WO2021237459A1 - 基于工业对象模型的数据处理方法、装置及设备 - Google Patents

基于工业对象模型的数据处理方法、装置及设备 Download PDF

Info

Publication number
WO2021237459A1
WO2021237459A1 PCT/CN2020/092355 CN2020092355W WO2021237459A1 WO 2021237459 A1 WO2021237459 A1 WO 2021237459A1 CN 2020092355 W CN2020092355 W CN 2020092355W WO 2021237459 A1 WO2021237459 A1 WO 2021237459A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
object model
processing
industrial
model
Prior art date
Application number
PCT/CN2020/092355
Other languages
English (en)
French (fr)
Inventor
国承斌
吴刚
骆建东
党君利
张荣洁
陈丹平
Original Assignee
深圳市智物联网络有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市智物联网络有限公司 filed Critical 深圳市智物联网络有限公司
Priority to CN202080000820.4A priority Critical patent/CN112204547B/zh
Priority to PCT/CN2020/092355 priority patent/WO2021237459A1/zh
Publication of WO2021237459A1 publication Critical patent/WO2021237459A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • 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
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • This application relates to the technical field of the Industrial Internet of Things, and in particular to a data processing method, device and equipment based on an industrial object model.
  • One of the objectives of the embodiments of the present application is to provide a method, device, and equipment for processing industrial data, aiming to solve the problem of low processing efficiency of industrial data and waste of resources.
  • a data processing method based on an industrial object model including:
  • the constructing an object model in combination with requirements of different scenarios in an industrial site includes:
  • an object model is constructed.
  • the constructing an object model based on the data processing requirements and object model construction rules includes:
  • an object model is constructed.
  • the object model includes at least one model of industrial equipment.
  • the processing result is one or more of data estimation result, data change result, data trend prediction result, data stability estimation result, risk estimation result, data increment estimation result, and data balance adjustment result. kind.
  • the performing matrix transformation processing on the object data according to a preset processing rule to obtain a processing result includes:
  • the performing matrix transformation processing on the object data according to a preset processing rule to obtain a processing result includes:
  • the object data is input into a neural network model that has been trained on the data to perform matrix transformation processing to obtain a processing result.
  • a data processing device based on an industrial object model including:
  • the determining unit constructs an object model in combination with the requirements of the industrial scene scene, and is used to screen the industrial data collected by the sensor according to the object model, and determine the model data corresponding to the object model;
  • the first construction unit is configured to construct the object data of the object model according to the model data of the object model at each time;
  • the processing unit is configured to perform matrix transformation processing on the object data according to a preset processing rule to obtain a processing result.
  • the determining unit includes:
  • the acquisition unit is used to acquire data processing requirements according to the requirements of the industrial scene
  • the second construction unit is used to construct an object model based on the data processing requirements and object model construction rules.
  • the second building unit is specifically used for:
  • an object model is constructed.
  • the object model includes at least one model of industrial equipment.
  • the processing result is one or more of data estimation result, data change result, data trend prediction result, data stability estimation result, risk estimation result, data increment estimation result, and data balance adjustment result. kind.
  • the processing unit is specifically configured to:
  • the processing unit is specifically configured to:
  • the object data is input into a neural network model that has been trained on the data to perform matrix transformation processing to obtain a processing result.
  • an embodiment of the present application provides a data processing device based on an industrial object model, including a memory, a processor, and a computer program stored in the memory and running on the processor.
  • the processor When the computer program is executed, the data processing method based on the industrial object model as described in the first aspect is realized.
  • an embodiment of the present application provides a computer-readable storage medium that stores a computer program that, when executed by a processor, implements the industry-based The data processing method of the object model.
  • the object model is constructed in combination with the requirements of the industrial scene, and the industrial data collected by the sensor is screened according to the object model to determine the model data corresponding to the object model; according to the model data of the object model at each time The object data of the object model; matrix transformation processing is performed on the object data according to preset processing rules to obtain a processing result.
  • the object model is constructed in advance, and the object data corresponding to the object model is obtained, and the object data is processed by the matrix transformation method according to the preset processing rules to obtain the processing result.
  • FIG. 1 is a schematic flowchart of a data processing method based on an industrial object model provided by the first embodiment of the present application;
  • FIG. 2 is a schematic diagram of matrix transformation in a data processing method based on an industrial object model provided by the first embodiment of the present application;
  • FIG. 3 is a schematic flowchart of another data processing method based on an industrial object model provided by the second embodiment of the present application.
  • FIG. 4 is a detailed schematic flowchart of S202 in another data processing method based on an industrial object model provided by the second embodiment of the present application;
  • FIG. 5 is a schematic diagram of a first scene type in another data processing method based on an industrial object model provided by the second embodiment of the present application;
  • Fig. 6 is a schematic diagram of a data processing device based on an industrial object model provided by a third embodiment of the present application.
  • Fig. 7 is a schematic diagram of a data processing device based on an industrial object model provided by a fourth embodiment of the present application.
  • FIG. 1 is a schematic flowchart of a method for processing industrial data provided by the first embodiment of the present application.
  • the execution subject of an industrial data processing method in this embodiment is a device with an industrial data processing function, for example, a server.
  • the industrial data processing method shown in Figure 1 may include:
  • S101 Construct an object model according to the requirements of the industrial scene scene, filter the industrial data collected by the sensor according to the object model, and determine the model data corresponding to the object model.
  • an object model is constructed in combination with the requirements of different scenes in the industrial scene.
  • the object model identifies a logical equipment model.
  • the object model is aimed at different industrial scenes and abstracts the industrial scene and industrial equipment to obtain the model.
  • the object model can be constructed based on one industrial device, or based on multiple industrial devices.
  • the object model can include only the model of industrial equipment, or the models of meters and sensors around the industrial equipment. Further, the preset industrial model may also include environmental factors, for example, the temperature and pressure of the environmental space.
  • a biogas power station has main equipment: one biogas pressurized purification equipment and three biogas generators.
  • the biogas purification and pressurization equipment purifies, filters and pressurizes the biogas extracted from the biogas digester, and then transports the biogas to the biogas generator to generate electricity.
  • the object model can be a biogas pressurized purification device, and the object model can also be a biogas pressurized purification device and three biogas generators.
  • the object model includes at least one model of industrial equipment.
  • the object model is the basis of industrial data processing in this embodiment.
  • the device obtains model data corresponding to the object model, and obtains the processing result of the industrial data based on the model data. Therefore, the composition of different preset industrial models is different, the corresponding model data is different, and the processing results of the obtained industrial data are also different. In other words, different processing results correspond to different object models, that is, different requirements correspond to different object models.
  • Object model 3 3# generator.
  • Object model 4 Biogas purification pressurization equipment.
  • Object model 2 biogas purification pressurization equipment + meter (front) + meter (rear).
  • the object model has nothing to do with the way of collecting industrial data, and the way of collecting industrial data is not limited in this embodiment, as long as all data on the industrial site can be collected. How many sensors are used and how each sensor is connected must be determined according to the site conditions.
  • the equipment obtains the industrial data collected by the sensor, and filters the industrial data collected by the sensor according to the object model to determine the model data corresponding to the object model.
  • the model data corresponding to the object model is the industrial data corresponding to all the equipment and elements included in the object model.
  • S102 Construct object data of the object model according to the model data of the object model at various moments.
  • the collection of the model data of the device at each time according to the object model is the object data of the object model.
  • the mathematical method of object data is expressed as: obj.ts.data; obj object label, time time series label, data is n-dimensional real number space data: ⁇ x 1 ,x 2 ,x 3 ,...,x n ⁇ . Therefore, the object data is expressed as: obj.ts. ⁇ x 1 ,x 2 ,x 3 ,...,x n ⁇ .
  • the object data is expressed as follows:
  • the parameter FV1 is temperature
  • the parameter FV2 is pressure
  • the temperature of 1001 is 100°C and the pressure is 0.50Mpa
  • the data is: 1001.2020-05-20 00:00:00. ⁇ "FV1":100,"FV2" :0.50 ⁇
  • the temperature of 1001 is 99°C and the pressure is 0.49Mpa
  • the data is: 1001.2020-05-20 00:00:00. ⁇ "FV1":99 ,”FV2":0.49 ⁇ .
  • S103 Perform matrix transformation processing on the object data according to a preset processing rule to obtain a processing result.
  • the matrix transformation processing method is shown in FIG. 2, the input data is a matrix X, and the output data is a matrix Y.
  • the input data matrix X is the object data
  • the abstract representation is as follows:
  • Xn is the object data obj.ts n at a certain time. ⁇ x 1 ,x 2 ,x 3 ,...,x n ⁇
  • the output data matrix Y is the processing result, which is abstractly expressed as:
  • Y (1,m) ⁇ Y 1 Y 2 Y 3 ... Y m ⁇ , where Ym is a set of results
  • processing rules are preset, and the preset processing rules are used to process the object data to obtain the processing result.
  • Different processing results correspond to different processing rules, and the preset processing rules are determined according to the needs of data processing.
  • the device processes the object data according to preset processing rules, and obtains the processing result.
  • the processing result may be one or more of data estimation result, data change result, data trend prediction result, data stability estimation result, risk estimation result, data increment estimation result, and data balance adjustment result. It is understandable that the processing results include, but are not limited to, data estimation results, data change results, data trend prediction results, data stability estimation results, risk estimation results, data increment estimation results, and data balance adjustment results.
  • the data estimation result can be the corresponding estimation result obtained according to the object data.
  • the object data is the power consumption
  • the data estimation result is the output estimated according to the power consumption
  • the data trend prediction result can be the unobtained result according to the object data.
  • the result of the risk assessment can be the risk level obtained from the risk assessment based on the object data
  • the data increment estimation result can be the increase estimated based on the object item data
  • the data balance adjustment result can be obtained based on the object data Need to adjust the data.
  • S103 may include: performing matrix transformation processing on the object data according to the corresponding relationship between the preset object data and the processing result to obtain the processing result.
  • the device stores the correspondence between the object data and the processing result, and the device processes the object data according to the correspondence between the object data and the processing result to obtain the processing result.
  • the correspondence between object data and processing results can be determined based on historical data.
  • the historical data includes historical object data and historical processing results.
  • the historical object data and historical processing results are used to determine the relationship between preset object data and processing results.
  • Correspondence apply the correspondence to the subsequent data processing, and obtain the processing result of the subsequent industrial data.
  • S103 may include: inputting the object data into a neural network model trained on the data to perform matrix transformation processing to obtain a processing result.
  • the data-trained neural network model M is pre-stored in the device.
  • the preset neural network model is obtained by training multiple training samples in the sample training set using a machine learning algorithm, and each training sample includes one sample Object data and its corresponding processing result label.
  • the neural network model can be pre-trained by the local device, or the file corresponding to the neural network model can be transplanted to the local device after being pre-trained by other devices. Specifically, when other devices have trained the neural network model, they freeze the model parameters of the deep learning network, and transplant the neural network model file corresponding to the frozen deep learning network to the local device.
  • the equipment inputs the object data into the neural network model for processing, and obtains the processing result.
  • the object model is constructed in combination with the requirements of the industrial scene, the industrial data collected by the sensor is screened according to the object model, and the model data corresponding to the object model is determined; The object data of the object model; matrix transformation processing is performed on the object data according to preset processing rules to obtain a processing result.
  • the object model is constructed in advance, and the object data corresponding to the object model is obtained, and the object data is processed according to the preset processing rules to obtain the processing result.
  • FIG. 3 is a schematic flowchart of another industrial data processing method provided by the second embodiment of the present application.
  • the execution subject of an industrial data processing method in this embodiment is a device with an industrial data processing function, for example, a server.
  • the difference between this embodiment and the first embodiment lies in S201 to S202.
  • S203 to S205 in this embodiment are the same as S101 to S103 in the first embodiment, and S201 to S202 can be executed before S203.
  • S201 ⁇ S202 are as follows:
  • the equipment obtains data processing requirements according to the requirements of the industrial field scene, and the data processing requirements correspond to the data processing results. Different processing results correspond to different processing requirements. For example, if the desired data processing result is the real-time monitoring data of three generators, then the data processing requirement can be to separately monitor and process the real-time data of the three target generators.
  • Object model construction rules are preset in the equipment, and the object model construction rules are used for component object models.
  • the object model construction rules may include the corresponding relationship between the preset data processing requirements and the object model, and the device determines the object model corresponding to the data processing requirements through the preset corresponding relationship between the data processing requirements and the object model.
  • S202 may include S2021 to S2022. As shown in FIG. 4, S2021 to S2022 are specifically as follows:
  • scene type is the classification of the object model. Different scene types correspond to different types of object models. Different scene types include different characteristics, and match the characteristics of the scene type according to the data processing requirements, so as to determine the scene type corresponding to the data processing requirements.
  • the scene type and its characteristics can be preset, as follows:
  • the first scene type This scene type has a single attribute. In this scene type, it can include a single device or a single device, regardless of the entry and exit of materials. This is the simplest and most basic type of scenario, for example, a single compressor, a single boiler, a single biogas generator set, and so on.
  • the second scene type is a multi-attribute scene type, and this scene type may include multiple devices or devices of the same or different types. For example: multiple air compressors in a gas station, multiple boilers in a boiler room, biogas generator set in a power station; or in addition to multiple air compressors in a gas station, there are also dryers and gas storage Tanks, various instrument transmitters, etc.; in addition to multiple boilers in the boiler room, there are softened water treatment equipment, pilot machines, etc.; in addition to multiple biogas generator sets, there are also biogas pretreatment equipment, etc. .
  • the third scene type on the basis of the first scene type and the second scene type, the incoming of materials is considered, but the outgoing of products is not considered.
  • the incoming biogas is also considered; in addition to the operation of the device, the incoming raw material liquid is also considered.
  • the fourth scene type on the basis of the first scene type and the second scene type, the input of materials is not considered, but the output of products is considered. For example, in addition to considering the operation of the CNC machine tool, the error of the processed workpiece is also considered.
  • the fifth scene type on the basis of the first scene type and the second scene type, the consumption of the object is considered. It is energy (energy) consumption, such as water, electricity, coal, gas, etc.
  • the sixth scene type On the basis of the first scene type and the second scene type, "emissions" are considered at the same time, such as exhaust gas, carbon emission, discharge (waste) water, discharge (waste) slag, etc. .
  • the seventh scene type As shown in Figure 5, on the basis of the first scene type and the second scene type, "in, out, consumption, and discharge" are considered at the same time.
  • the device After the device determines the scene type, it can initially determine the target type of the object model.
  • the device can obtain data processing requirements again, and construct an object model of the target type according to the data processing requirements.
  • the data processing requirements include real-time detection of the data of the core equipment, then full parameter monitoring of the core equipment is required, that is, a core equipment (device) in an industry scenario is monitored , And it is full parameter monitoring. Therefore, three generating units are the core equipment, and each unit has 120 parameters, so each unit is taken as an object model:
  • the object number of the generator set is 1003, parameters ⁇ FV1,FV2...,FV120 ⁇
  • the data processing requirements include real-time detection of important parameters of the core equipment, assuming that there are only 30 important parameters of the biogas generator set, and 30 parameters can clearly describe the operation of the generator set, it may not be necessary to achieve "full parameters”. Data collection and monitoring are carried out for these 30 parameters, and the object model is defined:
  • the object number of the generator set is 1003, and the parameters are ⁇ FV1,FV2...,FV30 ⁇ .
  • FIG. 6 is a schematic diagram of a data processing device based on an industrial object model provided by a third embodiment of the present application.
  • the included units are used to execute the steps in the embodiments corresponding to FIGS. 1 and 3 to 4.
  • the data processing device 6 based on the industrial object model includes:
  • the determining unit 610 is configured to construct an object model according to the requirements of the industrial scene scene, filter the industrial data collected by the sensor according to the object model, and determine the model data corresponding to the object model;
  • the first construction unit 620 is configured to construct the object data of the object model according to the model data of the object model at various moments;
  • the processing unit 630 is configured to perform matrix transformation processing on the object data according to a preset processing rule to obtain a processing result.
  • the determining unit 610 includes:
  • the acquisition unit is used to acquire data processing requirements according to the requirements of the industrial scene
  • the second construction unit is used to construct an object model based on the data processing requirements and object model construction rules.
  • the second construction unit is specifically used for:
  • an object model is constructed.
  • the object model includes at least one model of industrial equipment.
  • processing result is one or more of data estimation result, data change result, data trend prediction result, data stability estimation result, risk estimation result, data increment estimation result, and data balance adjustment result.
  • processing unit 630 is specifically configured to:
  • processing unit 630 is specifically configured to:
  • the object data is input into a neural network model that has been trained on the data to perform matrix transformation processing to obtain a processing result.
  • Fig. 7 is a schematic diagram of a data processing device based on an industrial object model provided by a fourth embodiment of the present application.
  • the data processing device 7 based on the industrial object model of this embodiment includes: a processor 70, a memory 71, and a computer program 72 that is stored in the memory 71 and can run on the processor 70, For example, data processing programs based on industrial object models.
  • the processor 70 executes the computer program 72, the steps in the foregoing embodiments of the data processing method based on the industrial object model are implemented, for example, steps 101 to 103 shown in FIG. 1.
  • the processor 70 executes the computer program 72, the functions of the modules/units in the foregoing device embodiments, for example, the functions of the modules 610 to 630 shown in FIG. 6 are realized.
  • the computer program 72 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 71 and executed by the processor 70 to complete This application.
  • the one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 72 in the industrial object model-based data processing device 7 .
  • the computer program 72 may be divided into a determination unit, a first construction unit, and a processing unit, and the specific functions of each unit are as follows:
  • the determining unit is configured to construct an object model in combination with the requirements of an industrial scene, filter the industrial data collected by the sensor according to the object model, and determine the model data corresponding to the object model;
  • the first construction unit is configured to construct the object data of the object model according to the model data of the object model at each time;
  • the processing unit is configured to perform matrix transformation processing on the object data according to a preset processing rule to obtain a processing result.
  • the data processing equipment based on the industrial object model may include, but is not limited to, a processor 70 and a memory 71.
  • FIG. 7 is only an example of the data processing device 7 based on the industrial object model, and does not constitute a limitation on the data processing device 7 based on the industrial object model, and may include more or less than that shown in the figure.
  • Components, or a combination of some components, or different components, for example, the data processing device based on the industrial object model may also include input and output devices, network access devices, buses, and so on.
  • the so-called processor 70 can be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the memory 71 may be an internal storage unit of the data processing device 7 based on the industrial object model, such as a hard disk or memory of the data processing device 7 based on the industrial object model.
  • the memory 71 may also be an external storage device of the data processing device 7 based on the industrial object model, for example, a plug-in hard disk equipped on the data processing device 7 based on the industrial object model, or a smart memory card (SmartMedia Card). ,SMC), Secure Digital (SD) card, Flash Card, etc.
  • the data processing device 7 based on the industrial object model may also include both an internal storage unit of the data processing device 7 based on the industrial object model and an external storage device.
  • the memory 71 is used to store the computer program and other programs and data required by the data processing device based on the industrial object model.
  • the memory 71 can also be used to temporarily store data that has been output or will be output.
  • An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and running on the at least one processor, and the processor executes The computer program implements the steps in any of the foregoing method embodiments.
  • the embodiments of the present application also provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in each of the foregoing method embodiments can be realized.
  • the embodiments of the present application provide a computer program product.
  • the steps in the foregoing method embodiments can be realized when the mobile terminal is executed.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the implementation of all or part of the processes in the above-mentioned embodiment methods in this application can be completed by instructing relevant hardware through a computer program.
  • the computer program can be stored in a computer-readable storage medium. When executed by the processor, the steps of the foregoing method embodiments can be implemented.
  • the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate form.
  • the computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the photographing device/terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), and random access memory (RAM, Random Access Memory), electric carrier signal, telecommunications signal and software distribution medium.
  • ROM read-only memory
  • RAM random access memory
  • electric carrier signal telecommunications signal and software distribution medium.
  • U disk mobile hard disk, floppy disk or CD-ROM, etc.
  • computer-readable media cannot be electrical carrier signals and telecommunication signals.
  • the disclosed apparatus/network equipment and method may be implemented in other ways.
  • the device/network device embodiments described above are only illustrative.
  • the division of the modules or units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units.
  • components can be combined or integrated into another system, or some features can be omitted or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Mathematical Physics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Mathematical Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Mathematical Optimization (AREA)
  • Development Economics (AREA)
  • Computing Systems (AREA)
  • Algebra (AREA)
  • Educational Administration (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种基于工业对象模型的数据处理方法，适用于工业物联网领域，包括：结合工业现场场景需求构建对象模型，根据对象模型对传感器采集的工业数据进行筛选，确定所述对象模型对应的模型数据（S101）；根据所述对象模型在各个时刻的模型数据构建所述对象模型的对象数据（S102）；根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果（S103）。该方法预先构建对象模型，并且获取对象模型对应的对象数据，根据预设的处理规则处理对象数据，得到处理结果。通过构建对象模型和矩阵变换方法，使得工业数据的处理过程更加的简单，更加的统一，从而提高了工业数据的处理效率，节省资源。

Description

基于工业对象模型的数据处理方法、装置及设备 技术领域
本申请涉及工业物联网技术领域，具体涉及一种基于工业对象模型的数据处理方法、装置及设备。
背景技术
随着工业互联网时代的来临，工业现场会设置多种工业设备，从而采集到的工业数据体量增加。现有的工业物联网平台，处理不同的工业数据需要有针对性的单独进行分析处理。但是，工业数据数量过大、分析处理的过程复杂都会导致工业数据的处理效率过低，浪费资源。
技术问题
本申请实施例的目的之一在于：提供一种工业数据的处理方法、装置以及设备，旨在解决工业数据的处理效率过低，浪费资源的问题。
技术解决方案
为解决上述技术问题，本申请实施例采用的技术方案是：
第一方面，提供了一种基于工业对象模型的数据处理方法，包括：
结合工业现场场景需求构建对象模型，根据所述对象模型对传感器采集的工业数据进行筛选，确定所述对象模型对应的模型数据；
根据所述对象模型在各个时刻的模型数据所述对象模型的对象数据；
根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果。
在一个实施例中，所述结合工业现场不同场景需求构建对象模型，包括：
根据工业现场场景需求获取数据处理需求；
基于所述数据处理需求和对象模型构建规则，构建对象模型。
在一个实施例中，所述基于所述数据处理需求和对象模型构建规则，构建对象模型，包括：
根据所述数据处理需求确定场景类型；
根据所述场景类型，构建对象模型。
在一个实施例中，所述对象模型中至少包括一个工业设备的模型。
在一个实施例中，所述处理结果为数据估计结果、数据变化结果、数据趋势预测结果、数据稳定性估计结果、风险估计结果、数据增量估计结果、数据平衡调整结果中的一种或多种。
在一个实施例中，所述根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果，包括：
根据对象数据和处理结果之间的对应关系，对所述对象数据进行矩阵变换处理，得到处理结果。
在一个实施例中，所述根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果，包 括：
将所述对象数据输入经过数据训练的神经网络模型进行矩阵变换处理，得到处理结果。
第二方面，提供了一种基于工业对象模型构建的数据处理装置，包括：
确定单元，结合工业现场场景需求构建对象模型，用于根据所述对象模型对传感器采集的工业数据进行筛选，确定所述对象模型对应的模型数据；
第一构建单元，用于根据所述对象模型在各个时刻的模型数据构建所述对象模型的对象数据；
处理单元，用于根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果。
在一个实施例中，所述确定单元，包括：
获取单元，用于根据工业现场场景需求获取数据处理需求；
第二构建单元，用于基于所述数据处理需求和对象模型构建规则，构建对象模型。
在一个实施例中，所述第二构建单元，具体用于：
根据所述数据处理需求确定场景类型；
根据所述场景类型，构建对象模型。
在一个实施例中，所述对象模型中至少包括一个工业设备的模型。
在一个实施例中，所述处理结果为数据估计结果、数据变化结果、数据趋势预测结果、数据稳定性估计结果、风险估计结果、数据增量估计结果、数据平衡调整结果中的一种或多种。
在一个实施例中，所述处理单元，具体用于：
根据预设对象数据和处理结果之间的对应关系，对所述对象数据进行矩阵变换处理，得到处理结果。
在一个实施例中，所述处理单元，具体用于：
将所述对象数据输入经过数据训练的神经网络模型进行矩阵变换处理，得到处理结果。
第三方面，本申请实施例提供了一种基于工业对象模型的数据处理设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如上述第一方面所述的基于工业对象模型的数据处理方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现如上述第一方面所述的基于工业对象模型的数据处理方法。
有益效果
本申请实施例中，结合工业现场场景需求构建对象模型，根据对象模型对传感器采集的工业数据进行筛选，确定所述对象模型对应的模型数据；根据所述对象模型在各个时刻的模型数据所述对象模型的对象数据；根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果。上述方案，预先构建对象模型，并且获取对象模型对应的对象数据，通过矩阵变换方法、根据预设的处理规则处理对象数据， 得到处理结果。通过构建对象模型和矩阵变换方法，使得工业数据的处理过程更加的简单，更加的统一，从而提高了工业数据的处理效率，节省资源。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或示范性技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它的附图。
图1是本申请第一实施例提供的一种基于工业对象模型的数据处理方法的示意流程图；
图2是本申请第一实施例提供的一种基于工业对象模型的数据处理方法中矩阵变换的示意图；
图3是本申请第二实施例提供的另一种基于工业对象模型的数据处理方法的示意流程图；
图4是本申请第二实施例提供的另一种基于工业对象模型的数据处理方法中S202的细化的示意流程图；
图5是本申请第二实施例提供的另一种基于工业对象模型的数据处理方法中第一场景类型的示意图；
图6是本申请第三实施例提供的基于工业对象模型的数据处理装置的示意图；
图7是本申请第四实施例提供的基于工业对象模型的数据处理设备的示意图。
本发明的实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本申请。
需说明的是，当部件被称为“固定于”或“设置于”另一个部件，它可以直接在另一个部件上或者间接在该另一个部件上。当一个部件被称为是“连接于”另一个部件，它可以是直接或者间接连接至该另一个部件上。术语“上”、“下”、“左”、“右”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制，对于本领域的普通技术人员而言，可以根据具体情况理解上述术语的具体含义。术语“第一”、“第二”仅用于便于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明技术特征的数量。“多个”的含义是两个或两个以上，除非另有明确具体的限定。
为了说明本申请所述的技术方案，以下结合具体附图及实施例进行详细说明。
请参见图1，图1是本申请第一实施例提供的一种工业数据的处理方法的示意流程图。本实施例中一种工业数据的处理方法的执行主体为具有工业数据的处理功能的设备，例如，服务器等。如图1所示的工业数据的处理方法可包括：
S101：结合工业现场场景需求构建对象模型，根据所述对象模型对传感器采集的工业数据进行筛选，确定所述对象模型对应的模型数据。
设备中结合工业现场不同场景需求构建对象模型，对象模型标识一个逻辑设备模型，对象模型是针对不同工业场景，对工业现场和工业设备进行抽象得到模型。对象模型可以根据一台工业设备进行构建，也可以根据多台工业设备进行构建。对象模型中可以仅仅包括工业设备的模型，也可以包括工业设备周边的仪表、传感器的模型。进一步地，预设工业模型里还可以包括环境因素，例如，环境空间的温度、压强等等。
举例来说，一个沼气发电站，主要设备有：一台沼气加压净化设备和三台沼气发电机。沼气净化加压设备把从沼气池抽出来的沼气进行净化、过滤，加压，然后把沼气输送到沼气发电机去发电。除了这四台设备外，还有一些仪表，分别用来检测净化加压前后的沼气流量、压力、温度，以及沼气浓度、输送到每台发电机的沼气流量、每台发电机所发的电量和整个发电站的发电量。在这个工业场景中，对象模型可以为一台沼气加压净化设备，对象模型也可以为一台沼气加压净化设备和三台沼气发电机。
进一步地，对象模型中至少包括一个工业设备的模型。
对象模型是本实施例中工业数据处理的基础，设备获取对象模型对应的模型数据，基于模型数据得到工业数据的处理结果。所以，不同的预设工业模型的构成不同，则对应的模型数据不同，得到的工业数据的处理结果也不相同。也就是说，不同的处理结果对应了不同的对象模型，即不同的需求对应了不同的对象模型。
例如，在上述沼气发电站中，如果想要得到的数据处理结果为三台发电机实时监控数据，那只需要定义三个对象模型：
对象模型1＝1#发电机
对象模型2＝2#发电机
对象模型3＝3#发电机。
如果想要得到的数据处理结果为沼气发电站的沼气净化加压设备和发电机的实时监控数据，那就多定义一个对象模型：
对象模型1＝1#发电机
对象模型2＝2#发电机
对象模型3＝3#发电机
对象模型4＝沼气净化加压设备。
如果想要得到的数据处理结果为沼气净化加压设备的运行情况和生产情况，需要定义两个对象模型：
对象模型1＝沼气净化加压设备
对象模型2＝沼气净化加压设备+仪表(前)+仪表(后)。
在本实施例中，对象模型与工业数据的采集方式无关，本实施例中并不限制工业数据采集的方式，只要可以采集到工业现场的所有数据即可。具体采用多少个传感器、各个传感器的对接方式，都要根据现场情况来定。
设备获取到传感器采集的工业数据，并且根据对象模型对传感器采集的工业数据进行筛选，确定对象模型对应的模型数据。其中，对象模型对应的模型数据即为对象模型中包括的所有的设备、元素对应的工业数据。
S102：根据所述对象模型在各个时刻的模型数据构建所述对象模型的对象数据。
设备根据对象模型在各个时刻的模型数据的集合即为所述对象模型的对象数据。其中，对象数据的数学方法表示为：obj.ts.data；obj对象标签，time时间序列标签，data是n维实数空间数据为：{x 1,x 2,x 3,...,x n}。因此，对象数据又表示为:obj.ts.{x 1,x 2,x 3,...,x n}。obj.ts.{x 1,x 2,x 3,...,x n}是某个时刻发生的瞬时值，经过一段时间的瞬时值累积后形成集合即为对象数据。其中，对象数据表示如下：
ts 1.{x 1,x 2,x 3,...,x n}
ts 2.{x 1,x 2,x 3,...,x n}
obj.ts 3.{x 1,x 2,x 3,...,x n}
...
ts n.{x 1,x 2,x 3,...,x n}
举例来说，定义对象标签1001，参数FV1为温度，参数FV2为压力。在2020-05-20 00:00:00时刻，1001的温度为100℃、压力为0.50Mpa，则数据为：1001.2020-05-20 00:00:00.{"FV1":100,"FV2":0.50}；在2020-05-20 00:00:01时刻，1001的温度为99℃、压力为0.49Mpa，则数据为：1001.2020-05-20 00:00:00.{"FV1":99,"FV2":0.49}。
S103：根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果。
在本实施例中，矩阵变换处理方法如图2所示，输入数据为矩阵X，输出数据为矩阵Y。
特别地，输入数据矩阵X为对象数据，抽象表示如下：
Figure PCTCN2020092355-appb-000001
其中，Xn即为对象某一时刻数据obj.ts n.{x 1,x 2,x 3,...,x n}
同时，输出数据矩阵Y为处理结果，抽象表示为：
Y (1,m)＝{Y 1 Y 2 Y 3 ... Y m}，其中，Ym为某一组结果
Figure PCTCN2020092355-appb-000002
转置为：
Figure PCTCN2020092355-appb-000003
预设处理规则为M (m,n)，则矩阵变换如下：
Figure PCTCN2020092355-appb-000004
矩阵变换时，预先设置处理规则，预设处理规则用于对对象数据进行处理，得到处理结果。不同的处理结果对应了不同的处理规则，预设处理规则是根据数据处理的需求来确定的。
设备根据预设处理规则对对象数据进行处理，得到处理结果。
进一步地，所述处理结果可以为数据估计结果、数据变化结果、数据趋势预测结果、数据稳定性 估计结果、风险估计结果、数据增量估计结果、数据平衡调整结果中的一种或多种。可以理解的是，处理结果包括但是并不限于数据估计结果、数据变化结果、数据趋势预测结果、数据稳定性估计结果、风险估计结果、数据增量估计结果、数据平衡调整结果。
其中，数据估计结果可以为根据对象数据得到对应的估计结果，例如，对象数据为耗电量，数据估计结果为根据耗电量估计出的产量；数据趋势预测结果可以为根据对象数据对未获取的数据进行的估计；风险评估结果可以为根据对象数据进行风险评估得到的风险等级；数据增量估计结果可以为根据对象项数据估计出的增量；数据平衡调整结果可以为根据对象数据得到的需要调整的数据。
一种实施方式中，S103可以包括：根据预设对象数据和处理结果之间的对应关系，对所述对象数据进行矩阵变换处理，得到处理结果。
此时对象数据X和处理结果M给定，得出处理规则M(此时M是要求得的训练数据)，即M＝Y T·X -1
在本实施例中，设备中存储对象数据和处理结果之间的对应关系，设备根据对象数据和处理结果之间的对应关系，对对象数据进行处理，得到处理结果。对象数据和处理结果之间的对应关系可以根据历史数据来确定，在历史数据中包括历史对象数据和历史处理结果，根据历史对象数据和历史处理结果来确定预设对象数据和处理结果之间的对应关系，将对应关系应用到后续的数据处理中，得到后续工业数据的处理结果。
另一种实施方式中，S103可以包括：将所述对象数据输入经过数据训练的神经网络模型进行矩阵变换处理，得到处理结果。
此时输入数据X和处理规则M给定，得出结果Y，即Y T＝M·X
在本实施例中，设备中预先存储经过数据训练的神经网络模型M，预设的神经网络模型由使用机器学习算法对样本训练集中的多个训练样本进行训练得到，每个训练样本包括一个样本对象数据及其对应的处理结果标签。可以理解的是，神经网络模型可以由本端设备预先训练好，也可以由其他设备预先训练好后将神经网络模型对应的文件移植至本端设备中。具体地，其他设备在训练好神经网络模型时，冻结深度学习网络的模型参数，将冻结后的深度学习网络对应的神经网络模型文件移植到本端设备中。设备将对象数据输入神经网络模型进行处理，得到处理结果。
本申请实施例中，结合工业现场场景需求构建对象模型，根据对象模型对传感器采集的工业数据进行筛选，确定所述对象模型对应的模型数据；根据所述对象模型在各个时刻的模型数据构建所述对象模型的对象数据；根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果。上述方案，预 先构建对象模型，并且获取对象模型对应的对象数据，根据预设的处理规则处理对象数据，得到处理结果。通过构建对象模型和矩阵变换方法，使得工业数据的处理过程更加的简单，更加的统一，从而提高了工业数据的处理效率，节省资源。
请参见图3，图3是本申请第二实施例提供的另一种工业数据的处理方法的示意流程图。本实施例中一种工业数据的处理方法的执行主体为具有工业数据的处理功能的设备，例如，服务器等。本实施例与第一实施例的区别在于S201～S202，本实施例中S203～S205与第一实施例中的S101～S103相同，S201～S202在S203之前执行即可。如图3所示，S201～S202具体如下：
S201：根据工业现场场景需求获取数据处理需求。
设备根据工业现场场景需求获取数据处理需求，数据处理需求与数据处理结果对应。不同的处理结果对应了不同的处理需求。例如，想要得到的数据处理结果为三台发电机实时监控数据，那么数据处理需求可以为对三台目标发电机各自的实时数据分别进行监控处理。
S202：基于所述数据处理需求和对象模型构建规则，构建对象模型。
设备中预先设置对象模型构建规则，对象模型构建规则用于构件对象模型。对象模型构建规则可以包括预设数据处理需求和对象模型之间的对应关系，设备通过预设数据处理需求和对象模型之间的对应关系，确定数据处理需求对应的对象模型。
进一步地，为了更准确构建对象模型，S202可以包括S2021～S2022，如图4所示，S2021～S2022具体如下：
S2021：根据所述数据处理需求确定场景类型。
设备中预先设置多个场景类型，场景类型为对象模型的分类。不同的场景类型对应了不同类型的对象模型。不同的场景类型包括不同的特征，根据数据处理需求去匹配场景类型的特征，从而确定数据处理需求对应的场景类型。
在本实施例中，可以预先设置场景类型及其特征，具体如下：
1.第一场景类型：该场景类型具有单一属性，在本场景类型中，可以包括单一设备或者单一装置，不考虑物料的进出。这是最简单最基本的场景类型，例如，单台压缩机、单台锅炉、单台沼气发电机组等等。
2.第二场景类型：该场景类型为多属性场景类型，在本场景类型中，可以包括多个相同或者不同类型的设备或装置。例如：一个气站里的多台空压机，一个锅炉房里的多台锅炉，一个电站里的沼气发电机组；或者一个气站里除了多台空压机外，还有干燥机、储气罐、各种仪表变送器等等；锅炉房里除了多台锅炉外，还有软化水处理设备、引机等等；电站里除了多台沼气发电机组外，还有沼气预处理设备等等。
3.第三场景类型：在第一场景类型和第二场景类型的基础上，考虑物料的进，但不考虑产品的出。 例如，除了沼气发电机组，还考虑进来的沼气；除了考虑装置运行情况外，还考虑进来的物料原液。
4.第四场景类型：在第一场景类型和第二场景类型的基础上，不考虑物料的进，但考虑产品的出。例如，除了考虑数控机床运行的情况，还考虑加工的工件产品的误差。
5.第五场景类型：在第一场景类型和第二场景类型的基础上，考虑对象的消耗。就是能源(能量)消耗，比如，水、电、煤、气等。
6.第六场景类型：在第一场景类型和第二场景类型的基础上，同时考虑了“排放”，如，排烟气、排碳、排(废)水、排(废)渣等等。
7.第七场景类型：如图5所示，在第一场景类型和第二场景类型的基础上，同时考虑“进、出、耗、排”。
S2022：根据所述场景类型，构建对象模型。
设备确定场景类型后，可以初步确定对象模型的目标类型。设备可以再次获取数据处理需求，根据数据处理需求构建出目标类型的对象模型。以目标类型为第一场景类型为例，数据处理需求中包括对核心设备的数据进行实时检测，那么需要对核心设备进行全参数监测，即把一个在业场景中的核心设备(装置)进行监控，而且是全参数监控。所以三台发电机组是核心设备，每台机组都有120个参数，则就把每台机组作为一个对象模型：
1#发电机组的对象编号1001，参数{FV1,FV2...,FV120}
2#发电机组的对象编号1002，参数{FV1,FV2...,FV120}
3#发电机组的对象编号1003，参数{FV1,FV2...,FV120}
如果数据处理需求中包括对核心设备的重要参数进行实时检测，假设沼气发电机组的重要参数只有30个，且30个参数就可以清楚描述发电机组的运行，则未必需要做到“全参数”。针对这30个参数进行数据采集和监测，定义对象模型：
1#发电机组的对象编号1001，参数{FV1,FV2...,FV30}
2#发电机组的对象编号1002，参数{FV1,FV2...,FV30}
3#发电机组的对象编号1003，参数{FV1,FV2...,FV30}。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
请参见图6，图6是本申请第三实施例提供的基于工业对象模型的数据处理装置的示意图。包括的各单元用于执行图1、图3～图4对应的实施例中的各步骤。具体请参阅图1、图3～图4各自对应的实施例中的相关描述。为了便于说明，仅示出了与本实施例相关的部分。参见图6，基于工业对象模型的数据处理装置6包括：
确定单元610，用于结合工业现场场景需求构建对象模型，根据所述对象模型对传感器采集的工 业数据进行筛选，确定所述对象模型对应的模型数据；
第一构建单元620，用于根据所述对象模型在各个时刻的模型数据构建所述对象模型的对象数据；
处理单元630，用于根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果。
进一步地，确定单元610，包括：
获取单元，用于根据工业现场场景需求获取数据处理需求；
第二构建单元，用于基于所述数据处理需求和对象模型构建规则，构建对象模型。
进一步地，所述第二构建单元，具体用于：
根据所述数据处理需求确定场景类型；
根据所述场景类型，构建对象模型。
进一步地，所述对象模型中至少包括一个工业设备的模型。
进一步地，所述处理结果为数据估计结果、数据变化结果、数据趋势预测结果、数据稳定性估计结果、风险估计结果、数据增量估计结果、数据平衡调整结果中的一种或多种。
进一步地，处理单元630，具体用于：
根据预设对象数据和处理结果之间的对应关系，对所述对象数据进行矩阵变换处理，得到处理结果。
进一步地，处理单元630，具体用于：
将所述对象数据输入经过数据训练的神经网络模型进行矩阵变换处理，得到处理结果。
图7是本申请第四实施例提供的基于工业对象模型的数据处理设备的示意图。如图7所示，该实施例的基于工业对象模型的数据处理设备7包括：处理器70、存储器71以及存储在所述存储器71中并可在所述处理器70上运行的计算机程序72，例如基于工业对象模型的数据处理程序。所述处理器70执行所述计算机程序72时实现上述各个基于工业对象模型的数据处理方法实施例中的步骤，例如图1所示的步骤101至103。或者，所述处理器70执行所述计算机程序72时实现上述各装置实施例中各模块/单元的功能，例如图6所示模块610至630的功能。
示例性的，所述计算机程序72可以被分割成一个或多个模块/单元，所述一个或者多个模块/单元被存储在所述存储器71中，并由所述处理器70执行，以完成本申请。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序72在所述基于工业对象模型的数据处理设备7中的执行过程。例如，所述计算机程序72可以被分割成确定单元、第一构建单元、处理单元，各单元具体功能如下：
确定单元，用于结合工业现场场景需求构建对象模型，根据所述对象模型对传感器采集的工业数据进行筛选，确定所述对象模型对应的模型数据；
第一构建单元，用于根据所述对象模型在各个时刻的模型数据构建所述对象模型的对象数据；
处理单元，用于根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果。
所述基于工业对象模型的数据处理设备可包括，但不仅限于，处理器70、存储器71。本领域技术人员可以理解，图7仅仅是基于工业对象模型的数据处理设备7的示例，并不构成对基于工业对象模型的数据处理设备7的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述基于工业对象模型的数据处理设备还可以包括输入输出设备、网络接入设备、总线等。
所称处理器70可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
所述存储器71可以是所述基于工业对象模型的数据处理设备7的内部存储单元，例如基于工业对象模型的数据处理设备7的硬盘或内存。所述存储器71也可以是所述基于工业对象模型的数据处理设备7的外部存储设备，例如所述基于工业对象模型的数据处理设备7上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。进一步地，所述基于工业对象模型的数据处理设备7还可以既包括所述基于工业对象模型的数据处理设备7的内部存储单元也包括外部存储设备。所述存储器71用于存储所述计算机程序以及所述基于工业对象模型的数据处理设备所需的其他程序和数据。所述存储器71还可以用于暂时地存储已经输出或者将要输出的数据。
需要说明的是，上述装置/单元之间的信息交互、执行过程等内容，由于与本申请方法实施例基于同一构思，其具体功能及带来的技术效果，具体可参见方法实施例部分，此处不再赘述。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述系统中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
本申请实施例还提供了一种网络设备，该网络设备包括：至少一个处理器、存储器以及存储在所述存储器中并可在所述至少一个处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述任意各个方法实施例中的步骤。
本申请实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所 述计算机程序被处理器执行时实现可实现上述各个方法实施例中的步骤。
本申请实施例提供了一种计算机程序产品，当计算机程序产品在移动终端上运行时，使得移动终端执行时实现可实现上述各个方法实施例中的步骤。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质至少可以包括：能够将计算机程序代码携带到拍照装置/终端设备的任何实体或装置、记录介质、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质。例如U盘、移动硬盘、磁碟或者光盘等。在某些司法管辖区，根据立法和专利实践，计算机可读介质不可以是电载波信号和电信信号。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的实施例中，应该理解到，所揭露的装置/网络设备和方法，可以通过其它的方式实现。例如，以上所描述的装置/网络设备实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口，装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种基于工业对象模型的数据处理方法，其特征在于，包括：
    结合工业现场场景需求构建对象模型，根据所述对象模型对传感器采集的工业数据进行筛选，确定所述对象模型对应的模型数据；
    根据所述对象模型在各个时刻的模型数据构建所述对象模型的对象数据；
    根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果。
  2. 如权利要求1所述的基于工业对象模型构建的数据处理方法，其特征在于，所述结合工业现场不同场景需求构建对象模型，包括：
    根据工业现场场景需求获取数据处理需求；
    基于所述数据处理需求和对象模型构建规则，构建对象模型。
  3. 如权利要求2所述的基于工业对象模型构建的数据处理方法，其特征在于，所述基于所述数据处理需求和对象模型构建规则，构建对象模型，包括：
    根据所述数据处理需求确定场景类型；
    根据所述场景类型，构建对象模型。
  4. 如权利要求1所述的基于工业对象模型构建的数据处理方法，其特征在于，所述对象模型中至少包括一个工业设备的模型。
  5. 如权利要求1所述的基于工业对象模型的数据处理方法，其特征在于，所述处理结果为数据估计结果、数据变化结果、数据趋势预测结果、数据稳定性估计结果、风险估计结果、数据增量估计结果、数据平衡调整结果中的一种或多种。
  6. 如权利要求1所述的基于工业对象模型的数据处理方法，其特征在于，所述根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果，包括：
    根据对象数据和处理结果之间的对应关系，对所述对象数据进行矩阵变换处理，得到处理结果。
  7. 如权利要求1所述的基于工业对象模型的数据处理方法，其特征在于，所述根据预设处理规则对所述对象数据进行矩阵变换处理，得到处理结果，包括：
    将所述对象数据输入经过数据训练的神经网络模型进行矩阵变换处理，得到处理结果。
  8. 一种基于工业对象模型的数据处理装置，其特征在于，包括：
    确定单元，结合工业现场场景需求构建对象模型，用于根据所述对象模型对传感器采集的工业数据进行筛选，确定所述对象模型对应的模型数据；
    第一构建单元，用于根据所述对象模型在各个时刻的模型数据构建所述对象模型的对象数据；
    处理单元，用于通过矩阵变换方法、根据预设处理规则对所述对象数据进行处理，得到处理结果。
  9. 一种基于工业对象模型的数据处理设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至7任一项所述的方法。
  10. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至7任一项所述的方法。
PCT/CN2020/092355 2020-05-26 2020-05-26 基于工业对象模型的数据处理方法、装置及设备 WO2021237459A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202080000820.4A CN112204547B (zh) 2020-05-26 2020-05-26 基于工业对象模型的数据处理方法、装置及设备
PCT/CN2020/092355 WO2021237459A1 (zh) 2020-05-26 2020-05-26 基于工业对象模型的数据处理方法、装置及设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/092355 WO2021237459A1 (zh) 2020-05-26 2020-05-26 基于工业对象模型的数据处理方法、装置及设备

Publications (1)

Publication Number Publication Date
WO2021237459A1 true WO2021237459A1 (zh) 2021-12-02

Family

ID=74033871

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/092355 WO2021237459A1 (zh) 2020-05-26 2020-05-26 基于工业对象模型的数据处理方法、装置及设备

Country Status (2)

Country Link
CN (1) CN112204547B (zh)
WO (1) WO2021237459A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116430821A (zh) * 2023-06-15 2023-07-14 埃睿迪信息技术（北京）有限公司 工业生产工艺模型的数据处理方法及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140340396A1 (en) * 2013-05-14 2014-11-20 Electronics And Telecommunications Research Institute Method of representing environment object in cyber-physical system using environment data model structure and computer-readable storage medium storing program therefor
CN104731051A (zh) * 2015-01-19 2015-06-24 成都创信云通科技有限公司 一种实现传感器点位对象化的方法
CN107390662A (zh) * 2017-08-29 2017-11-24 清华大学 基于监控对象模型的工业监控方法及装置
CN110648080A (zh) * 2019-09-30 2020-01-03 石化盈科信息技术有限责任公司 基于智能点的信息物理系统及其构建方法

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103116283A (zh) * 2013-01-18 2013-05-22 杭州电子科技大学 一种非自衡对象的动态矩阵控制方法
US20170315529A1 (en) * 2016-04-29 2017-11-02 Rockwell Automation Technologies, Inc. Unique udts to exploit the power of the connected enterprise
US20170322732A1 (en) * 2016-05-04 2017-11-09 Nasdaq Technology Ab Computer systems and methods for implementing in-memory data structures
CN106776995B (zh) * 2016-12-06 2020-08-28 北京神舟航天软件技术有限公司 一种基于模型驱动架构的结构化数据树形采集方法
CA3072045A1 (en) * 2017-08-02 2019-02-07 Strong Force Iot Portfolio 2016, Llc Methods and systems for detection in an industrial internet of things data collection environment with large data sets
CN108229828A (zh) * 2018-01-04 2018-06-29 上海电气集团股份有限公司 一种基于工业数据的分析系统
CN109190979A (zh) * 2018-09-03 2019-01-11 深圳市智物联网络有限公司 一种工业物联网数据分析方法、系统及相关设备
CN109615265A (zh) * 2018-12-26 2019-04-12 北京寄云鼎城科技有限公司 基于集成开发系统的工业数据分析方法、装置与电子设备
CN109670267B (zh) * 2018-12-29 2023-06-13 北京航天数据股份有限公司 一种数据处理方法和装置
CN110471376A (zh) * 2019-07-10 2019-11-19 深圳市乾行达科技有限公司 一种工业现场故障检测方法及设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140340396A1 (en) * 2013-05-14 2014-11-20 Electronics And Telecommunications Research Institute Method of representing environment object in cyber-physical system using environment data model structure and computer-readable storage medium storing program therefor
CN104731051A (zh) * 2015-01-19 2015-06-24 成都创信云通科技有限公司 一种实现传感器点位对象化的方法
CN107390662A (zh) * 2017-08-29 2017-11-24 清华大学 基于监控对象模型的工业监控方法及装置
CN110648080A (zh) * 2019-09-30 2020-01-03 石化盈科信息技术有限责任公司 基于智能点的信息物理系统及其构建方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116430821A (zh) * 2023-06-15 2023-07-14 埃睿迪信息技术（北京）有限公司 工业生产工艺模型的数据处理方法及装置
CN116430821B (zh) * 2023-06-15 2023-08-29 埃睿迪信息技术（北京）有限公司 工业生产工艺模型的数据处理方法及装置

Also Published As

Publication number Publication date
CN112204547B (zh) 2023-06-16
CN112204547A (zh) 2021-01-08

Similar Documents

Publication Publication Date Title
CN111581189B (zh) 一种空气质量检测数据缺失的补全方法及补全装置
CN112149329B (zh) 核电厂关键设备的状态预演方法、系统、设备及存储介质
CN111695730B (zh) 基于arima及rnn的立磨振动预测方法及装置
CN111625754B (zh) 用于计算锅炉能效的方法、装置、终端设备和存储介质
CN111339072B (zh) 基于用户行为的变化值分析方法、装置、电子设备及介质
CN113268403A (zh) 时间序列的分析预测方法、装置、设备及存储介质
CN116187552A (zh) 异常检测方法、计算设备及计算机存储介质
WO2021237459A1 (zh) 基于工业对象模型的数据处理方法、装置及设备
WO2024015014A1 (en) Method and apparatus for displaying carbon intensities, and device, storage medium, and program product thereof
US20220229904A1 (en) Privacy-protection-based data processing model acquisition method and apparatus, terminal device and storage medium
CN112984722A (zh) 风管机静压的识别方法、装置、计算机设备和存储介质
CN111626360A (zh) 用于检测锅炉故障类型的方法、装置、设备和存储介质
CN115577933A (zh) 一种智慧园区孵化企业信息管理系统及方法
CN116168403A (zh) 医疗数据分类模型训练方法、分类方法、装置及相关介质
CN115993808A (zh) 燃气蒸汽锅炉能耗诊断系统及方法
CN114154415A (zh) 设备寿命的预测方法及装置
CN111651652B (zh) 基于人工智能的情感倾向识别方法、装置、设备及介质
CN111652741A (zh) 用户偏好分析方法、装置及可读存储介质
CN116707331B (zh) 基于模型预测的逆变器输出电压高精度调节方法及系统
CN117521528B (zh) 一种涡轮设备仿真模型进化方法、装置、介质及计算设备
CN115329148B (zh) 一种基于多重大数据处理的数据筛选整合方法及系统
CN115983663B (zh) 基于新能源的发电分析方法及相关设备
CN117424238A (zh) 一种电网能量优化调度方法、系统及存储介质
CN116303689A (zh) 数据报表的生成方法、装置、计算机设备及可读存储介质
CN115454864A (zh) 佣金计算系统自动化测试方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20937918

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 20/01/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20937918

Country of ref document: EP

Kind code of ref document: A1