畫平滑化處理後的時間序列資料的理想軌跡的方法較為適合。帶觸控面板功能的顯示元件4根據操作人員的操作而逐一檢測手指或書寫工具等所接觸到的畫面上的位置，輸出表示所檢測位置之位置座標信號(圖7步驟15S103)。 The operator checks the waveform of the time series data displayed on the display element 4 with a touch panel function, and inputs the ideal trajectory (waveform) of the time series data after the smoothing process. As an input method, a method of drawing an ideal trajectory of the time-series data after the smoothing process by sliding a finger or a writing tool on the screen of the display element 4 with a touch panel function is suitable. The display element 4 with a touch panel function detects the positions on the screen touched by a finger or a writing tool, etc. one by one according to the operation of the operator, and outputs position coordinate signals indicating the detected positions (step 15S103 in FIG. 7).
圖8、圖9為表示操作人員在帶觸控面板功能的顯示元件4的畫面 40上劃動手指400來輸入平滑化處理後的時間序列資料的理想軌跡的情況的圖。圖8展表示操作人員針對畫面40上顯示的時間序列資料D1有意提取高頻變動而輸入軌跡L1的例子。圖9表示操作人員有意提取低頻變動而輸入軌跡L2的例子。 FIG. 8 and FIG. 9 are diagrams showing a situation where an operator swipes his finger 400 on the screen 40 of the display element 4 with a touch panel function to input an ideal trajectory of the time-series data after the smoothing process. FIG. 8 shows an example in which the operator intentionally extracts high-frequency fluctuations for the time-series data D1 displayed on the screen 40 and inputs the trajectory L1. FIG. 9 shows an example in which the operator intentionally extracts low-frequency fluctuations and inputs the trajectory L2.
當參考軌跡輸出部6接收到從帶觸控面板功能的顯示元件4輸出的位置座標信號時，將位置座標信號所表示的畫面上的各點轉換為與資料存儲部2中存儲的時間序列資料相同的坐標系上的點，由此生成並輸出由轉換後的各點匯集而成的參考軌跡資料(圖7步驟S104)。當然，時間序列資料的坐標系的橫軸為時間，縱軸為資料的值。資料顯示控制部5將時間序列資料轉換為畫面的坐標系上的點並顯示在帶觸控面板功能的顯示元件4上。參考軌跡輸出部6進行與該資料顯示控制部5相反的處理即可。 When the reference trajectory output section 6 receives the position coordinate signals output from the display element 4 with a touch panel function, each point on the screen indicated by the position coordinate signals is converted into time series data stored in the data storage section 2 The points on the same coordinate system are used to generate and output reference trajectory data collected from the converted points (step S104 in FIG. 7). Of course, the horizontal axis of the coordinate system of time series data is time, and the vertical axis is the value of the data. The data display control unit 5 converts the time-series data into points on the screen coordinate system and displays them on the display element 4 with a touch panel function. The reference trajectory output section 6 may perform processing opposite to that of the data display control section 5.
再者，時間序列資料是沿時間軸排列的離散型資料。因此，資料顯示控制部5需要對離散的各資料進行插補而以連續波形顯示時間序列資料。這種插補處理為公知技術，因此省略詳細說明。此外，如後文所述，要利用處理探索執行部7對時間序列資料與參考軌跡資料進行比5較，因此，參考軌跡資料較理想為與時間序列資料相同的離散型資料。即，參考軌跡輸出部6較理想為將參考軌跡資料的各點的時間間隔設為與時間序列資料的採樣週期相同的值。 Furthermore, the time series data are discrete data arranged along the time axis. Therefore, the data display control unit 5 needs to interpolate discrete data to display time series data in a continuous waveform. Since such interpolation processing is a well-known technique, detailed description is omitted. In addition, as will be described later, the processing exploration execution unit 7 is used to compare the time series data with the reference trajectory data. Therefore, the reference trajectory data is preferably the same discrete data as the time series data. That is, the reference trajectory output unit 6 desirably sets the time interval of each point of the reference trajectory data to the same value as the sampling period of the time series data.
接著，處理探索執行部7對資料存儲部2中存儲的時間序列資料執行遵循處理方法存10儲部3中存儲的處理方法的平滑化處理(圖7步驟S105)。在本實施例中，在執行基於中值濾波的平滑化處理之後執行基於一階遲滯後低通濾波的平滑化處理這一處理方法(運算次序)預先被存儲在處理方法存儲部3中。 Next, the processing exploration execution unit 7 performs a smoothing process on the time series data stored in the data storage unit 2 in accordance with the processing method stored in the processing method storage 10 and the storage unit 3 (step S105 in FIG. 7). In the present embodiment, a processing method (operation order) in which the smoothing processing based on the first-order lag low-pass filtering is performed after the smoothing processing based on the median filtering is performed is stored in the processing method storage section 3 in advance.
處理探索執行部7計算平滑化處理後的時間序列資料與參考軌跡 資料的誤差，判定誤差是否為規定的容許值以下(圖7步驟S106)。在平滑化處理後的時間序列資料與參考軌跡資料的誤差超過容許值的情況下，處理探索執行部7變更平滑化處理的處理方法以及平滑化處理的參數中的至少一方(圖7步驟S107)，並返回至步驟S105，再次執行針對時間序列資料的平滑化處理。 The process search execution unit 7 calculates an error between the time-series data and the reference trajectory data after the smoothing process, and determines whether or not the error is below a predetermined allowable value (step S106 in Fig. 7). When the error between the time series data and the reference trajectory data after the smoothing process exceeds an allowable value, the processing exploration execution unit 7 changes at least one of the smoothing process processing method and the parameters of the smoothing process (step S107 in FIG. 7). And return to step S105 to perform the smoothing process on the time series data again.
如此，處理探索執行部7反復執行步驟S105~107的處理直至平滑化處理後的時間序列資料與參考軌跡資料的誤差達到容許值以下為止，由此探索平滑化處理後的時間序列資料與參考軌跡資料最符合的處理方法及參數中的至少一方。作為這種探索方法，可以運用單純形法等公知方法。 In this way, the process exploration execution unit 7 repeatedly executes the processing of steps S105 to 107 until the error between the time series data and the reference trajectory data after the smoothing processing has reached an allowable value or less, thereby searching for the time series data and the reference trajectory after the smoothing processing. At least one of the processing methods and parameters that best match the data. As such a search method, a known method such as a simplex method can be used.
在本實施例中，處理方法存儲部3中預先存儲的處理方法被固定為1種，因此變為探索平滑化處理的參數(例如中值濾波的資料數和一階遲滯後低通濾波的時間常數)的最佳解。再者，較佳在處理方法存儲部3中預先存儲與平滑化處理的處理方法相對應的參數的上下限值。由此，處理探索執行部7在上下限值的範圍內變更參數。 In this embodiment, since the processing method stored in the processing method storage unit 3 is fixed to one type, it becomes a parameter for exploring the smoothing processing (for example, the number of data of the median filter and the time of the low-pass filtering of the first-order lag). Constant). Furthermore, it is preferable that the processing method storage unit 3 stores the upper and lower limits of the parameters corresponding to the processing method of the smoothing processing in advance. As a result, the process search execution unit 7 changes the parameters within the range of the upper and lower limits.
當平滑化處理後的時間序列資料與參考軌跡資料的誤差達到容許值以下而探索結束時(步驟S106中的“是”)，探索結果顯示控制部8使探索結果即處理方法的名稱以及參數的值顯示在帶觸控面板功能的顯示元件4上(圖7步驟S108)。 When the error between the time-series data and the reference trajectory data after the smoothing processing has reached an allowable value or less and the search is completed (YES in step S106), the search result display control unit 8 causes the search result, that is, the name of the processing method and the parameters The value is displayed on the display element 4 with a touch panel function (step S108 in FIG. 7).
平滑化處理結果顯示控制部9使通過處理方法及參數的探索而確定的平滑化處理後的時間序列資料的波形以與已顯示出來的時間序列資料的波形重疊的方式顯示在帶觸控面板功能的顯示元件4上(圖步驟S109)。與資料顯示控制部5的情況一樣，平滑化處理結果顯示控制部9對離散的各資料進行插補而以連續波形顯示平滑化處理後的時間序列資料。 Smoothing processing result display control unit 9 displays the waveform of the time-series data after smoothing processing determined by searching for processing methods and parameters on the touch panel function so as to overlap the waveform of the displayed time-series data. On the display element 4 (step S109 in the figure). As in the case of the data display control unit 5, the smoothing process result display control unit 9 interpolates the discrete data and displays the time-series data after the smoothing process in a continuous waveform.
此外，平滑化處理結果顯示控制部9也可以使參考軌跡資料的波形和通過處理方法及參數的探索而確定的平滑化處理後的時間序列資料的波形 以重疊的方式顯示在帶觸控面板功能的顯示元件4上(圖7步驟S110)。然後，時間序列資料處理裝置的處理結束。 In addition, the smoothing processing result display control unit 9 may display the waveform of the reference trajectory data and the waveform of the time-series data after smoothing processing determined by searching for processing methods and parameters in an overlapping manner with a touch panel function. On the display element 4 (step S110 in FIG. 7). Then, the processing of the time-series data processing device ends.
圖10~圖13為表示平滑化處理結果顯示控制部9的顯示例的圖。圖10表示在帶觸控面板功能的顯示元件4的畫面40上以重疊的方式顯示平滑化處理前的時間序列資料D1的波形和通過處理方法及參數的探索而確定的平滑化處理後的時間序列資料D6的波形的例子。平滑化處理後的時間序列資料D6表示根據有意提取時間序列資料DI的高頻變動而輸入的軌跡L1(圖8)來探索平滑化處理的參數的結果。如上所述，在本實施例中，在執行基於中值濾波的平滑化處理之後執行基於一階遲滯後低通濾波的平滑化處理這一處理方法預先存儲在處理方法存儲部3中。探索的結果所獲得的參數的最佳解為，中值濾波的資料數為3個，一階遲滯後低通濾波的時間常數為0.05秒。 10 to 13 are diagrams showing display examples of the smoothing processing result display control unit 9. FIG. 10 shows the waveform of the time-series data D1 before the smoothing process and the time after the smoothing process determined by the exploration of the processing method and parameters on the screen 40 of the display element 4 with a touch panel function in an overlapping manner. Example of the waveform of the sequence data D6. The time-series data D6 after the smoothing process indicates a result of exploring the parameters of the smoothing process based on the trajectory L1 (FIG. 8) inputted by intentionally extracting the high-frequency fluctuation of the time-series data DI. As described above, in the present embodiment, the processing method of performing the smoothing processing based on the first-order lag low-pass filtering after performing the smoothing processing based on the median filtering is stored in the processing method storage section 3 in advance. The best solution to the parameters obtained from the exploration results is that the number of median filtered data is 3 and the time constant of the low-pass filtering of the first-order hysteresis is 0.05 seconds.
圖11表示在畫面40上以重疊的方式顯示平滑化處理前的時間序列資料D1的波形和平滑化處理後的時間序列資料D7的波形的例子。平滑化處理後的時間序列資料D7表示根據有意提取時間序列資料D1的低頻變動而輸入的軌跡L2(圖9)來探索平滑化處理的參數的結果。探索的結果所獲得的參數的最佳解為，中值濾波的資料數為11個，一階遲滯後低通濾波的時間常數為0.35秒。 FIG. 11 shows an example in which the waveform of the time-series data D1 before the smoothing process and the waveform of the time-series data D7 after the smoothing process are displayed on the screen 40 in an overlapping manner. The time-series data D7 after the smoothing process represents a result of exploring the parameters of the smoothing process based on the trajectory L2 (FIG. 9) inputted by intentionally extracting the low-frequency fluctuations of the time-series data D1. The best solution of the parameters obtained from the exploration results is that the number of median filtered data is 11 and the time constant of the low-pass filtering of the first-order lag is 0.35 seconds.
圖12表示在畫面40上以重疊的方式顯示基於軌跡L1(圖8)的參考軌跡資料RD1的波形和平滑化處理後的時間序列資料D6的波形的例子。圖13表示在畫面40上以重疊的方式顯示基於軌跡L2(圖9)的參考軌跡資料RD2的波形和平滑化處理後的時間序列資料D7的波形的例子。 FIG. 12 shows an example in which the waveform of the reference trajectory data RD1 based on the trajectory L1 (FIG. 8) and the waveform of the time-series data D6 after the smoothing process are displayed on the screen 40 in an overlapping manner. FIG. 13 shows an example in which the waveform of the reference trajectory data RD2 based on the trajectory L2 (FIG. 9) and the waveform of the time-series data D7 after smoothing are displayed on the screen 40 in an overlapping manner.
再者，可以通過操作人員的操作來選擇使圖10、圖11這樣的形態(步驟S109)和圖12、圖13這樣的形態(步驟S110)中的哪一方顯示出來。此外，還可以選擇其他顯示形態。例如，雖未表示具體例，但可在圖10~圖13所示的 畫面40中顯示探索出的處理方法的名稱(本實施例中為中值濾波和一階遲滯後低通濾波)以及參數的值。 In addition, it is possible to select which one of the form shown in FIG. 10 and FIG. 11 (step S109) and the form shown in FIG. 12 and FIG. 13 (step S110) can be selected by the operator's operation. In addition, other display modes can be selected. For example, although a specific example is not shown, the name of the discovered processing method (median filtering and first-order lag low-pass filtering) and parameters can be displayed on the screen 40 shown in FIGS. 10 to 13. Value.
[本實施例的效果的驗證] [Verification of effect of this embodiment]
接著，對本實施例的效果進行驗證。此處，著眼於變化點的檢測，嘗試確認時間序列資料的微分值(由於是離散資料，因此嚴格來說是差分值)的符號變為零或者從正轉移至負的點。 Next, the effect of this embodiment is verified. Here, focusing on the detection of the change point, an attempt is made to confirm that the sign of the differential value of the time series data (due to the difference data is strictly a difference value because it is discrete data) becomes zero or shifts from positive to negative.
圖14為表示基於有意提取時間序列資料D1的高頻變動而輸入的軌跡L1的參考軌跡資料RDI的差分值△RD1(微分值)以及圖2所示的以往的平滑化處理的時間序列資料D2的差分值△D2(微分值)的圖。RP1為差分值△RD1的變化點(差分值的符號變為零的點)，DP2為差分值△D2的變化點。從而瞭解，即使是像圖14那樣放大後的範圍，在以往的平滑化20處理結果中，相較於操作人員所意識的軌跡L1的圖像而言也多出現了4個變化點。 FIG. 14 shows the difference value ΔRD1 (differential value) of the reference trajectory data RDI of the trajectory L1 input based on intentionally extracted time series data D1 and the time series data D2 of the conventional smoothing process shown in FIG. 2. Figure of the difference value ΔD2 (differential value). RP1 is the change point of the difference value ΔRD1 (the point at which the sign of the difference value becomes zero), and DP2 is the change point of the difference value ΔD2. Therefore, it is understood that even if the range is enlarged as shown in FIG. 14, in the conventional smoothing 20 processing result, there are four more change points than the image of the trajectory L1 that the operator is aware of.
圖15為表示基於有意提取時間序列資料DI的低頻變動而輸入的軌跡L2的參考軌跡資料RD2的差分值△RD2(微分值)以及圖3所示的以往的平滑化處理的時間序列資料D3的差分值△D3(微分值)的圖。RP2為差分值△RD2的變化點，DP3為差分值△D3的變化25點。從而瞭解，即使是像圖15那樣放大後的範圍，在以往的平滑化處理結果中，相較於操作人員所意識的軌跡L2的圖像而言也多出現了15個變化點。 FIG. 15 shows the difference value ΔRD2 (differential value) of the reference trajectory data RD2 of the trajectory L2 input based on intentionally extracted time series data DI, and the time series data D3 of the conventional smoothing process shown in FIG. 3. Graph of difference value ΔD3 (differential value). RP2 is the change point of the difference value ΔRD2, and DP3 is the change point of the difference value ΔD3 by 25 points. Therefore, it is understood that even if the range is enlarged as shown in FIG. 15, in the conventional smoothing processing result, there are 15 more change points than the image of the trajectory L2 that the operator is aware of.
圖16為表示基於有意提取時間序列資料DI的高頻變動而輸入的軌跡L1的參考軌跡資料RD1的差分值△RD1(微分值)以及圖10所示的本實施例的平滑化處理後的時間序列資料D6的差分值△D6(微分值)的圖。RP1為差分值△RDI的變化點，DP6為差分值△D6的變化點。從而瞭解，根據本實施例的平滑化處理結果，出現了與操作人員所意識的軌跡L1的圖像相同數量的變化點。 FIG. 16 shows the difference value ΔRD1 (differential value) of the reference trajectory data RD1 of the trajectory L1 that is input based on the intentionally extracted time series data DI, and the time after the smoothing process of this embodiment shown in FIG. 10 Diagram of the difference value ΔD6 (differential value) of the sequence data D6. RP1 is the change point of the difference value ΔRDI, and DP6 is the change point of the difference value ΔD6. It is thus understood that according to the smoothing processing result of this embodiment, the same number of change points as the image of the trajectory L1 that the operator is aware of appear.
圖17為表示基於有意提取時間序列資料D1的低頻變動而輸入的 軌跡L2的參考軌跡資料RD2的差分值△RD2(分值)以及圖11所示的本實施例的平滑化處理後的時間序列資料D7的差分值△D7(微分值)的圖。RP2為差分值△RD2的變化點，DP7為差分值△D7的變化點。從而瞭解，與圖16的情況一樣，根據本實施例的平滑化處理結果，出現了與操作人員所意識的軌跡L2的圖像相同數量的變化點。 FIG. 17 shows the difference value ΔRD2 (score) of the reference trajectory data RD2 of the trajectory L2 input based on the intentional extraction of the low-frequency fluctuations of the time series data D1, and the time series after the smoothing process of the present embodiment shown in FIG. Graph of difference value ΔD7 (differential value) of data D7. RP2 is the change point of the difference value ΔRD2, and DP7 is the change point of the difference value ΔD7. It is thus understood that, as in the case of FIG. 16, according to the smoothing processing result of the present embodiment, the same number of change points as the image of the trajectory L2 that the operator is aware of appear.
如上所述，在本實施例中，可以根據操作人員所輸入的軌跡來恰當地決定平滑化處理的參數(著眼的資料數、資料時間、時間常數)，因此，能夠降低用以決定參數的試錯的繁雜性。 As described above, in this embodiment, the parameters of the smoothing process (the number of data to be focused on, the time of the data, and the time constant) can be appropriately determined according to the trajectory input by the operator. Therefore, the test for determining the parameters can be reduced. Wrong complexity.
再者，獲得平滑化的效果的處理方法不限於中值濾波、低通濾波，也可使用其他處理方法。作為其他處理方法，有移動平均法、日本專利特開平04-121621號公報中揭示的資料平滑方法等。 Furthermore, the processing method for obtaining the smoothing effect is not limited to the median filtering and the low-pass filtering, and other processing methods may be used. As another processing method, there are a moving average method and a data smoothing method disclosed in Japanese Patent Laid-Open No. 04-121621.
此外，在本實施例中，使處理方法存儲部3存儲有一種處理方法，但也可使其存儲有能夠選擇的多種處理方法。在處理方法存儲部3中存儲有多種處理方法的情況下，處理探索執行部7是在處理方法存儲部3中存儲的內容的範圍內變更處理方法及參數兩方或者變更處理方法及參數中的任一方來探索處理方法及參數的最佳解。由此，不僅可以恰當地決定參數，還可以恰當地決定平滑化處理的處理方法，因此能夠降低用以決定處理方法的試錯的繁雜性。 In addition, in this embodiment, the processing method storage unit 3 stores one processing method, but it is also possible to store a plurality of processing methods that can be selected. When a plurality of processing methods are stored in the processing method storage unit 3, the processing exploration execution unit 7 changes both of the processing methods and parameters or changes the processing methods and parameters within the scope of the content stored in the processing method storage unit 3. Either party can explore the best solution for processing methods and parameters. Thereby, not only the parameters can be appropriately determined, but also the processing method of the smoothing processing can be appropriately determined, and thus the complexity of trial and error for determining the processing method can be reduced.
[第2實施例] [Second embodiment]
接著，對本發明的第2實施例進行說明。本實施例是對應於上述發明的原理2的例子。圖18為表示本實施例的時間序列資料處理裝置的構成的方塊圖，對與圖6相同的構成標註有同一符號。本實施例的時間序列資料處理裝置具備；資料獲取部1；資料存儲部2：處理方法存儲部3；帶觸控面板功能的顯示元件4；資料顯示控制部5；參考軌跡輸出部6；處理探索執行部7a，其針對分 割後的每一時間區域而執行時間序列資料的平滑化處理，並針對每一時間區域而探索平滑化處理的處理方法及參數中的至少一方；探索結果顯示控制部8a，其針對分割後的每一時間區域而顯示探索結果；平滑化處理結果顯示控制部9；以及區域分割處理部10，其以預先規定好的次序分割時間序列資料的時間區域。 Next, a second embodiment of the present invention will be described. This embodiment is an example corresponding to principle 2 of the above-mentioned invention. FIG. 18 is a block diagram showing a configuration of a time-series data processing device according to the present embodiment, and the same components as those in FIG. 6 are denoted by the same reference numerals. The time-series data processing device of this embodiment includes: a data acquisition section 1; a data storage section 2: a processing method storage section 3; a display element 4 with a touch panel function; a data display control section 5; a reference trajectory output section 6; processing The exploration execution unit 7a performs smoothing processing of time series data for each time region after division, and explores at least one of a processing method and parameters of the smoothing processing for each time region; the search result display control unit 8a, which displays a search result for each time region after division; a smoothing process result display control unit 9; and a region division processing unit 10, which divides the time region of the time series data in a predetermined order.
接著，參考圖19，對本實施例的時間序列資料處理裝置的動作進行說明。資料獲取部1、資料存儲部2、帶觸控面板功能的顯示元件4以及參考軌跡輸出部6的動作(圖19步驟S100~S104)與在第1實施例中說明過的一致。 Next, an operation of the time-series data processing device according to this embodiment will be described with reference to FIG. 19. The operations of the data acquisition unit 1, the data storage unit 2, the display element 4 with a touch panel function, and the reference trajectory output unit 6 (steps S100 to S104 in FIG. 19) are the same as those described in the first embodiment.
圖20表示本實施例中從監視物件採集到的時間序列資料D8(溫度資料)。在該例中，時間序列資料D8中重疊有測量雜訊、1秒週期左右的高頻變動、以及12秒週期左右的低頻變動，進而，在時刻7秒附近，高頻變動的振幅變大。 FIG. 20 shows time-series data D8 (temperature data) collected from the monitoring object in this embodiment. In this example, measurement noise, high-frequency fluctuations around a 1-second period, and low-frequency fluctuations around a 12-second period are superimposed on the time-series data D8, and further, the amplitude of the high-frequency fluctuations becomes large around time 7 seconds.
圖21~圖23為表示本實施例中操作人員在帶觸控面板功能的顯示元件4的畫面40上劃動手指400來輸入平滑化處理後的時間序列資料的理想軌跡的情況的圖。圖21表示了操作人員針對畫面40上顯示的時間序列資料D8有意提取高頻變動而輸入軌跡L8的例子。圖22表示操作人員有意提取低頻變動而輸入軌跡L9的例子。圖23表示操作人員針對時刻7秒之前的前半部分無意時間序列資料D8的高頻變動而有意提取低頻變動而輸入軌跡L10、並且針對時刻7秒之後的後半部分意在提取振幅變大的高頻變動而輸入軌跡L11的例子。 21 to FIG. 23 are diagrams showing an example in which the operator flicks his finger 400 on the screen 40 of the display element 4 with a touch panel function to input an ideal trajectory of the time-series data after the smoothing process. FIG. 21 shows an example in which the operator intentionally extracts a high-frequency fluctuation with respect to the time-series data D8 displayed on the screen 40 and inputs the trajectory L8. FIG. 22 shows an example in which the operator intentionally extracts low-frequency fluctuations and inputs the trajectory L9. FIG. 23 shows that the operator intentionally extracts low-frequency fluctuations in response to the high-frequency fluctuations of the first half of the unintentional time series data D8 before time 7 seconds, and enters the trajectory L10, and intends to extract high-frequency fluctuations in which the amplitude becomes larger for the second half of time 7 seconds later An example in which the trajectory L11 is input while changing.
接著，區域分割處理部10以預先規定好的次序分割資料存儲部2中存儲的時間序列資料的時間區域(圖19步驟S111)。在本實施例中，將時間序列資料的時間區域均等地4分割。再者，如前文所述，也可從MES等獲取狀態資訊(例如監視物件加熱裝置的模式資訊等)，以監視物件裝置的狀態的切換(模式的切換點)為時間區域的交界來分割時間序列資料的時間區域。 Next, the area division processing unit 10 divides the time regions of the time-series data stored in the data storage unit 2 in a predetermined order (step S111 in FIG. 19). In this embodiment, the time region of the time series data is equally divided into four. In addition, as described above, status information (such as the mode information of the monitoring object heating device) can also be obtained from the MES, etc., and the time of the monitoring object device switching (mode switching point) is used as the boundary of the time zone to divide the time. The time zone of the sequence data.
處理探索執行部7a的步驟S105a、S106a、S107a的處理分別與第1實施例的步驟S105、S106、S107相同。但是，處理探索執行部7a是針對通過步驟S111分割後的每一時間區域而進行這些步驟S1050、S106a、S107a的處理。 The processes of steps S105a, S106a, and S107a of the process search execution unit 7a are the same as those of steps S105, S106, and S107 of the first embodiment, respectively. However, the process search execution unit 7a performs the processes of steps S1050, S106a, and S107a for each time region divided by step S111.
當所有時間區域的平滑化處理後的時間序列資料與參考軌跡資料的誤差都達到容許值以下而探索結束時(圖19步驟S112中的“是”)，探索結果顯示控制部8a針對分割後的每一時間區域而使探索結果即處理方法的名稱以及參數的值顯示在帶觸控面板功能的顯示元件4上(圖19步驟S108a)。 When the error between the time series data and the reference trajectory data after the smoothing process in all time regions has reached an allowable value or less and the search is completed (YES in step S112 of FIG. 19), the search result display control unit 8a For each time zone, the search result, that is, the name of the processing method and the value of the parameter are displayed on the display element 4 with a touch panel function (step S108a in FIG. 19).
平滑化處理結果顯示控制部9的步驟S109、步驟S110的處理與在第1實施例中說明過的一致。然後，本實施例的時間序列資料處理裝置的處理結束。 The processing of step S109 and step S110 of the smoothing processing result display control unit 9 is the same as that described in the first embodiment. Then, the processing of the time-series data processing device of this embodiment ends.
圖24為表示本實施例的平滑化處理結果顯示控制部9的顯示例的圖。圖24表示在10帶觸控面板功能的顯示元件4的畫面40上以重疊的方式顯示平滑化處理前的時間序列資料D8的波形和通過處理方法及參數的探索來確定的平滑化處理後的時間序列資料D9的波形的例子。平滑化處理後的時間序列資料D9表示根據操作人員所輸入的軌跡L10、L11(圖23)來探索平滑化處理的參數的結果。 FIG. 24 is a diagram showing a display example of the smoothing processing result display control unit 9 of this embodiment. FIG. 24 shows the waveform of the time-series data D8 before the smoothing process and the smoothing process determined by the exploration of the processing method and parameters on the screen 40 of the display element 4 with a touch panel function in an overlapping manner. An example of the waveform of the time series data D9. The time-series data D9 after the smoothing process indicates a result of searching for parameters of the smoothing process based on the trajectories L10 and L11 (FIG. 23) input by the operator.
根據圖24的例子，在經4分割後的時間區域中的前半部分的Area1、Area2這2個時間區域內，由於操作人員輸入的是有意提取低頻變動的軌跡L10，因此，平滑化處理後的時間序列資料D9的波形成為與軌跡L10大致一致的形狀。另一方面，在後半部分的Area3、Area4這2個時間區域內，由於操作人員輸入的是有意提取高頻變動的軌跡L11，因此，使用不同於前半部分的參數來進行時間序列資料D8的平滑化處理，使得平滑化處理後的時間序列資料D9的波形成為與軌跡L11大致一致的形狀。 According to the example in FIG. 24, in the two time regions of Area1 and Area2 in the first half of the time region after 4 divisions, since the operator inputs the trajectory L10 that intentionally extracts low-frequency fluctuations, the smoothed The waveform of the time-series data D9 has a shape that substantially matches the trajectory L10. On the other hand, in the two time areas of Area3 and Area4 in the second half, because the operator inputs the trajectory L11 that intentionally extracts high-frequency fluctuations, the parameters different from the first half are used to smooth the time series data D8. The smoothing process causes the waveform of the time-series data D9 after the smoothing process to have a shape substantially consistent with the trajectory L11.
與第1實施例一樣，可以通過操作人員的操作來選擇使步驟S109中說明過的形態(圖24)和步驟S110中說明過的形態中的哪一方顯示。此外，也可以選擇其他顯示形態。例如，雖未表示具體例，但可在圖24所示的畫面40中針對分割後的每一時間區域而顯示探索出的處理方法的名稱以及參數的值。 As in the first embodiment, it is possible to select which of the form described in step S109 (FIG. 24) and the form described in step S110 to be displayed by the operator's operation. In addition, other display modes can be selected. For example, although a specific example is not shown, the screen 40 shown in FIG. 24 may display the name of a searched processing method and the value of a parameter for each time region after division.
此外，為了使操作人員識別分割好的時間區域，探索結果顯示控制部8a及平滑化處理結果顯示控制部9例如可以像圖24那樣顯示時間區域的分割線TL1、TL2、TL3和時間區域的編號Area1、Area2、Area3、Area4，也可以不顯示。 In addition, in order for the operator to recognize the divided time zone, the search result display control unit 8a and the smoothing process result display control unit 9 may display the time zone division lines TL1, TL2, TL3, and the time zone numbers as shown in FIG. 24, for example. Area1, Area2, Area3, and Area4 may not be displayed.
再者，可將第1、第2實施例中說明過的時間序列資料處理裝置搭載於調節器的內部，也可獨立於調節器而另行設置。此外，將平滑化處理後的時間序列資料從時間序列資料處理裝置中輸出並利用該時間序列資料這一內容為普通事項。本發明當然可以運用於平滑化處理後的時間序列資料的各種利用形態。此外，在第1、第2實施例中，列舉溫度資料作為時間序列資料的例子來進行了說明，但時間序列資料當然不限於溫度資料。 Furthermore, the time-series data processing device described in the first and second embodiments may be mounted inside the regulator, or may be separately provided independently of the regulator. In addition, it is a common matter to output smoothed time-series data from a time-series data processing device and use the time-series data. The present invention can of course be applied to various utilization forms of time-series data after smoothing processing. In the first and second embodiments, temperature data has been described as an example of time-series data, but the time-series data is not limited to temperature data, of course.
第1、第2實施例中說明過的時間序列資料處理裝置中的資料獲取部1、資料存儲部2、處理方法存儲部3、資料顯示控制部5、參考軌跡輸出部6、處理探索執行部7、7a、探索結果顯示控制部8、8a、平滑化處理結果顯示控制部9以及區域分割處理部10可以通過具備CPU(Central Processing Unit，中央處理單元)、存儲裝置及介面的電腦和控制這些硬體資源的程式來實現。CPU按照存儲裝置中存儲的程式來執行第1、第2實施例中說明過的處理。 The data acquisition unit 1, the data storage unit 2, the processing method storage unit 3, the data display control unit 5, the reference trajectory output unit 6, and the processing exploration execution unit in the time series data processing device described in the first and second embodiments. 7, 7a, the search result display control unit 8, 8a, the smoothing process result display control unit 9, and the area division processing unit 10 can be controlled by a computer including a CPU (Central Processing Unit, central processing unit), a storage device, and an interface. Hardware resource program. The CPU executes the processes described in the first and second embodiments in accordance with a program stored in the storage device.
本發明可以運用於對時間序列資料進行平滑化處理的技術。 The invention can be applied to the technology for smoothing the time series data.
Claims (10)
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2017004020A JP6803241B2 (en) | 2017-01-13 | 2017-01-13 | Time series data processing device and processing method |
| JPJP2017-004020 | 2017-01-13 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| TW201830223A true TW201830223A (en) | 2018-08-16 |
| TWI643120B TWI643120B (en) | 2018-12-01 |
Family
ID=62868441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW107100790A TWI643120B (en) | 2017-01-13 | 2018-01-09 | Time series data processing device and processing method |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP6803241B2 (en) |
| KR (1) | KR102031944B1 (en) |
| CN (1) | CN108303967B (en) |
| TW (1) | TWI643120B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109410145B (en) * | 2018-11-01 | 2020-12-18 | 北京达佳互联信息技术有限公司 | Time sequence smoothing method and device and electronic equipment |
| TWI734330B (en) * | 2019-01-31 | 2021-07-21 | 日商住友重機械工業股份有限公司 | Support device, support method and recording medium |
| CN111752254A (en) * | 2019-03-28 | 2020-10-09 | 深圳市商汤科技有限公司 | Test method, device, medium and equipment for trajectory tracking controller |
| CN111797127B (en) * | 2019-04-09 | 2024-06-25 | Oppo广东移动通信有限公司 | Time sequence data segmentation method and device, storage medium and electronic equipment |
Family Cites Families (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63115289A (en) * | 1986-10-31 | 1988-05-19 | Nec Corp | Preprocessing circuit for handwritten character recognition |
| JPH0464014A (en) * | 1990-07-04 | 1992-02-28 | Hitachi Ltd | Data monitoring apparatus |
| JP3108317B2 (en) * | 1995-04-07 | 2000-11-13 | 古河電気工業株式会社 | Signal processing device and signal processing method |
| JP4308345B2 (en) * | 1998-08-21 | 2009-08-05 | パナソニック株式会社 | Multi-mode speech encoding apparatus and decoding apparatus |
| JP3727496B2 (en) * | 1998-12-01 | 2005-12-14 | 株式会社日立製作所 | Etching method |
| KR100877457B1 (en) * | 2001-02-21 | 2009-01-07 | 소니 가부시끼 가이샤 | Signal processing device and method and recording medium for recording signal processing program |
| JP2003067046A (en) * | 2001-08-29 | 2003-03-07 | Toshiba Corp | Transient phenomenon recording and evaluating device |
| DE10259719B4 (en) * | 2002-12-19 | 2007-03-15 | Cs Clean Systems Ag | Method for minimizing the error of a measured variable |
| JP2005201869A (en) * | 2004-01-19 | 2005-07-28 | Mitsutoyo Corp | Signal-processing method, signal-processing program, recording medium with the program stored, and signal processing apparatus |
| JP4914188B2 (en) * | 2006-11-27 | 2012-04-11 | 富士重工業株式会社 | Smoothing filter device and speed detection device |
| JP2009053873A (en) * | 2007-08-24 | 2009-03-12 | Fujitsu Ten Ltd | Control device, vehicle control device, processing method, and control program |
| JP4544351B2 (en) * | 2008-07-17 | 2010-09-15 | カシオ計算機株式会社 | Time information acquisition device and radio clock |
| CN101369322B (en) * | 2008-09-27 | 2010-09-22 | 哈尔滨工业大学 | Heat supply load interval prediction method based on chaos theory |
| JP5099066B2 (en) * | 2009-04-10 | 2012-12-12 | オムロン株式会社 | Energy monitoring apparatus, control method therefor, and energy monitoring program |
| JP5475484B2 (en) | 2010-01-28 | 2014-04-16 | アンリツ株式会社 | Waveform observation apparatus and method |
| JP5484932B2 (en) * | 2010-01-28 | 2014-05-07 | アズビル株式会社 | PID adjustment support apparatus and method |
| US9110452B2 (en) * | 2011-09-19 | 2015-08-18 | Fisher-Rosemount Systems, Inc. | Inferential process modeling, quality prediction and fault detection using multi-stage data segregation |
| KR101664643B1 (en) * | 2012-03-30 | 2016-10-10 | 미쓰비시덴키 가부시키가이샤 | Motor drive device |
| JP2015082739A (en) * | 2013-10-22 | 2015-04-27 | 日本電信電話株式会社 | Adaptive signal processing method and device |
| JP6364800B2 (en) * | 2014-02-10 | 2018-08-01 | オムロン株式会社 | Monitoring device and monitoring method |
| US10126162B2 (en) * | 2014-03-20 | 2018-11-13 | Ishida Co., Ltd. | Weighing device using filtering to improve accuracy |
| US10139803B2 (en) * | 2014-04-16 | 2018-11-27 | Mitsubishi Electric Corporation | Instruction value generation device |
| JP2016038762A (en) * | 2014-08-08 | 2016-03-22 | アズビル株式会社 | Display device |
| JP6213435B2 (en) | 2014-09-18 | 2017-10-18 | 株式会社デンソーアイティーラボラトリ | Over-attention state determination device and over-attention state determination program |
| US9474064B2 (en) * | 2015-01-28 | 2016-10-18 | Alcatel Lucent | System and method for controlling an operation of an application by forecasting a smoothed transport block size |
-
2017
- 2017-01-13 JP JP2017004020A patent/JP6803241B2/en active Active
-
2018
- 2018-01-08 CN CN201810015200.2A patent/CN108303967B/en active Active
- 2018-01-09 TW TW107100790A patent/TWI643120B/en active
- 2018-01-11 KR KR1020180003931A patent/KR102031944B1/en active IP Right Grant
Also Published As
| Publication number | Publication date |
|---|---|
| JP2018112504A (en) | 2018-07-19 |
| JP6803241B2 (en) | 2020-12-23 |
| CN108303967A (en) | 2018-07-20 |
| TWI643120B (en) | 2018-12-01 |
| KR20180083810A (en) | 2018-07-23 |
| KR102031944B1 (en) | 2019-10-14 |
| CN108303967B (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI643120B (en) | Time series data processing device and processing method | |
| US11762474B2 (en) | Systems, methods and devices for gesture recognition | |
| WO2016115895A1 (en) | On-line user type identification method and system based on visual behaviour | |
| CN104007819A (en) | Gesture recognition method and device and Leap Motion system | |
| CN111951637B (en) | Task-context-associated unmanned aerial vehicle pilot visual attention distribution mode extraction method | |
| US20180129875A1 (en) | Gesture identification with natural images | |
| CN107909042B (en) | continuous gesture segmentation recognition method | |
| CN107239137A (en) | A kind of character input method and device based on dummy keyboard | |
| KR101553484B1 (en) | Apparatus for detecting hand motion and method thereof | |
| CN107037951B (en) | Automatic operation mode identification method and terminal | |
| CN104050454A (en) | Movement gesture track obtaining method and system | |
| JP2003310564A (en) | Automatic brain wave analyzing apparatus and method | |
| CN107229330A (en) | A kind of character input method and device based on Steady State Visual Evoked Potential | |
| US7443395B2 (en) | Multi-variable operations | |
| WO2020170986A1 (en) | Information processing device, method, and program | |
| CN111366184B (en) | Shield tunneling machine multi-sensor performance online monitoring method | |
| CN115390659A (en) | Data glove dynamic calibration device and method | |
| CN105511643B (en) | A kind of gesture identification method based on 3-axis acceleration sensor | |
| CN105404449B (en) | Can level expansion more pie body-sensing menus and its grammar-guided recognition methods | |
| US10796506B2 (en) | Information output device and information output method | |
| CN110554791B (en) | Touch panel signal detection method and device | |
| CN112114672A (en) | Eye movement and voice combined auxiliary interaction device and method | |
| CN112070141A (en) | SSVEP asynchronous classification method fused with attention detection | |
| Jaber et al. | Proposing a three-stage model to quantify bradykinesia on a symptom severity level using deep learning | |
| CN106845523A (en) | A kind of data processing method for blending geodata and sensor signal data |